diff options
| author | Mark Brown <broonie@kernel.org> | 2024-04-30 00:15:57 +0900 |
|---|---|---|
| committer | Mark Brown <broonie@kernel.org> | 2024-04-30 00:15:57 +0900 |
| commit | 9b4f41684b239eedac96913270db4a5669956671 (patch) | |
| tree | cb9b4800c3d6b93bc4af31fa3e377933c68f9bb2 | |
| parent | 2da01ca3674c6e90dbeeda02168849e2ec877edc (diff) | |
| parent | bda16500dd0b05e2e047093b36cbe0873c95aeae (diff) | |
ASoC: Merge up fixes
Some new SOF changes depend on the fixes there.
418 files changed, 6867 insertions, 2828 deletions
@@ -20,6 +20,7 @@ Adam Oldham <oldhamca@gmail.com> Adam Radford <aradford@gmail.com> Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com> Adrian Bunk <bunk@stusta.de> +Ajay Kaher <ajay.kaher@broadcom.com> <akaher@vmware.com> Akhil P Oommen <quic_akhilpo@quicinc.com> <akhilpo@codeaurora.org> Alan Cox <alan@lxorguk.ukuu.org.uk> Alan Cox <root@hraefn.swansea.linux.org.uk> @@ -36,6 +37,7 @@ Alexei Avshalom Lazar <quic_ailizaro@quicinc.com> <ailizaro@codeaurora.org> Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com> Alexei Starovoitov <ast@kernel.org> <ast@fb.com> Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com> +Alexey Makhalov <alexey.amakhalov@broadcom.com> <amakhalov@vmware.com> Alex Hung <alexhung@gmail.com> <alex.hung@canonical.com> Alex Shi <alexs@kernel.org> <alex.shi@intel.com> Alex Shi <alexs@kernel.org> <alex.shi@linaro.org> @@ -110,6 +112,7 @@ Brendan Higgins <brendan.higgins@linux.dev> <brendanhiggins@google.com> Brian Avery <b.avery@hp.com> Brian King <brking@us.ibm.com> Brian Silverman <bsilver16384@gmail.com> <brian.silverman@bluerivertech.com> +Bryan Tan <bryan-bt.tan@broadcom.com> <bryantan@vmware.com> Cai Huoqing <cai.huoqing@linux.dev> <caihuoqing@baidu.com> Can Guo <quic_cang@quicinc.com> <cang@codeaurora.org> Carl Huang <quic_cjhuang@quicinc.com> <cjhuang@codeaurora.org> @@ -529,6 +532,7 @@ Rocky Liao <quic_rjliao@quicinc.com> <rjliao@codeaurora.org> Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com> Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com> Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru> +Ronak Doshi <ronak.doshi@broadcom.com> <doshir@vmware.com> Muchun Song <muchun.song@linux.dev> <songmuchun@bytedance.com> Muchun Song <muchun.song@linux.dev> <smuchun@gmail.com> Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com> @@ -651,6 +655,7 @@ Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com> Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com> Viresh Kumar <viresh.kumar@linaro.org> <viresh.kumar@linaro.org> Viresh Kumar <viresh.kumar@linaro.org> <viresh.kumar@linaro.com> +Vishnu Dasa <vishnu.dasa@broadcom.com> <vdasa@vmware.com> Vivek Aknurwar <quic_viveka@quicinc.com> <viveka@codeaurora.org> Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com> Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bb884c14b2f6..623fce7d5fcd 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6599,7 +6599,7 @@ To turn off having tracepoints sent to printk, echo 0 > /proc/sys/kernel/tracepoint_printk Note, echoing 1 into this file without the - tracepoint_printk kernel cmdline option has no effect. + tp_printk kernel cmdline option has no effect. The tp_printk_stop_on_boot (see below) can also be used to stop the printing of events to console at diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst index b42132969e31..13632671adae 100644 --- a/Documentation/admin-guide/mm/zswap.rst +++ b/Documentation/admin-guide/mm/zswap.rst @@ -155,7 +155,7 @@ Setting this parameter to 100 will disable the hysteresis. Some users cannot tolerate the swapping that comes with zswap store failures and zswap writebacks. Swapping can be disabled entirely (without disabling -zswap itself) on a cgroup-basis as follows: +zswap itself) on a cgroup-basis as follows:: echo 0 > /sys/fs/cgroup/<cgroup-name>/memory.zswap.writeback @@ -166,7 +166,7 @@ writeback (because the same pages might be rejected again and again). When there is a sizable amount of cold memory residing in the zswap pool, it can be advantageous to proactively write these cold pages to swap and reclaim the memory for other use cases. By default, the zswap shrinker is disabled. -User can enable it as follows: +User can enable it as follows:: echo Y > /sys/module/zswap/parameters/shrinker_enabled diff --git a/Documentation/dev-tools/testing-overview.rst b/Documentation/dev-tools/testing-overview.rst index 0aaf6ea53608..1619e5e5cc9c 100644 --- a/Documentation/dev-tools/testing-overview.rst +++ b/Documentation/dev-tools/testing-overview.rst @@ -104,6 +104,8 @@ Some of these tools are listed below: KASAN and can be used in production. See Documentation/dev-tools/kfence.rst * lockdep is a locking correctness validator. See Documentation/locking/lockdep-design.rst +* Runtime Verification (RV) supports checking specific behaviours for a given + subsystem. See Documentation/trace/rv/runtime-verification.rst * There are several other pieces of debug instrumentation in the kernel, many of which can be found in lib/Kconfig.debug diff --git a/Documentation/devicetree/bindings/clock/keystone-gate.txt b/Documentation/devicetree/bindings/clock/keystone-gate.txt index c5aa187026e3..43f6fb6c9392 100644 --- a/Documentation/devicetree/bindings/clock/keystone-gate.txt +++ b/Documentation/devicetree/bindings/clock/keystone-gate.txt @@ -1,5 +1,3 @@ -Status: Unstable - ABI compatibility may be broken in the future - Binding for Keystone gate control driver which uses PSC controller IP. This binding uses the common clock binding[1]. diff --git a/Documentation/devicetree/bindings/clock/keystone-pll.txt b/Documentation/devicetree/bindings/clock/keystone-pll.txt index 9a3fbc665606..69b0eb7c03c9 100644 --- a/Documentation/devicetree/bindings/clock/keystone-pll.txt +++ b/Documentation/devicetree/bindings/clock/keystone-pll.txt @@ -1,5 +1,3 @@ -Status: Unstable - ABI compatibility may be broken in the future - Binding for keystone PLLs. The main PLL IP typically has a multiplier, a divider and a post divider. The additional PLL IPs like ARMPLL, DDRPLL and PAPLL are controlled by the memory mapped register where as the Main diff --git a/Documentation/devicetree/bindings/clock/ti/adpll.txt b/Documentation/devicetree/bindings/clock/ti/adpll.txt index 4c8a2ce2cd70..3122360adcf3 100644 --- a/Documentation/devicetree/bindings/clock/ti/adpll.txt +++ b/Documentation/devicetree/bindings/clock/ti/adpll.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments ADPLL clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register-mapped ADPLL with two to three selectable input clocks and three to four children. diff --git a/Documentation/devicetree/bindings/clock/ti/apll.txt b/Documentation/devicetree/bindings/clock/ti/apll.txt index ade4dd4c30f0..bbd505c1199d 100644 --- a/Documentation/devicetree/bindings/clock/ti/apll.txt +++ b/Documentation/devicetree/bindings/clock/ti/apll.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments APLL clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register-mapped APLL with usually two selectable input clocks (reference clock and bypass clock), with analog phase locked diff --git a/Documentation/devicetree/bindings/clock/ti/autoidle.txt b/Documentation/devicetree/bindings/clock/ti/autoidle.txt index 7c735dde9fe9..05645a10a9e3 100644 --- a/Documentation/devicetree/bindings/clock/ti/autoidle.txt +++ b/Documentation/devicetree/bindings/clock/ti/autoidle.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments autoidle clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register mapped clock which can be put to idle automatically by hardware based on the usage and a configuration bit setting. Autoidle clock is never an individual diff --git a/Documentation/devicetree/bindings/clock/ti/clockdomain.txt b/Documentation/devicetree/bindings/clock/ti/clockdomain.txt index 9c6199249ce5..edf0b5d42768 100644 --- a/Documentation/devicetree/bindings/clock/ti/clockdomain.txt +++ b/Documentation/devicetree/bindings/clock/ti/clockdomain.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments clockdomain. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1] in consumer role. Every clock on TI SoC belongs to one clockdomain, but software only needs this information for specific clocks which require diff --git a/Documentation/devicetree/bindings/clock/ti/composite.txt b/Documentation/devicetree/bindings/clock/ti/composite.txt index 33ac7c9ad053..6f7e1331b546 100644 --- a/Documentation/devicetree/bindings/clock/ti/composite.txt +++ b/Documentation/devicetree/bindings/clock/ti/composite.txt @@ -1,7 +1,5 @@ Binding for TI composite clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register-mapped composite clock with multiple different sub-types; diff --git a/Documentation/devicetree/bindings/clock/ti/divider.txt b/Documentation/devicetree/bindings/clock/ti/divider.txt index 9b13b32974f9..4d7c76f0b356 100644 --- a/Documentation/devicetree/bindings/clock/ti/divider.txt +++ b/Documentation/devicetree/bindings/clock/ti/divider.txt @@ -1,7 +1,5 @@ Binding for TI divider clock -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register-mapped adjustable clock rate divider that does not gate and has only one input clock or parent. By default the value programmed into diff --git a/Documentation/devicetree/bindings/clock/ti/dpll.txt b/Documentation/devicetree/bindings/clock/ti/dpll.txt index 37a7cb6ad07d..14a1b72c2e71 100644 --- a/Documentation/devicetree/bindings/clock/ti/dpll.txt +++ b/Documentation/devicetree/bindings/clock/ti/dpll.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments DPLL clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register-mapped DPLL with usually two selectable input clocks (reference clock and bypass clock), with digital phase locked diff --git a/Documentation/devicetree/bindings/clock/ti/fapll.txt b/Documentation/devicetree/bindings/clock/ti/fapll.txt index c19b3f253b8c..88986ef39ddd 100644 --- a/Documentation/devicetree/bindings/clock/ti/fapll.txt +++ b/Documentation/devicetree/bindings/clock/ti/fapll.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments FAPLL clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register-mapped FAPLL with usually two selectable input clocks (reference clock and bypass clock), and one or more child diff --git a/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt b/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt index 518e3c142276..dc69477b6e98 100644 --- a/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt +++ b/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt @@ -1,7 +1,5 @@ Binding for TI fixed factor rate clock sources. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1], and also uses the autoidle support from TI autoidle clock [2]. diff --git a/Documentation/devicetree/bindings/clock/ti/gate.txt b/Documentation/devicetree/bindings/clock/ti/gate.txt index 4982615c01b9..a8e0335b006a 100644 --- a/Documentation/devicetree/bindings/clock/ti/gate.txt +++ b/Documentation/devicetree/bindings/clock/ti/gate.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments gate clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. This clock is quite much similar to the basic gate-clock [2], however, it supports a number of additional features. If no register diff --git a/Documentation/devicetree/bindings/clock/ti/interface.txt b/Documentation/devicetree/bindings/clock/ti/interface.txt index d3eb5ca92a7f..85fb1f2d2d28 100644 --- a/Documentation/devicetree/bindings/clock/ti/interface.txt +++ b/Documentation/devicetree/bindings/clock/ti/interface.txt @@ -1,7 +1,5 @@ Binding for Texas Instruments interface clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. This clock is quite much similar to the basic gate-clock [2], however, it supports a number of additional features, including diff --git a/Documentation/devicetree/bindings/clock/ti/mux.txt b/Documentation/devicetree/bindings/clock/ti/mux.txt index b33f641f1043..cd56d3c1c09f 100644 --- a/Documentation/devicetree/bindings/clock/ti/mux.txt +++ b/Documentation/devicetree/bindings/clock/ti/mux.txt @@ -1,7 +1,5 @@ Binding for TI mux clock. -Binding status: Unstable - ABI compatibility may be broken in the future - This binding uses the common clock binding[1]. It assumes a register-mapped multiplexer with multiple input clock signals or parents, one of which can be selected as output. This clock does not diff --git a/Documentation/devicetree/bindings/dts-coding-style.rst b/Documentation/devicetree/bindings/dts-coding-style.rst index a9bdd2b59dca..8a68331075a0 100644 --- a/Documentation/devicetree/bindings/dts-coding-style.rst +++ b/Documentation/devicetree/bindings/dts-coding-style.rst @@ -144,6 +144,8 @@ Example:: #dma-cells = <1>; clocks = <&clock_controller 0>, <&clock_controller 1>; clock-names = "bus", "host"; + #address-cells = <1>; + #size-cells = <1>; vendor,custom-property = <2>; status = "disabled"; diff --git a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml index 528ef3572b62..055a3351880b 100644 --- a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml +++ b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml @@ -94,6 +94,10 @@ properties: local-bd-address: true + qcom,local-bd-address-broken: + type: boolean + description: + boot firmware is incorrectly passing the address in big-endian order required: - compatible diff --git a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt index 25f8658e216f..48a49c516b62 100644 --- a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt +++ b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt @@ -1,9 +1,6 @@ TI Davinci DSP devices ======================= -Binding status: Unstable - Subject to changes for DT representation of clocks - and resets - The TI Davinci family of SoCs usually contains a TI DSP Core sub-system that is used to offload some of the processor-intensive tasks or algorithms, for achieving various system level goals. diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml index 397f75909b20..ce1a6505eb51 100644 --- a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml +++ b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml @@ -51,7 +51,7 @@ properties: ranges: true patternProperties: - "^clock-controller@[0-9a-z]+$": + "^clock-controller@[0-9a-f]+$": $ref: /schemas/clock/fsl,flexspi-clock.yaml# required: diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml index 8d088b5fe823..a6a511b00a12 100644 --- a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml +++ b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml @@ -41,7 +41,7 @@ properties: ranges: true patternProperties: - "^interrupt-controller@[a-z0-9]+$": + "^interrupt-controller@[a-f0-9]+$": $ref: /schemas/interrupt-controller/fsl,ls-extirq.yaml# required: diff --git a/Documentation/devicetree/bindings/sound/rt5645.txt b/Documentation/devicetree/bindings/sound/rt5645.txt index 41a62fd2ae1f..c1fa379f5f3e 100644 --- a/Documentation/devicetree/bindings/sound/rt5645.txt +++ b/Documentation/devicetree/bindings/sound/rt5645.txt @@ -20,6 +20,11 @@ Optional properties: a GPIO spec for the external headphone detect pin. If jd-mode = 0, we will get the JD status by getting the value of hp-detect-gpios. +- cbj-sleeve-gpios: + a GPIO spec to control the external combo jack circuit to tie the sleeve/ring2 + contacts to the ground or floating. It could avoid some electric noise from the + active speaker jacks. + - realtek,in2-differential Boolean. Indicate MIC2 input are differential, rather than single-ended. @@ -68,6 +73,7 @@ codec: rt5650@1a { compatible = "realtek,rt5650"; reg = <0x1a>; hp-detect-gpios = <&gpio 19 0>; + cbj-sleeve-gpios = <&gpio 20 0>; interrupt-parent = <&gpio>; interrupts = <7 IRQ_TYPE_EDGE_FALLING>; realtek,dmic-en = "true"; diff --git a/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml b/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml index 7a4a6ab85970..ab8f28993139 100644 --- a/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml +++ b/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml @@ -60,7 +60,7 @@ properties: be implemented in an always-on power domain." patternProperties: - '^frame@[0-9a-z]*$': + '^frame@[0-9a-f]+$': type: object additionalProperties: false description: A timer node has up to 8 frame sub-nodes, each with the following properties. diff --git a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml index 10c146424baa..cd3680dc002f 100644 --- a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml +++ b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml @@ -27,10 +27,13 @@ properties: - qcom,msm8996-ufshc - qcom,msm8998-ufshc - qcom,sa8775p-ufshc + - qcom,sc7180-ufshc - qcom,sc7280-ufshc + - qcom,sc8180x-ufshc - qcom,sc8280xp-ufshc - qcom,sdm845-ufshc - qcom,sm6115-ufshc + - qcom,sm6125-ufshc - qcom,sm6350-ufshc - qcom,sm8150-ufshc - qcom,sm8250-ufshc @@ -42,11 +45,11 @@ properties: - const: jedec,ufs-2.0 clocks: - minItems: 8 + minItems: 7 maxItems: 11 clock-names: - minItems: 8 + minItems: 7 maxItems: 11 dma-coherent: true @@ -117,9 +120,35 @@ allOf: compatible: contains: enum: + - qcom,sc7180-ufshc + then: + properties: + clocks: + minItems: 7 + maxItems: 7 + clock-names: + items: + - const: core_clk + - const: bus_aggr_clk + - const: iface_clk + - const: core_clk_unipro + - const: ref_clk + - const: tx_lane0_sync_clk + - const: rx_lane0_sync_clk + reg: + maxItems: 1 + reg-names: + maxItems: 1 + + - if: + properties: + compatible: + contains: + enum: - qcom,msm8998-ufshc - qcom,sa8775p-ufshc - qcom,sc7280-ufshc + - qcom,sc8180x-ufshc - qcom,sc8280xp-ufshc - qcom,sm8250-ufshc - qcom,sm8350-ufshc @@ -215,6 +244,7 @@ allOf: contains: enum: - qcom,sm6115-ufshc + - qcom,sm6125-ufshc then: properties: clocks: @@ -248,7 +278,7 @@ allOf: reg: maxItems: 1 clocks: - minItems: 8 + minItems: 7 maxItems: 8 else: properties: @@ -256,7 +286,7 @@ allOf: minItems: 1 maxItems: 2 clocks: - minItems: 8 + minItems: 7 maxItems: 11 unevaluatedProperties: false diff --git a/Documentation/networking/devlink/devlink-eswitch-attr.rst b/Documentation/networking/devlink/devlink-eswitch-attr.rst new file mode 100644 index 000000000000..08bb39ab1528 --- /dev/null +++ b/Documentation/networking/devlink/devlink-eswitch-attr.rst @@ -0,0 +1,76 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================== +Devlink E-Switch Attribute +========================== + +Devlink E-Switch supports two modes of operation: legacy and switchdev. +Legacy mode operates based on traditional MAC/VLAN steering rules. Switching +decisions are made based on MAC addresses, VLANs, etc. There is limited ability +to offload switching rules to hardware. + +On the other hand, switchdev mode allows for more advanced offloading +capabilities of the E-Switch to hardware. In switchdev mode, more switching +rules and logic can be offloaded to the hardware switch ASIC. It enables +representor netdevices that represent the slow path of virtual functions (VFs) +or scalable-functions (SFs) of the device. See more information about +:ref:`Documentation/networking/switchdev.rst <switchdev>` and +:ref:`Documentation/networking/representors.rst <representors>`. + +In addition, the devlink E-Switch also comes with other attributes listed +in the following section. + +Attributes Description +====================== + +The following is a list of E-Switch attributes. + +.. list-table:: E-Switch attributes + :widths: 8 5 45 + + * - Name + - Type + - Description + * - ``mode`` + - enum + - The mode of the device. The mode can be one of the following: + + * ``legacy`` operates based on traditional MAC/VLAN steering + rules. + * ``switchdev`` allows for more advanced offloading capabilities of + the E-Switch to hardware. + * - ``inline-mode`` + - enum + - Some HWs need the VF driver to put part of the packet + headers on the TX descriptor so the e-switch can do proper + matching and steering. Support for both switchdev mode and legacy mode. + + * ``none`` none. + * ``link`` L2 mode. + * ``network`` L3 mode. + * ``transport`` L4 mode. + * - ``encap-mode`` + - enum + - The encapsulation mode of the device. Support for both switchdev mode + and legacy mode. The mode can be one of the following: + + * ``none`` Disable encapsulation support. + * ``basic`` Enable encapsulation support. + +Example Usage +============= + +.. code:: shell + + # enable switchdev mode + $ devlink dev eswitch set pci/0000:08:00.0 mode switchdev + + # set inline-mode and encap-mode + $ devlink dev eswitch set pci/0000:08:00.0 inline-mode none encap-mode basic + + # display devlink device eswitch attributes + $ devlink dev eswitch show pci/0000:08:00.0 + pci/0000:08:00.0: mode switchdev inline-mode none encap-mode basic + + # enable encap-mode with legacy mode + $ devlink dev eswitch set pci/0000:08:00.0 mode legacy inline-mode none encap-mode basic diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index e14d7a701b72..948c8c44e233 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -67,6 +67,7 @@ general. devlink-selftests devlink-trap devlink-linecard + devlink-eswitch-attr Driver-specific documentation ----------------------------- diff --git a/Documentation/networking/representors.rst b/Documentation/networking/representors.rst index decb39c19b9e..5e23386f6968 100644 --- a/Documentation/networking/representors.rst +++ b/Documentation/networking/representors.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GPL-2.0 +.. _representors: ============================= Network Function Representors diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index 995780088eb2..84335d119ff1 100644 --- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -46,21 +46,16 @@ SEV hardware uses ASIDs to associate a memory encryption key with a VM. Hence, the ASID for the SEV-enabled guests must be from 1 to a maximum value defined in the CPUID 0x8000001f[ecx] field. -SEV Key Management -================== +The KVM_MEMORY_ENCRYPT_OP ioctl +=============================== -The SEV guest key management is handled by a separate processor called the AMD -Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure -key management interface to perform common hypervisor activities such as -encrypting bootstrap code, snapshot, migrating and debugging the guest. For more -information, see the SEV Key Management spec [api-spec]_ - -The main ioctl to access SEV is KVM_MEMORY_ENCRYPT_OP. If the argument -to KVM_MEMORY_ENCRYPT_OP is NULL, the ioctl returns 0 if SEV is enabled -and ``ENOTTY`` if it is disabled (on some older versions of Linux, -the ioctl runs normally even with a NULL argument, and therefore will -likely return ``EFAULT``). If non-NULL, the argument to KVM_MEMORY_ENCRYPT_OP -must be a struct kvm_sev_cmd:: +The main ioctl to access SEV is KVM_MEMORY_ENCRYPT_OP, which operates on +the VM file descriptor. If the argument to KVM_MEMORY_ENCRYPT_OP is NULL, +the ioctl returns 0 if SEV is enabled and ``ENOTTY`` if it is disabled +(on some older versions of Linux, the ioctl tries to run normally even +with a NULL argument, and therefore will likely return ``EFAULT`` instead +of zero if SEV is enabled). If non-NULL, the argument to +KVM_MEMORY_ENCRYPT_OP must be a struct kvm_sev_cmd:: struct kvm_sev_cmd { __u32 id; @@ -87,10 +82,6 @@ guests, such as launching, running, snapshotting, migrating and decommissioning. The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform context. In a typical workflow, this command should be the first command issued. -The firmware can be initialized either by using its own non-volatile storage or -the OS can manage the NV storage for the firmware using the module parameter -``init_ex_path``. If the file specified by ``init_ex_path`` does not exist or -is invalid, the OS will create or override the file with output from PSP. Returns: 0 on success, -negative on error @@ -434,6 +425,21 @@ issued by the hypervisor to make the guest ready for execution. Returns: 0 on success, -negative on error +Firmware Management +=================== + +The SEV guest key management is handled by a separate processor called the AMD +Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure +key management interface to perform common hypervisor activities such as +encrypting bootstrap code, snapshot, migrating and debugging the guest. For more +information, see the SEV Key Management spec [api-spec]_ + +The AMD-SP firmware can be initialized either by using its own non-volatile +storage or the OS can manage the NV storage for the firmware using +parameter ``init_ex_path`` of the ``ccp`` module. If the file specified +by ``init_ex_path`` does not exist or is invalid, the OS will create or +override the file with PSP non-volatile storage. + References ========== diff --git a/Documentation/virt/kvm/x86/msr.rst b/Documentation/virt/kvm/x86/msr.rst index 9315fc385fb0..3aecf2a70e7b 100644 --- a/Documentation/virt/kvm/x86/msr.rst +++ b/Documentation/virt/kvm/x86/msr.rst @@ -193,8 +193,8 @@ data: Asynchronous page fault (APF) control MSR. Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area - which must be in guest RAM and must be zeroed. This memory is expected - to hold a copy of the following structure:: + which must be in guest RAM. This memory is expected to hold the + following structure:: struct kvm_vcpu_pv_apf_data { /* Used for 'page not present' events delivered via #PF */ @@ -204,7 +204,6 @@ data: __u32 token; __u8 pad[56]; - __u32 enabled; }; Bits 5-4 of the MSR are reserved and should be zero. Bit 0 is set to 1 @@ -232,14 +231,14 @@ data: as regular page fault, guest must reset 'flags' to '0' before it does something that can generate normal page fault. - Bytes 5-7 of 64 byte memory location ('token') will be written to by the + Bytes 4-7 of 64 byte memory location ('token') will be written to by the hypervisor at the time of APF 'page ready' event injection. The content - of these bytes is a token which was previously delivered as 'page not - present' event. The event indicates the page in now available. Guest is - supposed to write '0' to 'token' when it is done handling 'page ready' - event and to write 1' to MSR_KVM_ASYNC_PF_ACK after clearing the location; - writing to the MSR forces KVM to re-scan its queue and deliver the next - pending notification. + of these bytes is a token which was previously delivered in CR2 as + 'page not present' event. The event indicates the page is now available. + Guest is supposed to write '0' to 'token' when it is done handling + 'page ready' event and to write '1' to MSR_KVM_ASYNC_PF_ACK after + clearing the location; writing to the MSR forces KVM to re-scan its + queue and deliver the next pending notification. Note, MSR_KVM_ASYNC_PF_INT MSR specifying the interrupt vector for 'page ready' APF delivery needs to be written to before enabling APF mechanism diff --git a/MAINTAINERS b/MAINTAINERS index aa3b455588e1..2eda0f98adb5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14019,6 +14019,7 @@ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) M: Saeed Mahameed <saeedm@nvidia.com> +M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -14086,6 +14087,7 @@ F: include/uapi/rdma/mlx4-abi.h MELLANOX MLX5 core VPI driver M: Saeed Mahameed <saeedm@nvidia.com> M: Leon Romanovsky <leonro@nvidia.com> +M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported @@ -16731,9 +16733,9 @@ F: include/uapi/linux/ppdev.h PARAVIRT_OPS INTERFACE M: Juergen Gross <jgross@suse.com> -R: Ajay Kaher <akaher@vmware.com> -R: Alexey Makhalov <amakhalov@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +R: Ajay Kaher <ajay.kaher@broadcom.com> +R: Alexey Makhalov <alexey.amakhalov@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: virtualization@lists.linux.dev L: x86@kernel.org S: Supported @@ -22441,6 +22443,7 @@ S: Maintained W: https://kernsec.org/wiki/index.php/Linux_Kernel_Integrity Q: https://patchwork.kernel.org/project/linux-integrity/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git +F: Documentation/devicetree/bindings/tpm/ F: drivers/char/tpm/ TPS546D24 DRIVER @@ -23665,9 +23668,9 @@ S: Supported F: drivers/misc/vmw_balloon.c VMWARE HYPERVISOR INTERFACE -M: Ajay Kaher <akaher@vmware.com> -M: Alexey Makhalov <amakhalov@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Ajay Kaher <ajay.kaher@broadcom.com> +M: Alexey Makhalov <alexey.amakhalov@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: virtualization@lists.linux.dev L: x86@kernel.org S: Supported @@ -23676,34 +23679,34 @@ F: arch/x86/include/asm/vmware.h F: arch/x86/kernel/cpu/vmware.c VMWARE PVRDMA DRIVER -M: Bryan Tan <bryantan@vmware.com> -M: Vishnu Dasa <vdasa@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Bryan Tan <bryan-bt.tan@broadcom.com> +M: Vishnu Dasa <vishnu.dasa@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/vmw_pvrdma/ VMWARE PVSCSI DRIVER -M: Vishal Bhakta <vbhakta@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Vishal Bhakta <vishal.bhakta@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-scsi@vger.kernel.org S: Supported F: drivers/scsi/vmw_pvscsi.c F: drivers/scsi/vmw_pvscsi.h VMWARE VIRTUAL PTP CLOCK DRIVER -M: Jeff Sipek <jsipek@vmware.com> -R: Ajay Kaher <akaher@vmware.com> -R: Alexey Makhalov <amakhalov@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Nick Shi <nick.shi@broadcom.com> +R: Ajay Kaher <ajay.kaher@broadcom.com> +R: Alexey Makhalov <alexey.amakhalov@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: drivers/ptp/ptp_vmw.c VMWARE VMCI DRIVER -M: Bryan Tan <bryantan@vmware.com> -M: Vishnu Dasa <vdasa@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Bryan Tan <bryan-bt.tan@broadcom.com> +M: Vishnu Dasa <vishnu.dasa@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-kernel@vger.kernel.org S: Supported F: drivers/misc/vmw_vmci/ @@ -23718,16 +23721,16 @@ F: drivers/input/mouse/vmmouse.c F: drivers/input/mouse/vmmouse.h VMWARE VMXNET3 ETHERNET DRIVER -M: Ronak Doshi <doshir@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Ronak Doshi <ronak.doshi@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/vmxnet3/ VMWARE VSOCK VMCI TRANSPORT DRIVER -M: Bryan Tan <bryantan@vmware.com> -M: Vishnu Dasa <vdasa@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Bryan Tan <bryan-bt.tan@broadcom.com> +M: Vishnu Dasa <vishnu.dasa@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-kernel@vger.kernel.org S: Supported F: net/vmw_vsock/vmci_transport* @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index f3a6da8b2890..5260c63db007 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -944,6 +944,8 @@ ap_spi_fp: &spi10 { vddrf-supply = <&pp1300_l2c>; vddch0-supply = <&pp3300_l10c>; max-speed = <3200000>; + + qcom,local-bd-address-broken; }; }; diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ce08b744aaab..06234c3a15f3 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -291,6 +291,21 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) blr x2 0: mov_q x0, HCR_HOST_NVHE_FLAGS + + /* + * Compliant CPUs advertise their VHE-onlyness with + * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be + * RES1 in that case. Publish the E2H bit early so that + * it can be picked up by the init_el2_state macro. + * + * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but + * don't advertise it (they predate this relaxation). + */ + mrs_s x1, SYS_ID_AA64MMFR4_EL1 + tbz x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f + + orr x0, x0, #HCR_E2H +1: msr hcr_el2, x0 isb @@ -303,22 +318,10 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) mov_q x1, INIT_SCTLR_EL1_MMU_OFF - /* - * Compliant CPUs advertise their VHE-onlyness with - * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be - * RES1 in that case. - * - * Fruity CPUs seem to have HCR_EL2.E2H set to RES1, but - * don't advertise it (they predate this relaxation). - */ - mrs_s x0, SYS_ID_AA64MMFR4_EL1 - ubfx x0, x0, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH - tbnz x0, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f - mrs x0, hcr_el2 and x0, x0, #HCR_E2H cbz x0, 2f -1: + /* Set a sane SCTLR_EL1, the VHE way */ pre_disable_mmu_workaround msr_s SYS_SCTLR_EL12, x1 diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 162b030ab9da..0d022599eb61 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -761,7 +761,6 @@ static void sve_init_header_from_task(struct user_sve_header *header, { unsigned int vq; bool active; - bool fpsimd_only; enum vec_type task_type; memset(header, 0, sizeof(*header)); @@ -777,12 +776,10 @@ static void sve_init_header_from_task(struct user_sve_header *header, case ARM64_VEC_SVE: if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; - fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); break; case ARM64_VEC_SME: if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; - fpsimd_only = false; break; default: WARN_ON_ONCE(1); @@ -790,7 +787,7 @@ static void sve_init_header_from_task(struct user_sve_header *header, } if (active) { - if (fpsimd_only) { + if (target->thread.fp_type == FP_STATE_FPSIMD) { header->flags |= SVE_PT_REGS_FPSIMD; } else { header->flags |= SVE_PT_REGS_SVE; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3dee5490eea9..c4a0a35e02c7 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2597,14 +2597,11 @@ static __init int kvm_arm_init(void) if (err) goto out_hyp; - if (is_protected_kvm_enabled()) { - kvm_info("Protected nVHE mode initialized successfully\n"); - } else if (in_hyp_mode) { - kvm_info("VHE mode initialized successfully\n"); - } else { - char mode = cpus_have_final_cap(ARM64_KVM_HVHE) ? 'h' : 'n'; - kvm_info("Hyp mode (%cVHE) initialized successfully\n", mode); - } + kvm_info("%s%sVHE mode initialized successfully\n", + in_hyp_mode ? "" : (is_protected_kvm_enabled() ? + "Protected " : "Hyp "), + in_hyp_mode ? "" : (cpus_have_final_cap(ARM64_KVM_HVHE) ? + "h" : "n")); /* * FIXME: Do something reasonable if kvm_init() fails after pKVM diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index a60fb13e2192..2fc68da4036d 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -154,7 +154,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, /* Switch to requested VMID */ __tlb_switch_to_guest(mmu, &cxt, false); - __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0); + __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, + TLBI_TTL_UNKNOWN); dsb(ish); __tlbi(vmalle1is); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 3fae5830f8d2..5a59ef88b646 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -528,7 +528,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, kvm_clear_pte(ctx->ptep); dsb(ishst); - __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); + __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), TLBI_TTL_UNKNOWN); } else { if (ctx->end - ctx->addr < granule) return -EINVAL; @@ -843,12 +843,15 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, * Perform the appropriate TLB invalidation based on the * evicted pte value (if any). */ - if (kvm_pte_table(ctx->old, ctx->level)) - kvm_tlb_flush_vmid_range(mmu, ctx->addr, - kvm_granule_size(ctx->level)); - else if (kvm_pte_valid(ctx->old)) + if (kvm_pte_table(ctx->old, ctx->level)) { + u64 size = kvm_granule_size(ctx->level); + u64 addr = ALIGN_DOWN(ctx->addr, size); + + kvm_tlb_flush_vmid_range(mmu, addr, size); + } else if (kvm_pte_valid(ctx->old)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); + } } if (stage2_pte_is_counted(ctx->old)) @@ -896,9 +899,13 @@ static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx, if (kvm_pte_valid(ctx->old)) { kvm_clear_pte(ctx->ptep); - if (!stage2_unmap_defer_tlb_flush(pgt)) - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, - ctx->addr, ctx->level); + if (kvm_pte_table(ctx->old, ctx->level)) { + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, + TLBI_TTL_UNKNOWN); + } else if (!stage2_unmap_defer_tlb_flush(pgt)) { + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, + ctx->level); + } } mm_ops->put_page(ctx->ptep); diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c index b32e2940df7d..1a60b95381e8 100644 --- a/arch/arm64/kvm/hyp/vhe/tlb.c +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -171,7 +171,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, /* Switch to requested VMID */ __tlb_switch_to_guest(mmu, &cxt); - __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0); + __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, + TLBI_TTL_UNKNOWN); dsb(ish); __tlbi(vmalle1is); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 18680771cdb0..dc04bc767865 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1637,7 +1637,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); - if (esr_fsc_is_permission_fault(esr)) { + if (esr_fsc_is_translation_fault(esr)) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c index 8d98af5c7201..9a8393e6b4a8 100644 --- a/arch/nios2/kernel/prom.c +++ b/arch/nios2/kernel/prom.c @@ -21,7 +21,8 @@ void __init early_init_devtree(void *params) { - __be32 *dtb = (u32 *)__dtb_start; + __be32 __maybe_unused *dtb = (u32 *)__dtb_start; + #if defined(CONFIG_NIOS2_DTB_AT_PHYS_ADDR) if (be32_to_cpup((__be32 *)CONFIG_NIOS2_DTB_PHYS_ADDR) == OF_DT_HEADER) { @@ -30,8 +31,11 @@ void __init early_init_devtree(void *params) return; } #endif + +#ifdef CONFIG_NIOS2_DTB_SOURCE_BOOL if (be32_to_cpu((__be32) *dtb) == OF_DT_HEADER) params = (void *)__dtb_start; +#endif early_init_dt_scan(params); } diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index f0a4cf01e85c..78302f6c2580 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -4,7 +4,6 @@ #ifndef __ASSEMBLY__ -#include <asm/page.h> #include <asm/vdso/timebase.h> #include <asm/barrier.h> #include <asm/unistd.h> @@ -95,7 +94,7 @@ const struct vdso_data *__arch_get_vdso_data(void); static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { - return (void *)vd + PAGE_SIZE; + return (void *)vd + (1U << CONFIG_PAGE_SHIFT); } #endif diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 252d63942f34..5b3115a19852 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -151,7 +151,7 @@ endif endif vdso-install-y += arch/riscv/kernel/vdso/vdso.so.dbg -vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg:../compat_vdso/compat_vdso.so +vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg ifneq ($(CONFIG_XIP_KERNEL),y) ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_ARCH_CANAAN),yy) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 97fcde30e247..9f8ea0e33eb1 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -593,6 +593,12 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, return ptep_test_and_clear_young(vma, address, ptep); } +#define pgprot_nx pgprot_nx +static inline pgprot_t pgprot_nx(pgprot_t _prot) +{ + return __pgprot(pgprot_val(_prot) & ~_PAGE_EXEC); +} + #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t _prot) { diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h index 980094c2e976..ac80216549ff 100644 --- a/arch/riscv/include/asm/syscall_wrapper.h +++ b/arch/riscv/include/asm/syscall_wrapper.h @@ -36,7 +36,8 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *); ulong) \ __attribute__((alias(__stringify(___se_##prefix##name)))); \ __diag_pop(); \ - static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + __used; \ static long ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) #define SC_RISCV_REGS_TO_ARGS(x, ...) \ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index ec0cab9fbddd..72ec1d9bd3f3 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -319,7 +319,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ if (unlikely(__kr_err)) \ @@ -328,7 +328,7 @@ do { \ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 10aaa83db89e..95050ebe9ad0 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -34,7 +34,7 @@ #define AT_L3_CACHEGEOMETRY 47 /* entries in ARCH_DLINFO */ -#define AT_VECTOR_SIZE_ARCH 9 +#define AT_VECTOR_SIZE_ARCH 10 #define AT_MINSIGSTKSZ 51 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 62fa393b2eb2..3df4cb788c1f 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -74,5 +74,5 @@ quiet_cmd_compat_vdsold = VDSOLD $@ rm $@.tmp # actual build commands -quiet_cmd_compat_vdsoas = VDSOAS $@ +quiet_cmd_compat_vdsoas = VDSOAS $@ cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $< diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 37e87fdcf6a0..30e12b310cab 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -80,6 +80,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len) */ lockdep_assert_held(&text_mutex); + preempt_disable(); + if (across_pages) patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); @@ -92,6 +94,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len) if (across_pages) patch_unmap(FIX_TEXT_POKE1); + preempt_enable(); + return 0; } NOKPROBE_SYMBOL(__patch_insn_set); @@ -122,6 +126,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len) if (!riscv_patch_in_stop_machine) lockdep_assert_held(&text_mutex); + preempt_disable(); + if (across_pages) patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); @@ -134,6 +140,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len) if (across_pages) patch_unmap(FIX_TEXT_POKE1); + preempt_enable(); + return ret; } NOKPROBE_SYMBOL(__patch_insn_write); diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 92922dbd5b5c..e4bc61c4e58a 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -27,8 +27,6 @@ #include <asm/vector.h> #include <asm/cpufeature.h> -register unsigned long gp_in_global __asm__("gp"); - #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> unsigned long __stack_chk_guard __read_mostly; @@ -37,7 +35,7 @@ EXPORT_SYMBOL(__stack_chk_guard); extern asmlinkage void ret_from_fork(void); -void arch_cpu_idle(void) +void noinstr arch_cpu_idle(void) { cpu_do_idle(); } @@ -207,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (unlikely(args->fn)) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 501e66debf69..5a2edd7f027e 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -119,6 +119,13 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) struct __sc_riscv_v_state __user *state = sc_vec; void __user *datap; + /* + * Mark the vstate as clean prior performing the actual copy, + * to avoid getting the vstate incorrectly clobbered by the + * discarded vector state. + */ + riscv_v_vstate_set_restore(current, regs); + /* Copy everything of __sc_riscv_v_state except datap. */ err = __copy_from_user(¤t->thread.vstate, &state->v_state, offsetof(struct __riscv_v_ext_state, datap)); @@ -133,13 +140,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) * Copy the whole vector content from user space datap. Use * copy_from_user to prevent information leak. */ - err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); - if (unlikely(err)) - return err; - - riscv_v_vstate_set_restore(current, regs); - - return err; + return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); } #else #define save_v_state(task, regs) (0) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 868d6280cf66..05a16b1f0aee 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -122,7 +122,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) print_vma_addr(KERN_CONT " in ", instruction_pointer(regs)); pr_cont("\n"); __show_regs(regs); - dump_instr(KERN_EMERG, regs); + dump_instr(KERN_INFO, regs); } force_sig_fault(signo, code, (void __user *)addr); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 9b517fe1b8a8..272c431ac5b9 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -37,6 +37,7 @@ endif # Disable -pg to prevent insert call site CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) +CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) # Disable profiling and instrumentation for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c index 39e72aa016a4..b467ba5ed910 100644 --- a/arch/riscv/kvm/aia_aplic.c +++ b/arch/riscv/kvm/aia_aplic.c @@ -137,11 +137,21 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) raw_spin_lock_irqsave(&irqd->lock, flags); sm = irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK; - if (!pending && - ((sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) || - (sm == APLIC_SOURCECFG_SM_LEVEL_LOW))) + if (sm == APLIC_SOURCECFG_SM_INACTIVE) goto skip_write_pending; + if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH || + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) { + if (!pending) + goto skip_write_pending; + if ((irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) + goto skip_write_pending; + if (!(irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) + goto skip_write_pending; + } + if (pending) irqd->state |= APLIC_IRQ_STATE_PENDING; else @@ -187,16 +197,31 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled) static bool aplic_read_input(struct aplic *aplic, u32 irq) { - bool ret; - unsigned long flags; + u32 sourcecfg, sm, raw_input, irq_inverted; struct aplic_irq *irqd; + unsigned long flags; + bool ret = false; if (!irq || aplic->nr_irqs <= irq) return false; irqd = &aplic->irqs[irq]; raw_spin_lock_irqsave(&irqd->lock, flags); - ret = (irqd->state & APLIC_IRQ_STATE_INPUT) ? true : false; + + sourcecfg = irqd->sourcecfg; + if (sourcecfg & APLIC_SOURCECFG_D) + goto skip; + + sm = sourcecfg & APLIC_SOURCECFG_SM_MASK; + if (sm == APLIC_SOURCECFG_SM_INACTIVE) + goto skip; + + raw_input = (irqd->state & APLIC_IRQ_STATE_INPUT) ? 1 : 0; + irq_inverted = (sm == APLIC_SOURCECFG_SM_LEVEL_LOW || + sm == APLIC_SOURCECFG_SM_EDGE_FALL) ? 1 : 0; + ret = !!(raw_input ^ irq_inverted); + +skip: raw_spin_unlock_irqrestore(&irqd->lock, flags); return ret; diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index f4a6124d25c9..994adc26db4b 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -986,7 +986,7 @@ static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu, static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu) { - return copy_isa_ext_reg_indices(vcpu, NULL);; + return copy_isa_ext_reg_indices(vcpu, NULL); } static int copy_sbi_ext_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 893566e004b7..07d743f87b3f 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -99,7 +99,7 @@ static void __ipi_flush_tlb_range_asid(void *info) local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid); } -static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid, +static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid, unsigned long start, unsigned long size, unsigned long stride) { @@ -200,7 +200,7 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, void flush_tlb_kernel_range(unsigned long start, unsigned long end) { - __flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID, + __flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID, start, end - start, PAGE_SIZE); } diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 7138d189cc42..0c4cad7d5a5b 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -15,31 +15,31 @@ #include <asm/barrier.h> #include <asm/cmpxchg.h> -static inline int arch_atomic_read(const atomic_t *v) +static __always_inline int arch_atomic_read(const atomic_t *v) { return __atomic_read(v); } #define arch_atomic_read arch_atomic_read -static inline void arch_atomic_set(atomic_t *v, int i) +static __always_inline void arch_atomic_set(atomic_t *v, int i) { __atomic_set(v, i); } #define arch_atomic_set arch_atomic_set -static inline int arch_atomic_add_return(int i, atomic_t *v) +static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { return __atomic_add_barrier(i, &v->counter) + i; } #define arch_atomic_add_return arch_atomic_add_return -static inline int arch_atomic_fetch_add(int i, atomic_t *v) +static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return __atomic_add_barrier(i, &v->counter); } #define arch_atomic_fetch_add arch_atomic_fetch_add -static inline void arch_atomic_add(int i, atomic_t *v) +static __always_inline void arch_atomic_add(int i, atomic_t *v) { __atomic_add(i, &v->counter); } @@ -50,11 +50,11 @@ static inline void arch_atomic_add(int i, atomic_t *v) #define arch_atomic_fetch_sub(_i, _v) arch_atomic_fetch_add(-(int)(_i), _v) #define ATOMIC_OPS(op) \ -static inline void arch_atomic_##op(int i, atomic_t *v) \ +static __always_inline void arch_atomic_##op(int i, atomic_t *v) \ { \ __atomic_##op(i, &v->counter); \ } \ -static inline int arch_atomic_fetch_##op(int i, atomic_t *v) \ +static __always_inline int arch_atomic_fetch_##op(int i, atomic_t *v) \ { \ return __atomic_##op##_barrier(i, &v->counter); \ } @@ -74,7 +74,7 @@ ATOMIC_OPS(xor) #define arch_atomic_xchg(v, new) (arch_xchg(&((v)->counter), new)) -static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) +static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { return __atomic_cmpxchg(&v->counter, old, new); } @@ -82,31 +82,31 @@ static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) #define ATOMIC64_INIT(i) { (i) } -static inline s64 arch_atomic64_read(const atomic64_t *v) +static __always_inline s64 arch_atomic64_read(const atomic64_t *v) { return __atomic64_read(v); } #define arch_atomic64_read arch_atomic64_read -static inline void arch_atomic64_set(atomic64_t *v, s64 i) +static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) { __atomic64_set(v, i); } #define arch_atomic64_set arch_atomic64_set -static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) { return __atomic64_add_barrier(i, (long *)&v->counter) + i; } #define arch_atomic64_add_return arch_atomic64_add_return -static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) +static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { return __atomic64_add_barrier(i, (long *)&v->counter); } #define arch_atomic64_fetch_add arch_atomic64_fetch_add -static inline void arch_atomic64_add(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) { __atomic64_add(i, (long *)&v->counter); } @@ -114,20 +114,20 @@ static inline void arch_atomic64_add(s64 i, atomic64_t *v) #define arch_atomic64_xchg(v, new) (arch_xchg(&((v)->counter), new)) -static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { return __atomic64_cmpxchg((long *)&v->counter, old, new); } #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg -#define ATOMIC64_OPS(op) \ -static inline void arch_atomic64_##op(s64 i, atomic64_t *v) \ -{ \ - __atomic64_##op(i, (long *)&v->counter); \ -} \ -static inline long arch_atomic64_fetch_##op(s64 i, atomic64_t *v) \ -{ \ - return __atomic64_##op##_barrier(i, (long *)&v->counter); \ +#define ATOMIC64_OPS(op) \ +static __always_inline void arch_atomic64_##op(s64 i, atomic64_t *v) \ +{ \ + __atomic64_##op(i, (long *)&v->counter); \ +} \ +static __always_inline long arch_atomic64_fetch_##op(s64 i, atomic64_t *v) \ +{ \ + return __atomic64_##op##_barrier(i, (long *)&v->counter); \ } ATOMIC64_OPS(and) diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h index 50510e08b893..7fa5f96a553a 100644 --- a/arch/s390/include/asm/atomic_ops.h +++ b/arch/s390/include/asm/atomic_ops.h @@ -8,7 +8,7 @@ #ifndef __ARCH_S390_ATOMIC_OPS__ #define __ARCH_S390_ATOMIC_OPS__ -static inline int __atomic_read(const atomic_t *v) +static __always_inline int __atomic_read(const atomic_t *v) { int c; @@ -18,14 +18,14 @@ static inline int __atomic_read(const atomic_t *v) return c; } -static inline void __atomic_set(atomic_t *v, int i) +static __always_inline void __atomic_set(atomic_t *v, int i) { asm volatile( " st %1,%0\n" : "=R" (v->counter) : "d" (i)); } -static inline s64 __atomic64_read(const atomic64_t *v) +static __always_inline s64 __atomic64_read(const atomic64_t *v) { s64 c; @@ -35,7 +35,7 @@ static inline s64 __atomic64_read(const atomic64_t *v) return c; } -static inline void __atomic64_set(atomic64_t *v, s64 i) +static __always_inline void __atomic64_set(atomic64_t *v, s64 i) { asm volatile( " stg %1,%0\n" @@ -45,7 +45,7 @@ static inline void __atomic64_set(atomic64_t *v, s64 i) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES #define __ATOMIC_OP(op_name, op_type, op_string, op_barrier) \ -static inline op_type op_name(op_type val, op_type *ptr) \ +static __always_inline op_type op_name(op_type val, op_type *ptr) \ { \ op_type old; \ \ @@ -96,7 +96,7 @@ __ATOMIC_CONST_OPS(__atomic64_add_const, long, "agsi") #else /* CONFIG_HAVE_MARCH_Z196_FEATURES */ #define __ATOMIC_OP(op_name, op_string) \ -static inline int op_name(int val, int *ptr) \ +static __always_inline int op_name(int val, int *ptr) \ { \ int old, new; \ \ @@ -122,7 +122,7 @@ __ATOMIC_OPS(__atomic_xor, "xr") #undef __ATOMIC_OPS #define __ATOMIC64_OP(op_name, op_string) \ -static inline long op_name(long val, long *ptr) \ +static __always_inline long op_name(long val, long *ptr) \ { \ long old, new; \ \ @@ -154,7 +154,7 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr") #endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */ -static inline int __atomic_cmpxchg(int *ptr, int old, int new) +static __always_inline int __atomic_cmpxchg(int *ptr, int old, int new) { asm volatile( " cs %[old],%[new],%[ptr]" @@ -164,7 +164,7 @@ static inline int __atomic_cmpxchg(int *ptr, int old, int new) return old; } -static inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new) +static __always_inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new) { int old_expected = old; @@ -176,7 +176,7 @@ static inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new) return old == old_expected; } -static inline long __atomic64_cmpxchg(long *ptr, long old, long new) +static __always_inline long __atomic64_cmpxchg(long *ptr, long old, long new) { asm volatile( " csg %[old],%[new],%[ptr]" @@ -186,7 +186,7 @@ static inline long __atomic64_cmpxchg(long *ptr, long old, long new) return old; } -static inline bool __atomic64_cmpxchg_bool(long *ptr, long old, long new) +static __always_inline bool __atomic64_cmpxchg_bool(long *ptr, long old, long new) { long old_expected = old; diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h index bf15da0fedbc..0e3da500e98c 100644 --- a/arch/s390/include/asm/preempt.h +++ b/arch/s390/include/asm/preempt.h @@ -12,12 +12,12 @@ #define PREEMPT_NEED_RESCHED 0x80000000 #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) -static inline int preempt_count(void) +static __always_inline int preempt_count(void) { return READ_ONCE(S390_lowcore.preempt_count) & ~PREEMPT_NEED_RESCHED; } -static inline void preempt_count_set(int pc) +static __always_inline void preempt_count_set(int pc) { int old, new; @@ -29,22 +29,22 @@ static inline void preempt_count_set(int pc) old, new) != old); } -static inline void set_preempt_need_resched(void) +static __always_inline void set_preempt_need_resched(void) { __atomic_and(~PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count); } -static inline void clear_preempt_need_resched(void) +static __always_inline void clear_preempt_need_resched(void) { __atomic_or(PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count); } -static inline bool test_preempt_need_resched(void) +static __always_inline bool test_preempt_need_resched(void) { return !(READ_ONCE(S390_lowcore.preempt_count) & PREEMPT_NEED_RESCHED); } -static inline void __preempt_count_add(int val) +static __always_inline void __preempt_count_add(int val) { /* * With some obscure config options and CONFIG_PROFILE_ALL_BRANCHES @@ -59,17 +59,17 @@ static inline void __preempt_count_add(int val) __atomic_add(val, &S390_lowcore.preempt_count); } -static inline void __preempt_count_sub(int val) +static __always_inline void __preempt_count_sub(int val) { __preempt_count_add(-val); } -static inline bool __preempt_count_dec_and_test(void) +static __always_inline bool __preempt_count_dec_and_test(void) { return __atomic_add(-1, &S390_lowcore.preempt_count) == 1; } -static inline bool should_resched(int preempt_offset) +static __always_inline bool should_resched(int preempt_offset) { return unlikely(READ_ONCE(S390_lowcore.preempt_count) == preempt_offset); @@ -79,45 +79,45 @@ static inline bool should_resched(int preempt_offset) #define PREEMPT_ENABLED (0) -static inline int preempt_count(void) +static __always_inline int preempt_count(void) { return READ_ONCE(S390_lowcore.preempt_count); } -static inline void preempt_count_set(int pc) +static __always_inline void preempt_count_set(int pc) { S390_lowcore.preempt_count = pc; } -static inline void set_preempt_need_resched(void) +static __always_inline void set_preempt_need_resched(void) { } -static inline void clear_preempt_need_resched(void) +static __always_inline void clear_preempt_need_resched(void) { } -static inline bool test_preempt_need_resched(void) +static __always_inline bool test_preempt_need_resched(void) { return false; } -static inline void __preempt_count_add(int val) +static __always_inline void __preempt_count_add(int val) { S390_lowcore.preempt_count += val; } -static inline void __preempt_count_sub(int val) +static __always_inline void __preempt_count_sub(int val) { S390_lowcore.preempt_count -= val; } -static inline bool __preempt_count_dec_and_test(void) +static __always_inline bool __preempt_count_dec_and_test(void) { return !--S390_lowcore.preempt_count && tif_need_resched(); } -static inline bool should_resched(int preempt_offset) +static __always_inline bool should_resched(int preempt_offset) { return unlikely(preempt_count() == preempt_offset && tif_need_resched()); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 787394978bc0..3dc85638bc63 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -635,6 +635,7 @@ SYM_DATA_START_LOCAL(daton_psw) SYM_DATA_END(daton_psw) .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame SYM_DATA_START(sys_call_table) #include "asm/syscall_table.h" diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index 823d652e3917..4ad472d130a3 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -90,7 +90,6 @@ static void paicrypt_event_destroy(struct perf_event *event) event->cpu); struct paicrypt_map *cpump = mp->mapptr; - cpump->event = NULL; static_branch_dec(&pai_key); mutex_lock(&pai_reserve_mutex); debug_sprintf_event(cfm_dbg, 5, "%s event %#llx cpu %d users %d" @@ -356,10 +355,15 @@ static int paicrypt_add(struct perf_event *event, int flags) static void paicrypt_stop(struct perf_event *event, int flags) { - if (!event->attr.sample_period) /* Counting */ + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; + + if (!event->attr.sample_period) { /* Counting */ paicrypt_read(event); - else /* Sampling */ + } else { /* Sampling */ perf_sched_cb_dec(event->pmu); + cpump->event = NULL; + } event->hw.state = PERF_HES_STOPPED; } diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index 616a25606cd6..a6da7e0cc7a6 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -122,7 +122,6 @@ static void paiext_event_destroy(struct perf_event *event) free_page(PAI_SAVE_AREA(event)); mutex_lock(&paiext_reserve_mutex); - cpump->event = NULL; if (refcount_dec_and_test(&cpump->refcnt)) /* Last reference gone */ paiext_free(mp); paiext_root_free(); @@ -362,10 +361,15 @@ static int paiext_add(struct perf_event *event, int flags) static void paiext_stop(struct perf_event *event, int flags) { - if (!event->attr.sample_period) /* Counting */ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + + if (!event->attr.sample_period) { /* Counting */ paiext_read(event); - else /* Sampling */ + } else { /* Sampling */ perf_sched_cb_dec(event->pmu); + cpump->event = NULL; + } event->hw.state = PERF_HES_STOPPED; } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index c421dd44ffbe..0c66b32e0f9f 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -75,7 +75,7 @@ static enum fault_type get_fault_type(struct pt_regs *regs) if (!IS_ENABLED(CONFIG_PGSTE)) return KERNEL_FAULT; gmap = (struct gmap *)S390_lowcore.gmap; - if (regs->cr1 == gmap->asce) + if (gmap && gmap->asce == regs->cr1) return GMAP_FAULT; return KERNEL_FAULT; } diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index d07be9d05cd0..b31ef2424d19 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -3,19 +3,28 @@ * Confidential Computing Platform Capability checks * * Copyright (C) 2021 Advanced Micro Devices, Inc. + * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * Author: Tom Lendacky <thomas.lendacky@amd.com> */ #include <linux/export.h> #include <linux/cc_platform.h> +#include <linux/string.h> +#include <linux/random.h> +#include <asm/archrandom.h> #include <asm/coco.h> #include <asm/processor.h> enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; u64 cc_mask __ro_after_init; +static struct cc_attr_flags { + __u64 host_sev_snp : 1, + __resv : 63; +} cc_flags; + static bool noinstr intel_cc_platform_has(enum cc_attr attr) { switch (attr) { @@ -89,6 +98,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_HOST_SEV_SNP: + return cc_flags.host_sev_snp; + default: return false; } @@ -148,3 +160,84 @@ u64 cc_mkdec(u64 val) } } EXPORT_SYMBOL_GPL(cc_mkdec); + +static void amd_cc_platform_clear(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 0; + break; + default: + break; + } +} + +void cc_platform_clear(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_clear(attr); + break; + default: + break; + } +} + +static void amd_cc_platform_set(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 1; + break; + default: + break; + } +} + +void cc_platform_set(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_set(attr); + break; + default: + break; + } +} + +__init void cc_random_init(void) +{ + /* + * The seed is 32 bytes (in units of longs), which is 256 bits, which + * is the security level that the RNG is targeting. + */ + unsigned long rng_seed[32 / sizeof(long)]; + size_t i, longs; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * Since the CoCo threat model includes the host, the only reliable + * source of entropy that can be neither observed nor manipulated is + * RDRAND. Usually, RDRAND failure is considered tolerable, but since + * CoCo guests have no other unobservable source of entropy, it's + * important to at least ensure the RNG gets some initial random seeds. + */ + for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) { + longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i); + + /* + * A zero return value means that the guest doesn't have RDRAND + * or the CPU is physically broken, and in both cases that + * means most crypto inside of the CoCo instance will be + * broken, defeating the purpose of CoCo in the first place. So + * just panic here because it's absolutely unsafe to continue + * executing. + */ + if (longs == 0) + panic("RDRAND is defective."); + } + add_device_randomness(rng_seed, sizeof(rng_seed)); + memzero_explicit(rng_seed, sizeof(rng_seed)); +} diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 2641ba620f12..e010bfed8417 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1237,11 +1237,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu = event->pmu; /* - * Make sure we get updated with the first PEBS - * event. It will trigger also during removal, but - * that does not hurt: + * Make sure we get updated with the first PEBS event. + * During removal, ->pebs_data_cfg is still valid for + * the last PEBS event. Don't clear it. */ - if (cpuc->n_pebs == 1) + if ((cpuc->n_pebs == 1) && add) cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index fcd20c6dc7f9..67b68d0d17d1 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void); extern void callthunks_patch_module_calls(struct callthunk_sites *sites, struct module *mod); extern void *callthunks_translate_call_dest(void *dest); -extern int x86_call_depth_emit_accounting(u8 **pprog, void *func); +extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip); #else static __always_inline void callthunks_patch_builtin_calls(void) {} static __always_inline void @@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest) return dest; } static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, - void *func) + void *func, void *ip) { return 0; } diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index fb7388bbc212..c086699b0d0c 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -22,6 +22,7 @@ static inline void cc_set_mask(u64 mask) u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); +void cc_random_init(void); #else #define cc_vendor (CC_VENDOR_NONE) @@ -34,6 +35,7 @@ static inline u64 cc_mkdec(u64 val) { return val; } +static inline void cc_random_init(void) { } #endif #endif /* _ASM_X86_COCO_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 42157ddcc09d..686e92d2663e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #define X86_CAP_FMT_NUM "%d:%d" diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 07e125f32528..7f57382afee4 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -228,7 +228,6 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); u64 sev_get_status(void); -void kdump_sev_callback(void); void sev_show_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } @@ -258,7 +257,6 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } static inline u64 snp_get_unsupported_features(u64 status) { return 0; } static inline u64 sev_get_status(void) { return 0; } -static inline void kdump_sev_callback(void) { } static inline void sev_show_status(void) { } #endif @@ -270,6 +268,7 @@ int psmash(u64 pfn); int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable); int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); +void kdump_sev_callback(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } @@ -282,6 +281,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as } static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; } static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} +static inline void kdump_sev_callback(void) { } #endif #endif diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index ad29984d5e39..ef11aa4cab42 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -694,6 +694,7 @@ enum sev_cmd_id { struct kvm_sev_cmd { __u32 id; + __u32 pad0; __u64 data; __u32 error; __u32 sev_fd; @@ -704,28 +705,35 @@ struct kvm_sev_launch_start { __u32 policy; __u64 dh_uaddr; __u32 dh_len; + __u32 pad0; __u64 session_uaddr; __u32 session_len; + __u32 pad1; }; struct kvm_sev_launch_update_data { __u64 uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_launch_secret { __u64 hdr_uaddr; __u32 hdr_len; + __u32 pad0; __u64 guest_uaddr; __u32 guest_len; + __u32 pad1; __u64 trans_uaddr; __u32 trans_len; + __u32 pad2; }; struct kvm_sev_launch_measure { __u64 uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_guest_status { @@ -738,33 +746,43 @@ struct kvm_sev_dbg { __u64 src_uaddr; __u64 dst_uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_attestation_report { __u8 mnonce[16]; __u64 uaddr; __u32 len; + __u32 pad0; }; struct kvm_sev_send_start { __u32 policy; + __u32 pad0; __u64 pdh_cert_uaddr; __u32 pdh_cert_len; + __u32 pad1; __u64 plat_certs_uaddr; __u32 plat_certs_len; + __u32 pad2; __u64 amd_certs_uaddr; __u32 amd_certs_len; + __u32 pad3; __u64 session_uaddr; __u32 session_len; + __u32 pad4; }; struct kvm_sev_send_update_data { __u64 hdr_uaddr; __u32 hdr_len; + __u32 pad0; __u64 guest_uaddr; __u32 guest_len; + __u32 pad1; __u64 trans_uaddr; __u32 trans_len; + __u32 pad2; }; struct kvm_sev_receive_start { @@ -772,17 +790,22 @@ struct kvm_sev_receive_start { __u32 policy; __u64 pdh_uaddr; __u32 pdh_len; + __u32 pad0; __u64 session_uaddr; __u32 session_len; + __u32 pad1; }; struct kvm_sev_receive_update_data { __u64 hdr_uaddr; __u32 hdr_len; + __u32 pad0; __u64 guest_uaddr; __u32 guest_len; + __u32 pad1; __u64 trans_uaddr; __u32 trans_len; + __u32 pad2; }; #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 6bc3456a8ebf..a1efa7907a0b 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -142,7 +142,6 @@ struct kvm_vcpu_pv_apf_data { __u32 token; __u8 pad[56]; - __u32 enabled; }; #define KVM_PV_EOI_BIT 0 diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 30335182b6b0..e92ff0c11db8 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -314,7 +314,7 @@ static bool is_callthunk(void *addr) return !bcmp(pad, insn_buff, tmpl_size); } -int x86_call_depth_emit_accounting(u8 **pprog, void *func) +int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip) { unsigned int tmpl_size = SKL_TMPL_SIZE; u8 insn_buff[MAX_PATCH_LEN]; @@ -327,7 +327,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func) return 0; memcpy(insn_buff, skl_call_thunk_template, tmpl_size); - apply_relocation(insn_buff, tmpl_size, *pprog, + apply_relocation(insn_buff, tmpl_size, ip, skl_call_thunk_template, tmpl_size); memcpy(*pprog, insn_buff, tmpl_size); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6d8677e80ddb..9bf17c9c29da 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -345,6 +345,28 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } +static void bsp_determine_snp(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_ARCH_HAS_CC_PLATFORM + cc_vendor = CC_VENDOR_AMD; + + if (cpu_has(c, X86_FEATURE_SEV_SNP)) { + /* + * RMP table entry format is not architectural and is defined by the + * per-processor PPR. Restrict SNP support on the known CPU models + * for which the RMP table entry format is currently defined for. + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && + c->x86 >= 0x19 && snp_probe_rmptable_info()) { + cc_platform_set(CC_ATTR_HOST_SEV_SNP); + } else { + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + } + } +#endif +} + static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -452,21 +474,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) break; } - if (cpu_has(c, X86_FEATURE_SEV_SNP)) { - /* - * RMP table entry format is not architectural and it can vary by processor - * and is defined by the per-processor PPR. Restrict SNP support on the - * known CPU model and family for which the RMP table entry format is - * currently defined for. - */ - if (!boot_cpu_has(X86_FEATURE_ZEN3) && - !boot_cpu_has(X86_FEATURE_ZEN4) && - !boot_cpu_has(X86_FEATURE_ZEN5)) - setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); - else if (!snp_probe_rmptable_info()) - setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); - } - + bsp_determine_snp(c); return; warn: diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index b5cc557cfc37..84d41be6d06b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2500,12 +2500,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 422a4ddc2ab7..7b29ebda024f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -108,7 +108,7 @@ static inline void k8_check_syscfg_dram_mod_en(void) (boot_cpu_data.x86 >= 0x0f))) return; - if (cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return; rdmsr(MSR_AMD64_SYSCFG, lo, hi); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index c99f26ebe7a6..1a8687f8073a 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -78,7 +78,8 @@ cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu) else cpu = cpumask_any_but(mask, exclude_cpu); - if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) + /* Only continue if tick_nohz_full_mask has been initialized. */ + if (!tick_nohz_full_enabled()) return cpu; /* If the CPU picked isn't marked nohz_full nothing more needs doing. */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4cadfd606e8e..7f0732bc0ccd 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -65,6 +65,7 @@ static int __init parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); +static DEFINE_PER_CPU_READ_MOSTLY(bool, async_pf_enabled); static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; @@ -244,7 +245,7 @@ noinstr u32 kvm_read_and_reset_apf_flags(void) { u32 flags = 0; - if (__this_cpu_read(apf_reason.enabled)) { + if (__this_cpu_read(async_pf_enabled)) { flags = __this_cpu_read(apf_reason.flags); __this_cpu_write(apf_reason.flags, 0); } @@ -295,7 +296,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) inc_irq_stat(irq_hv_callback_count); - if (__this_cpu_read(apf_reason.enabled)) { + if (__this_cpu_read(async_pf_enabled)) { token = __this_cpu_read(apf_reason.token); kvm_async_pf_task_wake(token); __this_cpu_write(apf_reason.token, 0); @@ -362,7 +363,7 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR); wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); - __this_cpu_write(apf_reason.enabled, 1); + __this_cpu_write(async_pf_enabled, true); pr_debug("setup async PF for cpu %d\n", smp_processor_id()); } @@ -383,11 +384,11 @@ static void kvm_guest_cpu_init(void) static void kvm_pv_disable_apf(void) { - if (!__this_cpu_read(apf_reason.enabled)) + if (!__this_cpu_read(async_pf_enabled)) return; wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); - __this_cpu_write(apf_reason.enabled, 0); + __this_cpu_write(async_pf_enabled, false); pr_debug("disable async PF for cpu %d\n", smp_processor_id()); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0109e6c510e0..e125e059e2c4 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -35,6 +35,7 @@ #include <asm/bios_ebda.h> #include <asm/bugs.h> #include <asm/cacheinfo.h> +#include <asm/coco.h> #include <asm/cpu.h> #include <asm/efi.h> #include <asm/gart.h> @@ -991,6 +992,7 @@ void __init setup_arch(char **cmdline_p) * memory size. */ mem_encrypt_setup_arch(); + cc_random_init(); efi_fake_memmap(); efi_find_mirror(); diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 7e1e63cc48e6..38ad066179d8 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -2284,16 +2284,6 @@ static int __init snp_init_platform_device(void) } device_initcall(snp_init_platform_device); -void kdump_sev_callback(void) -{ - /* - * Do wbinvd() on remote CPUs when SNP is enabled in order to - * safely do SNP_SHUTDOWN on the local CPU. - */ - if (cpu_feature_enabled(X86_FEATURE_SEV_SNP)) - wbinvd(); -} - void sev_show_status(void) { int i; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3aaf7e86a859..0ebdd088f28b 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -122,6 +122,7 @@ config KVM_AMD_SEV default y depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) + select ARCH_HAS_CC_PLATFORM help Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index adba49afb5fe..bfc0bfcb2bc6 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -189,15 +189,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, - const char *sig) +static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries, + int nent, const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_hypervisor_cpuid_base(base) { - entry = kvm_find_cpuid_entry(vcpu, base); + entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (entry) { u32 signature[3]; @@ -217,22 +217,29 @@ static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcp return cpuid; } -static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu, - struct kvm_cpuid_entry2 *entries, int nent) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { - u32 base = vcpu->arch.kvm_cpuid.base; - - if (!base) - return NULL; + return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, sig); +} - return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, +static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries, + int nent, u32 kvm_cpuid_base) +{ + return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES, KVM_CPUID_INDEX_NOT_SIGNIFICANT); } static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) { - return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent); + u32 base = vcpu->arch.kvm_cpuid.base; + + if (!base) + return NULL; + + return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, base); } void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) @@ -266,6 +273,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e int nent) { struct kvm_cpuid_entry2 *best; + struct kvm_hypervisor_cpuid kvm_cpuid; best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { @@ -292,10 +300,12 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent); - if (kvm_hlt_in_guest(vcpu->kvm) && best && - (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) - best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE); + if (kvm_cpuid.base) { + best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base); + if (kvm_hlt_in_guest(vcpu->kvm) && best) + best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + } if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index aadefcaa9561..58ac8d69c94b 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -102,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index ae0ac12382b9..61a7531d41b0 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -84,9 +84,10 @@ struct enc_region { }; /* Called with the sev_bitmap_lock held, or on shutdown */ -static int sev_flush_asids(int min_asid, int max_asid) +static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) { - int ret, asid, error = 0; + int ret, error = 0; + unsigned int asid; /* Check if there are any ASIDs to reclaim before performing a flush */ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); @@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm) } /* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(int min_asid, int max_asid) +static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid) { if (sev_flush_asids(min_asid, max_asid)) return false; @@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev) { - int asid, min_asid, max_asid, ret; + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + * Note: min ASID can end up larger than the max if basic SEV support is + * effectively disabled by disallowing use of ASIDs for SEV guests. + */ + unsigned int min_asid = sev->es_active ? 1 : min_sev_asid; + unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; + unsigned int asid; bool retry = true; + int ret; + + if (min_asid > max_asid) + return -ENOTTY; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); @@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev) mutex_lock(&sev_bitmap_lock); - /* - * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. - * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. - */ - min_asid = sev->es_active ? 1 : min_sev_asid; - max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); if (asid > max_asid) { @@ -179,7 +186,8 @@ again: mutex_unlock(&sev_bitmap_lock); - return asid; + sev->asid = asid; + return 0; e_uncharge: sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); @@ -187,7 +195,7 @@ e_uncharge: return ret; } -static int sev_get_asid(struct kvm *kvm) +static unsigned int sev_get_asid(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -247,21 +255,19 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_platform_init_args init_args = {0}; - int asid, ret; + int ret; if (kvm->created_vcpus) return -EINVAL; - ret = -EBUSY; if (unlikely(sev->active)) - return ret; + return -EINVAL; sev->active = true; sev->es_active = argp->id == KVM_SEV_ES_INIT; - asid = sev_asid_new(sev); - if (asid < 0) + ret = sev_asid_new(sev); + if (ret) goto e_no_asid; - sev->asid = asid; init_args.probe = false; ret = sev_platform_init(&init_args); @@ -287,8 +293,8 @@ e_no_asid: static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { + unsigned int asid = sev_get_asid(kvm); struct sev_data_activate activate; - int asid = sev_get_asid(kvm); int ret; /* activate ASID on the given handle */ @@ -2240,8 +2246,10 @@ void __init sev_hardware_setup(void) goto out; } - sev_asid_count = max_sev_asid - min_sev_asid + 1; - WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + if (min_sev_asid <= max_sev_asid) { + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + } sev_supported = true; /* SEV-ES support requested? */ @@ -2272,7 +2280,9 @@ void __init sev_hardware_setup(void) out: if (boot_cpu_has(X86_FEATURE_SEV)) pr_info("SEV %s (ASIDs %u - %u)\n", - sev_supported ? "enabled" : "disabled", + sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : + "unusable" : + "disabled", min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", @@ -2320,7 +2330,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) */ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { - int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + unsigned int asid = sev_get_asid(vcpu->kvm); /* * Note! The address must be a kernel address, as regular page walk @@ -2638,7 +2648,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - int asid = sev_get_asid(svm->vcpu.kvm); + unsigned int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ svm->asid = asid; @@ -3174,7 +3184,7 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) unsigned long pfn; struct page *p; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); /* diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 88659de4d2a7..c6b4b1728006 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -735,13 +735,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit, * Tracepoint for nested #vmexit because of interrupt pending */ TRACE_EVENT(kvm_invlpga, - TP_PROTO(__u64 rip, int asid, u64 address), + TP_PROTO(__u64 rip, unsigned int asid, u64 address), TP_ARGS(rip, asid, address), TP_STRUCT__entry( - __field( __u64, rip ) - __field( int, asid ) - __field( __u64, address ) + __field( __u64, rip ) + __field( unsigned int, asid ) + __field( __u64, address ) ), TP_fast_assign( @@ -750,7 +750,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", + TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 02cde194a99e..e674ccf720b9 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -228,8 +228,12 @@ SYM_CODE_END(srso_return_thunk) #else /* !CONFIG_MITIGATION_SRSO */ /* Dummy for the alternative in CALL_UNTRAIN_RET. */ SYM_CODE_START(srso_alias_untrain_ret) - RET + ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR + ret + int3 SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #define JMP_SRSO_UNTRAIN_RET "ud2" #endif /* CONFIG_MITIGATION_SRSO */ diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 104544359d69..025fd7ea5d69 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,6 +24,7 @@ #include <linux/memblock.h> #include <linux/init.h> +#include <asm/pgtable_areas.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 0d72183b5dd0..36b603d0cdde 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -947,6 +947,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -957,20 +989,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1045,7 +1070,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1053,11 +1077,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a7ba8e178645..df5fac428408 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -480,7 +480,7 @@ static int emit_call(u8 **pprog, void *func, void *ip) static int emit_rsb_call(u8 **pprog, void *func, void *ip) { OPTIMIZER_HIDE_VAR(func); - x86_call_depth_emit_accounting(pprog, func); + ip += x86_call_depth_emit_accounting(pprog, func, ip); return emit_patch(pprog, func, ip, 0xE8); } @@ -1972,20 +1972,17 @@ populate_extable: /* call */ case BPF_JMP | BPF_CALL: { - int offs; + u8 *ip = image + addrs[i - 1]; func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); - if (!imm32) - return -EINVAL; - offs = 7 + x86_call_depth_emit_accounting(&prog, func); - } else { - if (!imm32) - return -EINVAL; - offs = x86_call_depth_emit_accounting(&prog, func); + ip += 7; } - if (emit_call(&prog, func, image + addrs[i - 1] + offs)) + if (!imm32) + return -EINVAL; + ip += x86_call_depth_emit_accounting(&prog, func, ip); + if (emit_call(&prog, func, ip)) return -EINVAL; break; } @@ -2835,7 +2832,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * Direct-call fentry stub, as such it needs accounting for the * __fentry__ call. */ - x86_call_depth_emit_accounting(&prog, NULL); + x86_call_depth_emit_accounting(&prog, NULL, image); } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index cffe1157a90a..ab0e8448bb6e 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -77,7 +77,7 @@ static int __mfd_enable(unsigned int cpu) { u64 val; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; rdmsrl(MSR_AMD64_SYSCFG, val); @@ -98,7 +98,7 @@ static int __snp_enable(unsigned int cpu) { u64 val; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; rdmsrl(MSR_AMD64_SYSCFG, val); @@ -174,11 +174,11 @@ static int __init snp_rmptable_init(void) u64 rmptable_size; u64 val; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return 0; if (!amd_iommu_snp_en) - return 0; + goto nosnp; if (!probed_rmp_size) goto nosnp; @@ -225,7 +225,7 @@ skip_enable: return 0; nosnp: - setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); return -ENOSYS; } @@ -246,7 +246,7 @@ static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level) { struct rmpentry *large_entry, *entry; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return ERR_PTR(-ENODEV); entry = get_rmpentry(pfn); @@ -363,7 +363,7 @@ int psmash(u64 pfn) unsigned long paddr = pfn << PAGE_SHIFT; int ret; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return -ENODEV; if (!pfn_valid(pfn)) @@ -472,7 +472,7 @@ static int rmpupdate(u64 pfn, struct rmp_state *state) unsigned long paddr = pfn << PAGE_SHIFT; int ret, level; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return -ENODEV; level = RMP_TO_PG_LEVEL(state->pagesize); @@ -558,3 +558,13 @@ void snp_leak_pages(u64 pfn, unsigned int npages) spin_unlock(&snp_leaked_pages_list_lock); } EXPORT_SYMBOL_GPL(snp_leak_pages); + +void kdump_sev_callback(void) +{ + /* + * Do wbinvd() on remote CPUs when SNP is enabled in order to + * safely do SNP_SHUTDOWN on the local CPU. + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + wbinvd(); +} diff --git a/block/bdev.c b/block/bdev.c index 7a5f611c3d2e..b8e32d933a63 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -583,9 +583,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder, mutex_unlock(&bdev->bd_holder_lock); bd_clear_claiming(whole, holder); mutex_unlock(&bdev_lock); - - if (hops && hops->get_holder) - hops->get_holder(holder); } /** @@ -608,7 +605,6 @@ EXPORT_SYMBOL(bd_abort_claiming); static void bd_end_claim(struct block_device *bdev, void *holder) { struct block_device *whole = bdev_whole(bdev); - const struct blk_holder_ops *hops = bdev->bd_holder_ops; bool unblock = false; /* @@ -631,9 +627,6 @@ static void bd_end_claim(struct block_device *bdev, void *holder) whole->bd_holder = NULL; mutex_unlock(&bdev_lock); - if (hops && hops->put_holder) - hops->put_holder(holder); - /* * If this was the last claim, remove holder link and unblock evpoll if * it was a write holder. @@ -776,17 +769,17 @@ void blkdev_put_no_open(struct block_device *bdev) static bool bdev_writes_blocked(struct block_device *bdev) { - return bdev->bd_writers == -1; + return bdev->bd_writers < 0; } static void bdev_block_writes(struct block_device *bdev) { - bdev->bd_writers = -1; + bdev->bd_writers--; } static void bdev_unblock_writes(struct block_device *bdev) { - bdev->bd_writers = 0; + bdev->bd_writers++; } static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode) @@ -813,6 +806,11 @@ static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode) bdev->bd_writers++; } +static inline bool bdev_unclaimed(const struct file *bdev_file) +{ + return bdev_file->private_data == BDEV_I(bdev_file->f_mapping->host); +} + static void bdev_yield_write_access(struct file *bdev_file) { struct block_device *bdev; @@ -820,14 +818,15 @@ static void bdev_yield_write_access(struct file *bdev_file) if (bdev_allow_write_mounted) return; + if (bdev_unclaimed(bdev_file)) + return; + bdev = file_bdev(bdev_file); - /* Yield exclusive or shared write access. */ - if (bdev_file->f_mode & FMODE_WRITE) { - if (bdev_writes_blocked(bdev)) - bdev_unblock_writes(bdev); - else - bdev->bd_writers--; - } + + if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED) + bdev_unblock_writes(bdev); + else if (bdev_file->f_mode & FMODE_WRITE) + bdev->bd_writers--; } /** @@ -907,6 +906,8 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT; if (bdev_nowait(bdev)) bdev_file->f_mode |= FMODE_NOWAIT; + if (mode & BLK_OPEN_RESTRICT_WRITES) + bdev_file->f_mode |= FMODE_WRITE_RESTRICTED; bdev_file->f_mapping = bdev->bd_inode->i_mapping; bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping); bdev_file->private_data = holder; @@ -1012,6 +1013,20 @@ struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, } EXPORT_SYMBOL(bdev_file_open_by_path); +static inline void bd_yield_claim(struct file *bdev_file) +{ + struct block_device *bdev = file_bdev(bdev_file); + void *holder = bdev_file->private_data; + + lockdep_assert_held(&bdev->bd_disk->open_mutex); + + if (WARN_ON_ONCE(IS_ERR_OR_NULL(holder))) + return; + + if (!bdev_unclaimed(bdev_file)) + bd_end_claim(bdev, holder); +} + void bdev_release(struct file *bdev_file) { struct block_device *bdev = file_bdev(bdev_file); @@ -1036,7 +1051,7 @@ void bdev_release(struct file *bdev_file) bdev_yield_write_access(bdev_file); if (holder) - bd_end_claim(bdev, holder); + bd_yield_claim(bdev_file); /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE @@ -1057,6 +1072,39 @@ put_no_open: } /** + * bdev_fput - yield claim to the block device and put the file + * @bdev_file: open block device + * + * Yield claim on the block device and put the file. Ensure that the + * block device can be reclaimed before the file is closed which is a + * deferred operation. + */ +void bdev_fput(struct file *bdev_file) +{ + if (WARN_ON_ONCE(bdev_file->f_op != &def_blk_fops)) + return; + + if (bdev_file->private_data) { + struct block_device *bdev = file_bdev(bdev_file); + struct gendisk *disk = bdev->bd_disk; + + mutex_lock(&disk->open_mutex); + bdev_yield_write_access(bdev_file); + bd_yield_claim(bdev_file); + /* + * Tell release we already gave up our hold on the + * device and if write restrictions are available that + * we already gave up write access to the device. + */ + bdev_file->private_data = BDEV_I(bdev_file->f_mapping->host); + mutex_unlock(&disk->open_mutex); + } + + fput(bdev_file); +} +EXPORT_SYMBOL(bdev_fput); + +/** * lookup_bdev() - Look up a struct block_device by name. * @pathname: Name of the block device in the filesystem. * @dev: Pointer to the block device's dev_t, if found. diff --git a/block/ioctl.c b/block/ioctl.c index 0c76137adcaa..a9028a2c2db5 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -96,7 +96,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; - uint64_t start, len; + uint64_t start, len, end; struct inode *inode = bdev->bd_inode; int err; @@ -117,7 +117,8 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, if (len & 511) return -EINVAL; - if (start + len > bdev_nr_bytes(bdev)) + if (check_add_overflow(start, len, &end) || + end > bdev_nr_bytes(bdev)) return -EINVAL; filemap_invalidate_lock(inode->i_mapping); diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 302dce0b2b50..d67881b50bca 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -662,14 +662,15 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz, { int result; - tz->thermal_zone = thermal_zone_device_register_with_trips("acpitz", - trip_table, - trip_count, - tz, - &acpi_thermal_zone_ops, - NULL, - passive_delay, - tz->polling_frequency * 100); + if (trip_count) + tz->thermal_zone = thermal_zone_device_register_with_trips( + "acpitz", trip_table, trip_count, tz, + &acpi_thermal_zone_ops, NULL, passive_delay, + tz->polling_frequency * 100); + else + tz->thermal_zone = thermal_tripless_zone_device_register( + "acpitz", tz, &acpi_thermal_zone_ops, NULL); + if (IS_ERR(tz->thermal_zone)) return PTR_ERR(tz->thermal_zone); @@ -901,11 +902,8 @@ static int acpi_thermal_add(struct acpi_device *device) trip++; } - if (trip == trip_table) { + if (trip == trip_table) pr_warn(FW_BUG "No valid trip points!\n"); - result = -ENODEV; - goto free_memory; - } result = acpi_thermal_register_thermal_zone(tz, trip_table, trip - trip_table, diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c index d4a626f87963..79a8b0aa37bf 100644 --- a/drivers/ata/ahci_st.c +++ b/drivers/ata/ahci_st.c @@ -30,7 +30,6 @@ #define ST_AHCI_OOBR_CIMAX_SHIFT 0 struct st_ahci_drv_data { - struct platform_device *ahci; struct reset_control *pwr; struct reset_control *sw_rst; struct reset_control *pwr_rst; diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 4ac854f6b057..88b2e9817f49 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -1371,9 +1371,6 @@ static struct pci_driver pata_macio_pci_driver = { .suspend = pata_macio_pci_suspend, .resume = pata_macio_pci_resume, #endif - .driver = { - .owner = THIS_MODULE, - }, }; MODULE_DEVICE_TABLE(pci, pata_macio_pci_match); diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index 400b22ee99c3..4c270999ba3c 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -200,7 +200,10 @@ int gemini_sata_start_bridge(struct sata_gemini *sg, unsigned int bridge) pclk = sg->sata0_pclk; else pclk = sg->sata1_pclk; - clk_enable(pclk); + ret = clk_enable(pclk); + if (ret) + return ret; + msleep(10); /* Do not keep clocking a bridge that is not online */ diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index e82786c63fbd..9bec0aee92e0 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -787,37 +787,6 @@ static const struct ata_port_info mv_port_info[] = { }, }; -static const struct pci_device_id mv_pci_tbl[] = { - { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, - { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, - /* RocketRAID 1720/174x have different identifiers */ - { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, - - { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, - { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, - { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, - - { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, - - /* Adaptec 1430SA */ - { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, - - /* Marvell 7042 support */ - { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, - - /* Highpoint RocketRAID PCIe series */ - { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, - { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, - - { } /* terminate list */ -}; - static const struct mv_hw_ops mv5xxx_ops = { .phy_errata = mv5_phy_errata, .enable_leds = mv5_enable_leds, @@ -4303,6 +4272,36 @@ static int mv_pci_init_one(struct pci_dev *pdev, static int mv_pci_device_resume(struct pci_dev *pdev); #endif +static const struct pci_device_id mv_pci_tbl[] = { + { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, + { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, + /* RocketRAID 1720/174x have different identifiers */ + { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, + + { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, + { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, + { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, + + { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, + + /* Adaptec 1430SA */ + { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, + + /* Marvell 7042 support */ + { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, + + /* Highpoint RocketRAID PCIe series */ + { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, + { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, + + { } /* terminate list */ +}; static struct pci_driver mv_pci_driver = { .name = DRV_NAME, @@ -4315,6 +4314,7 @@ static struct pci_driver mv_pci_driver = { #endif }; +MODULE_DEVICE_TABLE(pci, mv_pci_tbl); /** * mv_print_info - Dump key info to kernel log for perusal. @@ -4487,7 +4487,6 @@ static void __exit mv_exit(void) MODULE_AUTHOR("Brett Russ"); MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers"); MODULE_LICENSE("GPL v2"); -MODULE_DEVICE_TABLE(pci, mv_pci_tbl); MODULE_VERSION(DRV_VERSION); MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index b51d7a9d0d90..a482741eb181 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -957,8 +957,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, offset -= (idx * window_size); idx++; - dist = ((long) (window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_fromio(psource, dimm_mmio + offset / 4, dist); psource += dist; @@ -1005,8 +1004,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, readl(mmio + PDC_DIMM_WINDOW_CTLR); offset -= (idx * window_size); idx++; - dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_toio(dimm_mmio + offset / 4, psource, dist); writel(0x01, mmio + PDC_GENERAL_CTLR); readl(mmio + PDC_GENERAL_CTLR); diff --git a/drivers/base/core.c b/drivers/base/core.c index b93f3c5716ae..5f4e03336e68 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -44,6 +44,7 @@ static bool fw_devlink_is_permissive(void); static void __fw_devlink_link_to_consumers(struct device *dev); static bool fw_devlink_drv_reg_done; static bool fw_devlink_best_effort; +static struct workqueue_struct *device_link_wq; /** * __fwnode_link_add - Create a link between two fwnode_handles. @@ -533,12 +534,26 @@ static void devlink_dev_release(struct device *dev) /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or - * supplier devices get deleted when it runs, so put it into the "long" - * workqueue. + * supplier devices get deleted when it runs, so put it into the + * dedicated workqueue. */ - queue_work(system_long_wq, &link->rm_work); + queue_work(device_link_wq, &link->rm_work); } +/** + * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate + */ +void device_link_wait_removal(void) +{ + /* + * devlink removal jobs are queued in the dedicated work queue. + * To be sure that all removal jobs are terminated, ensure that any + * scheduled work has run to completion. + */ + flush_workqueue(device_link_wq); +} +EXPORT_SYMBOL_GPL(device_link_wait_removal); + static struct class devlink_class = { .name = "devlink", .dev_groups = devlink_groups, @@ -4164,9 +4179,14 @@ int __init devices_init(void) sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; + device_link_wq = alloc_workqueue("device_link_wq", 0, 0); + if (!device_link_wq) + goto wq_err; return 0; + wq_err: + kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 41edd6a430eb..55999a50ccc0 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -112,7 +112,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min, unsigned long *entry, *lower, *upper; unsigned long lower_index, lower_last; unsigned long upper_index, upper_last; - int ret; + int ret = 0; lower = NULL; upper = NULL; @@ -145,7 +145,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min, upper_index = max + 1; upper_last = mas.last; - upper = kmemdup(&entry[max + 1], + upper = kmemdup(&entry[max - mas.index + 1], ((mas.last - max) * sizeof(unsigned long)), map->alloc_flags); @@ -244,7 +244,7 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min, unsigned long lmin = min; unsigned long lmax = max; unsigned int r, v, sync_start; - int ret; + int ret = 0; bool sync_needed = false; map->cache_bypass = true; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 5cb425f6f02d..0a34dd3c4f38 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2839,6 +2839,43 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) EXPORT_SYMBOL_GPL(regmap_read); /** + * regmap_read_bypassed() - Read a value from a single register direct + * from the device, bypassing the cache + * + * @map: Register map to read from + * @reg: Register to be read from + * @val: Pointer to store read value + * + * A value of zero will be returned on success, a negative errno will + * be returned in error cases. + */ +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val) +{ + int ret; + bool bypass, cache_only; + + if (!IS_ALIGNED(reg, map->reg_stride)) + return -EINVAL; + + map->lock(map->lock_arg); + + bypass = map->cache_bypass; + cache_only = map->cache_only; + map->cache_bypass = true; + map->cache_only = false; + + ret = _regmap_read(map, reg, val); + + map->cache_bypass = bypass; + map->cache_only = cache_only; + + map->unlock(map->lock_arg); + + return ret; +} +EXPORT_SYMBOL_GPL(regmap_read_bypassed); + +/** * regmap_raw_read() - Read raw data from the device * * @map: Register map to read from diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 71c39bcd872c..ed33cf7192d2 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1965,10 +1965,10 @@ static int null_add_dev(struct nullb_device *dev) out_ida_free: ida_free(&nullb_indexes, nullb->index); -out_cleanup_zone: - null_free_zoned_dev(dev); out_cleanup_disk: put_disk(nullb->disk); +out_cleanup_zone: + null_free_zoned_dev(dev); out_cleanup_tags: if (nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index b40b32fa7f1c..19cfc342fc7b 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -826,11 +826,15 @@ EXPORT_SYMBOL_GPL(qca_uart_setup); int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) { + bdaddr_t bdaddr_swapped; struct sk_buff *skb; int err; - skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, bdaddr, - HCI_EV_VENDOR, HCI_INIT_TIMEOUT); + baswap(&bdaddr_swapped, bdaddr); + + skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, + &bdaddr_swapped, HCI_EV_VENDOR, + HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "QCA Change address cmd failed (%d)", err); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 8a60ad7acd70..ecbc52eaf101 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -7,7 +7,6 @@ * * Copyright (C) 2007 Texas Instruments, Inc. * Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved. - * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. * * Acknowledgements: * This file is based on hci_ll.c, which was... @@ -226,6 +225,7 @@ struct qca_serdev { struct qca_power *bt_power; u32 init_speed; u32 oper_speed; + bool bdaddr_property_broken; const char *firmware_name; }; @@ -1843,6 +1843,7 @@ static int qca_setup(struct hci_uart *hu) const char *firmware_name = qca_get_firmware_name(hu); int ret; struct qca_btsoc_version ver; + struct qca_serdev *qcadev; const char *soc_name; ret = qca_check_speeds(hu); @@ -1904,16 +1905,11 @@ retry: case QCA_WCN6750: case QCA_WCN6855: case QCA_WCN7850: + set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); - /* Set BDA quirk bit for reading BDA value from fwnode property - * only if that property exist in DT. - */ - if (fwnode_property_present(dev_fwnode(hdev->dev.parent), "local-bd-address")) { - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); - bt_dev_info(hdev, "setting quirk bit to read BDA from fwnode later"); - } else { - bt_dev_dbg(hdev, "local-bd-address` is not present in the devicetree so not setting quirk bit for BDA"); - } + qcadev = serdev_device_get_drvdata(hu->serdev); + if (qcadev->bdaddr_property_broken) + set_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks); hci_set_aosp_capable(hdev); @@ -2295,6 +2291,9 @@ static int qca_serdev_probe(struct serdev_device *serdev) if (!qcadev->oper_speed) BT_DBG("UART will pick default operating speed"); + qcadev->bdaddr_property_broken = device_property_read_bool(&serdev->dev, + "qcom,local-bd-address-broken"); + if (data) qcadev->btsoc_type = data->soc_type; else diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index f44efbb89c34..2102377f727b 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -1090,7 +1090,7 @@ static int __sev_snp_init_locked(int *error) void *arg = &data; int cmd, rc = 0; - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return -ENODEV; sev = psp->sev_data; diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 7bc71f4be64a..38d19410a2be 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -2060,6 +2060,8 @@ static void bus_reset_work(struct work_struct *work) ohci->generation = generation; reg_write(ohci, OHCI1394_IntEventClear, OHCI1394_busReset); + if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) + reg_write(ohci, OHCI1394_IntMaskSet, OHCI1394_busReset); if (ohci->quirks & QUIRK_RESET_PACKET) ohci->request_generation = generation; @@ -2125,12 +2127,14 @@ static irqreturn_t irq_handler(int irq, void *data) return IRQ_NONE; /* - * busReset and postedWriteErr must not be cleared yet + * busReset and postedWriteErr events must not be cleared yet * (OHCI 1.1 clauses 7.2.3.2 and 13.2.8.1) */ reg_write(ohci, OHCI1394_IntEventClear, event & ~(OHCI1394_busReset | OHCI1394_postedWriteErr)); log_irqs(ohci, event); + if (event & OHCI1394_busReset) + reg_write(ohci, OHCI1394_IntMaskClear, OHCI1394_busReset); if (event & OHCI1394_selfIDComplete) queue_work(selfid_workqueue, &ohci->bus_reset_work); diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index fa9635610251..d09c7d728365 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -728,6 +728,25 @@ static u32 line_event_id(int level) GPIO_V2_LINE_EVENT_FALLING_EDGE; } +static inline char *make_irq_label(const char *orig) +{ + char *new; + + if (!orig) + return NULL; + + new = kstrdup_and_replace(orig, '/', ':', GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + return new; +} + +static inline void free_irq_label(const char *label) +{ + kfree(label); +} + #ifdef CONFIG_HTE static enum hte_return process_hw_ts_thread(void *p) @@ -1015,6 +1034,7 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us) { unsigned long irqflags; int ret, level, irq; + char *label; /* try hardware */ ret = gpiod_set_debounce(line->desc, debounce_period_us); @@ -1037,11 +1057,17 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us) if (irq < 0) return -ENXIO; + label = make_irq_label(line->req->label); + if (IS_ERR(label)) + return -ENOMEM; + irqflags = IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING; ret = request_irq(irq, debounce_irq_handler, irqflags, - line->req->label, line); - if (ret) + label, line); + if (ret) { + free_irq_label(label); return ret; + } line->irq = irq; } else { ret = hte_edge_setup(line, GPIO_V2_LINE_FLAG_EDGE_BOTH); @@ -1083,16 +1109,6 @@ static u32 gpio_v2_line_config_debounce_period(struct gpio_v2_line_config *lc, return 0; } -static inline char *make_irq_label(const char *orig) -{ - return kstrdup_and_replace(orig, '/', ':', GFP_KERNEL); -} - -static inline void free_irq_label(const char *label) -{ - kfree(label); -} - static void edge_detector_stop(struct line *line) { if (line->irq) { @@ -1158,8 +1174,8 @@ static int edge_detector_setup(struct line *line, irqflags |= IRQF_ONESHOT; label = make_irq_label(line->req->label); - if (!label) - return -ENOMEM; + if (IS_ERR(label)) + return PTR_ERR(label); /* Request a thread to read the events */ ret = request_threaded_irq(irq, edge_irq_handler, edge_irq_thread, @@ -2217,8 +2233,8 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) goto out_free_le; label = make_irq_label(le->label); - if (!label) { - ret = -ENOMEM; + if (IS_ERR(label)) { + ret = PTR_ERR(label); goto out_free_le; } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 59ccf9a3e153..94903fc1c145 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1175,6 +1175,9 @@ struct gpio_device *gpio_device_find(const void *data, list_for_each_entry_srcu(gdev, &gpio_devices, list, srcu_read_lock_held(&gpio_devices_srcu)) { + if (!device_is_registered(&gdev->dev)) + continue; + guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); diff --git a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c index bd61e20770a5..14a2a8473682 100644 --- a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c +++ b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c @@ -52,7 +52,7 @@ * @adapter: I2C adapter for the DDC bus * @offset: register offset * @buffer: buffer for return data - * @size: sizo of the buffer + * @size: size of the buffer * * Reads @size bytes from the DP dual mode adaptor registers * starting at @offset. @@ -116,7 +116,7 @@ EXPORT_SYMBOL(drm_dp_dual_mode_read); * @adapter: I2C adapter for the DDC bus * @offset: register offset * @buffer: buffer for write data - * @size: sizo of the buffer + * @size: size of the buffer * * Writes @size bytes to the DP dual mode adaptor registers * starting at @offset. diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 7352bde299d5..03bd3c7bd0dc 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -582,7 +582,12 @@ int drm_gem_map_attach(struct dma_buf *dma_buf, { struct drm_gem_object *obj = dma_buf->priv; - if (!obj->funcs->get_sg_table) + /* + * drm_gem_map_dma_buf() requires obj->get_sg_table(), but drivers + * that implement their own ->map_dma_buf() do not. + */ + if (dma_buf->ops->map_dma_buf == drm_gem_map_dma_buf && + !obj->funcs->get_sg_table) return -ENOSYS; return drm_gem_pin(obj); diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 4c2f85632391..fba73c38e235 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -118,6 +118,7 @@ gt-y += \ gt/intel_ggtt_fencing.o \ gt/intel_gt.o \ gt/intel_gt_buffer_pool.o \ + gt/intel_gt_ccs_mode.o \ gt/intel_gt_clock_utils.o \ gt/intel_gt_debugfs.o \ gt/intel_gt_engines_debugfs.o \ diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index ab2f52d21bad..8af9e6128277 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -2709,15 +2709,6 @@ static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state) */ intel_de_write(dev_priv, PIPESRC(pipe), PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1)); - - if (!crtc_state->enable_psr2_su_region_et) - return; - - width = drm_rect_width(&crtc_state->psr2_su_area); - height = drm_rect_height(&crtc_state->psr2_su_area); - - intel_de_write(dev_priv, PIPE_SRCSZ_ERLY_TPT(pipe), - PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1)); } static bool intel_pipe_is_interlaced(const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h index fe4268813786..9b1bce2624b9 100644 --- a/drivers/gpu/drm/i915/display/intel_display_device.h +++ b/drivers/gpu/drm/i915/display/intel_display_device.h @@ -47,6 +47,7 @@ struct drm_printer; #define HAS_DPT(i915) (DISPLAY_VER(i915) >= 13) #define HAS_DSB(i915) (DISPLAY_INFO(i915)->has_dsb) #define HAS_DSC(__i915) (DISPLAY_RUNTIME_INFO(__i915)->has_dsc) +#define HAS_DSC_MST(__i915) (DISPLAY_VER(__i915) >= 12 && HAS_DSC(__i915)) #define HAS_FBC(i915) (DISPLAY_RUNTIME_INFO(i915)->fbc_mask != 0) #define HAS_FPGA_DBG_UNCLAIMED(i915) (DISPLAY_INFO(i915)->has_fpga_dbg) #define HAS_FW_BLC(i915) (DISPLAY_VER(i915) >= 3) diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 9104f18753b4..bf3f942e19c3 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1423,6 +1423,8 @@ struct intel_crtc_state { u32 psr2_man_track_ctl; + u32 pipe_srcsz_early_tpt; + struct drm_rect psr2_su_area; /* Variable Refresh Rate state */ diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index f98ef4b42a44..abd62bebc46d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -499,7 +499,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp) /* The values must be in increasing order */ static const int mtl_rates[] = { 162000, 216000, 243000, 270000, 324000, 432000, 540000, 675000, - 810000, 1000000, 1350000, 2000000, + 810000, 1000000, 2000000, }; static const int icl_rates[] = { 162000, 216000, 270000, 324000, 432000, 540000, 648000, 810000, @@ -1422,7 +1422,8 @@ static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp, if (DISPLAY_VER(dev_priv) >= 12) return true; - if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A) + if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A && + !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST)) return true; return false; @@ -1917,8 +1918,9 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp, dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1); for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) { - if (valid_dsc_bpp[i] < dsc_min_bpp || - valid_dsc_bpp[i] > dsc_max_bpp) + if (valid_dsc_bpp[i] < dsc_min_bpp) + continue; + if (valid_dsc_bpp[i] > dsc_max_bpp) break; ret = dsc_compute_link_config(intel_dp, @@ -6557,6 +6559,7 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, intel_connector->get_hw_state = intel_ddi_connector_get_hw_state; else intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->sync_state = intel_dp_connector_sync_state; if (!intel_edp_init_connector(intel_dp, intel_connector)) { intel_dp_aux_fini(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 53aec023ce92..b651c990af85 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -1355,7 +1355,7 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, return 0; } - if (DISPLAY_VER(dev_priv) >= 10 && + if (HAS_DSC_MST(dev_priv) && drm_dp_sink_supports_dsc(intel_connector->dp.dsc_dpcd)) { /* * TBD pass the connector BPC, diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 6927785fd6ff..b6e539f1342c 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1994,6 +1994,7 @@ static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp) void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; struct intel_encoder *encoder; @@ -2013,6 +2014,12 @@ void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_st intel_de_write(dev_priv, PSR2_MAN_TRK_CTL(cpu_transcoder), crtc_state->psr2_man_track_ctl); + + if (!crtc_state->enable_psr2_su_region_et) + return; + + intel_de_write(dev_priv, PIPE_SRCSZ_ERLY_TPT(crtc->pipe), + crtc_state->pipe_srcsz_early_tpt); } static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, @@ -2051,6 +2058,20 @@ exit: crtc_state->psr2_man_track_ctl = val; } +static u32 psr2_pipe_srcsz_early_tpt_calc(struct intel_crtc_state *crtc_state, + bool full_update) +{ + int width, height; + + if (!crtc_state->enable_psr2_su_region_et || full_update) + return 0; + + width = drm_rect_width(&crtc_state->psr2_su_area); + height = drm_rect_height(&crtc_state->psr2_su_area); + + return PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1); +} + static void clip_area_update(struct drm_rect *overlap_damage_area, struct drm_rect *damage_area, struct drm_rect *pipe_src) @@ -2095,21 +2116,36 @@ static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st * cursor fully when cursor is in SU area. */ static void -intel_psr2_sel_fetch_et_alignment(struct intel_crtc_state *crtc_state, - struct intel_plane_state *cursor_state) +intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state, + struct intel_crtc *crtc) { - struct drm_rect inter; + struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); + struct intel_plane_state *new_plane_state; + struct intel_plane *plane; + int i; - if (!crtc_state->enable_psr2_su_region_et || - !cursor_state->uapi.visible) + if (!crtc_state->enable_psr2_su_region_et) return; - inter = crtc_state->psr2_su_area; - if (!drm_rect_intersect(&inter, &cursor_state->uapi.dst)) - return; + for_each_new_intel_plane_in_state(state, plane, new_plane_state, i) { + struct drm_rect inter; - clip_area_update(&crtc_state->psr2_su_area, &cursor_state->uapi.dst, - &crtc_state->pipe_src); + if (new_plane_state->uapi.crtc != crtc_state->uapi.crtc) + continue; + + if (plane->id != PLANE_CURSOR) + continue; + + if (!new_plane_state->uapi.visible) + continue; + + inter = crtc_state->psr2_su_area; + if (!drm_rect_intersect(&inter, &new_plane_state->uapi.dst)) + continue; + + clip_area_update(&crtc_state->psr2_su_area, &new_plane_state->uapi.dst, + &crtc_state->pipe_src); + } } /* @@ -2152,8 +2188,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, { struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - struct intel_plane_state *new_plane_state, *old_plane_state, - *cursor_plane_state = NULL; + struct intel_plane_state *new_plane_state, *old_plane_state; struct intel_plane *plane; bool full_update = false; int i, ret; @@ -2238,13 +2273,6 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, damaged_area.x2 += new_plane_state->uapi.dst.x1 - src.x1; clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &crtc_state->pipe_src); - - /* - * Cursor plane new state is stored to adjust su area to cover - * cursor are fully. - */ - if (plane->id == PLANE_CURSOR) - cursor_plane_state = new_plane_state; } /* @@ -2273,9 +2301,13 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, if (ret) return ret; - /* Adjust su area to cover cursor fully as necessary */ - if (cursor_plane_state) - intel_psr2_sel_fetch_et_alignment(crtc_state, cursor_plane_state); + /* + * Adjust su area to cover cursor fully as necessary (early + * transport). This needs to be done after + * drm_atomic_add_affected_planes to ensure visible cursor is added into + * affected planes even when cursor is not updated by itself. + */ + intel_psr2_sel_fetch_et_alignment(state, crtc); intel_psr2_sel_fetch_pipe_alignment(crtc_state); @@ -2338,6 +2370,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, skip_sel_fetch_set_loop: psr2_man_trk_ctl_calc(crtc_state, full_update); + crtc_state->pipe_srcsz_early_tpt = + psr2_pipe_srcsz_early_tpt_calc(crtc_state, full_update); return 0; } diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index fa46d2308b0e..81bf2216371b 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -961,6 +961,9 @@ static int gen8_init_rsvd(struct i915_address_space *vm) struct i915_vma *vma; int ret; + if (!intel_gt_needs_wa_16018031267(vm->gt)) + return 0; + /* The memory will be used only by GPU. */ obj = i915_gem_object_create_lmem(i915, PAGE_SIZE, I915_BO_ALLOC_VOLATILE | diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 1ade568ffbfa..7a6dc371c384 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -908,6 +908,23 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) info->engine_mask &= ~BIT(GSC0); } + /* + * Do not create the command streamer for CCS slices beyond the first. + * All the workload submitted to the first engine will be shared among + * all the slices. + * + * Once the user will be allowed to customize the CCS mode, then this + * check needs to be removed. + */ + if (IS_DG2(gt->i915)) { + u8 first_ccs = __ffs(CCS_MASK(gt)); + + /* Mask off all the CCS engine */ + info->engine_mask &= ~GENMASK(CCS3, CCS0); + /* Put back in the first CCS engine */ + info->engine_mask |= BIT(_CCS(first_ccs)); + } + return info->engine_mask; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index a425db5ed3a2..6a2c2718bcc3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -1024,6 +1024,12 @@ enum i915_map_type intel_gt_coherent_map_type(struct intel_gt *gt, return I915_MAP_WC; } +bool intel_gt_needs_wa_16018031267(struct intel_gt *gt) +{ + /* Wa_16018031267, Wa_16018063123 */ + return IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 55), IP_VER(12, 71)); +} + bool intel_gt_needs_wa_22016122933(struct intel_gt *gt) { return MEDIA_VER_FULL(gt->i915) == IP_VER(13, 0) && gt->type == GT_MEDIA; diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 608f5c872928..003eb93b826f 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -82,17 +82,18 @@ struct drm_printer; ##__VA_ARGS__); \ } while (0) -#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \ - IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 55), IP_VER(12, 71)) && \ - engine->class == COPY_ENGINE_CLASS && engine->instance == 0) - static inline bool gt_is_root(struct intel_gt *gt) { return !gt->info.id; } +bool intel_gt_needs_wa_16018031267(struct intel_gt *gt); bool intel_gt_needs_wa_22016122933(struct intel_gt *gt); +#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \ + intel_gt_needs_wa_16018031267(engine->gt) && \ + engine->class == COPY_ENGINE_CLASS && engine->instance == 0) + static inline struct intel_gt *uc_to_gt(struct intel_uc *uc) { return container_of(uc, struct intel_gt, uc); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c new file mode 100644 index 000000000000..044219c5960a --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include "i915_drv.h" +#include "intel_gt.h" +#include "intel_gt_ccs_mode.h" +#include "intel_gt_regs.h" + +void intel_gt_apply_ccs_mode(struct intel_gt *gt) +{ + int cslice; + u32 mode = 0; + int first_ccs = __ffs(CCS_MASK(gt)); + + if (!IS_DG2(gt->i915)) + return; + + /* Build the value for the fixed CCS load balancing */ + for (cslice = 0; cslice < I915_MAX_CCS; cslice++) { + if (CCS_MASK(gt) & BIT(cslice)) + /* + * If available, assign the cslice + * to the first available engine... + */ + mode |= XEHP_CCS_MODE_CSLICE(cslice, first_ccs); + + else + /* + * ... otherwise, mark the cslice as + * unavailable if no CCS dispatches here + */ + mode |= XEHP_CCS_MODE_CSLICE(cslice, + XEHP_CCS_MODE_CSLICE_MASK); + } + + intel_uncore_write(gt->uncore, XEHP_CCS_MODE, mode); +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h new file mode 100644 index 000000000000..9e5549caeb26 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef __INTEL_GT_CCS_MODE_H__ +#define __INTEL_GT_CCS_MODE_H__ + +struct intel_gt; + +void intel_gt_apply_ccs_mode(struct intel_gt *gt); + +#endif /* __INTEL_GT_CCS_MODE_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 50962cfd1353..743fe3566722 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -1477,8 +1477,14 @@ #define ECOBITS_PPGTT_CACHE4B (0 << 8) #define GEN12_RCU_MODE _MMIO(0x14800) +#define XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE REG_BIT(1) #define GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0) +#define XEHP_CCS_MODE _MMIO(0x14804) +#define XEHP_CCS_MODE_CSLICE_MASK REG_GENMASK(2, 0) /* CCS0-3 + rsvd */ +#define XEHP_CCS_MODE_CSLICE_WIDTH ilog2(XEHP_CCS_MODE_CSLICE_MASK + 1) +#define XEHP_CCS_MODE_CSLICE(cslice, ccs) (ccs << (cslice * XEHP_CCS_MODE_CSLICE_WIDTH)) + #define CHV_FUSE_GT _MMIO(VLV_GUNIT_BASE + 0x2168) #define CHV_FGT_DISABLE_SS0 (1 << 10) #define CHV_FGT_DISABLE_SS1 (1 << 11) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 25413809b9dc..6ec3582c9735 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -10,6 +10,7 @@ #include "intel_engine_regs.h" #include "intel_gpu_commands.h" #include "intel_gt.h" +#include "intel_gt_ccs_mode.h" #include "intel_gt_mcr.h" #include "intel_gt_print.h" #include "intel_gt_regs.h" @@ -51,7 +52,8 @@ * registers belonging to BCS, VCS or VECS should be implemented in * xcs_engine_wa_init(). Workarounds for registers not belonging to a specific * engine's MMIO range but that are part of of the common RCS/CCS reset domain - * should be implemented in general_render_compute_wa_init(). + * should be implemented in general_render_compute_wa_init(). The settings + * about the CCS load balancing should be added in ccs_engine_wa_mode(). * * - GT workarounds: the list of these WAs is applied whenever these registers * revert to their default values: on GPU reset, suspend/resume [1]_, etc. @@ -2854,6 +2856,28 @@ add_render_compute_tuning_settings(struct intel_gt *gt, wa_write_clr(wal, GEN8_GARBCNTL, GEN12_BUS_HASH_CTL_BIT_EXC); } +static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal) +{ + struct intel_gt *gt = engine->gt; + + if (!IS_DG2(gt->i915)) + return; + + /* + * Wa_14019159160: This workaround, along with others, leads to + * significant challenges in utilizing load balancing among the + * CCS slices. Consequently, an architectural decision has been + * made to completely disable automatic CCS load balancing. + */ + wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE); + + /* + * After having disabled automatic load balancing we need to + * assign all slices to a single CCS. We will call it CCS mode 1 + */ + intel_gt_apply_ccs_mode(gt); +} + /* * The workarounds in this function apply to shared registers in * the general render reset domain that aren't tied to a @@ -3004,8 +3028,10 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal * to a single RCS/CCS engine's workaround list since * they're reset as part of the general render domain reset. */ - if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) + if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) { general_render_compute_wa_init(engine, wal); + ccs_engine_wa_mode(engine, wal); + } if (engine->class == COMPUTE_CLASS) ccs_engine_wa_init(engine, wal); diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index 0a0a11dc9ec0..ee02cd833c5e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -812,15 +812,15 @@ op_remap(struct drm_gpuva_op_remap *r, struct drm_gpuva_op_unmap *u = r->unmap; struct nouveau_uvma *uvma = uvma_from_va(u->va); u64 addr = uvma->va.va.addr; - u64 range = uvma->va.va.range; + u64 end = uvma->va.va.addr + uvma->va.va.range; if (r->prev) addr = r->prev->va.addr + r->prev->va.range; if (r->next) - range = r->next->va.addr - addr; + end = r->next->va.addr; - op_unmap_range(u, addr, range); + op_unmap_range(u, addr, end - addr); } static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index 986e8d547c94..060c74a80eb1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -420,7 +420,7 @@ gf100_gr_chan_new(struct nvkm_gr *base, struct nvkm_chan *fifoch, return ret; } else { ret = nvkm_memory_map(gr->attrib_cb, 0, chan->vmm, chan->attrib_cb, - &args, sizeof(args));; + &args, sizeof(args)); if (ret) return ret; } diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index 9063ce254642..fd8e44992184 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -441,19 +441,19 @@ void panfrost_gpu_power_off(struct panfrost_device *pfdev) gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO, - val, !val, 1, 1000); + val, !val, 1, 2000); if (ret) dev_err(pfdev->dev, "shader power transition timeout"); gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO, - val, !val, 1, 1000); + val, !val, 1, 2000); if (ret) dev_err(pfdev->dev, "tiler power transition timeout"); gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present); ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO, - val, !val, 0, 1000); + val, !val, 0, 2000); if (ret) dev_err(pfdev->dev, "l2 power transition timeout"); } diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index ca85e81fdb44..d32ff3857e65 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -193,6 +193,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy) { struct xe_device *xe = to_xe_device(dev); + if (xe->preempt_fence_wq) + destroy_workqueue(xe->preempt_fence_wq); + if (xe->ordered_wq) destroy_workqueue(xe->ordered_wq); @@ -258,9 +261,15 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, INIT_LIST_HEAD(&xe->pinned.external_vram); INIT_LIST_HEAD(&xe->pinned.evicted); + xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0); xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0); xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0); - if (!xe->ordered_wq || !xe->unordered_wq) { + if (!xe->ordered_wq || !xe->unordered_wq || + !xe->preempt_fence_wq) { + /* + * Cleanup done in xe_device_destroy via + * drmm_add_action_or_reset register above + */ drm_err(&xe->drm, "Failed to allocate xe workqueues\n"); err = -ENOMEM; goto err; diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 9785eef2e5a4..8e3a222b41cf 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -363,6 +363,9 @@ struct xe_device { /** @ufence_wq: user fence wait queue */ wait_queue_head_t ufence_wq; + /** @preempt_fence_wq: used to serialize preempt fences */ + struct workqueue_struct *preempt_fence_wq; + /** @ordered_wq: used to serialize compute mode resume */ struct workqueue_struct *ordered_wq; diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 826c8b389672..cc5e0f75de3c 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -94,48 +94,16 @@ * Unlock all */ +/* + * Add validation and rebinding to the drm_exec locking loop, since both can + * trigger eviction which may require sleeping dma_resv locks. + */ static int xe_exec_fn(struct drm_gpuvm_exec *vm_exec) { struct xe_vm *vm = container_of(vm_exec->vm, struct xe_vm, gpuvm); - struct drm_gem_object *obj; - unsigned long index; - int num_fences; - int ret; - - ret = drm_gpuvm_validate(vm_exec->vm, &vm_exec->exec); - if (ret) - return ret; - - /* - * 1 fence slot for the final submit, and 1 more for every per-tile for - * GPU bind and 1 extra for CPU bind. Note that there are potentially - * many vma per object/dma-resv, however the fence slot will just be - * re-used, since they are largely the same timeline and the seqno - * should be in order. In the case of CPU bind there is dummy fence used - * for all CPU binds, so no need to have a per-tile slot for that. - */ - num_fences = 1 + 1 + vm->xe->info.tile_count; - /* - * We don't know upfront exactly how many fence slots we will need at - * the start of the exec, since the TTM bo_validate above can consume - * numerous fence slots. Also due to how the dma_resv_reserve_fences() - * works it only ensures that at least that many fence slots are - * available i.e if there are already 10 slots available and we reserve - * two more, it can just noop without reserving anything. With this it - * is quite possible that TTM steals some of the fence slots and then - * when it comes time to do the vma binding and final exec stage we are - * lacking enough fence slots, leading to some nasty BUG_ON() when - * adding the fences. Hence just add our own fences here, after the - * validate stage. - */ - drm_exec_for_each_locked_object(&vm_exec->exec, index, obj) { - ret = dma_resv_reserve_fences(obj->resv, num_fences); - if (ret) - return ret; - } - - return 0; + /* The fence slot added here is intended for the exec sched job. */ + return xe_vm_validate_rebind(vm, &vm_exec->exec, 1); } int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) @@ -152,7 +120,6 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct drm_exec *exec = &vm_exec.exec; u32 i, num_syncs = 0, num_ufence = 0; struct xe_sched_job *job; - struct dma_fence *rebind_fence; struct xe_vm *vm; bool write_locked, skip_retry = false; ktime_t end = 0; @@ -290,39 +257,7 @@ retry: goto err_exec; } - /* - * Rebind any invalidated userptr or evicted BOs in the VM, non-compute - * VM mode only. - */ - rebind_fence = xe_vm_rebind(vm, false); - if (IS_ERR(rebind_fence)) { - err = PTR_ERR(rebind_fence); - goto err_put_job; - } - - /* - * We store the rebind_fence in the VM so subsequent execs don't get - * scheduled before the rebinds of userptrs / evicted BOs is complete. - */ - if (rebind_fence) { - dma_fence_put(vm->rebind_fence); - vm->rebind_fence = rebind_fence; - } - if (vm->rebind_fence) { - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, - &vm->rebind_fence->flags)) { - dma_fence_put(vm->rebind_fence); - vm->rebind_fence = NULL; - } else { - dma_fence_get(vm->rebind_fence); - err = drm_sched_job_add_dependency(&job->drm, - vm->rebind_fence); - if (err) - goto err_put_job; - } - } - - /* Wait behind munmap style rebinds */ + /* Wait behind rebinds */ if (!xe_vm_in_lr_mode(vm)) { err = drm_sched_job_add_resv_dependencies(&job->drm, xe_vm_resv(vm), diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 62b3d9d1d7cd..462b33195032 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -148,6 +148,11 @@ struct xe_exec_queue { const struct xe_ring_ops *ring_ops; /** @entity: DRM sched entity for this exec queue (1 to 1 relationship) */ struct drm_sched_entity *entity; + /** + * @tlb_flush_seqno: The seqno of the last rebind tlb flush performed + * Protected by @vm's resv. Unused if @vm == NULL. + */ + u64 tlb_flush_seqno; /** @lrc: logical ring context for this exec queue */ struct xe_lrc lrc[]; }; diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 241c294270d9..fa9e9853c53b 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -100,10 +100,9 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma, { struct xe_bo *bo = xe_vma_bo(vma); struct xe_vm *vm = xe_vma_vm(vma); - unsigned int num_shared = 2; /* slots for bind + move */ int err; - err = xe_vm_prepare_vma(exec, vma, num_shared); + err = xe_vm_lock_vma(exec, vma); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index f03e077f81a0..e598a4363d01 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -61,7 +61,6 @@ int xe_gt_tlb_invalidation_init(struct xe_gt *gt) INIT_LIST_HEAD(>->tlb_invalidation.pending_fences); spin_lock_init(>->tlb_invalidation.pending_lock); spin_lock_init(>->tlb_invalidation.lock); - gt->tlb_invalidation.fence_context = dma_fence_context_alloc(1); INIT_DELAYED_WORK(>->tlb_invalidation.fence_tdr, xe_gt_tlb_fence_timeout); diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h index 70c615dd1498..07b2f724ec45 100644 --- a/drivers/gpu/drm/xe/xe_gt_types.h +++ b/drivers/gpu/drm/xe/xe_gt_types.h @@ -177,13 +177,6 @@ struct xe_gt { * xe_gt_tlb_fence_timeout after the timeut interval is over. */ struct delayed_work fence_tdr; - /** @tlb_invalidation.fence_context: context for TLB invalidation fences */ - u64 fence_context; - /** - * @tlb_invalidation.fence_seqno: seqno to TLB invalidation fences, protected by - * tlb_invalidation.lock - */ - u32 fence_seqno; /** @tlb_invalidation.lock: protects TLB invalidation fences */ spinlock_t lock; } tlb_invalidation; diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c index 7bce2a332603..7d50c6e89d8e 100644 --- a/drivers/gpu/drm/xe/xe_preempt_fence.c +++ b/drivers/gpu/drm/xe/xe_preempt_fence.c @@ -49,7 +49,7 @@ static bool preempt_fence_enable_signaling(struct dma_fence *fence) struct xe_exec_queue *q = pfence->q; pfence->error = q->ops->suspend(q); - queue_work(system_unbound_wq, &pfence->preempt_work); + queue_work(q->vm->xe->preempt_fence_wq, &pfence->preempt_work); return true; } diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 7f54bc3e389d..4efc8c1a3d7a 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1135,8 +1135,7 @@ static int invalidation_fence_init(struct xe_gt *gt, spin_lock_irq(>->tlb_invalidation.lock); dma_fence_init(&ifence->base.base, &invalidation_fence_ops, >->tlb_invalidation.lock, - gt->tlb_invalidation.fence_context, - ++gt->tlb_invalidation.fence_seqno); + dma_fence_context_alloc(1), 1); spin_unlock_irq(>->tlb_invalidation.lock); INIT_LIST_HEAD(&ifence->base.link); @@ -1236,6 +1235,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue err = xe_pt_prepare_bind(tile, vma, entries, &num_entries); if (err) goto err; + + err = dma_resv_reserve_fences(xe_vm_resv(vm), 1); + if (!err && !xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm) + err = dma_resv_reserve_fences(xe_vma_bo(vma)->ttm.base.resv, 1); + if (err) + goto err; + xe_tile_assert(tile, num_entries <= ARRAY_SIZE(entries)); xe_vm_dbg_print_entries(tile_to_xe(tile), entries, num_entries); @@ -1254,11 +1260,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue * non-faulting LR, in particular on user-space batch buffer chaining, * it needs to be done here. */ - if ((rebind && !xe_vm_in_lr_mode(vm) && !vm->batch_invalidate_tlb) || - (!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) { + if ((!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) { ifence = kzalloc(sizeof(*ifence), GFP_KERNEL); if (!ifence) return ERR_PTR(-ENOMEM); + } else if (rebind && !xe_vm_in_lr_mode(vm)) { + /* We bump also if batch_invalidate_tlb is true */ + vm->tlb_flush_seqno++; } rfence = kzalloc(sizeof(*rfence), GFP_KERNEL); @@ -1297,7 +1305,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue } /* add shared fence now for pagetable delayed destroy */ - dma_resv_add_fence(xe_vm_resv(vm), fence, !rebind && + dma_resv_add_fence(xe_vm_resv(vm), fence, rebind || last_munmap_rebind ? DMA_RESV_USAGE_KERNEL : DMA_RESV_USAGE_BOOKKEEP); @@ -1576,6 +1584,7 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu struct dma_fence *fence = NULL; struct invalidation_fence *ifence; struct xe_range_fence *rfence; + int err; LLIST_HEAD(deferred); @@ -1593,6 +1602,12 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu xe_pt_calc_rfence_interval(vma, &unbind_pt_update, entries, num_entries); + err = dma_resv_reserve_fences(xe_vm_resv(vm), 1); + if (!err && !xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm) + err = dma_resv_reserve_fences(xe_vma_bo(vma)->ttm.base.resv, 1); + if (err) + return ERR_PTR(err); + ifence = kzalloc(sizeof(*ifence), GFP_KERNEL); if (!ifence) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index c4edffcd4a32..5b2b37b59813 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -219,10 +219,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc { u32 dw[MAX_JOB_SIZE_DW], i = 0; u32 ppgtt_flag = get_ppgtt_flag(job); - struct xe_vm *vm = job->q->vm; struct xe_gt *gt = job->q->gt; - if (vm && vm->batch_invalidate_tlb) { + if (job->ring_ops_flush_tlb) { dw[i++] = preparser_disable(true); i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), seqno, true, dw, i); @@ -270,7 +269,6 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, struct xe_gt *gt = job->q->gt; struct xe_device *xe = gt_to_xe(gt); bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE; - struct xe_vm *vm = job->q->vm; dw[i++] = preparser_disable(true); @@ -282,13 +280,13 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, i = emit_aux_table_inv(gt, VE0_AUX_INV, dw, i); } - if (vm && vm->batch_invalidate_tlb) + if (job->ring_ops_flush_tlb) i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), seqno, true, dw, i); dw[i++] = preparser_disable(false); - if (!vm || !vm->batch_invalidate_tlb) + if (!job->ring_ops_flush_tlb) i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), seqno, dw, i); @@ -317,7 +315,6 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, struct xe_gt *gt = job->q->gt; struct xe_device *xe = gt_to_xe(gt); bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK); - struct xe_vm *vm = job->q->vm; u32 mask_flags = 0; dw[i++] = preparser_disable(true); @@ -327,7 +324,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS; /* See __xe_pt_bind_vma() for a discussion on TLB invalidations. */ - i = emit_pipe_invalidate(mask_flags, vm && vm->batch_invalidate_tlb, dw, i); + i = emit_pipe_invalidate(mask_flags, job->ring_ops_flush_tlb, dw, i); /* hsdes: 1809175790 */ if (has_aux_ccs(xe)) diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c index 8151ddafb940..b0c7fa4693cf 100644 --- a/drivers/gpu/drm/xe/xe_sched_job.c +++ b/drivers/gpu/drm/xe/xe_sched_job.c @@ -250,6 +250,16 @@ bool xe_sched_job_completed(struct xe_sched_job *job) void xe_sched_job_arm(struct xe_sched_job *job) { + struct xe_exec_queue *q = job->q; + struct xe_vm *vm = q->vm; + + if (vm && !xe_sched_job_is_migration(q) && !xe_vm_in_lr_mode(vm) && + (vm->batch_invalidate_tlb || vm->tlb_flush_seqno != q->tlb_flush_seqno)) { + xe_vm_assert_held(vm); + q->tlb_flush_seqno = vm->tlb_flush_seqno; + job->ring_ops_flush_tlb = true; + } + drm_sched_job_arm(&job->drm); } diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h index b1d83da50a53..5e12724219fd 100644 --- a/drivers/gpu/drm/xe/xe_sched_job_types.h +++ b/drivers/gpu/drm/xe/xe_sched_job_types.h @@ -39,6 +39,8 @@ struct xe_sched_job { } user_fence; /** @migrate_flush_flags: Additional flush flags for migration jobs */ u32 migrate_flush_flags; + /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */ + bool ring_ops_flush_tlb; /** @batch_addr: batch buffer address of job */ u64 batch_addr[]; }; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index f88faef4142b..62d1ef8867a8 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -482,17 +482,53 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) return 0; } +/** + * xe_vm_validate_rebind() - Validate buffer objects and rebind vmas + * @vm: The vm for which we are rebinding. + * @exec: The struct drm_exec with the locked GEM objects. + * @num_fences: The number of fences to reserve for the operation, not + * including rebinds and validations. + * + * Validates all evicted gem objects and rebinds their vmas. Note that + * rebindings may cause evictions and hence the validation-rebind + * sequence is rerun until there are no more objects to validate. + * + * Return: 0 on success, negative error code on error. In particular, + * may return -EINTR or -ERESTARTSYS if interrupted, and -EDEADLK if + * the drm_exec transaction needs to be restarted. + */ +int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec, + unsigned int num_fences) +{ + struct drm_gem_object *obj; + unsigned long index; + int ret; + + do { + ret = drm_gpuvm_validate(&vm->gpuvm, exec); + if (ret) + return ret; + + ret = xe_vm_rebind(vm, false); + if (ret) + return ret; + } while (!list_empty(&vm->gpuvm.evict.list)); + + drm_exec_for_each_locked_object(exec, index, obj) { + ret = dma_resv_reserve_fences(obj->resv, num_fences); + if (ret) + return ret; + } + + return 0; +} + static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, bool *done) { int err; - /* - * 1 fence for each preempt fence plus a fence for each tile from a - * possible rebind - */ - err = drm_gpuvm_prepare_vm(&vm->gpuvm, exec, vm->preempt.num_exec_queues + - vm->xe->info.tile_count); + err = drm_gpuvm_prepare_vm(&vm->gpuvm, exec, 0); if (err) return err; @@ -507,7 +543,7 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, return 0; } - err = drm_gpuvm_prepare_objects(&vm->gpuvm, exec, vm->preempt.num_exec_queues); + err = drm_gpuvm_prepare_objects(&vm->gpuvm, exec, 0); if (err) return err; @@ -515,14 +551,19 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, if (err) return err; - return drm_gpuvm_validate(&vm->gpuvm, exec); + /* + * Add validation and rebinding to the locking loop since both can + * cause evictions which may require blocing dma_resv locks. + * The fence reservation here is intended for the new preempt fences + * we attach at the end of the rebind work. + */ + return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues); } static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); struct drm_exec exec; - struct dma_fence *rebind_fence; unsigned int fence_count = 0; LIST_HEAD(preempt_fences); ktime_t end = 0; @@ -568,18 +609,11 @@ retry: if (err) goto out_unlock; - rebind_fence = xe_vm_rebind(vm, true); - if (IS_ERR(rebind_fence)) { - err = PTR_ERR(rebind_fence); + err = xe_vm_rebind(vm, true); + if (err) goto out_unlock; - } - if (rebind_fence) { - dma_fence_wait(rebind_fence, false); - dma_fence_put(rebind_fence); - } - - /* Wait on munmap style VM unbinds */ + /* Wait on rebinds and munmap style VM unbinds */ wait = dma_resv_wait_timeout(xe_vm_resv(vm), DMA_RESV_USAGE_KERNEL, false, MAX_SCHEDULE_TIMEOUT); @@ -773,14 +807,14 @@ xe_vm_bind_vma(struct xe_vma *vma, struct xe_exec_queue *q, struct xe_sync_entry *syncs, u32 num_syncs, bool first_op, bool last_op); -struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker) +int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker) { - struct dma_fence *fence = NULL; + struct dma_fence *fence; struct xe_vma *vma, *next; lockdep_assert_held(&vm->lock); if (xe_vm_in_lr_mode(vm) && !rebind_worker) - return NULL; + return 0; xe_vm_assert_held(vm); list_for_each_entry_safe(vma, next, &vm->rebind_list, @@ -788,17 +822,17 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker) xe_assert(vm->xe, vma->tile_present); list_del_init(&vma->combined_links.rebind); - dma_fence_put(fence); if (rebind_worker) trace_xe_vma_rebind_worker(vma); else trace_xe_vma_rebind_exec(vma); fence = xe_vm_bind_vma(vma, NULL, NULL, 0, false, false); if (IS_ERR(fence)) - return fence; + return PTR_ERR(fence); + dma_fence_put(fence); } - return fence; + return 0; } static void xe_vma_free(struct xe_vma *vma) @@ -1004,35 +1038,26 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence) } /** - * xe_vm_prepare_vma() - drm_exec utility to lock a vma + * xe_vm_lock_vma() - drm_exec utility to lock a vma * @exec: The drm_exec object we're currently locking for. * @vma: The vma for witch we want to lock the vm resv and any attached * object's resv. - * @num_shared: The number of dma-fence slots to pre-allocate in the - * objects' reservation objects. * * Return: 0 on success, negative error code on error. In particular * may return -EDEADLK on WW transaction contention and -EINTR if * an interruptible wait is terminated by a signal. */ -int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma, - unsigned int num_shared) +int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma) { struct xe_vm *vm = xe_vma_vm(vma); struct xe_bo *bo = xe_vma_bo(vma); int err; XE_WARN_ON(!vm); - if (num_shared) - err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared); - else - err = drm_exec_lock_obj(exec, xe_vm_obj(vm)); - if (!err && bo && !bo->vm) { - if (num_shared) - err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared); - else - err = drm_exec_lock_obj(exec, &bo->ttm.base); - } + + err = drm_exec_lock_obj(exec, xe_vm_obj(vm)); + if (!err && bo && !bo->vm) + err = drm_exec_lock_obj(exec, &bo->ttm.base); return err; } @@ -1044,7 +1069,7 @@ static void xe_vma_destroy_unlocked(struct xe_vma *vma) drm_exec_init(&exec, 0, 0); drm_exec_until_all_locked(&exec) { - err = xe_vm_prepare_vma(&exec, vma, 0); + err = xe_vm_lock_vma(&exec, vma); drm_exec_retry_on_contention(&exec); if (XE_WARN_ON(err)) break; @@ -1589,7 +1614,6 @@ static void vm_destroy_work_func(struct work_struct *w) XE_WARN_ON(vm->pt_root[id]); trace_xe_vm_free(vm); - dma_fence_put(vm->rebind_fence); kfree(vm); } @@ -2512,7 +2536,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm, lockdep_assert_held_write(&vm->lock); - err = xe_vm_prepare_vma(exec, vma, 1); + err = xe_vm_lock_vma(exec, vma); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index 6df1f1c7f85d..306cd0934a19 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -207,7 +207,7 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm); int xe_vm_userptr_check_repin(struct xe_vm *vm); -struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker); +int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker); int xe_vm_invalidate_vma(struct xe_vma *vma); @@ -242,8 +242,10 @@ bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end); int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id); -int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma, - unsigned int num_shared); +int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma); + +int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec, + unsigned int num_fences); /** * xe_vm_resv() - Return's the vm's reservation object diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index ae5fb565f6bf..badf3945083d 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -177,9 +177,6 @@ struct xe_vm { */ struct list_head rebind_list; - /** @rebind_fence: rebind fence from execbuf */ - struct dma_fence *rebind_fence; - /** * @destroy_work: worker to destroy VM, needed as a dma_fence signaling * from an irq context can be last put and the destroy needs to be able @@ -264,6 +261,11 @@ struct xe_vm { bool capture_once; } error_capture; + /** + * @tlb_flush_seqno: Required TLB flush seqno for the next exec. + * protected by the vm resv. + */ + u64 tlb_flush_seqno; /** @batch_invalidate_tlb: Always invalidate TLB before batch start */ bool batch_invalidate_tlb; /** @xef: XE file handle for tracking this VM's drm client */ diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index 76f79b68cef8..888ca636f3f3 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -324,6 +324,7 @@ static void decode_ISR(unsigned int val) decode_bits(KERN_DEBUG "ISR", isr_bits, ARRAY_SIZE(isr_bits), val); } +#ifdef CONFIG_I2C_PXA_SLAVE static const struct bits icr_bits[] = { PXA_BIT(ICR_START, "START", NULL), PXA_BIT(ICR_STOP, "STOP", NULL), @@ -342,7 +343,6 @@ static const struct bits icr_bits[] = { PXA_BIT(ICR_UR, "UR", "ur"), }; -#ifdef CONFIG_I2C_PXA_SLAVE static void decode_ICR(unsigned int val) { decode_bits(KERN_DEBUG "ICR", icr_bits, ARRAY_SIZE(icr_bits), val); diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index e7a44929f0da..33228c1c8980 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3228,7 +3228,7 @@ out: static void iommu_snp_enable(void) { #ifdef CONFIG_KVM_AMD_SEV - if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return; /* * The SNP support requires that IOMMU must be enabled, and is @@ -3236,12 +3236,14 @@ static void iommu_snp_enable(void) */ if (no_iommu || iommu_default_passthrough()) { pr_err("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n"); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); return; } amd_iommu_snp_en = check_feature(FEATURE_SNP); if (!amd_iommu_snp_en) { pr_err("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n"); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); return; } diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index 97a00ec9a4d4..caacdc0a3819 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -209,7 +209,7 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) if (dev->bdev_file) { invalidate_mapping_pages(dev->bdev_file->f_mapping, 0, -1); - fput(dev->bdev_file); + bdev_fput(dev->bdev_file); } kfree(dev); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 9ed1821184ec..c95787cb9086 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -5503,8 +5503,12 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .family = MV88E6XXX_FAMILY_6250, .name = "Marvell 88E6020", .num_databases = 64, - .num_ports = 4, + /* Ports 2-4 are not routed to pins + * => usable ports 0, 1, 5, 6 + */ + .num_ports = 7, .num_internal_phys = 2, + .invalid_port_mask = BIT(2) | BIT(3) | BIT(4), .max_vid = 4095, .port_base_addr = 0x8, .phy_base_addr = 0x0, diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 833e55e4b961..52ddb4ef259e 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -94,7 +94,7 @@ int sja1110_pcs_mdio_read_c45(struct mii_bus *bus, int phy, int mmd, int reg) return tmp & 0xffff; } -int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int reg, int mmd, +int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int mmd, int reg, u16 val) { struct sja1105_mdio_private *mdio_priv = bus->priv; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 7396e2823e32..b1f84b37032a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3280,7 +3280,7 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, } /* Returns a reusable dma control register value */ -static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) +static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx) { unsigned int i; u32 reg; @@ -3305,6 +3305,14 @@ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) udelay(10); bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH); + if (flush_rx) { + reg = bcmgenet_rbuf_ctrl_get(priv); + bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0)); + udelay(10); + bcmgenet_rbuf_ctrl_set(priv, reg); + udelay(10); + } + return dma_ctrl; } @@ -3368,8 +3376,8 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_set_hw_addr(priv, dev->dev_addr); - /* Disable RX/TX DMA and flush TX queues */ - dma_ctrl = bcmgenet_dma_disable(priv); + /* Disable RX/TX DMA and flush TX and RX queues */ + dma_ctrl = bcmgenet_dma_disable(priv, true); /* Reinitialize TDMA and RDMA and SW housekeeping */ ret = bcmgenet_init_dma(priv); @@ -4235,7 +4243,7 @@ static int bcmgenet_resume(struct device *d) bcmgenet_hfb_create_rxnfc_filter(priv, rule); /* Disable RX/TX DMA and flush TX queues */ - dma_ctrl = bcmgenet_dma_disable(priv); + dma_ctrl = bcmgenet_dma_disable(priv, false); /* Reinitialize TDMA and RDMA and SW housekeeping */ ret = bcmgenet_init_dma(priv); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d7693fdf640d..8bd213da8fb6 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2454,8 +2454,6 @@ static int fec_enet_mii_probe(struct net_device *ndev) fep->link = 0; fep->full_duplex = 0; - phy_dev->mac_managed_pm = true; - phy_attached_info(phy_dev); return 0; @@ -2467,10 +2465,12 @@ static int fec_enet_mii_init(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); bool suppress_preamble = false; + struct phy_device *phydev; struct device_node *node; int err = -ENXIO; u32 mii_speed, holdtime; u32 bus_freq; + int addr; /* * The i.MX28 dual fec interfaces are not equal. @@ -2584,6 +2584,13 @@ static int fec_enet_mii_init(struct platform_device *pdev) goto err_out_free_mdiobus; of_node_put(node); + /* find all the PHY devices on the bus and set mac_managed_pm to true */ + for (addr = 0; addr < PHY_MAX_ADDR; addr++) { + phydev = mdiobus_get_phy(fep->mii_bus, addr); + if (phydev) + phydev->mac_managed_pm = true; + } + mii_cnt++; /* save fec0 mii_bus */ diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 1fef6bb5a5fb..4b6e7536170a 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -628,6 +628,7 @@ struct e1000_phy_info { u32 id; u32 reset_delay_us; /* in usec */ u32 revision; + u32 retry_count; enum e1000_media_type media_type; @@ -644,6 +645,7 @@ struct e1000_phy_info { bool polarity_correction; bool speed_downgraded; bool autoneg_wait_to_complete; + bool retry_enabled; }; struct e1000_nvm_info { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 19e450a5bd31..f9e94be36e97 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -222,11 +222,18 @@ out: if (hw->mac.type >= e1000_pch_lpt) { /* Only unforce SMBus if ME is not active */ if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) { + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + /* Unforce SMBus mode in PHY */ e1e_rphy_locked(hw, CV_SMB_CTRL, &phy_reg); phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS; e1e_wphy_locked(hw, CV_SMB_CTRL, phy_reg); + e1000e_enable_phy_retry(hw); + /* Unforce SMBus mode in MAC */ mac_reg = er32(CTRL_EXT); mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; @@ -310,6 +317,11 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) goto out; } + /* There is no guarantee that the PHY is accessible at this time + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + /* The MAC-PHY interconnect may be in SMBus mode. If the PHY is * inaccessible and resetting the PHY is not blocked, toggle the * LANPHYPC Value bit to force the interconnect to PCIe mode. @@ -380,6 +392,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) break; } + e1000e_enable_phy_retry(hw); + hw->phy.ops.release(hw); if (!ret_val) { @@ -449,6 +463,11 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) phy->id = e1000_phy_unknown; + if (hw->mac.type == e1000_pch_mtp) { + phy->retry_count = 2; + e1000e_enable_phy_retry(hw); + } + ret_val = e1000_init_phy_workarounds_pchlan(hw); if (ret_val) return ret_val; @@ -1146,18 +1165,6 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) if (ret_val) goto out; - /* Force SMBus mode in PHY */ - ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); - if (ret_val) - goto release; - phy_reg |= CV_SMB_CTRL_FORCE_SMBUS; - e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); - - /* Force SMBus mode in MAC */ - mac_reg = er32(CTRL_EXT); - mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, mac_reg); - /* Si workaround for ULP entry flow on i127/rev6 h/w. Enable * LPLU and disable Gig speed when entering ULP */ @@ -1313,6 +1320,11 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) /* Toggle LANPHYPC Value bit */ e1000_toggle_lanphypc_pch_lpt(hw); + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + /* Unforce SMBus mode in PHY */ ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); if (ret_val) { @@ -1333,6 +1345,8 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS; e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); + e1000e_enable_phy_retry(hw); + /* Unforce SMBus mode in MAC */ mac_reg = er32(CTRL_EXT); mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index cc8c531ec3df..3692fce20195 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6623,6 +6623,7 @@ 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) @@ -6696,6 +6697,23 @@ 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/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 5e329156d1ba..93544f1cc2a5 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -107,6 +107,16 @@ s32 e1000e_phy_reset_dsp(struct e1000_hw *hw) return e1e_wphy(hw, M88E1000_PHY_GEN_CONTROL, 0); } +void e1000e_disable_phy_retry(struct e1000_hw *hw) +{ + hw->phy.retry_enabled = false; +} + +void e1000e_enable_phy_retry(struct e1000_hw *hw) +{ + hw->phy.retry_enabled = true; +} + /** * e1000e_read_phy_reg_mdic - Read MDI control register * @hw: pointer to the HW structure @@ -118,55 +128,73 @@ s32 e1000e_phy_reset_dsp(struct e1000_hw *hw) **/ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) { + u32 i, mdic = 0, retry_counter, retry_max; struct e1000_phy_info *phy = &hw->phy; - u32 i, mdic = 0; + bool success; if (offset > MAX_PHY_REG_ADDRESS) { e_dbg("PHY Address %d is out of range\n", offset); return -E1000_ERR_PARAM; } + retry_max = phy->retry_enabled ? phy->retry_count : 0; + /* Set up Op-code, Phy Address, and register offset in the MDI * Control register. The MAC will take care of interfacing with the * PHY to retrieve the desired data. */ - mdic = ((offset << E1000_MDIC_REG_SHIFT) | - (phy->addr << E1000_MDIC_PHY_SHIFT) | - (E1000_MDIC_OP_READ)); + for (retry_counter = 0; retry_counter <= retry_max; retry_counter++) { + success = true; - ew32(MDIC, mdic); + mdic = ((offset << E1000_MDIC_REG_SHIFT) | + (phy->addr << E1000_MDIC_PHY_SHIFT) | + (E1000_MDIC_OP_READ)); - /* Poll the ready bit to see if the MDI read completed - * Increasing the time out as testing showed failures with - * the lower time out - */ - for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { - udelay(50); - mdic = er32(MDIC); - if (mdic & E1000_MDIC_READY) - break; - } - if (!(mdic & E1000_MDIC_READY)) { - e_dbg("MDI Read PHY Reg Address %d did not complete\n", offset); - return -E1000_ERR_PHY; - } - if (mdic & E1000_MDIC_ERROR) { - e_dbg("MDI Read PHY Reg Address %d Error\n", offset); - return -E1000_ERR_PHY; - } - if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { - e_dbg("MDI Read offset error - requested %d, returned %d\n", - offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); - return -E1000_ERR_PHY; + ew32(MDIC, mdic); + + /* Poll the ready bit to see if the MDI read completed + * Increasing the time out as testing showed failures with + * the lower time out + */ + for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { + usleep_range(50, 60); + mdic = er32(MDIC); + if (mdic & E1000_MDIC_READY) + break; + } + if (!(mdic & E1000_MDIC_READY)) { + e_dbg("MDI Read PHY Reg Address %d did not complete\n", + offset); + success = false; + } + if (mdic & E1000_MDIC_ERROR) { + e_dbg("MDI Read PHY Reg Address %d Error\n", offset); + success = false; + } + if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { + e_dbg("MDI Read offset error - requested %d, returned %d\n", + offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); + success = false; + } + + /* Allow some time after each MDIC transaction to avoid + * reading duplicate data in the next MDIC transaction. + */ + if (hw->mac.type == e1000_pch2lan) + usleep_range(100, 150); + + if (success) { + *data = (u16)mdic; + return 0; + } + + if (retry_counter != retry_max) { + e_dbg("Perform retry on PHY transaction...\n"); + mdelay(10); + } } - *data = (u16)mdic; - /* Allow some time after each MDIC transaction to avoid - * reading duplicate data in the next MDIC transaction. - */ - if (hw->mac.type == e1000_pch2lan) - udelay(100); - return 0; + return -E1000_ERR_PHY; } /** @@ -179,56 +207,72 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) **/ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) { + u32 i, mdic = 0, retry_counter, retry_max; struct e1000_phy_info *phy = &hw->phy; - u32 i, mdic = 0; + bool success; if (offset > MAX_PHY_REG_ADDRESS) { e_dbg("PHY Address %d is out of range\n", offset); return -E1000_ERR_PARAM; } + retry_max = phy->retry_enabled ? phy->retry_count : 0; + /* Set up Op-code, Phy Address, and register offset in the MDI * Control register. The MAC will take care of interfacing with the * PHY to retrieve the desired data. */ - mdic = (((u32)data) | - (offset << E1000_MDIC_REG_SHIFT) | - (phy->addr << E1000_MDIC_PHY_SHIFT) | - (E1000_MDIC_OP_WRITE)); + for (retry_counter = 0; retry_counter <= retry_max; retry_counter++) { + success = true; - ew32(MDIC, mdic); + mdic = (((u32)data) | + (offset << E1000_MDIC_REG_SHIFT) | + (phy->addr << E1000_MDIC_PHY_SHIFT) | + (E1000_MDIC_OP_WRITE)); - /* Poll the ready bit to see if the MDI read completed - * Increasing the time out as testing showed failures with - * the lower time out - */ - for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { - udelay(50); - mdic = er32(MDIC); - if (mdic & E1000_MDIC_READY) - break; - } - if (!(mdic & E1000_MDIC_READY)) { - e_dbg("MDI Write PHY Reg Address %d did not complete\n", offset); - return -E1000_ERR_PHY; - } - if (mdic & E1000_MDIC_ERROR) { - e_dbg("MDI Write PHY Red Address %d Error\n", offset); - return -E1000_ERR_PHY; - } - if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { - e_dbg("MDI Write offset error - requested %d, returned %d\n", - offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); - return -E1000_ERR_PHY; - } + ew32(MDIC, mdic); - /* Allow some time after each MDIC transaction to avoid - * reading duplicate data in the next MDIC transaction. - */ - if (hw->mac.type == e1000_pch2lan) - udelay(100); + /* Poll the ready bit to see if the MDI read completed + * Increasing the time out as testing showed failures with + * the lower time out + */ + for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { + usleep_range(50, 60); + mdic = er32(MDIC); + if (mdic & E1000_MDIC_READY) + break; + } + if (!(mdic & E1000_MDIC_READY)) { + e_dbg("MDI Write PHY Reg Address %d did not complete\n", + offset); + success = false; + } + if (mdic & E1000_MDIC_ERROR) { + e_dbg("MDI Write PHY Reg Address %d Error\n", offset); + success = false; + } + if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { + e_dbg("MDI Write offset error - requested %d, returned %d\n", + offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); + success = false; + } - return 0; + /* Allow some time after each MDIC transaction to avoid + * reading duplicate data in the next MDIC transaction. + */ + if (hw->mac.type == e1000_pch2lan) + usleep_range(100, 150); + + if (success) + return 0; + + if (retry_counter != retry_max) { + e_dbg("Perform retry on PHY transaction...\n"); + mdelay(10); + } + } + + return -E1000_ERR_PHY; } /** diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h index c48777d09523..049bb325b4b1 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.h +++ b/drivers/net/ethernet/intel/e1000e/phy.h @@ -51,6 +51,8 @@ s32 e1000e_read_phy_reg_bm2(struct e1000_hw *hw, u32 offset, u16 *data); s32 e1000e_write_phy_reg_bm2(struct e1000_hw *hw, u32 offset, u16 data); void e1000_power_up_phy_copper(struct e1000_hw *hw); void e1000_power_down_phy_copper(struct e1000_hw *hw); +void e1000e_disable_phy_retry(struct e1000_hw *hw); +void e1000e_enable_phy_retry(struct e1000_hw *hw); s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data); s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data); s32 e1000_read_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 *data); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index ba24f3fa92c3..2fbabcdb5bb5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -955,6 +955,7 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; + bool in_busy_poll; int irq_num; /* IRQ assigned to this q_vector */ } ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f86578857e8a..48b9ddb2b1b3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1253,8 +1253,11 @@ int i40e_count_filters(struct i40e_vsi *vsi) int bkt; int cnt = 0; - hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) - ++cnt; + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_ACTIVE) + ++cnt; + } return cnt; } @@ -3911,6 +3914,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; + /* Set ITR for software interrupts triggered after exiting + * busy-loop polling. + */ + wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1), + I40E_ITR_20K); + wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 14ab642cafdb..432afbb64201 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -333,8 +333,11 @@ #define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3 #define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) #define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5 +#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT) #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24 #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT) +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25 +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT) #define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */ #define I40E_PFINT_ICR0_INTEVENT_SHIFT 0 #define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 0d7177083708..1a12b732818e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2630,7 +2630,22 @@ process_next: return failure ? budget : (int)total_rx_packets; } -static inline u32 i40e_buildreg_itr(const int type, u16 itr) +/** + * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register + * @itr_idx: interrupt throttling index + * @interval: interrupt throttling interval value in usecs + * @force_swint: force software interrupt + * + * The function builds a value for I40E_PFINT_DYN_CTLN register that + * is used to update interrupt throttling interval for specified ITR index + * and optionally enforces a software interrupt. If the @itr_idx is equal + * to I40E_ITR_NONE then no interval change is applied and only @force_swint + * parameter is taken into account. If the interval change and enforced + * software interrupt are not requested then the built value just enables + * appropriate vector interrupt. + **/ +static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval, + bool force_swint) { u32 val; @@ -2644,23 +2659,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) * an event in the PBA anyway so we need to rely on the automask * to hold pending events for us until the interrupt is re-enabled * - * The itr value is reported in microseconds, and the register - * value is recorded in 2 microsecond units. For this reason we - * only need to shift by the interval shift - 1 instead of the - * full value. + * We have to shift the given value as it is reported in microseconds + * and the register value is recorded in 2 microsecond units. */ - itr &= I40E_ITR_MASK; + interval >>= 1; + /* 1. Enable vector interrupt + * 2. Update the interval for the specified ITR index + * (I40E_ITR_NONE in the register is used to indicate that + * no interval update is requested) + */ val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1)); + FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) | + FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval); + + /* 3. Enforce software interrupt trigger if requested + * (These software interrupts rate is limited by ITR2 that is + * set to 20K interrupts per second) + */ + if (force_swint) + val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK | + I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK | + FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK, + I40E_SW_ITR); return val; } -/* a small macro to shorten up some long lines */ -#define INTREG I40E_PFINT_DYN_CTLN - /* The act of updating the ITR will cause it to immediately trigger. In order * to prevent this from throwing off adaptive update statistics we defer the * update so that it can only happen so often. So after either Tx or Rx are @@ -2679,8 +2704,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { + enum i40e_dyn_idx itr_idx = I40E_ITR_NONE; struct i40e_hw *hw = &vsi->back->hw; - u32 intval; + u16 interval = 0; + u32 itr_val; /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) { @@ -2702,8 +2729,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ if (q_vector->rx.target_itr < q_vector->rx.current_itr) { /* Rx ITR needs to be reduced, this is highest priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || @@ -2712,25 +2739,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* Tx ITR needs to be reduced, this is second priority * Tx ITR needs to be increased more than Rx, fourth priority */ - intval = i40e_buildreg_itr(I40E_TX_ITR, - q_vector->tx.target_itr); + itr_idx = I40E_TX_ITR; + interval = q_vector->tx.target_itr; q_vector->tx.current_itr = q_vector->tx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { /* Rx ITR needs to be increased, third priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else { /* No ITR update, lowest priority */ - intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); if (q_vector->itr_countdown) q_vector->itr_countdown--; } - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), intval); + /* Do not update interrupt control register if VSI is down */ + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return; + + /* Update ITR interval if necessary and enforce software interrupt + * if we are exiting busy poll. + */ + if (q_vector->in_busy_poll) { + itr_val = i40e_buildreg_itr(itr_idx, interval, true); + q_vector->in_busy_poll = false; + } else { + itr_val = i40e_buildreg_itr(itr_idx, interval, false); + } + wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val); } /** @@ -2845,6 +2883,8 @@ tx_only: */ if (likely(napi_complete_done(napi, work_done))) i40e_update_enable_itr(vsi, q_vector); + else + q_vector->in_busy_poll = true; return min(work_done, budget - 1); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index abf15067eb5d..2cdc7de6301c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -68,6 +68,7 @@ enum i40e_dyn_idx { /* these are indexes into ITRN registers */ #define I40E_RX_ITR I40E_IDX_ITR0 #define I40E_TX_ITR I40E_IDX_ITR1 +#define I40E_SW_ITR I40E_IDX_ITR2 /* Supported RSS offloads */ #define I40E_DEFAULT_RSS_HENA ( \ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 83a34e98bdc7..232b65b9c8ea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1624,8 +1624,8 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) { struct i40e_hw *hw = &pf->hw; struct i40e_vf *vf; - int i, v; u32 reg; + int i; /* If we don't have any VFs, then there is nothing to reset */ if (!pf->num_alloc_vfs) @@ -1636,11 +1636,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) return false; /* Begin reset on all VFs at once */ - for (v = 0; v < pf->num_alloc_vfs; v++) { - vf = &pf->vf[v]; + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is being reset no need to trigger reset again */ if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) - i40e_trigger_vf_reset(&pf->vf[v], flr); + i40e_trigger_vf_reset(vf, flr); } /* HW requires some time to make sure it can flush the FIFO for a VF @@ -1649,14 +1648,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) * the VFs using a simple iterator that increments once that VF has * finished resetting. */ - for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + for (i = 0, vf = &pf->vf[0]; i < 10 && vf < &pf->vf[pf->num_alloc_vfs]; ++i) { usleep_range(10000, 20000); /* Check each VF in sequence, beginning with the VF to fail * the previous check. */ - while (v < pf->num_alloc_vfs) { - vf = &pf->vf[v]; + while (vf < &pf->vf[pf->num_alloc_vfs]) { if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) { reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) @@ -1666,7 +1664,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* If the current VF has finished resetting, move on * to the next VF in sequence. */ - v++; + ++vf; } } @@ -1676,39 +1674,39 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* Display a warning if at least one VF didn't manage to reset in * time, but continue on with the operation. */ - if (v < pf->num_alloc_vfs) + if (vf < &pf->vf[pf->num_alloc_vfs]) dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", - pf->vf[v].vf_id); + vf->vf_id); usleep_range(10000, 20000); /* Begin disabling all the rings associated with VFs, but do not wait * between each VF. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_stop_rings_no_wait(pf->vsi[vf->lan_vsi_idx]); } /* Now that we've notified HW to disable all of the VF rings, wait * until they finish. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_wait_queues_disabled(pf->vsi[vf->lan_vsi_idx]); } /* Hw may need up to 50ms to finish disabling the RX queues. We @@ -1717,12 +1715,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) mdelay(50); /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_cleanup_reset_vf(&pf->vf[v]); + i40e_cleanup_reset_vf(vf); } i40e_flush(hw); @@ -3139,11 +3137,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) /* Allow to delete VF primary MAC only if it was not set * administratively by PF or if VF is trusted. */ - if (ether_addr_equal(addr, vf->default_lan_addr.addr) && - i40e_can_vf_change_mac(vf)) - was_unimac_deleted = true; - else - continue; + if (ether_addr_equal(addr, vf->default_lan_addr.addr)) { + if (i40e_can_vf_change_mac(vf)) + was_unimac_deleted = true; + else + continue; + } if (i40e_del_mac_filter(vsi, al->list[i].addr)) { ret = -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index db4b2844e1f7..d9f6cc71d900 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1002,8 +1002,8 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) */ int ice_init_hw(struct ice_hw *hw) { - struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); - void *mac_buf __free(kfree); + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; + void *mac_buf __free(kfree) = NULL; u16 mac_buf_len; int status; @@ -3272,7 +3272,7 @@ int ice_update_link_info(struct ice_port_info *pi) return status; if (li->link_info & ICE_AQ_MEDIA_AVAILABLE) { - struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) @@ -3420,7 +3420,7 @@ ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, int ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) { - struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; struct ice_aqc_set_phy_cfg_data cfg = { 0 }; struct ice_hw *hw; int status; @@ -3561,7 +3561,7 @@ int ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec) { - struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree) = NULL; struct ice_hw *hw; int status; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 255a9c8151b4..78b833b3e1d7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -941,11 +941,11 @@ static u64 ice_loopback_test(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *orig_vsi = np->vsi, *test_vsi; struct ice_pf *pf = orig_vsi->back; + u8 *tx_frame __free(kfree) = NULL; u8 broadcast[ETH_ALEN], ret = 0; int num_frames, valid_frames; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - u8 *tx_frame __free(kfree); int i; netdev_info(netdev, "loopback test\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index 80dc4bcdd3a4..b3e1bdcb80f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -26,24 +26,22 @@ static void ice_port_vlan_on(struct ice_vsi *vsi) struct ice_vsi_vlan_ops *vlan_ops; struct ice_pf *pf = vsi->back; - if (ice_is_dvm_ena(&pf->hw)) { - vlan_ops = &vsi->outer_vlan_ops; - - /* setup outer VLAN ops */ - vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; + if (ice_is_dvm_ena(&pf->hw)) { vlan_ops->add_vlan = noop_vlan_arg; vlan_ops->del_vlan = noop_vlan_arg; vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } else { - vlan_ops = &vsi->inner_vlan_ops; + /* setup outer VLAN ops */ + vlan_ops = &vsi->outer_vlan_ops; + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + } else { vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 6dd7a66bb897..f5bc4a278074 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -2941,6 +2941,8 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, rx_ptype = le16_get_bits(rx_desc->ptype_err_fflags0, VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M); + skb->protocol = eth_type_trans(skb, rxq->vport->netdev); + decoded = rxq->vport->rx_ptype_lkup[rx_ptype]; /* If we don't know the ptype we can't do anything else with it. Just * pass it up the stack as-is. @@ -2951,8 +2953,6 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, /* process RSS/hash */ idpf_rx_hash(rxq, skb, rx_desc, &decoded); - skb->protocol = eth_type_trans(skb, rxq->vport->netdev); - if (le16_get_bits(rx_desc->hdrlen_flags, VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M)) return idpf_rx_rsc(rxq, skb, rx_desc, &decoded); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 72e060cf6b61..e9bf9231b018 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -160,6 +160,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) continue; lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { + if (iter >= MAX_LMAC_COUNT) + continue; lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu), iter); rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index e350242bbafb..be709f83f331 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -1657,7 +1657,7 @@ static int npc_fwdb_detect_load_prfl_img(struct rvu *rvu, uint64_t prfl_sz, struct npc_coalesced_kpu_prfl *img_data = NULL; int i = 0, rc = -EINVAL; void __iomem *kpu_prfl_addr; - u16 offset; + u32 offset; img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr; if (le64_to_cpu(img_data->signature) == KPU_SIGN && diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index b40bd0e46751..3f46d5e0fb2e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1933,7 +1933,7 @@ int otx2_open(struct net_device *netdev) * mcam entries are enabled to receive the packets. Hence disable the * packet I/O. */ - if (err == EIO) + if (err == -EIO) goto err_disable_rxtx; else if (err) goto err_tx_stop_queues; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 77134ca92938..ba303868686a 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/rtnetlink.h> #include <linux/skbuff.h> #include "mlxbf_gige.h" @@ -492,8 +493,13 @@ static void mlxbf_gige_shutdown(struct platform_device *pdev) { struct mlxbf_gige *priv = platform_get_drvdata(pdev); - writeq(0, priv->base + MLXBF_GIGE_INT_EN); - mlxbf_gige_clean_port(priv); + rtnl_lock(); + netif_device_detach(priv->netdev); + + if (netif_running(priv->netdev)) + dev_close(priv->netdev); + + rtnl_unlock(); } static const struct acpi_device_id __maybe_unused mlxbf_gige_acpi_match[] = { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 59287c6e6cee..d8af5e7e15b4 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -601,7 +601,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; - *datasize = ALIGN(mtu + ETH_HLEN, MANA_RX_DATA_ALIGN); + *datasize = mtu + ETH_HLEN; } static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 5c879a5c86d7..6f1e6f386b7b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1314,17 +1314,40 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) RTL_W8(tp, IBCR0, RTL_R8(tp, IBCR0) & ~0x01); } +static void rtl_dash_loop_wait(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long usecs, int n, bool high) +{ + if (!tp->dash_enabled) + return; + rtl_loop_wait(tp, c, usecs, n, high); +} + +static void rtl_dash_loop_wait_high(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long d, int n) +{ + rtl_dash_loop_wait(tp, c, d, n, true); +} + +static void rtl_dash_loop_wait_low(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long d, int n) +{ + rtl_dash_loop_wait(tp, c, d, n, false); +} + static void rtl8168dp_driver_start(struct rtl8169_private *tp) { r8168dp_oob_notify(tp, OOB_CMD_DRIVER_START); - rtl_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10); } static void rtl8168ep_driver_start(struct rtl8169_private *tp) { r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); + rtl_dash_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } static void rtl8168_driver_start(struct rtl8169_private *tp) @@ -1338,7 +1361,7 @@ static void rtl8168_driver_start(struct rtl8169_private *tp) static void rtl8168dp_driver_stop(struct rtl8169_private *tp) { r8168dp_oob_notify(tp, OOB_CMD_DRIVER_STOP); - rtl_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10); } static void rtl8168ep_driver_stop(struct rtl8169_private *tp) @@ -1346,7 +1369,7 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp) rtl8168ep_stop_cmac(tp); r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10); } static void rtl8168_driver_stop(struct rtl8169_private *tp) @@ -5141,6 +5164,15 @@ static int r8169_mdio_register(struct rtl8169_private *tp) struct mii_bus *new_bus; int ret; + /* On some boards with this chip version the BIOS is buggy and misses + * to reset the PHY page selector. This results in the PHY ID read + * accessing registers on a different page, returning a more or + * less random value. Fix this by resetting the page selector first. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_25 || + tp->mac_version == RTL_GIGA_MAC_VER_26) + r8169_mdio_write(tp, 0x1f, 0); + new_bus = devm_mdiobus_alloc(&pdev->dev); if (!new_bus) return -ENOMEM; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index d1be030c8848..ba01c8cc3c90 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1324,12 +1324,12 @@ static int ravb_poll(struct napi_struct *napi, int budget) int q = napi - priv->napi; int mask = BIT(q); int quota = budget; + bool unmask; /* Processing RX Descriptor Ring */ /* Clear RX interrupt */ ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); - if (ravb_rx(ndev, "a, q)) - goto out; + unmask = !ravb_rx(ndev, "a, q); /* Processing TX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); @@ -1339,6 +1339,18 @@ static int ravb_poll(struct napi_struct *napi, int budget) netif_wake_subqueue(ndev, q); spin_unlock_irqrestore(&priv->lock, flags); + /* Receive error message handling */ + priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; + if (info->nc_queues) + priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; + if (priv->rx_over_errors != ndev->stats.rx_over_errors) + ndev->stats.rx_over_errors = priv->rx_over_errors; + if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) + ndev->stats.rx_fifo_errors = priv->rx_fifo_errors; + + if (!unmask) + goto out; + napi_complete(napi); /* Re-enable RX/TX interrupts */ @@ -1352,14 +1364,6 @@ static int ravb_poll(struct napi_struct *napi, int budget) } spin_unlock_irqrestore(&priv->lock, flags); - /* Receive error message handling */ - priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; - if (info->nc_queues) - priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; - if (priv->rx_over_errors != ndev->stats.rx_over_errors) - ndev->stats.rx_over_errors = priv->rx_over_errors; - if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) - ndev->stats.rx_fifo_errors = priv->rx_fifo_errors; out: return budget - quota; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 6b6d0de09619..cef25efbdff9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -92,19 +92,41 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 base_register; - u32 value; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; - if (queue >= 4) - queue -= 4; + ctrl2 = readl(ioaddr + GMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + GMAC_RXQ_CTRL3); - value = readl(ioaddr + base_register); + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << GMAC_RXQCTRL_PSRQX_SHIFT(i)) & + GMAC_RXQCTRL_PSRQX_MASK(i)); + + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + GMAC_RXQCTRL_PSRQX_MASK(queue); - value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue); - value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + } else { + queue -= 4; + + ctrl3 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & GMAC_RXQCTRL_PSRQX_MASK(queue); - writel(value, ioaddr + base_register); + + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + } } static void dwmac4_tx_queue_priority(struct mac_device_info *hw, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 1af2f89a0504..e841e312077e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -105,17 +105,41 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 value, reg; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; - if (queue >= 4) + ctrl2 = readl(ioaddr + XGMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + XGMAC_RXQ_CTRL3); + + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << XGMAC_PSRQ_SHIFT(i)) & + XGMAC_PSRQ(i)); + + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); + + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + } else { queue -= 4; - value = readl(ioaddr + reg); - value &= ~XGMAC_PSRQ(queue); - value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue); + ctrl3 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); - writel(value, ioaddr + reg); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + } } static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c index 5b5d5e4310d1..2fa511227eac 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -20,6 +20,8 @@ #include "txgbe_phy.h" #include "txgbe_hw.h" +#define TXGBE_I2C_CLK_DEV_NAME "i2c_dw" + static int txgbe_swnodes_register(struct txgbe *txgbe) { struct txgbe_nodes *nodes = &txgbe->nodes; @@ -571,8 +573,8 @@ static int txgbe_clock_register(struct txgbe *txgbe) char clk_name[32]; struct clk *clk; - snprintf(clk_name, sizeof(clk_name), "i2c_dw.%d", - pci_dev_id(pdev)); + snprintf(clk_name, sizeof(clk_name), "%s.%d", + TXGBE_I2C_CLK_DEV_NAME, pci_dev_id(pdev)); clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 156250000); if (IS_ERR(clk)) @@ -634,7 +636,7 @@ static int txgbe_i2c_register(struct txgbe *txgbe) info.parent = &pdev->dev; info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_I2C]); - info.name = "i2c_designware"; + info.name = TXGBE_I2C_CLK_DEV_NAME; info.id = pci_dev_id(pdev); info.res = &DEFINE_RES_IRQ(pdev->irq); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 8b8634600c51..ddb50a0e2bc8 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2431,6 +2431,7 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct lan8814_ptp_rx_ts *rx_ts, *tmp; int txcfg = 0, rxcfg = 0; int pkt_ts_enable; + int tx_mod; ptp_priv->hwts_tx_type = config->tx_type; ptp_priv->rx_filter = config->rx_filter; @@ -2477,9 +2478,14 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_RX_TIMESTAMP_EN, pkt_ts_enable); lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_TIMESTAMP_EN, pkt_ts_enable); - if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) + tx_mod = lanphy_read_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD); + if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) { lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, - PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + tx_mod | PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + } else if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ON) { + lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, + tx_mod & ~PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + } if (config->rx_filter != HWTSTAMP_FILTER_NONE) lan8814_config_ts_intr(ptp_priv->phydev, true); @@ -2537,7 +2543,7 @@ static void lan8814_txtstamp(struct mii_timestamper *mii_ts, } } -static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) +static bool lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) { struct ptp_header *ptp_header; u32 type; @@ -2547,7 +2553,11 @@ static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) ptp_header = ptp_parse_header(skb, type); skb_pull_inline(skb, ETH_HLEN); + if (!ptp_header) + return false; + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + return true; } static bool lan8814_match_rx_skb(struct kszphy_ptp_priv *ptp_priv, @@ -2559,7 +2569,8 @@ static bool lan8814_match_rx_skb(struct kszphy_ptp_priv *ptp_priv, bool ret = false; u16 skb_sig; - lan8814_get_sig_rx(skb, &skb_sig); + if (!lan8814_get_sig_rx(skb, &skb_sig)) + return ret; /* Iterate over all RX timestamps and match it with the received skbs */ spin_lock_irqsave(&ptp_priv->rx_ts_lock, flags); @@ -2834,7 +2845,7 @@ static int lan8814_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm) return 0; } -static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) +static bool lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) { struct ptp_header *ptp_header; u32 type; @@ -2842,7 +2853,11 @@ static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) type = ptp_classify_raw(skb); ptp_header = ptp_parse_header(skb, type); + if (!ptp_header) + return false; + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + return true; } static void lan8814_match_tx_skb(struct kszphy_ptp_priv *ptp_priv, @@ -2856,7 +2871,8 @@ static void lan8814_match_tx_skb(struct kszphy_ptp_priv *ptp_priv, spin_lock_irqsave(&ptp_priv->tx_queue.lock, flags); skb_queue_walk_safe(&ptp_priv->tx_queue, skb, skb_tmp) { - lan8814_get_sig_tx(skb, &skb_sig); + if (!lan8814_get_sig_tx(skb, &skb_sig)) + continue; if (memcmp(&skb_sig, &seq_id, sizeof(seq_id))) continue; @@ -2910,7 +2926,8 @@ static bool lan8814_match_skb(struct kszphy_ptp_priv *ptp_priv, spin_lock_irqsave(&ptp_priv->rx_queue.lock, flags); skb_queue_walk_safe(&ptp_priv->rx_queue, skb, skb_tmp) { - lan8814_get_sig_rx(skb, &skb_sig); + if (!lan8814_get_sig_rx(skb, &skb_sig)) + continue; if (memcmp(&skb_sig, &rx_ts->seq_id, sizeof(rx_ts->seq_id))) continue; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 88e084534853..a9c418890a1c 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1273,6 +1273,8 @@ static void ax88179_get_mac_addr(struct usbnet *dev) if (is_valid_ether_addr(mac)) { eth_hw_addr_set(dev->net, mac); + if (!is_local_ether_addr(mac)) + dev->net->addr_assign_type = NET_ADDR_PERM; } else { netdev_info(dev->net, "invalid MAC address, using random\n"); eth_hw_addr_random(dev->net); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index ad29f370034e..8d2aee88526c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -285,6 +285,7 @@ static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue) return NULL; } skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE); + skb_mark_for_recycle(skb); /* Align ip header to a 16 bytes boundary */ skb_reserve(skb, NET_IP_ALIGN); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 943d72bdd794..27281a9a8951 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2076,6 +2076,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT; struct queue_limits lim; struct nvme_id_ns_nvm *nvm = NULL; + struct nvme_zone_info zi = {}; struct nvme_id_ns *id; sector_t capacity; unsigned lbaf; @@ -2088,9 +2089,10 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (id->ncap == 0) { /* namespace not allocated or attached */ info->is_removed = true; - ret = -ENODEV; + ret = -ENXIO; goto out; } + lbaf = nvme_lbaf_index(id->flbas); if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) { ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm); @@ -2098,8 +2100,14 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, goto out; } + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + ns->head->ids.csi == NVME_CSI_ZNS) { + ret = nvme_query_zone_info(ns, lbaf, &zi); + if (ret < 0) + goto out; + } + blk_mq_freeze_queue(ns->disk->queue); - lbaf = nvme_lbaf_index(id->flbas); ns->head->lba_shift = id->lbaf[lbaf].ds; ns->head->nuse = le64_to_cpu(id->nuse); capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze)); @@ -2112,13 +2120,8 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, capacity = 0; nvme_config_discard(ns, &lim); if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && - ns->head->ids.csi == NVME_CSI_ZNS) { - ret = nvme_update_zone_info(ns, lbaf, &lim); - if (ret) { - blk_mq_unfreeze_queue(ns->disk->queue); - goto out; - } - } + ns->head->ids.csi == NVME_CSI_ZNS) + nvme_update_zone_info(ns, &lim, &zi); ret = queue_limits_commit_update(ns->disk->queue, &lim); if (ret) { blk_mq_unfreeze_queue(ns->disk->queue); @@ -2201,6 +2204,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) } if (!ret && nvme_ns_head_multipath(ns->head)) { + struct queue_limits *ns_lim = &ns->disk->queue->limits; struct queue_limits lim; blk_mq_freeze_queue(ns->head->disk->queue); @@ -2212,7 +2216,26 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); nvme_mpath_revalidate_paths(ns); + /* + * queue_limits mixes values that are the hardware limitations + * for bio splitting with what is the device configuration. + * + * For NVMe the device configuration can change after e.g. a + * Format command, and we really want to pick up the new format + * value here. But we must still stack the queue limits to the + * least common denominator for multipathing to split the bios + * properly. + * + * To work around this, we explicitly set the device + * configuration to those that we just queried, but only stack + * the splitting limits in to make sure we still obey possibly + * lower limitations of other controllers. + */ lim = queue_limits_start_update(ns->head->disk->queue); + lim.logical_block_size = ns_lim->logical_block_size; + lim.physical_block_size = ns_lim->physical_block_size; + lim.io_min = ns_lim->io_min; + lim.io_opt = ns_lim->io_opt; queue_limits_stack_bdev(&lim, ns->disk->part0, 0, ns->head->disk->disk_name); ret = queue_limits_commit_update(ns->head->disk->queue, &lim); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 68a5d971657b..a5b29e9ad342 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2428,7 +2428,7 @@ nvme_fc_ctrl_get(struct nvme_fc_ctrl *ctrl) * controller. Called after last nvme_put_ctrl() call */ static void -nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl) +nvme_fc_free_ctrl(struct nvme_ctrl *nctrl) { struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); @@ -3384,7 +3384,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .reg_read32 = nvmf_reg_read32, .reg_read64 = nvmf_reg_read64, .reg_write32 = nvmf_reg_write32, - .free_ctrl = nvme_fc_nvme_ctrl_freed, + .free_ctrl = nvme_fc_free_ctrl, .submit_async_event = nvme_fc_submit_async_event, .delete_ctrl = nvme_fc_delete_ctrl, .get_address = nvmf_get_address, diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 24193fcb8bd5..d0ed64dc7380 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -1036,10 +1036,18 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk) } #endif /* CONFIG_NVME_MULTIPATH */ +struct nvme_zone_info { + u64 zone_size; + unsigned int max_open_zones; + unsigned int max_active_zones; +}; + int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); -int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf, - struct queue_limits *lim); +int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf, + struct nvme_zone_info *zi); +void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim, + struct nvme_zone_info *zi); #ifdef CONFIG_BLK_DEV_ZONED blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 722384bcc765..77aa0f440a6d 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -35,8 +35,8 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl) return 0; } -int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf, - struct queue_limits *lim) +int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf, + struct nvme_zone_info *zi) { struct nvme_effects_log *log = ns->head->effects; struct nvme_command c = { }; @@ -89,27 +89,34 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf, goto free_data; } - ns->head->zsze = - nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze)); - if (!is_power_of_2(ns->head->zsze)) { + zi->zone_size = le64_to_cpu(id->lbafe[lbaf].zsze); + if (!is_power_of_2(zi->zone_size)) { dev_warn(ns->ctrl->device, - "invalid zone size:%llu for namespace:%u\n", - ns->head->zsze, ns->head->ns_id); + "invalid zone size: %llu for namespace: %u\n", + zi->zone_size, ns->head->ns_id); status = -ENODEV; goto free_data; } + zi->max_open_zones = le32_to_cpu(id->mor) + 1; + zi->max_active_zones = le32_to_cpu(id->mar) + 1; - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue); - lim->zoned = 1; - lim->max_open_zones = le32_to_cpu(id->mor) + 1; - lim->max_active_zones = le32_to_cpu(id->mar) + 1; - lim->chunk_sectors = ns->head->zsze; - lim->max_zone_append_sectors = ns->ctrl->max_zone_append; free_data: kfree(id); return status; } +void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim, + struct nvme_zone_info *zi) +{ + lim->zoned = 1; + lim->max_open_zones = zi->max_open_zones; + lim->max_active_zones = zi->max_active_zones; + lim->max_zone_append_sectors = ns->ctrl->max_zone_append; + lim->chunk_sectors = ns->head->zsze = + nvme_lba_to_sect(ns->head, zi->zone_size); + blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue); +} + static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns, unsigned int nr_zones, size_t *buflen) { diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 77a6e817b315..a2325330bf22 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1613,6 +1613,11 @@ static struct config_group *nvmet_subsys_make(struct config_group *group, return ERR_PTR(-EINVAL); } + if (sysfs_streq(name, nvmet_disc_subsys->subsysnqn)) { + pr_err("can't create subsystem using unique discovery NQN\n"); + return ERR_PTR(-EINVAL); + } + subsys = nvmet_subsys_alloc(name, NVME_NQN_NVME); if (IS_ERR(subsys)) return ERR_CAST(subsys); @@ -2159,7 +2164,49 @@ static const struct config_item_type nvmet_hosts_type = { static struct config_group nvmet_hosts_group; +static ssize_t nvmet_root_discovery_nqn_show(struct config_item *item, + char *page) +{ + return snprintf(page, PAGE_SIZE, "%s\n", nvmet_disc_subsys->subsysnqn); +} + +static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, + const char *page, size_t count) +{ + struct list_head *entry; + size_t len; + + len = strcspn(page, "\n"); + if (!len || len > NVMF_NQN_FIELD_LEN - 1) + return -EINVAL; + + down_write(&nvmet_config_sem); + list_for_each(entry, &nvmet_subsystems_group.cg_children) { + struct config_item *item = + container_of(entry, struct config_item, ci_entry); + + if (!strncmp(config_item_name(item), page, len)) { + pr_err("duplicate NQN %s\n", config_item_name(item)); + up_write(&nvmet_config_sem); + return -EINVAL; + } + } + memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN); + memcpy(nvmet_disc_subsys->subsysnqn, page, len); + up_write(&nvmet_config_sem); + + return len; +} + +CONFIGFS_ATTR(nvmet_root_, discovery_nqn); + +static struct configfs_attribute *nvmet_root_attrs[] = { + &nvmet_root_attr_discovery_nqn, + NULL, +}; + static const struct config_item_type nvmet_root_type = { + .ct_attrs = nvmet_root_attrs, .ct_owner = THIS_MODULE, }; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 6bbe4df0166c..8860a3eb71ec 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1541,6 +1541,13 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port, } down_read(&nvmet_config_sem); + if (!strncmp(nvmet_disc_subsys->subsysnqn, subsysnqn, + NVMF_NQN_SIZE)) { + if (kref_get_unless_zero(&nvmet_disc_subsys->ref)) { + up_read(&nvmet_config_sem); + return nvmet_disc_subsys; + } + } list_for_each_entry(p, &port->subsystems, entry) { if (!strncmp(p->subsys->subsysnqn, subsysnqn, NVMF_NQN_SIZE)) { diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index fd229f310c93..337ee1cb09ae 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1115,16 +1115,21 @@ nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc) } static bool -nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id) +nvmet_fc_assoc_exists(struct nvmet_fc_tgtport *tgtport, u64 association_id) { struct nvmet_fc_tgt_assoc *a; + bool found = false; + rcu_read_lock(); list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) { - if (association_id == a->association_id) - return true; + if (association_id == a->association_id) { + found = true; + break; + } } + rcu_read_unlock(); - return false; + return found; } static struct nvmet_fc_tgt_assoc * @@ -1164,13 +1169,11 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) ran = ran << BYTES_FOR_QID_SHIFT; spin_lock_irqsave(&tgtport->lock, flags); - rcu_read_lock(); - if (!nvmet_fc_assoc_exits(tgtport, ran)) { + if (!nvmet_fc_assoc_exists(tgtport, ran)) { assoc->association_id = ran; list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list); done = true; } - rcu_read_unlock(); spin_unlock_irqrestore(&tgtport->lock, flags); } while (!done); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 3bf27052832f..4d57a4e34105 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "OF: " fmt +#include <linux/device.h> #include <linux/of.h> #include <linux/spinlock.h> #include <linux/slab.h> @@ -667,6 +668,17 @@ void of_changeset_destroy(struct of_changeset *ocs) { struct of_changeset_entry *ce, *cen; + /* + * When a device is deleted, the device links to/from it are also queued + * for deletion. Until these device links are freed, the devices + * themselves aren't freed. If the device being deleted is due to an + * overlay change, this device might be holding a reference to a device + * node that will be freed. So, wait until all already pending device + * links are deleted before freeing a device node. This ensures we don't + * free any device node that has a non-zero reference count. + */ + device_link_wait_removal(); + list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node) __of_changeset_entry_destroy(ce); } diff --git a/drivers/of/module.c b/drivers/of/module.c index 0e8aa974f0f2..f58e624953a2 100644 --- a/drivers/of/module.c +++ b/drivers/of/module.c @@ -16,6 +16,14 @@ ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len) ssize_t csize; ssize_t tsize; + /* + * Prevent a kernel oops in vsnprintf() -- it only allows passing a + * NULL ptr when the length is also 0. Also filter out the negative + * lengths... + */ + if ((len > 0 && !str) || len < 0) + return -EINVAL; + /* Name & Type */ /* %p eats all alphanum characters, so %c must be used here */ csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T', diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index c78a6fd6c57f..b4efdddb2ad9 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -313,6 +313,10 @@ static int riscv_pmu_event_init(struct perf_event *event) u64 event_config = 0; uint64_t cmask; + /* driver does not support branch stack sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + hwc->flags = 0; mapped_event = rvpmu->event_map(event, &event_config); if (mapped_event < 0) { diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index d70f793ce4b3..403525cc1783 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -443,7 +443,7 @@ of_pwm_single_xlate(struct pwm_chip *chip, const struct of_phandle_args *args) if (IS_ERR(pwm)) return pwm; - if (args->args_count > 1) + if (args->args_count > 0) pwm->args.period = args->args[0]; pwm->args.polarity = PWM_POLARITY_NORMAL; diff --git a/drivers/regulator/tps65132-regulator.c b/drivers/regulator/tps65132-regulator.c index a06f5f2d7932..9c2f0dd42613 100644 --- a/drivers/regulator/tps65132-regulator.c +++ b/drivers/regulator/tps65132-regulator.c @@ -267,10 +267,17 @@ static const struct i2c_device_id tps65132_id[] = { }; MODULE_DEVICE_TABLE(i2c, tps65132_id); +static const struct of_device_id __maybe_unused tps65132_of_match[] = { + { .compatible = "ti,tps65132" }, + {}, +}; +MODULE_DEVICE_TABLE(of, tps65132_of_match); + static struct i2c_driver tps65132_i2c_driver = { .driver = { .name = "tps65132", .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .of_match_table = of_match_ptr(tps65132_of_match), }, .probe = tps65132_probe, .id_table = tps65132_id, diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 5c261005b74e..f6e6db8b8aba 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -135,7 +135,7 @@ static int smp_execute_task(struct domain_device *dev, void *req, int req_size, static inline void *alloc_smp_req(int size) { - u8 *p = kzalloc(size, GFP_KERNEL); + u8 *p = kzalloc(ALIGN(size, ARCH_DMA_MINALIGN), GFP_KERNEL); if (p) p[0] = SMP_REQUEST; return p; diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index ca2e932dd9b7..f684eb5e0489 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -1775,9 +1775,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrb_devstate_name(ldev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); } else { struct myrb_pdev_state *pdev_info = sdev->hostdata; @@ -1796,9 +1796,9 @@ static ssize_t raid_state_show(struct device *dev, else name = myrb_devstate_name(pdev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->state); } return ret; @@ -1886,11 +1886,11 @@ static ssize_t raid_level_show(struct device *dev, name = myrb_raidlevel_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } - return snprintf(buf, 32, "Physical Drive\n"); + return snprintf(buf, 64, "Physical Drive\n"); } static DEVICE_ATTR_RO(raid_level); @@ -1903,15 +1903,15 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < myrb_logical_channel(sdev->host)) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); status = myrb_get_rbld_progress(cb, &rbld_buf); if (rbld_buf.ldev_num != sdev->id || status != MYRB_STATUS_SUCCESS) - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); - return snprintf(buf, 32, "rebuilding block %u of %u\n", + return snprintf(buf, 64, "rebuilding block %u of %u\n", rbld_buf.ldev_size - rbld_buf.blocks_left, rbld_buf.ldev_size); } diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index a1eec65a9713..e824be9d9bbb 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -947,9 +947,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrs_devstate_name(ldev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else { struct myrs_pdev_info *pdev_info; @@ -958,9 +958,9 @@ static ssize_t raid_state_show(struct device *dev, pdev_info = sdev->hostdata; name = myrs_devstate_name(pdev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->dev_state); } return ret; @@ -1066,13 +1066,13 @@ static ssize_t raid_level_show(struct device *dev, ldev_info = sdev->hostdata; name = myrs_raid_level_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else name = myrs_raid_level_name(MYRS_RAID_PHYSICAL); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } static DEVICE_ATTR_RO(raid_level); @@ -1086,7 +1086,7 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); ldev_info = sdev->hostdata; ldev_num = ldev_info->ldev_num; @@ -1098,11 +1098,11 @@ static ssize_t rebuild_show(struct device *dev, return -EIO; } if (ldev_info->rbld_active) { - return snprintf(buf, 32, "rebuilding block %zu of %zu\n", + return snprintf(buf, 64, "rebuilding block %zu of %zu\n", (size_t)ldev_info->rbld_lba, (size_t)ldev_info->cfg_devsize); } else - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); } static ssize_t rebuild_store(struct device *dev, @@ -1190,7 +1190,7 @@ static ssize_t consistency_check_show(struct device *dev, unsigned short ldev_num; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not checking\n"); + return snprintf(buf, 64, "physical device - not checking\n"); ldev_info = sdev->hostdata; if (!ldev_info) @@ -1198,11 +1198,11 @@ static ssize_t consistency_check_show(struct device *dev, ldev_num = ldev_info->ldev_num; myrs_get_ldev_info(cs, ldev_num, ldev_info); if (ldev_info->cc_active) - return snprintf(buf, 32, "checking block %zu of %zu\n", + return snprintf(buf, 64, "checking block %zu of %zu\n", (size_t)ldev_info->cc_lba, (size_t)ldev_info->cfg_devsize); else - return snprintf(buf, 32, "not checking\n"); + return snprintf(buf, 64, "not checking\n"); } static ssize_t consistency_check_store(struct device *dev, diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3cf898670290..58fdf679341d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3920,7 +3920,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { - put_device(&sdkp->disk_dev); + device_unregister(&sdkp->disk_dev); put_disk(gd); goto out; } diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 079035db7dd8..92a662d1b55c 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -852,39 +852,39 @@ static int fsl_lpspi_probe(struct platform_device *pdev) fsl_lpspi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(fsl_lpspi->base)) { ret = PTR_ERR(fsl_lpspi->base); - goto out_controller_put; + return ret; } fsl_lpspi->base_phys = res->start; irq = platform_get_irq(pdev, 0); if (irq < 0) { ret = irq; - goto out_controller_put; + return ret; } ret = devm_request_irq(&pdev->dev, irq, fsl_lpspi_isr, 0, dev_name(&pdev->dev), fsl_lpspi); if (ret) { dev_err(&pdev->dev, "can't get irq%d: %d\n", irq, ret); - goto out_controller_put; + return ret; } fsl_lpspi->clk_per = devm_clk_get(&pdev->dev, "per"); if (IS_ERR(fsl_lpspi->clk_per)) { ret = PTR_ERR(fsl_lpspi->clk_per); - goto out_controller_put; + return ret; } fsl_lpspi->clk_ipg = devm_clk_get(&pdev->dev, "ipg"); if (IS_ERR(fsl_lpspi->clk_ipg)) { ret = PTR_ERR(fsl_lpspi->clk_ipg); - goto out_controller_put; + return ret; } /* enable the clock */ ret = fsl_lpspi_init_rpm(fsl_lpspi); if (ret) - goto out_controller_put; + return ret; ret = pm_runtime_get_sync(fsl_lpspi->dev); if (ret < 0) { @@ -945,8 +945,6 @@ out_pm_get: pm_runtime_dont_use_autosuspend(fsl_lpspi->dev); pm_runtime_put_sync(fsl_lpspi->dev); pm_runtime_disable(fsl_lpspi->dev); -out_controller_put: - spi_controller_put(controller); return ret; } diff --git a/drivers/spi/spi-pci1xxxx.c b/drivers/spi/spi-pci1xxxx.c index 969965d7bc98..cc18d320370f 100644 --- a/drivers/spi/spi-pci1xxxx.c +++ b/drivers/spi/spi-pci1xxxx.c @@ -725,6 +725,8 @@ static int pci1xxxx_spi_probe(struct pci_dev *pdev, const struct pci_device_id * spi_bus->spi_int[iter] = devm_kzalloc(&pdev->dev, sizeof(struct pci1xxxx_spi_internal), GFP_KERNEL); + if (!spi_bus->spi_int[iter]) + return -ENOMEM; spi_sub_ptr = spi_bus->spi_int[iter]; spi_sub_ptr->spi_host = devm_spi_alloc_host(dev, sizeof(struct spi_controller)); if (!spi_sub_ptr->spi_host) diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 9fcbe040cb2f..f726d8670428 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -430,7 +430,7 @@ static bool s3c64xx_spi_can_dma(struct spi_controller *host, struct s3c64xx_spi_driver_data *sdd = spi_controller_get_devdata(host); if (sdd->rx_dma.ch && sdd->tx_dma.ch) - return xfer->len > sdd->fifo_depth; + return xfer->len >= sdd->fifo_depth; return false; } @@ -826,10 +826,9 @@ static int s3c64xx_spi_transfer_one(struct spi_controller *host, return status; } - if (!is_polling(sdd) && (xfer->len > fifo_len) && + if (!is_polling(sdd) && xfer->len >= fifo_len && sdd->rx_dma.ch && sdd->tx_dma.ch) { use_dma = 1; - } else if (xfer->len >= fifo_len) { tx_buf = xfer->tx_buf; rx_buf = xfer->rx_buf; diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c index 1b17dc4c219c..e25e48d76aa7 100644 --- a/drivers/thermal/gov_power_allocator.c +++ b/drivers/thermal/gov_power_allocator.c @@ -606,7 +606,7 @@ static int allocate_actors_buffer(struct power_allocator_params *params, /* There might be no cooling devices yet. */ if (!num_actors) { - ret = -EINVAL; + ret = 0; goto clean_state; } @@ -679,11 +679,6 @@ static int power_allocator_bind(struct thermal_zone_device *tz) return -ENOMEM; get_governor_trips(tz, params); - if (!params->trip_max) { - dev_warn(&tz->device, "power_allocator: missing trip_max\n"); - kfree(params); - return -EINVAL; - } ret = check_power_actors(tz, params); if (ret < 0) { @@ -714,9 +709,10 @@ static int power_allocator_bind(struct thermal_zone_device *tz) else params->sustainable_power = tz->tzp->sustainable_power; - estimate_pid_constants(tz, tz->tzp->sustainable_power, - params->trip_switch_on, - params->trip_max->temperature); + if (params->trip_max) + estimate_pid_constants(tz, tz->tzp->sustainable_power, + params->trip_switch_on, + params->trip_max->temperature); reset_pid_controller(params); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index e30fd125988d..a0f8e930167d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -3217,7 +3217,9 @@ retry: /* MCQ mode */ if (is_mcq_enabled(hba)) { - err = ufshcd_clear_cmd(hba, lrbp->task_tag); + /* successfully cleared the command, retry if needed */ + if (ufshcd_clear_cmd(hba, lrbp->task_tag) == 0) + err = -EAGAIN; hba->dev_cmd.complete = NULL; return err; } @@ -9791,7 +9793,10 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) /* UFS device & link must be active before we enter in this function */ if (!ufshcd_is_ufs_dev_active(hba) || !ufshcd_is_link_active(hba)) { - ret = -EINVAL; + /* Wait err handler finish or trigger err recovery */ + if (!ufshcd_eh_in_progress(hba)) + ufshcd_force_error_recovery(hba); + ret = -EBUSY; goto enable_scaling; } @@ -1202,8 +1202,8 @@ static void aio_complete(struct aio_kiocb *iocb) spin_lock_irqsave(&ctx->wait.lock, flags); list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry) if (avail >= curr->min_nr) { - list_del_init_careful(&curr->w.entry); wake_up_process(curr->w.private); + list_del_init_careful(&curr->w.entry); } spin_unlock_irqrestore(&ctx->wait.lock, flags); } diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile index b02796c8a595..66ca0bbee639 100644 --- a/fs/bcachefs/Makefile +++ b/fs/bcachefs/Makefile @@ -17,6 +17,7 @@ bcachefs-y := \ btree_journal_iter.o \ btree_key_cache.o \ btree_locking.o \ + btree_node_scan.o \ btree_trans_commit.o \ btree_update.o \ btree_update_interior.o \ @@ -37,6 +38,7 @@ bcachefs-y := \ error.o \ extents.o \ extent_update.o \ + eytzinger.o \ fs.o \ fs-common.o \ fs-ioctl.o \ @@ -67,6 +69,7 @@ bcachefs-y := \ quota.o \ rebalance.o \ recovery.o \ + recovery_passes.o \ reflink.o \ replicas.o \ sb-clean.o \ diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index 893e38f9db80..4ff56fa4d539 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -1713,34 +1713,37 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, if (ret) goto out; - if (BCH_ALLOC_V4_NEED_INC_GEN(&a->v)) { - a->v.gen++; - SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false); - goto write; - } - - if (a->v.journal_seq > c->journal.flushed_seq_ondisk) { - if (c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info) { - bch2_trans_inconsistent(trans, - "clearing need_discard but journal_seq %llu > flushed_seq %llu\n" - "%s", - a->v.journal_seq, - c->journal.flushed_seq_ondisk, - (bch2_bkey_val_to_text(&buf, c, k), buf.buf)); + if (a->v.dirty_sectors) { + if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, + trans, "attempting to discard bucket with dirty data\n%s", + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) ret = -EIO; - } goto out; } if (a->v.data_type != BCH_DATA_need_discard) { - if (c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info) { - bch2_trans_inconsistent(trans, - "bucket incorrectly set in need_discard btree\n" - "%s", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf)); - ret = -EIO; + if (data_type_is_empty(a->v.data_type) && + BCH_ALLOC_V4_NEED_INC_GEN(&a->v)) { + a->v.gen++; + SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false); + goto write; } + if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, + trans, "bucket incorrectly set in need_discard btree\n" + "%s", + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + ret = -EIO; + goto out; + } + + if (a->v.journal_seq > c->journal.flushed_seq_ondisk) { + if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, + trans, "clearing need_discard but journal_seq %llu > flushed_seq %llu\n%s", + a->v.journal_seq, + c->journal.flushed_seq_ondisk, + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + ret = -EIO; goto out; } @@ -1835,6 +1838,7 @@ static int bch2_clear_bucket_needs_discard(struct btree_trans *trans, struct bpo if (ret) goto err; + BUG_ON(a->v.dirty_sectors); SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); a->v.data_type = alloc_data_type(a->v, a->v.data_type); @@ -1942,6 +1946,7 @@ static int invalidate_one_bucket(struct btree_trans *trans, goto out; BUG_ON(a->v.data_type != BCH_DATA_cached); + BUG_ON(a->v.dirty_sectors); if (!a->v.cached_sectors) bch_err(c, "invalidating empty bucket, confused"); diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index 214b15c84d1f..a1fc30adf912 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -188,8 +188,10 @@ long bch2_bucket_alloc_new_fs(struct bch_dev *ca) static inline unsigned open_buckets_reserved(enum bch_watermark watermark) { switch (watermark) { - case BCH_WATERMARK_reclaim: + case BCH_WATERMARK_interior_updates: return 0; + case BCH_WATERMARK_reclaim: + return OPEN_BUCKETS_COUNT / 6; case BCH_WATERMARK_btree: case BCH_WATERMARK_btree_copygc: return OPEN_BUCKETS_COUNT / 4; diff --git a/fs/bcachefs/alloc_types.h b/fs/bcachefs/alloc_types.h index b91b7a461056..c2226e947c41 100644 --- a/fs/bcachefs/alloc_types.h +++ b/fs/bcachefs/alloc_types.h @@ -22,7 +22,8 @@ struct bucket_alloc_state { x(copygc) \ x(btree) \ x(btree_copygc) \ - x(reclaim) + x(reclaim) \ + x(interior_updates) enum bch_watermark { #define x(name) BCH_WATERMARK_##name, diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 8cb35ea572cb..114328acde72 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -8,6 +8,7 @@ #include "btree_update.h" #include "btree_update_interior.h" #include "btree_write_buffer.h" +#include "checksum.h" #include "error.h" #include <linux/mm.h> @@ -29,8 +30,7 @@ static bool extent_matches_bp(struct bch_fs *c, if (p.ptr.cached) continue; - bch2_extent_ptr_to_bp(c, btree_id, level, k, p, - &bucket2, &bp2); + bch2_extent_ptr_to_bp(c, btree_id, level, k, p, entry, &bucket2, &bp2); if (bpos_eq(bucket, bucket2) && !memcmp(&bp, &bp2, sizeof(bp))) return true; @@ -44,6 +44,11 @@ int bch2_backpointer_invalid(struct bch_fs *c, struct bkey_s_c k, struct printbuf *err) { struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); + + /* these will be caught by fsck */ + if (!bch2_dev_exists2(c, bp.k->p.inode)) + return 0; + struct bpos bucket = bp_pos_to_bucket(c, bp.k->p); int ret = 0; @@ -378,7 +383,7 @@ static int bch2_check_btree_backpointer(struct btree_trans *trans, struct btree_ backpointer_to_missing_alloc, "backpointer for nonexistent alloc key: %llu:%llu:0\n%s", alloc_iter.pos.inode, alloc_iter.pos.offset, - (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = bch2_btree_delete_at(trans, bp_iter, 0); goto out; } @@ -414,6 +419,84 @@ struct extents_to_bp_state { struct bkey_buf last_flushed; }; +static int drop_dev_and_update(struct btree_trans *trans, enum btree_id btree, + struct bkey_s_c extent, unsigned dev) +{ + struct bkey_i *n = bch2_bkey_make_mut_noupdate(trans, extent); + int ret = PTR_ERR_OR_ZERO(n); + if (ret) + return ret; + + bch2_bkey_drop_device(bkey_i_to_s(n), dev); + return bch2_btree_insert_trans(trans, btree, n, 0); +} + +static int check_extent_checksum(struct btree_trans *trans, + enum btree_id btree, struct bkey_s_c extent, + enum btree_id o_btree, struct bkey_s_c extent2, unsigned dev) +{ + struct bch_fs *c = trans->c; + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(extent); + const union bch_extent_entry *entry; + struct extent_ptr_decoded p; + struct printbuf buf = PRINTBUF; + void *data_buf = NULL; + struct bio *bio = NULL; + size_t bytes; + int ret = 0; + + if (bkey_is_btree_ptr(extent.k)) + return false; + + bkey_for_each_ptr_decode(extent.k, ptrs, p, entry) + if (p.ptr.dev == dev) + goto found; + BUG(); +found: + if (!p.crc.csum_type) + return false; + + bytes = p.crc.compressed_size << 9; + + struct bch_dev *ca = bch_dev_bkey_exists(c, dev); + if (!bch2_dev_get_ioref(ca, READ)) + return false; + + data_buf = kvmalloc(bytes, GFP_KERNEL); + if (!data_buf) { + ret = -ENOMEM; + goto err; + } + + bio = bio_alloc(ca->disk_sb.bdev, 1, REQ_OP_READ, GFP_KERNEL); + bio->bi_iter.bi_sector = p.ptr.offset; + bch2_bio_map(bio, data_buf, bytes); + ret = submit_bio_wait(bio); + if (ret) + goto err; + + prt_str(&buf, "extents pointing to same space, but first extent checksum bad:"); + prt_printf(&buf, "\n %s ", bch2_btree_id_str(btree)); + bch2_bkey_val_to_text(&buf, c, extent); + prt_printf(&buf, "\n %s ", bch2_btree_id_str(o_btree)); + bch2_bkey_val_to_text(&buf, c, extent2); + + struct nonce nonce = extent_nonce(extent.k->version, p.crc); + struct bch_csum csum = bch2_checksum(c, p.crc.csum_type, nonce, data_buf, bytes); + if (fsck_err_on(bch2_crc_cmp(csum, p.crc.csum), + c, dup_backpointer_to_bad_csum_extent, + "%s", buf.buf)) + ret = drop_dev_and_update(trans, btree, extent, dev) ?: 1; +fsck_err: +err: + if (bio) + bio_put(bio); + kvfree(data_buf); + percpu_ref_put(&ca->io_ref); + printbuf_exit(&buf); + return ret; +} + static int check_bp_exists(struct btree_trans *trans, struct extents_to_bp_state *s, struct bpos bucket, @@ -421,7 +504,8 @@ static int check_bp_exists(struct btree_trans *trans, struct bkey_s_c orig_k) { struct bch_fs *c = trans->c; - struct btree_iter bp_iter = { NULL }; + struct btree_iter bp_iter = {}; + struct btree_iter other_extent_iter = {}; struct printbuf buf = PRINTBUF; struct bkey_s_c bp_k; struct bkey_buf tmp; @@ -429,13 +513,19 @@ static int check_bp_exists(struct btree_trans *trans, bch2_bkey_buf_init(&tmp); + if (!bch2_dev_bucket_exists(c, bucket)) { + prt_str(&buf, "extent for nonexistent device:bucket "); + bch2_bpos_to_text(&buf, bucket); + prt_str(&buf, "\n "); + bch2_bkey_val_to_text(&buf, c, orig_k); + bch_err(c, "%s", buf.buf); + return -BCH_ERR_fsck_repair_unimplemented; + } + if (bpos_lt(bucket, s->bucket_start) || bpos_gt(bucket, s->bucket_end)) return 0; - if (!bch2_dev_bucket_exists(c, bucket)) - goto missing; - bp_k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers, bucket_pos_to_bp(c, bucket, bp.bucket_offset), 0); @@ -461,21 +551,94 @@ static int check_bp_exists(struct btree_trans *trans, ret = -BCH_ERR_transaction_restart_write_buffer_flush; goto out; } - goto missing; + + goto check_existing_bp; } out: err: fsck_err: + bch2_trans_iter_exit(trans, &other_extent_iter); bch2_trans_iter_exit(trans, &bp_iter); bch2_bkey_buf_exit(&tmp, c); printbuf_exit(&buf); return ret; +check_existing_bp: + /* Do we have a backpointer for a different extent? */ + if (bp_k.k->type != KEY_TYPE_backpointer) + goto missing; + + struct bch_backpointer other_bp = *bkey_s_c_to_backpointer(bp_k).v; + + struct bkey_s_c other_extent = + bch2_backpointer_get_key(trans, &other_extent_iter, bp_k.k->p, other_bp, 0); + ret = bkey_err(other_extent); + if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) + ret = 0; + if (ret) + goto err; + + if (!other_extent.k) + goto missing; + + if (bch2_extents_match(orig_k, other_extent)) { + printbuf_reset(&buf); + prt_printf(&buf, "duplicate versions of same extent, deleting smaller\n "); + bch2_bkey_val_to_text(&buf, c, orig_k); + prt_str(&buf, "\n "); + bch2_bkey_val_to_text(&buf, c, other_extent); + bch_err(c, "%s", buf.buf); + + if (other_extent.k->size <= orig_k.k->size) { + ret = drop_dev_and_update(trans, other_bp.btree_id, other_extent, bucket.inode); + if (ret) + goto err; + goto out; + } else { + ret = drop_dev_and_update(trans, bp.btree_id, orig_k, bucket.inode); + if (ret) + goto err; + goto missing; + } + } + + ret = check_extent_checksum(trans, other_bp.btree_id, other_extent, bp.btree_id, orig_k, bucket.inode); + if (ret < 0) + goto err; + if (ret) { + ret = 0; + goto missing; + } + + ret = check_extent_checksum(trans, bp.btree_id, orig_k, other_bp.btree_id, other_extent, bucket.inode); + if (ret < 0) + goto err; + if (ret) { + ret = 0; + goto out; + } + + printbuf_reset(&buf); + prt_printf(&buf, "duplicate extents pointing to same space on dev %llu\n ", bucket.inode); + bch2_bkey_val_to_text(&buf, c, orig_k); + prt_str(&buf, "\n "); + bch2_bkey_val_to_text(&buf, c, other_extent); + bch_err(c, "%s", buf.buf); + ret = -BCH_ERR_fsck_repair_unimplemented; + goto err; missing: + printbuf_reset(&buf); prt_printf(&buf, "missing backpointer for btree=%s l=%u ", bch2_btree_id_str(bp.btree_id), bp.level); bch2_bkey_val_to_text(&buf, c, orig_k); - prt_printf(&buf, "\nbp pos "); - bch2_bpos_to_text(&buf, bp_iter.pos); + prt_printf(&buf, "\n got: "); + bch2_bkey_val_to_text(&buf, c, bp_k); + + struct bkey_i_backpointer n_bp_k; + bkey_backpointer_init(&n_bp_k.k_i); + n_bp_k.k.p = bucket_pos_to_bp(trans->c, bucket, bp.bucket_offset); + n_bp_k.v = bp; + prt_printf(&buf, "\n want: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&n_bp_k.k_i)); if (fsck_err(c, ptr_to_missing_backpointer, "%s", buf.buf)) ret = bch2_bucket_backpointer_mod(trans, bucket, bp, orig_k, true); @@ -502,8 +665,7 @@ static int check_extent_to_backpointers(struct btree_trans *trans, if (p.ptr.cached) continue; - bch2_extent_ptr_to_bp(c, btree, level, - k, p, &bucket_pos, &bp); + bch2_extent_ptr_to_bp(c, btree, level, k, p, entry, &bucket_pos, &bp); ret = check_bp_exists(trans, s, bucket_pos, bp, k); if (ret) diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h index 327365a9feac..da012ca7daee 100644 --- a/fs/bcachefs/backpointers.h +++ b/fs/bcachefs/backpointers.h @@ -90,20 +90,40 @@ static inline int bch2_bucket_backpointer_mod(struct btree_trans *trans, return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp_k.k_i); } -static inline enum bch_data_type bkey_ptr_data_type(enum btree_id btree_id, unsigned level, - struct bkey_s_c k, struct extent_ptr_decoded p) +static inline enum bch_data_type bch2_bkey_ptr_data_type(struct bkey_s_c k, + struct extent_ptr_decoded p, + const union bch_extent_entry *entry) { - return level ? BCH_DATA_btree : - p.has_ec ? BCH_DATA_stripe : - BCH_DATA_user; + switch (k.k->type) { + case KEY_TYPE_btree_ptr: + case KEY_TYPE_btree_ptr_v2: + return BCH_DATA_btree; + case KEY_TYPE_extent: + case KEY_TYPE_reflink_v: + return p.has_ec ? BCH_DATA_stripe : BCH_DATA_user; + case KEY_TYPE_stripe: { + const struct bch_extent_ptr *ptr = &entry->ptr; + struct bkey_s_c_stripe s = bkey_s_c_to_stripe(k); + + BUG_ON(ptr < s.v->ptrs || + ptr >= s.v->ptrs + s.v->nr_blocks); + + return ptr >= s.v->ptrs + s.v->nr_blocks - s.v->nr_redundant + ? BCH_DATA_parity + : BCH_DATA_user; + } + default: + BUG(); + } } static inline void bch2_extent_ptr_to_bp(struct bch_fs *c, enum btree_id btree_id, unsigned level, struct bkey_s_c k, struct extent_ptr_decoded p, + const union bch_extent_entry *entry, struct bpos *bucket_pos, struct bch_backpointer *bp) { - enum bch_data_type data_type = bkey_ptr_data_type(btree_id, level, k, p); + enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry); s64 sectors = level ? btree_sectors(c) : k.k->size; u32 bucket_offset; diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 799aa32b6b4d..a31a5f706929 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -209,7 +209,7 @@ #include "fifo.h" #include "nocow_locking_types.h" #include "opts.h" -#include "recovery_types.h" +#include "recovery_passes_types.h" #include "sb-errors_types.h" #include "seqmutex.h" #include "time_stats.h" @@ -456,6 +456,7 @@ enum bch_time_stats { #include "alloc_types.h" #include "btree_types.h" +#include "btree_node_scan_types.h" #include "btree_write_buffer_types.h" #include "buckets_types.h" #include "buckets_waiting_for_journal_types.h" @@ -614,6 +615,7 @@ struct bch_dev { */ #define BCH_FS_FLAGS() \ + x(new_fs) \ x(started) \ x(may_go_rw) \ x(rw) \ @@ -796,6 +798,7 @@ struct bch_fs { u64 features; u64 compat; unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)]; + u64 btrees_lost_data; } sb; @@ -810,7 +813,6 @@ struct bch_fs { /* snapshot.c: */ struct snapshot_table __rcu *snapshots; - size_t snapshot_table_size; struct mutex snapshot_table_lock; struct rw_semaphore snapshot_create_lock; @@ -1104,6 +1106,8 @@ struct bch_fs { struct journal_keys journal_keys; struct list_head journal_iters; + struct find_btree_nodes found_btree_nodes; + u64 last_bucket_seq_cleanup; u64 counters_on_mount[BCH_COUNTER_NR]; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index bff8750ac0d7..63102992d955 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -818,6 +818,7 @@ struct bch_sb_field_ext { struct bch_sb_field field; __le64 recovery_passes_required[2]; __le64 errors_silent[8]; + __le64 btrees_lost_data; }; struct bch_sb_field_downgrade_entry { diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c index 3fd1085b6c61..3bb477840eab 100644 --- a/fs/bcachefs/bset.c +++ b/fs/bcachefs/bset.c @@ -134,18 +134,24 @@ void bch2_dump_btree_node_iter(struct btree *b, printbuf_exit(&buf); } -#ifdef CONFIG_BCACHEFS_DEBUG - -void __bch2_verify_btree_nr_keys(struct btree *b) +struct btree_nr_keys bch2_btree_node_count_keys(struct btree *b) { struct bset_tree *t; struct bkey_packed *k; - struct btree_nr_keys nr = { 0 }; + struct btree_nr_keys nr = {}; for_each_bset(b, t) bset_tree_for_each_key(b, t, k) if (!bkey_deleted(k)) btree_keys_account_key_add(&nr, t - b->set, k); + return nr; +} + +#ifdef CONFIG_BCACHEFS_DEBUG + +void __bch2_verify_btree_nr_keys(struct btree *b) +{ + struct btree_nr_keys nr = bch2_btree_node_count_keys(b); BUG_ON(memcmp(&nr, &b->nr, sizeof(nr))); } diff --git a/fs/bcachefs/bset.h b/fs/bcachefs/bset.h index 79c77baaa383..120a79fd456b 100644 --- a/fs/bcachefs/bset.h +++ b/fs/bcachefs/bset.h @@ -458,6 +458,8 @@ struct bkey_s_c bch2_btree_node_iter_peek_unpack(struct btree_node_iter *, /* Accounting: */ +struct btree_nr_keys bch2_btree_node_count_keys(struct btree *); + static inline void btree_keys_account_key(struct btree_nr_keys *n, unsigned bset, struct bkey_packed *k, diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 562561a9a510..84474324dba9 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -808,7 +808,8 @@ static noinline void btree_bad_header(struct bch_fs *c, struct btree *b) prt_printf(&buf, "\nmax "); bch2_bpos_to_text(&buf, b->data->max_key); - bch2_fs_inconsistent(c, "%s", buf.buf); + bch2_fs_topology_error(c, "%s", buf.buf); + printbuf_exit(&buf); } @@ -1134,6 +1135,8 @@ void bch2_btree_node_evict(struct btree_trans *trans, const struct bkey_i *k) b = btree_cache_find(bc, k); if (!b) return; + + BUG_ON(b == btree_node_root(trans->c, b)); wait_on_io: /* not allowed to wait on io with btree locks held: */ diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index bdaed29f084a..6280da1244b5 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -7,11 +7,13 @@ #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" +#include "backpointers.h" #include "bkey_methods.h" #include "bkey_buf.h" #include "btree_journal_iter.h" #include "btree_key_cache.h" #include "btree_locking.h" +#include "btree_node_scan.h" #include "btree_update_interior.h" #include "btree_io.h" #include "btree_gc.h" @@ -24,7 +26,7 @@ #include "journal.h" #include "keylist.h" #include "move.h" -#include "recovery.h" +#include "recovery_passes.h" #include "reflink.h" #include "replicas.h" #include "super-io.h" @@ -40,6 +42,7 @@ #define DROP_THIS_NODE 10 #define DROP_PREV_NODE 11 +#define DID_FILL_FROM_SCAN 12 static struct bkey_s unsafe_bkey_s_c_to_s(struct bkey_s_c k) { @@ -70,90 +73,6 @@ static inline void gc_pos_set(struct bch_fs *c, struct gc_pos new_pos) __gc_pos_set(c, new_pos); } -/* - * Missing: if an interior btree node is empty, we need to do something - - * perhaps just kill it - */ -static int bch2_gc_check_topology(struct bch_fs *c, - struct btree *b, - struct bkey_buf *prev, - struct bkey_buf cur, - bool is_last) -{ - struct bpos node_start = b->data->min_key; - struct bpos node_end = b->data->max_key; - struct bpos expected_start = bkey_deleted(&prev->k->k) - ? node_start - : bpos_successor(prev->k->k.p); - struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; - int ret = 0; - - if (cur.k->k.type == KEY_TYPE_btree_ptr_v2) { - struct bkey_i_btree_ptr_v2 *bp = bkey_i_to_btree_ptr_v2(cur.k); - - if (!bpos_eq(expected_start, bp->v.min_key)) { - bch2_topology_error(c); - - if (bkey_deleted(&prev->k->k)) { - prt_printf(&buf1, "start of node: "); - bch2_bpos_to_text(&buf1, node_start); - } else { - bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(prev->k)); - } - bch2_bkey_val_to_text(&buf2, c, bkey_i_to_s_c(cur.k)); - - if (__fsck_err(c, - FSCK_CAN_FIX| - FSCK_CAN_IGNORE| - FSCK_NO_RATELIMIT, - btree_node_topology_bad_min_key, - "btree node with incorrect min_key at btree %s level %u:\n" - " prev %s\n" - " cur %s", - bch2_btree_id_str(b->c.btree_id), b->c.level, - buf1.buf, buf2.buf) && should_restart_for_topology_repair(c)) { - bch_info(c, "Halting mark and sweep to start topology repair pass"); - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); - goto err; - } else { - set_bit(BCH_FS_initial_gc_unfixed, &c->flags); - } - } - } - - if (is_last && !bpos_eq(cur.k->k.p, node_end)) { - bch2_topology_error(c); - - printbuf_reset(&buf1); - printbuf_reset(&buf2); - - bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(cur.k)); - bch2_bpos_to_text(&buf2, node_end); - - if (__fsck_err(c, FSCK_CAN_FIX|FSCK_CAN_IGNORE|FSCK_NO_RATELIMIT, - btree_node_topology_bad_max_key, - "btree node with incorrect max_key at btree %s level %u:\n" - " %s\n" - " expected %s", - bch2_btree_id_str(b->c.btree_id), b->c.level, - buf1.buf, buf2.buf) && - should_restart_for_topology_repair(c)) { - bch_info(c, "Halting mark and sweep to start topology repair pass"); - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); - goto err; - } else { - set_bit(BCH_FS_initial_gc_unfixed, &c->flags); - } - } - - bch2_bkey_buf_copy(prev, c, cur.k); -err: -fsck_err: - printbuf_exit(&buf2); - printbuf_exit(&buf1); - return ret; -} - static void btree_ptr_to_v2(struct btree *b, struct bkey_i_btree_ptr_v2 *dst) { switch (b->key.k.type) { @@ -212,6 +131,17 @@ static int set_node_min(struct bch_fs *c, struct btree *b, struct bpos new_min) struct bkey_i_btree_ptr_v2 *new; int ret; + if (c->opts.verbose) { + struct printbuf buf = PRINTBUF; + + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + prt_str(&buf, " -> "); + bch2_bpos_to_text(&buf, new_min); + + bch_info(c, "%s(): %s", __func__, buf.buf); + printbuf_exit(&buf); + } + new = kmalloc_array(BKEY_BTREE_PTR_U64s_MAX, sizeof(u64), GFP_KERNEL); if (!new) return -BCH_ERR_ENOMEM_gc_repair_key; @@ -237,6 +167,17 @@ static int set_node_max(struct bch_fs *c, struct btree *b, struct bpos new_max) struct bkey_i_btree_ptr_v2 *new; int ret; + if (c->opts.verbose) { + struct printbuf buf = PRINTBUF; + + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + prt_str(&buf, " -> "); + bch2_bpos_to_text(&buf, new_max); + + bch_info(c, "%s(): %s", __func__, buf.buf); + printbuf_exit(&buf); + } + ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level + 1, b->key.k.p); if (ret) return ret; @@ -268,127 +209,138 @@ static int set_node_max(struct bch_fs *c, struct btree *b, struct bpos new_max) return 0; } -static int btree_repair_node_boundaries(struct bch_fs *c, struct btree *b, - struct btree *prev, struct btree *cur) +static int btree_check_node_boundaries(struct bch_fs *c, struct btree *b, + struct btree *prev, struct btree *cur, + struct bpos *pulled_from_scan) { struct bpos expected_start = !prev ? b->data->min_key : bpos_successor(prev->key.k.p); - struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; + struct printbuf buf = PRINTBUF; int ret = 0; - if (!prev) { - prt_printf(&buf1, "start of node: "); - bch2_bpos_to_text(&buf1, b->data->min_key); - } else { - bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(&prev->key)); + BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 && + !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key, + b->data->min_key)); + + if (bpos_eq(expected_start, cur->data->min_key)) + return 0; + + prt_printf(&buf, " at btree %s level %u:\n parent: ", + bch2_btree_id_str(b->c.btree_id), b->c.level); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + + if (prev) { + prt_printf(&buf, "\n prev: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&prev->key)); } - bch2_bkey_val_to_text(&buf2, c, bkey_i_to_s_c(&cur->key)); - - if (prev && - bpos_gt(expected_start, cur->data->min_key) && - BTREE_NODE_SEQ(cur->data) > BTREE_NODE_SEQ(prev->data)) { - /* cur overwrites prev: */ - - if (mustfix_fsck_err_on(bpos_ge(prev->data->min_key, - cur->data->min_key), c, - btree_node_topology_overwritten_by_next_node, - "btree node overwritten by next node at btree %s level %u:\n" - " node %s\n" - " next %s", - bch2_btree_id_str(b->c.btree_id), b->c.level, - buf1.buf, buf2.buf)) { - ret = DROP_PREV_NODE; - goto out; - } + prt_str(&buf, "\n next: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&cur->key)); - if (mustfix_fsck_err_on(!bpos_eq(prev->key.k.p, - bpos_predecessor(cur->data->min_key)), c, - btree_node_topology_bad_max_key, - "btree node with incorrect max_key at btree %s level %u:\n" - " node %s\n" - " next %s", - bch2_btree_id_str(b->c.btree_id), b->c.level, - buf1.buf, buf2.buf)) - ret = set_node_max(c, prev, - bpos_predecessor(cur->data->min_key)); - } else { - /* prev overwrites cur: */ - - if (mustfix_fsck_err_on(bpos_ge(expected_start, - cur->data->max_key), c, - btree_node_topology_overwritten_by_prev_node, - "btree node overwritten by prev node at btree %s level %u:\n" - " prev %s\n" - " node %s", - bch2_btree_id_str(b->c.btree_id), b->c.level, - buf1.buf, buf2.buf)) { - ret = DROP_THIS_NODE; - goto out; - } + if (bpos_lt(expected_start, cur->data->min_key)) { /* gap */ + if (b->c.level == 1 && + bpos_lt(*pulled_from_scan, cur->data->min_key)) { + ret = bch2_get_scanned_nodes(c, b->c.btree_id, 0, + expected_start, + bpos_predecessor(cur->data->min_key)); + if (ret) + goto err; - if (mustfix_fsck_err_on(!bpos_eq(expected_start, cur->data->min_key), c, - btree_node_topology_bad_min_key, - "btree node with incorrect min_key at btree %s level %u:\n" - " prev %s\n" - " node %s", - bch2_btree_id_str(b->c.btree_id), b->c.level, - buf1.buf, buf2.buf)) - ret = set_node_min(c, cur, expected_start); + *pulled_from_scan = cur->data->min_key; + ret = DID_FILL_FROM_SCAN; + } else { + if (mustfix_fsck_err(c, btree_node_topology_bad_min_key, + "btree node with incorrect min_key%s", buf.buf)) + ret = set_node_min(c, cur, expected_start); + } + } else { /* overlap */ + if (prev && BTREE_NODE_SEQ(cur->data) > BTREE_NODE_SEQ(prev->data)) { /* cur overwrites prev */ + if (bpos_ge(prev->data->min_key, cur->data->min_key)) { /* fully? */ + if (mustfix_fsck_err(c, btree_node_topology_overwritten_by_next_node, + "btree node overwritten by next node%s", buf.buf)) + ret = DROP_PREV_NODE; + } else { + if (mustfix_fsck_err(c, btree_node_topology_bad_max_key, + "btree node with incorrect max_key%s", buf.buf)) + ret = set_node_max(c, prev, + bpos_predecessor(cur->data->min_key)); + } + } else { + if (bpos_ge(expected_start, cur->data->max_key)) { /* fully? */ + if (mustfix_fsck_err(c, btree_node_topology_overwritten_by_prev_node, + "btree node overwritten by prev node%s", buf.buf)) + ret = DROP_THIS_NODE; + } else { + if (mustfix_fsck_err(c, btree_node_topology_bad_min_key, + "btree node with incorrect min_key%s", buf.buf)) + ret = set_node_min(c, cur, expected_start); + } + } } -out: +err: fsck_err: - printbuf_exit(&buf2); - printbuf_exit(&buf1); + printbuf_exit(&buf); return ret; } static int btree_repair_node_end(struct bch_fs *c, struct btree *b, - struct btree *child) + struct btree *child, struct bpos *pulled_from_scan) { - struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; + struct printbuf buf = PRINTBUF; int ret = 0; - bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(&child->key)); - bch2_bpos_to_text(&buf2, b->key.k.p); + if (bpos_eq(child->key.k.p, b->key.k.p)) + return 0; - if (mustfix_fsck_err_on(!bpos_eq(child->key.k.p, b->key.k.p), c, - btree_node_topology_bad_max_key, - "btree node with incorrect max_key at btree %s level %u:\n" - " %s\n" - " expected %s", - bch2_btree_id_str(b->c.btree_id), b->c.level, - buf1.buf, buf2.buf)) { - ret = set_node_max(c, child, b->key.k.p); - if (ret) - goto err; + prt_printf(&buf, "at btree %s level %u:\n parent: ", + bch2_btree_id_str(b->c.btree_id), b->c.level); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + + prt_str(&buf, "\n child: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&child->key)); + + if (mustfix_fsck_err(c, btree_node_topology_bad_max_key, + "btree node with incorrect max_key%s", buf.buf)) { + if (b->c.level == 1 && + bpos_lt(*pulled_from_scan, b->key.k.p)) { + ret = bch2_get_scanned_nodes(c, b->c.btree_id, 0, + bpos_successor(child->key.k.p), b->key.k.p); + if (ret) + goto err; + + *pulled_from_scan = b->key.k.p; + ret = DID_FILL_FROM_SCAN; + } else { + ret = set_node_max(c, child, b->key.k.p); + } } err: fsck_err: - printbuf_exit(&buf2); - printbuf_exit(&buf1); + printbuf_exit(&buf); return ret; } -static int bch2_btree_repair_topology_recurse(struct btree_trans *trans, struct btree *b) +static int bch2_btree_repair_topology_recurse(struct btree_trans *trans, struct btree *b, + struct bpos *pulled_from_scan) { struct bch_fs *c = trans->c; struct btree_and_journal_iter iter; struct bkey_s_c k; struct bkey_buf prev_k, cur_k; struct btree *prev = NULL, *cur = NULL; - bool have_child, dropped_children = false; + bool have_child, new_pass = false; struct printbuf buf = PRINTBUF; int ret = 0; if (!b->c.level) return 0; -again: - prev = NULL; - have_child = dropped_children = false; + bch2_bkey_buf_init(&prev_k); bch2_bkey_buf_init(&cur_k); +again: + cur = prev = NULL; + have_child = new_pass = false; bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); iter.prefetch = true; @@ -415,9 +367,10 @@ again: b->c.level - 1, buf.buf)) { bch2_btree_node_evict(trans, cur_k.k); - ret = bch2_journal_key_delete(c, b->c.btree_id, - b->c.level, cur_k.k->k.p); cur = NULL; + ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes) ?: + bch2_journal_key_delete(c, b->c.btree_id, + b->c.level, cur_k.k->k.p); if (ret) break; continue; @@ -427,7 +380,23 @@ again: if (ret) break; - ret = btree_repair_node_boundaries(c, b, prev, cur); + if (bch2_btree_node_is_stale(c, cur)) { + bch_info(c, "btree node %s older than nodes found by scanning", buf.buf); + six_unlock_read(&cur->c.lock); + bch2_btree_node_evict(trans, cur_k.k); + ret = bch2_journal_key_delete(c, b->c.btree_id, + b->c.level, cur_k.k->k.p); + cur = NULL; + if (ret) + break; + continue; + } + + ret = btree_check_node_boundaries(c, b, prev, cur, pulled_from_scan); + if (ret == DID_FILL_FROM_SCAN) { + new_pass = true; + ret = 0; + } if (ret == DROP_THIS_NODE) { six_unlock_read(&cur->c.lock); @@ -445,6 +414,7 @@ again: prev = NULL; if (ret == DROP_PREV_NODE) { + bch_info(c, "dropped prev node"); bch2_btree_node_evict(trans, prev_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level, prev_k.k->k.p); @@ -452,8 +422,6 @@ again: break; bch2_btree_and_journal_iter_exit(&iter); - bch2_bkey_buf_exit(&prev_k, c); - bch2_bkey_buf_exit(&cur_k, c); goto again; } else if (ret) break; @@ -465,7 +433,11 @@ again: if (!ret && !IS_ERR_OR_NULL(prev)) { BUG_ON(cur); - ret = btree_repair_node_end(c, b, prev); + ret = btree_repair_node_end(c, b, prev, pulled_from_scan); + if (ret == DID_FILL_FROM_SCAN) { + new_pass = true; + ret = 0; + } } if (!IS_ERR_OR_NULL(prev)) @@ -479,6 +451,10 @@ again: goto err; bch2_btree_and_journal_iter_exit(&iter); + + if (new_pass) + goto again; + bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); iter.prefetch = true; @@ -495,7 +471,7 @@ again: if (ret) goto err; - ret = bch2_btree_repair_topology_recurse(trans, cur); + ret = bch2_btree_repair_topology_recurse(trans, cur, pulled_from_scan); six_unlock_read(&cur->c.lock); cur = NULL; @@ -503,7 +479,7 @@ again: bch2_btree_node_evict(trans, cur_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level, cur_k.k->k.p); - dropped_children = true; + new_pass = true; } if (ret) @@ -530,12 +506,14 @@ fsck_err: six_unlock_read(&cur->c.lock); bch2_btree_and_journal_iter_exit(&iter); - bch2_bkey_buf_exit(&prev_k, c); - bch2_bkey_buf_exit(&cur_k, c); - if (!ret && dropped_children) + if (!ret && new_pass) goto again; + BUG_ON(!ret && bch2_btree_node_check_topology(trans, b)); + + bch2_bkey_buf_exit(&prev_k, c); + bch2_bkey_buf_exit(&cur_k, c); printbuf_exit(&buf); return ret; } @@ -543,32 +521,63 @@ fsck_err: int bch2_check_topology(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); - struct btree *b; - unsigned i; + struct bpos pulled_from_scan = POS_MIN; int ret = 0; - for (i = 0; i < btree_id_nr_alive(c) && !ret; i++) { + for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) { struct btree_root *r = bch2_btree_id_root(c, i); + bool reconstructed_root = false; - if (!r->alive) - continue; + if (r->error) { + ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); + if (ret) + break; +reconstruct_root: + bch_info(c, "btree root %s unreadable, must recover from scan", bch2_btree_id_str(i)); - b = r->b; - if (btree_node_fake(b)) - continue; + r->alive = false; + r->error = 0; + + if (!bch2_btree_has_scanned_nodes(c, i)) { + mustfix_fsck_err(c, btree_root_unreadable_and_scan_found_nothing, + "no nodes found for btree %s, continue?", bch2_btree_id_str(i)); + bch2_btree_root_alloc_fake(c, i, 0); + } else { + bch2_btree_root_alloc_fake(c, i, 1); + ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX); + if (ret) + break; + } + + bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + reconstructed_root = true; + } + + struct btree *b = r->b; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); - ret = bch2_btree_repair_topology_recurse(trans, b); + ret = bch2_btree_repair_topology_recurse(trans, b, &pulled_from_scan); six_unlock_read(&b->c.lock); if (ret == DROP_THIS_NODE) { - bch_err(c, "empty btree root - repair unimplemented"); - ret = -BCH_ERR_fsck_repair_unimplemented; + bch2_btree_node_hash_remove(&c->btree_cache, b); + mutex_lock(&c->btree_cache.lock); + list_move(&b->list, &c->btree_cache.freeable); + mutex_unlock(&c->btree_cache.lock); + + r->b = NULL; + + if (!reconstructed_root) + goto reconstruct_root; + + bch_err(c, "empty btree root %s", bch2_btree_id_str(i)); + bch2_btree_root_alloc_fake(c, i, 0); + r->alive = false; + ret = 0; } } - +fsck_err: bch2_trans_put(trans); - return ret; } @@ -591,7 +600,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id bkey_for_each_ptr_decode(k->k, ptrs_c, p, entry_c) { struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev); struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); - enum bch_data_type data_type = bch2_bkey_ptr_data_type(*k, &entry_c->ptr); + enum bch_data_type data_type = bch2_bkey_ptr_data_type(*k, p, entry_c); if (fsck_err_on(!g->gen_valid, c, ptr_to_missing_alloc_key, @@ -657,7 +666,8 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id continue; if (fsck_err_on(bucket_data_type(g->data_type) && - bucket_data_type(g->data_type) != data_type, c, + bucket_data_type(g->data_type) != + bucket_data_type(data_type), c, ptr_bucket_data_type_mismatch, "bucket %u:%zu different types of data in same bucket: %s, %s\n" "while marking %s", @@ -698,18 +708,13 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id } if (do_update) { - struct bkey_ptrs ptrs; - union bch_extent_entry *entry; - struct bch_extent_ptr *ptr; - struct bkey_i *new; - if (is_root) { bch_err(c, "cannot update btree roots yet"); ret = -EINVAL; goto err; } - new = kmalloc(bkey_bytes(k->k), GFP_KERNEL); + struct bkey_i *new = kmalloc(bkey_bytes(k->k), GFP_KERNEL); if (!new) { ret = -BCH_ERR_ENOMEM_gc_repair_key; bch_err_msg(c, ret, "allocating new key"); @@ -724,7 +729,7 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id * btree node isn't there anymore, the read path will * sort it out: */ - ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); + struct bkey_ptrs ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); bkey_for_each_ptr(ptrs, ptr) { struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev); struct bucket *g = PTR_GC_BUCKET(ca, ptr); @@ -732,19 +737,26 @@ static int bch2_check_fix_ptrs(struct btree_trans *trans, enum btree_id btree_id ptr->gen = g->gen; } } else { - bch2_bkey_drop_ptrs(bkey_i_to_s(new), ptr, ({ - struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev); - struct bucket *g = PTR_GC_BUCKET(ca, ptr); - enum bch_data_type data_type = bch2_bkey_ptr_data_type(*k, ptr); - - (ptr->cached && - (!g->gen_valid || gen_cmp(ptr->gen, g->gen) > 0)) || - (!ptr->cached && - gen_cmp(ptr->gen, g->gen) < 0) || - gen_cmp(g->gen, ptr->gen) > BUCKET_GC_GEN_MAX || - (g->data_type && - g->data_type != data_type); - })); + struct bkey_ptrs ptrs; + union bch_extent_entry *entry; +restart_drop_ptrs: + ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); + bkey_for_each_ptr_decode(bkey_i_to_s(new).k, ptrs, p, entry) { + struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev); + struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); + enum bch_data_type data_type = bch2_bkey_ptr_data_type(bkey_i_to_s_c(new), p, entry); + + if ((p.ptr.cached && + (!g->gen_valid || gen_cmp(p.ptr.gen, g->gen) > 0)) || + (!p.ptr.cached && + gen_cmp(p.ptr.gen, g->gen) < 0) || + gen_cmp(g->gen, p.ptr.gen) > BUCKET_GC_GEN_MAX || + (g->data_type && + g->data_type != data_type)) { + bch2_bkey_drop_ptr(bkey_i_to_s(new), &entry->ptr); + goto restart_drop_ptrs; + } + } again: ptrs = bch2_bkey_ptrs(bkey_i_to_s(new)); bkey_extent_entry_for_each(ptrs, entry) { @@ -774,12 +786,6 @@ found: } } - ret = bch2_journal_key_insert_take(c, btree_id, level, new); - if (ret) { - kfree(new); - goto err; - } - if (level) bch2_btree_node_update_key_early(trans, btree_id, level - 1, *k, new); @@ -793,6 +799,12 @@ found: bch_info(c, "new key %s", buf.buf); } + ret = bch2_journal_key_insert_take(c, btree_id, level, new); + if (ret) { + kfree(new); + goto err; + } + *k = bkey_i_to_s_c(new); } err: @@ -819,10 +831,6 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, BUG_ON(bch2_journal_seq_verify && k->k->version.lo > atomic64_read(&c->journal.seq)); - ret = bch2_check_fix_ptrs(trans, btree_id, level, is_root, k); - if (ret) - goto err; - if (fsck_err_on(k->k->version.lo > atomic64_read(&c->key_version), c, bkey_version_in_future, "key version number higher than recorded: %llu > %llu", @@ -831,8 +839,13 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, atomic64_set(&c->key_version, k->k->version.lo); } + ret = bch2_check_fix_ptrs(trans, btree_id, level, is_root, k); + if (ret) + goto err; + ret = commit_do(trans, NULL, NULL, 0, - bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC)); + bch2_key_trigger(trans, btree_id, level, old, + unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC)); fsck_err: err: bch_err_fn(c, ret); @@ -841,42 +854,30 @@ err: static int btree_gc_mark_node(struct btree_trans *trans, struct btree *b, bool initial) { - struct bch_fs *c = trans->c; struct btree_node_iter iter; struct bkey unpacked; struct bkey_s_c k; - struct bkey_buf prev, cur; int ret = 0; + ret = bch2_btree_node_check_topology(trans, b); + if (ret) + return ret; + if (!btree_node_type_needs_gc(btree_node_type(b))) return 0; bch2_btree_node_iter_init_from_start(&iter, b); - bch2_bkey_buf_init(&prev); - bch2_bkey_buf_init(&cur); - bkey_init(&prev.k->k); while ((k = bch2_btree_node_iter_peek_unpack(&iter, b, &unpacked)).k) { ret = bch2_gc_mark_key(trans, b->c.btree_id, b->c.level, false, &k, initial); if (ret) - break; + return ret; bch2_btree_node_iter_advance(&iter, b); - - if (b->c.level) { - bch2_bkey_buf_reassemble(&cur, c, k); - - ret = bch2_gc_check_topology(c, b, &prev, cur, - bch2_btree_node_iter_end(&iter)); - if (ret) - break; - } } - bch2_bkey_buf_exit(&cur, c); - bch2_bkey_buf_exit(&prev, c); - return ret; + return 0; } static int bch2_gc_btree(struct btree_trans *trans, enum btree_id btree_id, @@ -925,14 +926,16 @@ static int bch2_gc_btree_init_recurse(struct btree_trans *trans, struct btree *b struct bch_fs *c = trans->c; struct btree_and_journal_iter iter; struct bkey_s_c k; - struct bkey_buf cur, prev; + struct bkey_buf cur; struct printbuf buf = PRINTBUF; int ret = 0; + ret = bch2_btree_node_check_topology(trans, b); + if (ret) + return ret; + bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); - bch2_bkey_buf_init(&prev); bch2_bkey_buf_init(&cur); - bkey_init(&prev.k->k); while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { BUG_ON(bpos_lt(k.k->p, b->data->min_key)); @@ -943,20 +946,7 @@ static int bch2_gc_btree_init_recurse(struct btree_trans *trans, struct btree *b if (ret) goto fsck_err; - if (b->c.level) { - bch2_bkey_buf_reassemble(&cur, c, k); - k = bkey_i_to_s_c(cur.k); - - bch2_btree_and_journal_iter_advance(&iter); - - ret = bch2_gc_check_topology(c, b, - &prev, cur, - !bch2_btree_and_journal_iter_peek(&iter).k); - if (ret) - goto fsck_err; - } else { - bch2_btree_and_journal_iter_advance(&iter); - } + bch2_btree_and_journal_iter_advance(&iter); } if (b->c.level > target_depth) { @@ -1015,7 +1005,6 @@ static int bch2_gc_btree_init_recurse(struct btree_trans *trans, struct btree *b } fsck_err: bch2_bkey_buf_exit(&cur, c); - bch2_bkey_buf_exit(&prev, c); bch2_btree_and_journal_iter_exit(&iter); printbuf_exit(&buf); return ret; @@ -1033,9 +1022,6 @@ static int bch2_gc_btree_init(struct btree_trans *trans, b = bch2_btree_id_root(c, btree_id)->b; - if (btree_node_fake(b)) - return 0; - six_lock_read(&b->c.lock, NULL, NULL); printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->min_key); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 34df8ccc5fec..d7de82ac3893 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -654,6 +654,7 @@ void bch2_btree_node_drop_keys_outside_node(struct btree *b) */ bch2_bset_set_no_aux_tree(b, b->set); bch2_btree_build_aux_trees(b); + b->nr = bch2_btree_node_count_keys(b); struct bkey_s_c k; struct bkey unpacked; @@ -1263,10 +1264,12 @@ out: return retry_read; fsck_err: if (ret == -BCH_ERR_btree_node_read_err_want_retry || - ret == -BCH_ERR_btree_node_read_err_must_retry) + ret == -BCH_ERR_btree_node_read_err_must_retry) { retry_read = 1; - else + } else { set_btree_node_read_error(b); + bch2_btree_lost_data(c, b->c.btree_id); + } goto out; } @@ -1327,6 +1330,7 @@ start: if (!can_retry) { set_btree_node_read_error(b); + bch2_btree_lost_data(c, b->c.btree_id); break; } } @@ -1526,9 +1530,10 @@ fsck_err: ret = -1; } - if (ret) + if (ret) { set_btree_node_read_error(b); - else if (*saw_error) + bch2_btree_lost_data(c, b->c.btree_id); + } else if (*saw_error) bch2_btree_node_rewrite_async(c, b); for (i = 0; i < ra->nr; i++) { @@ -1657,13 +1662,14 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b, prt_str(&buf, "btree node read error: no device to read from\n at "); bch2_btree_pos_to_text(&buf, c, b); - bch_err(c, "%s", buf.buf); + bch_err_ratelimited(c, "%s", buf.buf); if (c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_check_topology) && c->curr_recovery_pass > BCH_RECOVERY_PASS_check_topology) bch2_fatal_error(c); set_btree_node_read_error(b); + bch2_btree_lost_data(c, b->c.btree_id); clear_btree_node_read_in_flight(b); wake_up_bit(&b->flags, BTREE_NODE_read_in_flight); printbuf_exit(&buf); @@ -1860,7 +1866,7 @@ static void btree_node_write_work(struct work_struct *work) } else { ret = bch2_trans_do(c, NULL, NULL, 0, bch2_btree_node_update_key_get_iter(trans, b, &wbio->key, - BCH_WATERMARK_reclaim| + BCH_WATERMARK_interior_updates| BCH_TRANS_COMMIT_journal_reclaim| BCH_TRANS_COMMIT_no_enospc| BCH_TRANS_COMMIT_no_check_rw, diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 51bcdc6c6d1c..2a211a4bebd1 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -927,8 +927,22 @@ static __always_inline int btree_path_down(struct btree_trans *trans, if (ret) goto err; } else { - bch2_bkey_buf_unpack(&tmp, c, l->b, - bch2_btree_node_iter_peek(&l->iter, l->b)); + struct bkey_packed *k = bch2_btree_node_iter_peek(&l->iter, l->b); + if (!k) { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "node not found at pos "); + bch2_bpos_to_text(&buf, path->pos); + prt_str(&buf, " within parent node "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&l->b->key)); + + bch2_fs_fatal_error(c, "%s", buf.buf); + printbuf_exit(&buf); + ret = -BCH_ERR_btree_need_topology_repair; + goto err; + } + + bch2_bkey_buf_unpack(&tmp, c, l->b, k); if ((flags & BTREE_ITER_PREFETCH) && c->opts.btree_node_prefetch) { @@ -962,7 +976,6 @@ err: return ret; } - static int bch2_btree_path_traverse_all(struct btree_trans *trans) { struct bch_fs *c = trans->c; @@ -2790,6 +2803,31 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size) struct btree_transaction_stats *s = btree_trans_stats(trans); s->max_mem = max(s->max_mem, new_bytes); + if (trans->used_mempool) { + if (trans->mem_bytes >= new_bytes) + goto out_change_top; + + /* No more space from mempool item, need malloc new one */ + new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN); + if (unlikely(!new_mem)) { + bch2_trans_unlock(trans); + + new_mem = kmalloc(new_bytes, GFP_KERNEL); + if (!new_mem) + return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); + + ret = bch2_trans_relock(trans); + if (ret) { + kfree(new_mem); + return ERR_PTR(ret); + } + } + memcpy(new_mem, trans->mem, trans->mem_top); + trans->used_mempool = false; + mempool_free(trans->mem, &c->btree_trans_mem_pool); + goto out_new_mem; + } + new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN); if (unlikely(!new_mem)) { bch2_trans_unlock(trans); @@ -2798,6 +2836,8 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size) if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) { new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL); new_bytes = BTREE_TRANS_MEM_MAX; + memcpy(new_mem, trans->mem, trans->mem_top); + trans->used_mempool = true; kfree(trans->mem); } @@ -2811,7 +2851,7 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size) if (ret) return ERR_PTR(ret); } - +out_new_mem: trans->mem = new_mem; trans->mem_bytes = new_bytes; @@ -2819,7 +2859,7 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size) trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes); return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_mem_realloced)); } - +out_change_top: p = trans->mem + trans->mem_top; trans->mem_top += size; memset(p, 0, size); @@ -3093,7 +3133,7 @@ void bch2_trans_put(struct btree_trans *trans) if (paths_allocated != trans->_paths_allocated) kvfree_rcu_mightsleep(paths_allocated); - if (trans->mem_bytes == BTREE_TRANS_MEM_MAX) + if (trans->used_mempool) mempool_free(trans->mem, &c->btree_trans_mem_pool); else kfree(trans->mem); diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c index 50e04356d72c..5cbcbfe85235 100644 --- a/fs/bcachefs/btree_journal_iter.c +++ b/fs/bcachefs/btree_journal_iter.c @@ -261,6 +261,22 @@ int bch2_journal_key_delete(struct bch_fs *c, enum btree_id id, return bch2_journal_key_insert(c, id, level, &whiteout); } +bool bch2_key_deleted_in_journal(struct btree_trans *trans, enum btree_id btree, + unsigned level, struct bpos pos) +{ + struct journal_keys *keys = &trans->c->journal_keys; + size_t idx = bch2_journal_key_search(keys, btree, level, pos); + + if (!trans->journal_replay_not_finished) + return false; + + return (idx < keys->size && + keys->data[idx].btree_id == btree && + keys->data[idx].level == level && + bpos_eq(keys->data[idx].k->k.p, pos) && + bkey_deleted(&keys->data[idx].k->k)); +} + void bch2_journal_key_overwritten(struct bch_fs *c, enum btree_id btree, unsigned level, struct bpos pos) { @@ -363,7 +379,7 @@ static void btree_and_journal_iter_prefetch(struct btree_and_journal_iter *_iter struct bkey_s_c bch2_btree_and_journal_iter_peek(struct btree_and_journal_iter *iter) { - struct bkey_s_c btree_k, journal_k, ret; + struct bkey_s_c btree_k, journal_k = bkey_s_c_null, ret; if (iter->prefetch && iter->journal.level) btree_and_journal_iter_prefetch(iter); @@ -375,9 +391,10 @@ again: bpos_lt(btree_k.k->p, iter->pos)) bch2_journal_iter_advance_btree(iter); - while ((journal_k = bch2_journal_iter_peek(&iter->journal)).k && - bpos_lt(journal_k.k->p, iter->pos)) - bch2_journal_iter_advance(&iter->journal); + if (iter->trans->journal_replay_not_finished) + while ((journal_k = bch2_journal_iter_peek(&iter->journal)).k && + bpos_lt(journal_k.k->p, iter->pos)) + bch2_journal_iter_advance(&iter->journal); ret = journal_k.k && (!btree_k.k || bpos_le(journal_k.k->p, btree_k.k->p)) @@ -435,7 +452,9 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans, bch2_btree_node_iter_init_from_start(&node_iter, b); __bch2_btree_and_journal_iter_init_node_iter(trans, iter, b, node_iter, b->data->min_key); - list_add(&iter->journal.list, &trans->c->journal_iters); + if (trans->journal_replay_not_finished && + !test_bit(BCH_FS_may_go_rw, &trans->c->flags)) + list_add(&iter->journal.list, &trans->c->journal_iters); } /* sort and dedup all keys in the journal: */ @@ -548,3 +567,22 @@ int bch2_journal_keys_sort(struct bch_fs *c) bch_verbose(c, "Journal keys: %zu read, %zu after sorting and compacting", nr_read, keys->nr); return 0; } + +void bch2_shoot_down_journal_keys(struct bch_fs *c, enum btree_id btree, + unsigned level_min, unsigned level_max, + struct bpos start, struct bpos end) +{ + struct journal_keys *keys = &c->journal_keys; + size_t dst = 0; + + move_gap(keys, keys->nr); + + darray_for_each(*keys, i) + if (!(i->btree_id == btree && + i->level >= level_min && + i->level <= level_max && + bpos_ge(i->k->k.p, start) && + bpos_le(i->k->k.p, end))) + keys->data[dst++] = *i; + keys->nr = keys->gap = dst; +} diff --git a/fs/bcachefs/btree_journal_iter.h b/fs/bcachefs/btree_journal_iter.h index c9d19da3ea04..af25046ebcaa 100644 --- a/fs/bcachefs/btree_journal_iter.h +++ b/fs/bcachefs/btree_journal_iter.h @@ -40,8 +40,8 @@ int bch2_journal_key_insert(struct bch_fs *, enum btree_id, unsigned, struct bkey_i *); int bch2_journal_key_delete(struct bch_fs *, enum btree_id, unsigned, struct bpos); -void bch2_journal_key_overwritten(struct bch_fs *, enum btree_id, - unsigned, struct bpos); +bool bch2_key_deleted_in_journal(struct btree_trans *, enum btree_id, unsigned, struct bpos); +void bch2_journal_key_overwritten(struct bch_fs *, enum btree_id, unsigned, struct bpos); void bch2_btree_and_journal_iter_advance(struct btree_and_journal_iter *); struct bkey_s_c bch2_btree_and_journal_iter_peek(struct btree_and_journal_iter *); @@ -66,4 +66,8 @@ void bch2_journal_entries_free(struct bch_fs *); int bch2_journal_keys_sort(struct bch_fs *); +void bch2_shoot_down_journal_keys(struct bch_fs *, enum btree_id, + unsigned, unsigned, + struct bpos, struct bpos); + #endif /* _BCACHEFS_BTREE_JOURNAL_ITER_H */ diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c new file mode 100644 index 000000000000..3f33be7e5e5c --- /dev/null +++ b/fs/bcachefs/btree_node_scan.c @@ -0,0 +1,495 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "bcachefs.h" +#include "btree_cache.h" +#include "btree_io.h" +#include "btree_journal_iter.h" +#include "btree_node_scan.h" +#include "btree_update_interior.h" +#include "buckets.h" +#include "error.h" +#include "journal_io.h" +#include "recovery_passes.h" + +#include <linux/kthread.h> +#include <linux/sort.h> + +struct find_btree_nodes_worker { + struct closure *cl; + struct find_btree_nodes *f; + struct bch_dev *ca; +}; + +static void found_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struct found_btree_node *n) +{ + prt_printf(out, "%s l=%u seq=%u cookie=%llx ", bch2_btree_id_str(n->btree_id), n->level, n->seq, n->cookie); + bch2_bpos_to_text(out, n->min_key); + prt_str(out, "-"); + bch2_bpos_to_text(out, n->max_key); + + if (n->range_updated) + prt_str(out, " range updated"); + if (n->overwritten) + prt_str(out, " overwritten"); + + for (unsigned i = 0; i < n->nr_ptrs; i++) { + prt_char(out, ' '); + bch2_extent_ptr_to_text(out, c, n->ptrs + i); + } +} + +static void found_btree_nodes_to_text(struct printbuf *out, struct bch_fs *c, found_btree_nodes nodes) +{ + printbuf_indent_add(out, 2); + darray_for_each(nodes, i) { + found_btree_node_to_text(out, c, i); + prt_newline(out); + } + printbuf_indent_sub(out, 2); +} + +static void found_btree_node_to_key(struct bkey_i *k, const struct found_btree_node *f) +{ + struct bkey_i_btree_ptr_v2 *bp = bkey_btree_ptr_v2_init(k); + + set_bkey_val_u64s(&bp->k, sizeof(struct bch_btree_ptr_v2) / sizeof(u64) + f->nr_ptrs); + bp->k.p = f->max_key; + bp->v.seq = cpu_to_le64(f->cookie); + bp->v.sectors_written = 0; + bp->v.flags = 0; + bp->v.min_key = f->min_key; + SET_BTREE_PTR_RANGE_UPDATED(&bp->v, f->range_updated); + memcpy(bp->v.start, f->ptrs, sizeof(struct bch_extent_ptr) * f->nr_ptrs); +} + +static bool found_btree_node_is_readable(struct btree_trans *trans, + const struct found_btree_node *f) +{ + struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } k; + + found_btree_node_to_key(&k.k, f); + + struct btree *b = bch2_btree_node_get_noiter(trans, &k.k, f->btree_id, f->level, false); + bool ret = !IS_ERR_OR_NULL(b); + if (ret) + six_unlock_read(&b->c.lock); + + /* + * We might update this node's range; if that happens, we need the node + * to be re-read so the read path can trim keys that are no longer in + * this node + */ + if (b != btree_node_root(trans->c, b)) + bch2_btree_node_evict(trans, &k.k); + return ret; +} + +static int found_btree_node_cmp_cookie(const void *_l, const void *_r) +{ + const struct found_btree_node *l = _l; + const struct found_btree_node *r = _r; + + return cmp_int(l->btree_id, r->btree_id) ?: + cmp_int(l->level, r->level) ?: + cmp_int(l->cookie, r->cookie); +} + +/* + * Given two found btree nodes, if their sequence numbers are equal, take the + * one that's readable: + */ +static int found_btree_node_cmp_time(const struct found_btree_node *l, + const struct found_btree_node *r) +{ + return cmp_int(l->seq, r->seq); +} + +static int found_btree_node_cmp_pos(const void *_l, const void *_r) +{ + const struct found_btree_node *l = _l; + const struct found_btree_node *r = _r; + + return cmp_int(l->btree_id, r->btree_id) ?: + -cmp_int(l->level, r->level) ?: + bpos_cmp(l->min_key, r->min_key) ?: + -found_btree_node_cmp_time(l, r); +} + +static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, + struct bio *bio, struct btree_node *bn, u64 offset) +{ + struct bch_fs *c = container_of(f, struct bch_fs, found_btree_nodes); + + bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ); + bio->bi_iter.bi_sector = offset; + bch2_bio_map(bio, bn, PAGE_SIZE); + + submit_bio_wait(bio); + if (bch2_dev_io_err_on(bio->bi_status, ca, BCH_MEMBER_ERROR_read, + "IO error in try_read_btree_node() at %llu: %s", + offset, bch2_blk_status_to_str(bio->bi_status))) + return; + + if (le64_to_cpu(bn->magic) != bset_magic(c)) + return; + + rcu_read_lock(); + struct found_btree_node n = { + .btree_id = BTREE_NODE_ID(bn), + .level = BTREE_NODE_LEVEL(bn), + .seq = BTREE_NODE_SEQ(bn), + .cookie = le64_to_cpu(bn->keys.seq), + .min_key = bn->min_key, + .max_key = bn->max_key, + .nr_ptrs = 1, + .ptrs[0].type = 1 << BCH_EXTENT_ENTRY_ptr, + .ptrs[0].offset = offset, + .ptrs[0].dev = ca->dev_idx, + .ptrs[0].gen = *bucket_gen(ca, sector_to_bucket(ca, offset)), + }; + rcu_read_unlock(); + + if (bch2_trans_run(c, found_btree_node_is_readable(trans, &n))) { + mutex_lock(&f->lock); + if (BSET_BIG_ENDIAN(&bn->keys) != CPU_BIG_ENDIAN) { + bch_err(c, "try_read_btree_node() can't handle endian conversion"); + f->ret = -EINVAL; + goto unlock; + } + + if (darray_push(&f->nodes, n)) + f->ret = -ENOMEM; +unlock: + mutex_unlock(&f->lock); + } +} + +static int read_btree_nodes_worker(void *p) +{ + struct find_btree_nodes_worker *w = p; + struct bch_fs *c = container_of(w->f, struct bch_fs, found_btree_nodes); + struct bch_dev *ca = w->ca; + void *buf = (void *) __get_free_page(GFP_KERNEL); + struct bio *bio = bio_alloc(NULL, 1, 0, GFP_KERNEL); + unsigned long last_print = jiffies; + + if (!buf || !bio) { + bch_err(c, "read_btree_nodes_worker: error allocating bio/buf"); + w->f->ret = -ENOMEM; + goto err; + } + + for (u64 bucket = ca->mi.first_bucket; bucket < ca->mi.nbuckets; bucket++) + for (unsigned bucket_offset = 0; + bucket_offset + btree_sectors(c) <= ca->mi.bucket_size; + bucket_offset += btree_sectors(c)) { + if (time_after(jiffies, last_print + HZ * 30)) { + u64 cur_sector = bucket * ca->mi.bucket_size + bucket_offset; + u64 end_sector = ca->mi.nbuckets * ca->mi.bucket_size; + + bch_info(ca, "%s: %2u%% done", __func__, + (unsigned) div64_u64(cur_sector * 100, end_sector)); + last_print = jiffies; + } + + try_read_btree_node(w->f, ca, bio, buf, + bucket * ca->mi.bucket_size + bucket_offset); + } +err: + bio_put(bio); + free_page((unsigned long) buf); + percpu_ref_get(&ca->io_ref); + closure_put(w->cl); + kfree(w); + return 0; +} + +static int read_btree_nodes(struct find_btree_nodes *f) +{ + struct bch_fs *c = container_of(f, struct bch_fs, found_btree_nodes); + struct closure cl; + int ret = 0; + + closure_init_stack(&cl); + + for_each_online_member(c, ca) { + struct find_btree_nodes_worker *w = kmalloc(sizeof(*w), GFP_KERNEL); + struct task_struct *t; + + if (!w) { + percpu_ref_put(&ca->io_ref); + ret = -ENOMEM; + goto err; + } + + percpu_ref_get(&ca->io_ref); + closure_get(&cl); + w->cl = &cl; + w->f = f; + w->ca = ca; + + t = kthread_run(read_btree_nodes_worker, w, "read_btree_nodes/%s", ca->name); + ret = IS_ERR_OR_NULL(t); + if (ret) { + percpu_ref_put(&ca->io_ref); + closure_put(&cl); + f->ret = ret; + bch_err(c, "error starting kthread: %i", ret); + break; + } + } +err: + closure_sync(&cl); + return f->ret ?: ret; +} + +static void bubble_up(struct found_btree_node *n, struct found_btree_node *end) +{ + while (n + 1 < end && + found_btree_node_cmp_pos(n, n + 1) > 0) { + swap(n[0], n[1]); + n++; + } +} + +static int handle_overwrites(struct bch_fs *c, + struct found_btree_node *start, + struct found_btree_node *end) +{ + struct found_btree_node *n; +again: + for (n = start + 1; + n < end && + n->btree_id == start->btree_id && + n->level == start->level && + bpos_lt(n->min_key, start->max_key); + n++) { + int cmp = found_btree_node_cmp_time(start, n); + + if (cmp > 0) { + if (bpos_cmp(start->max_key, n->max_key) >= 0) + n->overwritten = true; + else { + n->range_updated = true; + n->min_key = bpos_successor(start->max_key); + n->range_updated = true; + bubble_up(n, end); + goto again; + } + } else if (cmp < 0) { + BUG_ON(bpos_cmp(n->min_key, start->min_key) <= 0); + + start->max_key = bpos_predecessor(n->min_key); + start->range_updated = true; + } else { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "overlapping btree nodes with same seq! halting\n "); + found_btree_node_to_text(&buf, c, start); + prt_str(&buf, "\n "); + found_btree_node_to_text(&buf, c, n); + bch_err(c, "%s", buf.buf); + printbuf_exit(&buf); + return -1; + } + } + + return 0; +} + +int bch2_scan_for_btree_nodes(struct bch_fs *c) +{ + struct find_btree_nodes *f = &c->found_btree_nodes; + struct printbuf buf = PRINTBUF; + size_t dst; + int ret = 0; + + if (f->nodes.nr) + return 0; + + mutex_init(&f->lock); + + ret = read_btree_nodes(f); + if (ret) + return ret; + + if (!f->nodes.nr) { + bch_err(c, "%s: no btree nodes found", __func__); + ret = -EINVAL; + goto err; + } + + if (0 && c->opts.verbose) { + printbuf_reset(&buf); + prt_printf(&buf, "%s: nodes found:\n", __func__); + found_btree_nodes_to_text(&buf, c, f->nodes); + bch2_print_string_as_lines(KERN_INFO, buf.buf); + } + + sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_cookie, NULL); + + dst = 0; + darray_for_each(f->nodes, i) { + struct found_btree_node *prev = dst ? f->nodes.data + dst - 1 : NULL; + + if (prev && + prev->cookie == i->cookie) { + if (prev->nr_ptrs == ARRAY_SIZE(prev->ptrs)) { + bch_err(c, "%s: found too many replicas for btree node", __func__); + ret = -EINVAL; + goto err; + } + prev->ptrs[prev->nr_ptrs++] = i->ptrs[0]; + } else { + f->nodes.data[dst++] = *i; + } + } + f->nodes.nr = dst; + + sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL); + + if (0 && c->opts.verbose) { + printbuf_reset(&buf); + prt_printf(&buf, "%s: nodes after merging replicas:\n", __func__); + found_btree_nodes_to_text(&buf, c, f->nodes); + bch2_print_string_as_lines(KERN_INFO, buf.buf); + } + + dst = 0; + darray_for_each(f->nodes, i) { + if (i->overwritten) + continue; + + ret = handle_overwrites(c, i, &darray_top(f->nodes)); + if (ret) + goto err; + + BUG_ON(i->overwritten); + f->nodes.data[dst++] = *i; + } + f->nodes.nr = dst; + + if (c->opts.verbose) { + printbuf_reset(&buf); + prt_printf(&buf, "%s: nodes found after overwrites:\n", __func__); + found_btree_nodes_to_text(&buf, c, f->nodes); + bch2_print_string_as_lines(KERN_INFO, buf.buf); + } + + eytzinger0_sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL); +err: + printbuf_exit(&buf); + return ret; +} + +static int found_btree_node_range_start_cmp(const void *_l, const void *_r) +{ + const struct found_btree_node *l = _l; + const struct found_btree_node *r = _r; + + return cmp_int(l->btree_id, r->btree_id) ?: + -cmp_int(l->level, r->level) ?: + bpos_cmp(l->max_key, r->min_key); +} + +#define for_each_found_btree_node_in_range(_f, _search, _idx) \ + for (size_t _idx = eytzinger0_find_gt((_f)->nodes.data, (_f)->nodes.nr, \ + sizeof((_f)->nodes.data[0]), \ + found_btree_node_range_start_cmp, &search); \ + _idx < (_f)->nodes.nr && \ + (_f)->nodes.data[_idx].btree_id == _search.btree_id && \ + (_f)->nodes.data[_idx].level == _search.level && \ + bpos_lt((_f)->nodes.data[_idx].min_key, _search.max_key); \ + _idx = eytzinger0_next(_idx, (_f)->nodes.nr)) + +bool bch2_btree_node_is_stale(struct bch_fs *c, struct btree *b) +{ + struct find_btree_nodes *f = &c->found_btree_nodes; + + struct found_btree_node search = { + .btree_id = b->c.btree_id, + .level = b->c.level, + .min_key = b->data->min_key, + .max_key = b->key.k.p, + }; + + for_each_found_btree_node_in_range(f, search, idx) + if (f->nodes.data[idx].seq > BTREE_NODE_SEQ(b->data)) + return true; + return false; +} + +bool bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree) +{ + struct found_btree_node search = { + .btree_id = btree, + .level = 0, + .min_key = POS_MIN, + .max_key = SPOS_MAX, + }; + + for_each_found_btree_node_in_range(&c->found_btree_nodes, search, idx) + return true; + return false; +} + +int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree, + unsigned level, struct bpos node_min, struct bpos node_max) +{ + struct find_btree_nodes *f = &c->found_btree_nodes; + + int ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); + if (ret) + return ret; + + if (c->opts.verbose) { + struct printbuf buf = PRINTBUF; + + prt_printf(&buf, "recovering %s l=%u ", bch2_btree_id_str(btree), level); + bch2_bpos_to_text(&buf, node_min); + prt_str(&buf, " - "); + bch2_bpos_to_text(&buf, node_max); + + bch_info(c, "%s(): %s", __func__, buf.buf); + printbuf_exit(&buf); + } + + struct found_btree_node search = { + .btree_id = btree, + .level = level, + .min_key = node_min, + .max_key = node_max, + }; + + for_each_found_btree_node_in_range(f, search, idx) { + struct found_btree_node n = f->nodes.data[idx]; + + n.range_updated |= bpos_lt(n.min_key, node_min); + n.min_key = bpos_max(n.min_key, node_min); + + n.range_updated |= bpos_gt(n.max_key, node_max); + n.max_key = bpos_min(n.max_key, node_max); + + struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } tmp; + + found_btree_node_to_key(&tmp.k, &n); + + struct printbuf buf = PRINTBUF; + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&tmp.k)); + bch_verbose(c, "%s(): recovering %s", __func__, buf.buf); + printbuf_exit(&buf); + + BUG_ON(bch2_bkey_invalid(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0, NULL)); + + ret = bch2_journal_key_insert(c, btree, level + 1, &tmp.k); + if (ret) + return ret; + } + + return 0; +} + +void bch2_find_btree_nodes_exit(struct find_btree_nodes *f) +{ + darray_exit(&f->nodes); +} diff --git a/fs/bcachefs/btree_node_scan.h b/fs/bcachefs/btree_node_scan.h new file mode 100644 index 000000000000..08687b209787 --- /dev/null +++ b/fs/bcachefs/btree_node_scan.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_BTREE_NODE_SCAN_H +#define _BCACHEFS_BTREE_NODE_SCAN_H + +int bch2_scan_for_btree_nodes(struct bch_fs *); +bool bch2_btree_node_is_stale(struct bch_fs *, struct btree *); +bool bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id); +int bch2_get_scanned_nodes(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos); +void bch2_find_btree_nodes_exit(struct find_btree_nodes *); + +#endif /* _BCACHEFS_BTREE_NODE_SCAN_H */ diff --git a/fs/bcachefs/btree_node_scan_types.h b/fs/bcachefs/btree_node_scan_types.h new file mode 100644 index 000000000000..abb7b27d556a --- /dev/null +++ b/fs/bcachefs/btree_node_scan_types.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_BTREE_NODE_SCAN_TYPES_H +#define _BCACHEFS_BTREE_NODE_SCAN_TYPES_H + +#include "darray.h" + +struct found_btree_node { + bool range_updated:1; + bool overwritten:1; + u8 btree_id; + u8 level; + u32 seq; + u64 cookie; + + struct bpos min_key; + struct bpos max_key; + + unsigned nr_ptrs; + struct bch_extent_ptr ptrs[BCH_REPLICAS_MAX]; +}; + +typedef DARRAY(struct found_btree_node) found_btree_nodes; + +struct find_btree_nodes { + int ret; + struct mutex lock; + found_btree_nodes nodes; +}; + +#endif /* _BCACHEFS_BTREE_NODE_SCAN_TYPES_H */ diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index 30d69a6d133e..aa9da4970740 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -318,7 +318,7 @@ static inline void btree_insert_entry_checks(struct btree_trans *trans, !(i->flags & BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) && test_bit(JOURNAL_REPLAY_DONE, &trans->c->journal.flags) && i->k->k.p.snapshot && - bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot)); + bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot) > 0); } static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans, @@ -887,6 +887,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, int ret, unsigned long trace_ip) { struct bch_fs *c = trans->c; + enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; switch (ret) { case -BCH_ERR_btree_insert_btree_node_full: @@ -905,7 +906,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags, * flag */ if ((flags & BCH_TRANS_COMMIT_journal_reclaim) && - (flags & BCH_WATERMARK_MASK) != BCH_WATERMARK_reclaim) { + watermark < BCH_WATERMARK_reclaim) { ret = -BCH_ERR_journal_reclaim_would_deadlock; break; } diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index a4b40c1656a5..8e47e260eba5 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -38,6 +38,9 @@ static noinline int extent_front_merge(struct btree_trans *trans, struct bkey_i *update; int ret; + if (unlikely(trans->journal_replay_not_finished)) + return 0; + update = bch2_bkey_make_mut_noupdate(trans, k); ret = PTR_ERR_OR_ZERO(update); if (ret) @@ -69,6 +72,9 @@ static noinline int extent_back_merge(struct btree_trans *trans, struct bch_fs *c = trans->c; int ret; + if (unlikely(trans->journal_replay_not_finished)) + return 0; + ret = bch2_key_has_snapshot_overwrites(trans, iter->btree_id, insert->k.p) ?: bch2_key_has_snapshot_overwrites(trans, iter->btree_id, k.k->p); if (ret < 0) diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index b2f5f2e50f7e..32397b99752f 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -2,6 +2,7 @@ #include "bcachefs.h" #include "alloc_foreground.h" +#include "bkey_buf.h" #include "bkey_methods.h" #include "btree_cache.h" #include "btree_gc.h" @@ -18,12 +19,20 @@ #include "journal.h" #include "journal_reclaim.h" #include "keylist.h" +#include "recovery_passes.h" #include "replicas.h" #include "super-io.h" #include "trace.h" #include <linux/random.h> +const char * const bch2_btree_update_modes[] = { +#define x(t) #t, + BCH_WATERMARKS() +#undef x + NULL +}; + static int bch2_btree_insert_node(struct btree_update *, struct btree_trans *, btree_path_idx_t, struct btree *, struct keylist *); static void bch2_btree_update_add_new_node(struct btree_update *, struct btree *); @@ -44,56 +53,103 @@ static btree_path_idx_t get_unlocked_mut_path(struct btree_trans *trans, return path_idx; } -/* Debug code: */ - /* * Verify that child nodes correctly span parent node's range: */ -static void btree_node_interior_verify(struct bch_fs *c, struct btree *b) +int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) { -#ifdef CONFIG_BCACHEFS_DEBUG - struct bpos next_node = b->data->min_key; - struct btree_node_iter iter; + struct bch_fs *c = trans->c; + struct bpos node_min = b->key.k.type == KEY_TYPE_btree_ptr_v2 + ? bkey_i_to_btree_ptr_v2(&b->key)->v.min_key + : b->data->min_key; + struct btree_and_journal_iter iter; struct bkey_s_c k; - struct bkey_s_c_btree_ptr_v2 bp; - struct bkey unpacked; - struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; + struct printbuf buf = PRINTBUF; + struct bkey_buf prev; + int ret = 0; - BUG_ON(!b->c.level); + BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 && + !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key, + b->data->min_key)); - if (!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) - return; + if (!b->c.level) + return 0; - bch2_btree_node_iter_init_from_start(&iter, b); + bch2_bkey_buf_init(&prev); + bkey_init(&prev.k->k); + bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); - while (1) { - k = bch2_btree_node_iter_peek_unpack(&iter, b, &unpacked); + while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { if (k.k->type != KEY_TYPE_btree_ptr_v2) - break; - bp = bkey_s_c_to_btree_ptr_v2(k); + goto out; - if (!bpos_eq(next_node, bp.v->min_key)) { - bch2_dump_btree_node(c, b); - bch2_bpos_to_text(&buf1, next_node); - bch2_bpos_to_text(&buf2, bp.v->min_key); - panic("expected next min_key %s got %s\n", buf1.buf, buf2.buf); - } + struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k); - bch2_btree_node_iter_advance(&iter, b); + struct bpos expected_min = bkey_deleted(&prev.k->k) + ? node_min + : bpos_successor(prev.k->k.p); - if (bch2_btree_node_iter_end(&iter)) { - if (!bpos_eq(k.k->p, b->key.k.p)) { - bch2_dump_btree_node(c, b); - bch2_bpos_to_text(&buf1, b->key.k.p); - bch2_bpos_to_text(&buf2, k.k->p); - panic("expected end %s got %s\n", buf1.buf, buf2.buf); - } - break; + if (!bpos_eq(expected_min, bp.v->min_key)) { + bch2_topology_error(c); + + printbuf_reset(&buf); + prt_str(&buf, "end of prev node doesn't match start of next node\n"), + prt_printf(&buf, " in btree %s level %u node ", + bch2_btree_id_str(b->c.btree_id), b->c.level); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + prt_str(&buf, "\n prev "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); + prt_str(&buf, "\n next "); + bch2_bkey_val_to_text(&buf, c, k); + + need_fsck_err(c, btree_node_topology_bad_min_key, "%s", buf.buf); + goto topology_repair; } - next_node = bpos_successor(k.k->p); + bch2_bkey_buf_reassemble(&prev, c, k); + bch2_btree_and_journal_iter_advance(&iter); + } + + if (bkey_deleted(&prev.k->k)) { + bch2_topology_error(c); + + printbuf_reset(&buf); + prt_str(&buf, "empty interior node\n"); + prt_printf(&buf, " in btree %s level %u node ", + bch2_btree_id_str(b->c.btree_id), b->c.level); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + + need_fsck_err(c, btree_node_topology_empty_interior_node, "%s", buf.buf); + goto topology_repair; + } else if (!bpos_eq(prev.k->k.p, b->key.k.p)) { + bch2_topology_error(c); + + printbuf_reset(&buf); + prt_str(&buf, "last child node doesn't end at end of parent node\n"); + prt_printf(&buf, " in btree %s level %u node ", + bch2_btree_id_str(b->c.btree_id), b->c.level); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); + prt_str(&buf, "\n last key "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); + + need_fsck_err(c, btree_node_topology_bad_max_key, "%s", buf.buf); + goto topology_repair; } -#endif +out: +fsck_err: + bch2_btree_and_journal_iter_exit(&iter); + bch2_bkey_buf_exit(&prev, c); + printbuf_exit(&buf); + return ret; +topology_repair: + if ((c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_check_topology)) && + c->curr_recovery_pass > BCH_RECOVERY_PASS_check_topology) { + bch2_inconsistent_error(c); + ret = -BCH_ERR_btree_need_topology_repair; + } else { + ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology); + } + goto out; } /* Calculate ideal packed bkey format for new btree nodes: */ @@ -254,7 +310,7 @@ static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans, struct open_buckets obs = { .nr = 0 }; struct bch_devs_list devs_have = (struct bch_devs_list) { 0 }; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; - unsigned nr_reserve = watermark > BCH_WATERMARK_reclaim + unsigned nr_reserve = watermark < BCH_WATERMARK_reclaim ? BTREE_NODE_RESERVE : 0; int ret; @@ -638,7 +694,7 @@ static void btree_update_nodes_written(struct btree_update *as) * which may require allocations as well. */ ret = commit_do(trans, &as->disk_res, &journal_seq, - BCH_WATERMARK_reclaim| + BCH_WATERMARK_interior_updates| BCH_TRANS_COMMIT_no_enospc| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_journal_reclaim, @@ -797,11 +853,11 @@ static void btree_update_updated_node(struct btree_update *as, struct btree *b) mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); - BUG_ON(as->mode != BTREE_INTERIOR_NO_UPDATE); + BUG_ON(as->mode != BTREE_UPDATE_none); BUG_ON(!btree_node_dirty(b)); BUG_ON(!b->c.level); - as->mode = BTREE_INTERIOR_UPDATING_NODE; + as->mode = BTREE_UPDATE_node; as->b = b; set_btree_node_write_blocked(b); @@ -824,7 +880,7 @@ static void btree_update_reparent(struct btree_update *as, lockdep_assert_held(&c->btree_interior_update_lock); child->b = NULL; - child->mode = BTREE_INTERIOR_UPDATING_AS; + child->mode = BTREE_UPDATE_update; bch2_journal_pin_copy(&c->journal, &as->journal, &child->journal, bch2_update_reparent_journal_pin_flush); @@ -835,7 +891,7 @@ static void btree_update_updated_root(struct btree_update *as, struct btree *b) struct bkey_i *insert = &b->key; struct bch_fs *c = as->c; - BUG_ON(as->mode != BTREE_INTERIOR_NO_UPDATE); + BUG_ON(as->mode != BTREE_UPDATE_none); BUG_ON(as->journal_u64s + jset_u64s(insert->k.u64s) > ARRAY_SIZE(as->journal_entries)); @@ -849,7 +905,7 @@ static void btree_update_updated_root(struct btree_update *as, struct btree *b) mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); - as->mode = BTREE_INTERIOR_UPDATING_ROOT; + as->mode = BTREE_UPDATE_root; mutex_unlock(&c->btree_interior_update_lock); } @@ -1027,7 +1083,7 @@ static void bch2_btree_update_done(struct btree_update *as, struct btree_trans * struct bch_fs *c = as->c; u64 start_time = as->start_time; - BUG_ON(as->mode == BTREE_INTERIOR_NO_UPDATE); + BUG_ON(as->mode == BTREE_UPDATE_none); if (as->took_gc_lock) up_read(&as->c->gc_lock); @@ -1072,7 +1128,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, unsigned journal_flags = watermark|JOURNAL_RES_GET_CHECK; if ((flags & BCH_TRANS_COMMIT_journal_reclaim) && - watermark != BCH_WATERMARK_reclaim) + watermark < BCH_WATERMARK_reclaim) journal_flags |= JOURNAL_RES_GET_NONBLOCK; ret = drop_locks_do(trans, @@ -1123,7 +1179,8 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, as->c = c; as->start_time = start_time; as->ip_started = _RET_IP_; - as->mode = BTREE_INTERIOR_NO_UPDATE; + as->mode = BTREE_UPDATE_none; + as->watermark = watermark; as->took_gc_lock = true; as->btree_id = path->btree_id; as->update_level = update_level; @@ -1168,7 +1225,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, */ if (bch2_err_matches(ret, ENOSPC) && (flags & BCH_TRANS_COMMIT_journal_reclaim) && - watermark != BCH_WATERMARK_reclaim) { + watermark < BCH_WATERMARK_reclaim) { ret = -BCH_ERR_journal_reclaim_would_deadlock; goto err; } @@ -1380,9 +1437,16 @@ static void __btree_split_node(struct btree_update *as, if (bkey_deleted(k)) continue; + uk = bkey_unpack_key(b, k); + + if (b->c.level && + u64s < n1_u64s && + u64s + k->u64s >= n1_u64s && + bch2_key_deleted_in_journal(trans, b->c.btree_id, b->c.level, uk.p)) + n1_u64s += k->u64s; + i = u64s >= n1_u64s; u64s += k->u64s; - uk = bkey_unpack_key(b, k); if (!i) n1_pos = uk.p; bch2_bkey_format_add_key(&format[i], &uk); @@ -1441,8 +1505,7 @@ static void __btree_split_node(struct btree_update *as, bch2_verify_btree_nr_keys(n[i]); - if (b->c.level) - btree_node_interior_verify(as->c, n[i]); + BUG_ON(bch2_btree_node_check_topology(trans, n[i])); } } @@ -1473,7 +1536,7 @@ static void btree_split_insert_keys(struct btree_update *as, __bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys); - btree_node_interior_verify(as->c, b); + BUG_ON(bch2_btree_node_check_topology(trans, b)); } } @@ -1488,9 +1551,14 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans, u64 start_time = local_clock(); int ret = 0; + bch2_verify_btree_nr_keys(b); BUG_ON(!parent && (b != btree_node_root(c, b))); BUG_ON(parent && !btree_node_intent_locked(trans->paths + path, b->c.level + 1)); + ret = bch2_btree_node_check_topology(trans, b); + if (ret) + return ret; + bch2_btree_interior_update_will_free_node(as, b); if (b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c)) { @@ -1710,7 +1778,11 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t goto split; } - btree_node_interior_verify(c, b); + ret = bch2_btree_node_check_topology(trans, b); + if (ret) { + bch2_btree_node_unlock_write(trans, path, b); + return ret; + } bch2_btree_insert_keys_interior(as, trans, path, b, keys); @@ -1728,7 +1800,7 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t bch2_btree_node_unlock_write(trans, path, b); - btree_node_interior_verify(c, b); + BUG_ON(bch2_btree_node_check_topology(trans, b)); return 0; split: /* @@ -1818,9 +1890,12 @@ int bch2_btree_increase_depth(struct btree_trans *trans, btree_path_idx_t path, { struct bch_fs *c = trans->c; struct btree *b = bch2_btree_id_root(c, trans->paths[path].btree_id)->b; + + if (btree_node_fake(b)) + return bch2_btree_split_leaf(trans, path, flags); + struct btree_update *as = - bch2_btree_update_start(trans, trans->paths + path, - b->c.level, true, flags); + bch2_btree_update_start(trans, trans->paths + path, b->c.level, true, flags); if (IS_ERR(as)) return PTR_ERR(as); @@ -2391,7 +2466,7 @@ void bch2_btree_set_root_for_read(struct bch_fs *c, struct btree *b) bch2_btree_set_root_inmem(c, b); } -static int __bch2_btree_root_alloc(struct btree_trans *trans, enum btree_id id) +static int __bch2_btree_root_alloc_fake(struct btree_trans *trans, enum btree_id id, unsigned level) { struct bch_fs *c = trans->c; struct closure cl; @@ -2410,7 +2485,7 @@ static int __bch2_btree_root_alloc(struct btree_trans *trans, enum btree_id id) set_btree_node_fake(b); set_btree_node_need_rewrite(b); - b->c.level = 0; + b->c.level = level; b->c.btree_id = id; bkey_btree_ptr_init(&b->key); @@ -2437,9 +2512,21 @@ static int __bch2_btree_root_alloc(struct btree_trans *trans, enum btree_id id) return 0; } -void bch2_btree_root_alloc(struct bch_fs *c, enum btree_id id) +void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned level) +{ + bch2_trans_run(c, __bch2_btree_root_alloc_fake(trans, id, level)); +} + +static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as) { - bch2_trans_run(c, __bch2_btree_root_alloc(trans, id)); + prt_printf(out, "%ps: btree=%s watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", + (void *) as->ip_started, + bch2_btree_id_str(as->btree_id), + bch2_watermarks[as->watermark], + bch2_btree_update_modes[as->mode], + as->nodes_written, + closure_nr_remaining(&as->cl), + as->journal.seq); } void bch2_btree_updates_to_text(struct printbuf *out, struct bch_fs *c) @@ -2448,12 +2535,7 @@ void bch2_btree_updates_to_text(struct printbuf *out, struct bch_fs *c) mutex_lock(&c->btree_interior_update_lock); list_for_each_entry(as, &c->btree_interior_update_list, list) - prt_printf(out, "%ps: mode=%u nodes_written=%u cl.remaining=%u journal_seq=%llu\n", - (void *) as->ip_started, - as->mode, - as->nodes_written, - closure_nr_remaining(&as->cl), - as->journal.seq); + bch2_btree_update_to_text(out, as); mutex_unlock(&c->btree_interior_update_lock); } diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index f651dd48aaa0..88dcf5a22a3b 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -10,6 +10,20 @@ #define BTREE_UPDATE_JOURNAL_RES (BTREE_UPDATE_NODES_MAX * (BKEY_BTREE_PTR_U64s_MAX + 1)) +int bch2_btree_node_check_topology(struct btree_trans *, struct btree *); + +#define BTREE_UPDATE_MODES() \ + x(none) \ + x(node) \ + x(root) \ + x(update) + +enum btree_update_mode { +#define x(n) BTREE_UPDATE_##n, + BTREE_UPDATE_MODES() +#undef x +}; + /* * Tracks an in progress split/rewrite of a btree node and the update to the * parent node: @@ -37,14 +51,8 @@ struct btree_update { struct list_head list; struct list_head unwritten_list; - /* What kind of update are we doing? */ - enum { - BTREE_INTERIOR_NO_UPDATE, - BTREE_INTERIOR_UPDATING_NODE, - BTREE_INTERIOR_UPDATING_ROOT, - BTREE_INTERIOR_UPDATING_AS, - } mode; - + enum btree_update_mode mode; + enum bch_watermark watermark; unsigned nodes_written:1; unsigned took_gc_lock:1; @@ -54,7 +62,7 @@ struct btree_update { struct disk_reservation disk_res; /* - * BTREE_INTERIOR_UPDATING_NODE: + * BTREE_UPDATE_node: * The update that made the new nodes visible was a regular update to an * existing interior node - @b. We can't write out the update to @b * until the new nodes we created are finished writing, so we block @b @@ -163,7 +171,7 @@ int bch2_btree_node_update_key_get_iter(struct btree_trans *, struct btree *, struct bkey_i *, unsigned, bool); void bch2_btree_set_root_for_read(struct bch_fs *, struct btree *); -void bch2_btree_root_alloc(struct bch_fs *, enum btree_id); +void bch2_btree_root_alloc_fake(struct bch_fs *, enum btree_id, unsigned); static inline unsigned btree_update_reserve_required(struct bch_fs *c, struct btree *b) diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index 5cbad8445782..baf63e2fddb6 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -11,6 +11,7 @@ #include "journal_reclaim.h" #include <linux/prefetch.h> +#include <linux/sort.h> static int bch2_btree_write_buffer_journal_flush(struct journal *, struct journal_entry_pin *, u64); @@ -46,6 +47,14 @@ static inline bool wb_key_ref_cmp(const struct wb_key_ref *l, const struct wb_ke #endif } +static int wb_key_seq_cmp(const void *_l, const void *_r) +{ + const struct btree_write_buffered_key *l = _l; + const struct btree_write_buffered_key *r = _r; + + return cmp_int(l->journal_seq, r->journal_seq); +} + /* Compare excluding idx, the low 24 bits: */ static inline bool wb_key_eq(const void *_l, const void *_r) { @@ -357,6 +366,11 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) */ trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, wb->flushing.keys.nr); + sort(wb->flushing.keys.data, + wb->flushing.keys.nr, + sizeof(wb->flushing.keys.data[0]), + wb_key_seq_cmp, NULL); + darray_for_each(wb->flushing.keys, i) { if (!i->journal_seq) continue; diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index 96edf2c34d43..941401a210f5 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -525,6 +525,7 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca, "different types of data in same bucket: %s, %s", bch2_data_type_str(g->data_type), bch2_data_type_str(data_type))) { + BUG(); ret = -EIO; goto err; } @@ -628,6 +629,7 @@ int bch2_check_bucket_ref(struct btree_trans *trans, bch2_data_type_str(ptr_data_type), (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf)); + BUG(); ret = -EIO; goto err; } @@ -815,14 +817,14 @@ static int __mark_pointer(struct btree_trans *trans, static int bch2_trigger_pointer(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bkey_s_c k, struct extent_ptr_decoded p, - s64 *sectors, - unsigned flags) + const union bch_extent_entry *entry, + s64 *sectors, unsigned flags) { bool insert = !(flags & BTREE_TRIGGER_OVERWRITE); struct bpos bucket; struct bch_backpointer bp; - bch2_extent_ptr_to_bp(trans->c, btree_id, level, k, p, &bucket, &bp); + bch2_extent_ptr_to_bp(trans->c, btree_id, level, k, p, entry, &bucket, &bp); *sectors = insert ? bp.bucket_len : -((s64) bp.bucket_len); if (flags & BTREE_TRIGGER_TRANSACTIONAL) { @@ -851,7 +853,7 @@ static int bch2_trigger_pointer(struct btree_trans *trans, if (flags & BTREE_TRIGGER_GC) { struct bch_fs *c = trans->c; struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev); - enum bch_data_type data_type = bkey_ptr_data_type(btree_id, level, k, p); + enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry); percpu_down_read(&c->mark_lock); struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr); @@ -979,7 +981,7 @@ static int __trigger_extent(struct btree_trans *trans, bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { s64 disk_sectors; - ret = bch2_trigger_pointer(trans, btree_id, level, k, p, &disk_sectors, flags); + ret = bch2_trigger_pointer(trans, btree_id, level, k, p, entry, &disk_sectors, flags); if (ret < 0) return ret; diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index 6387e039f789..00aaf4bb5139 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -226,6 +226,7 @@ static inline u64 bch2_dev_buckets_reserved(struct bch_dev *ca, enum bch_waterma fallthrough; case BCH_WATERMARK_btree_copygc: case BCH_WATERMARK_reclaim: + case BCH_WATERMARK_interior_updates: break; } diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index 38defa19d52d..cbfa6459bdbc 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -7,7 +7,7 @@ #include "chardev.h" #include "journal.h" #include "move.h" -#include "recovery.h" +#include "recovery_passes.h" #include "replicas.h" #include "super.h" #include "super-io.h" diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 4150feca42a2..34731ee0217f 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -14,6 +14,7 @@ #include "move.h" #include "nocow_locking.h" #include "rebalance.h" +#include "snapshot.h" #include "subvolume.h" #include "trace.h" @@ -509,6 +510,14 @@ int bch2_data_update_init(struct btree_trans *trans, unsigned ptrs_locked = 0; int ret = 0; + /* + * fs is corrupt we have a key for a snapshot node that doesn't exist, + * and we have to check for this because we go rw before repairing the + * snapshots table - just skip it, we can move it later. + */ + if (unlikely(k.k->p.snapshot && !bch2_snapshot_equiv(c, k.k->p.snapshot))) + return -BCH_ERR_data_update_done; + bch2_bkey_buf_init(&m->k); bch2_bkey_buf_reassemble(&m->k, c, k); m->btree_id = btree_id; @@ -571,8 +580,7 @@ int bch2_data_update_init(struct btree_trans *trans, move_ctxt_wait_event(ctxt, (locked = bch2_bucket_nocow_trylock(&c->nocow_locks, PTR_BUCKET_POS(c, &p.ptr), 0)) || - (!atomic_read(&ctxt->read_sectors) && - !atomic_read(&ctxt->write_sectors))); + list_empty(&ctxt->ios)); if (!locked) bch2_bucket_nocow_lock(&c->nocow_locks, diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index af25d8ec60f2..01a79fa3eacb 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -252,7 +252,8 @@ x(BCH_ERR_nopromote, nopromote_in_flight) \ x(BCH_ERR_nopromote, nopromote_no_writes) \ x(BCH_ERR_nopromote, nopromote_enomem) \ - x(0, need_inode_lock) + x(0, need_inode_lock) \ + x(0, invalid_snapshot_node) enum bch_errcode { BCH_ERR_START = 2048, diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index 043431206799..82a6656c941c 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "error.h" -#include "recovery.h" +#include "journal.h" +#include "recovery_passes.h" #include "super.h" #include "thread_with_file.h" @@ -16,7 +17,8 @@ bool bch2_inconsistent_error(struct bch_fs *c) return false; case BCH_ON_ERROR_ro: if (bch2_fs_emergency_read_only(c)) - bch_err(c, "inconsistency detected - emergency read only"); + bch_err(c, "inconsistency detected - emergency read only at journal seq %llu", + journal_cur_seq(&c->journal)); return true; case BCH_ON_ERROR_panic: panic(bch2_fmt(c, "panic after error")); diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index ae1d6674c512..36caedf72d89 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -32,6 +32,12 @@ bool bch2_inconsistent_error(struct bch_fs *); int bch2_topology_error(struct bch_fs *); +#define bch2_fs_topology_error(c, ...) \ +({ \ + bch_err(c, "btree topology error: " __VA_ARGS__); \ + bch2_topology_error(c); \ +}) + #define bch2_fs_inconsistent(c, ...) \ ({ \ bch_err(c, __VA_ARGS__); \ diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 61395b113df9..0e3ca99fbd2d 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -189,13 +189,18 @@ int bch2_btree_ptr_v2_invalid(struct bch_fs *c, struct bkey_s_c k, enum bkey_invalid_flags flags, struct printbuf *err) { + struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k); int ret = 0; - bkey_fsck_err_on(bkey_val_u64s(k.k) > BKEY_BTREE_PTR_VAL_U64s_MAX, c, err, - btree_ptr_v2_val_too_big, + bkey_fsck_err_on(bkey_val_u64s(k.k) > BKEY_BTREE_PTR_VAL_U64s_MAX, + c, err, btree_ptr_v2_val_too_big, "value too big (%zu > %zu)", bkey_val_u64s(k.k), BKEY_BTREE_PTR_VAL_U64s_MAX); + bkey_fsck_err_on(bpos_ge(bp.v->min_key, bp.k->p), + c, err, btree_ptr_v2_min_key_bad, + "min_key > key"); + ret = bch2_bkey_ptrs_invalid(c, k, flags, err); fsck_err: return ret; @@ -973,6 +978,31 @@ bool bch2_extent_normalize(struct bch_fs *c, struct bkey_s k) return bkey_deleted(k.k); } +void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struct bch_extent_ptr *ptr) +{ + struct bch_dev *ca = c && ptr->dev < c->sb.nr_devices && c->devs[ptr->dev] + ? bch_dev_bkey_exists(c, ptr->dev) + : NULL; + + if (!ca) { + prt_printf(out, "ptr: %u:%llu gen %u%s", ptr->dev, + (u64) ptr->offset, ptr->gen, + ptr->cached ? " cached" : ""); + } else { + u32 offset; + u64 b = sector_to_bucket_and_offset(ca, ptr->offset, &offset); + + prt_printf(out, "ptr: %u:%llu:%u gen %u", + ptr->dev, b, offset, ptr->gen); + if (ptr->cached) + prt_str(out, " cached"); + if (ptr->unwritten) + prt_str(out, " unwritten"); + if (ca && ptr_stale(ca, ptr)) + prt_printf(out, " stale"); + } +} + void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { @@ -988,31 +1018,10 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, prt_printf(out, " "); switch (__extent_entry_type(entry)) { - case BCH_EXTENT_ENTRY_ptr: { - const struct bch_extent_ptr *ptr = entry_to_ptr(entry); - struct bch_dev *ca = c && ptr->dev < c->sb.nr_devices && c->devs[ptr->dev] - ? bch_dev_bkey_exists(c, ptr->dev) - : NULL; - - if (!ca) { - prt_printf(out, "ptr: %u:%llu gen %u%s", ptr->dev, - (u64) ptr->offset, ptr->gen, - ptr->cached ? " cached" : ""); - } else { - u32 offset; - u64 b = sector_to_bucket_and_offset(ca, ptr->offset, &offset); - - prt_printf(out, "ptr: %u:%llu:%u gen %u", - ptr->dev, b, offset, ptr->gen); - if (ptr->cached) - prt_str(out, " cached"); - if (ptr->unwritten) - prt_str(out, " unwritten"); - if (ca && ptr_stale(ca, ptr)) - prt_printf(out, " stale"); - } + case BCH_EXTENT_ENTRY_ptr: + bch2_extent_ptr_to_text(out, c, entry_to_ptr(entry)); break; - } + case BCH_EXTENT_ENTRY_crc32: case BCH_EXTENT_ENTRY_crc64: case BCH_EXTENT_ENTRY_crc128: { diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index fd2669cdd76f..528e817eacbd 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -596,30 +596,6 @@ static inline struct bch_devs_list bch2_bkey_cached_devs(struct bkey_s_c k) return ret; } -static inline unsigned bch2_bkey_ptr_data_type(struct bkey_s_c k, const struct bch_extent_ptr *ptr) -{ - switch (k.k->type) { - case KEY_TYPE_btree_ptr: - case KEY_TYPE_btree_ptr_v2: - return BCH_DATA_btree; - case KEY_TYPE_extent: - case KEY_TYPE_reflink_v: - return BCH_DATA_user; - case KEY_TYPE_stripe: { - struct bkey_s_c_stripe s = bkey_s_c_to_stripe(k); - - BUG_ON(ptr < s.v->ptrs || - ptr >= s.v->ptrs + s.v->nr_blocks); - - return ptr >= s.v->ptrs + s.v->nr_blocks - s.v->nr_redundant - ? BCH_DATA_parity - : BCH_DATA_user; - } - default: - BUG(); - } -} - unsigned bch2_bkey_nr_ptrs(struct bkey_s_c); unsigned bch2_bkey_nr_ptrs_allocated(struct bkey_s_c); unsigned bch2_bkey_nr_ptrs_fully_allocated(struct bkey_s_c); @@ -700,6 +676,7 @@ bch2_extent_has_ptr(struct bkey_s_c, struct extent_ptr_decoded, struct bkey_s); void bch2_extent_ptr_set_cached(struct bkey_s, struct bch_extent_ptr *); bool bch2_extent_normalize(struct bch_fs *, struct bkey_s); +void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *); void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_bkey_ptrs_invalid(struct bch_fs *, struct bkey_s_c, diff --git a/fs/bcachefs/eytzinger.c b/fs/bcachefs/eytzinger.c new file mode 100644 index 000000000000..4ce5e957a6e9 --- /dev/null +++ b/fs/bcachefs/eytzinger.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "eytzinger.h" + +/** + * is_aligned - is this pointer & size okay for word-wide copying? + * @base: pointer to data + * @size: size of each element + * @align: required alignment (typically 4 or 8) + * + * Returns true if elements can be copied using word loads and stores. + * The size must be a multiple of the alignment, and the base address must + * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. + * + * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" + * to "if ((a | b) & mask)", so we do that by hand. + */ +__attribute_const__ __always_inline +static bool is_aligned(const void *base, size_t size, unsigned char align) +{ + unsigned char lsbits = (unsigned char)size; + + (void)base; +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + lsbits |= (unsigned char)(uintptr_t)base; +#endif + return (lsbits & (align - 1)) == 0; +} + +/** + * swap_words_32 - swap two elements in 32-bit chunks + * @a: pointer to the first element to swap + * @b: pointer to the second element to swap + * @n: element size (must be a multiple of 4) + * + * Exchange the two objects in memory. This exploits base+index addressing, + * which basically all CPUs have, to minimize loop overhead computations. + * + * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the + * bottom of the loop, even though the zero flag is still valid from the + * subtract (since the intervening mov instructions don't alter the flags). + * Gcc 8.1.0 doesn't have that problem. + */ +static void swap_words_32(void *a, void *b, size_t n) +{ + do { + u32 t = *(u32 *)(a + (n -= 4)); + *(u32 *)(a + n) = *(u32 *)(b + n); + *(u32 *)(b + n) = t; + } while (n); +} + +/** + * swap_words_64 - swap two elements in 64-bit chunks + * @a: pointer to the first element to swap + * @b: pointer to the second element to swap + * @n: element size (must be a multiple of 8) + * + * Exchange the two objects in memory. This exploits base+index + * addressing, which basically all CPUs have, to minimize loop overhead + * computations. + * + * We'd like to use 64-bit loads if possible. If they're not, emulating + * one requires base+index+4 addressing which x86 has but most other + * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, + * but it's possible to have 64-bit loads without 64-bit pointers (e.g. + * x32 ABI). Are there any cases the kernel needs to worry about? + */ +static void swap_words_64(void *a, void *b, size_t n) +{ + do { +#ifdef CONFIG_64BIT + u64 t = *(u64 *)(a + (n -= 8)); + *(u64 *)(a + n) = *(u64 *)(b + n); + *(u64 *)(b + n) = t; +#else + /* Use two 32-bit transfers to avoid base+index+4 addressing */ + u32 t = *(u32 *)(a + (n -= 4)); + *(u32 *)(a + n) = *(u32 *)(b + n); + *(u32 *)(b + n) = t; + + t = *(u32 *)(a + (n -= 4)); + *(u32 *)(a + n) = *(u32 *)(b + n); + *(u32 *)(b + n) = t; +#endif + } while (n); +} + +/** + * swap_bytes - swap two elements a byte at a time + * @a: pointer to the first element to swap + * @b: pointer to the second element to swap + * @n: element size + * + * This is the fallback if alignment doesn't allow using larger chunks. + */ +static void swap_bytes(void *a, void *b, size_t n) +{ + do { + char t = ((char *)a)[--n]; + ((char *)a)[n] = ((char *)b)[n]; + ((char *)b)[n] = t; + } while (n); +} + +/* + * The values are arbitrary as long as they can't be confused with + * a pointer, but small integers make for the smallest compare + * instructions. + */ +#define SWAP_WORDS_64 (swap_r_func_t)0 +#define SWAP_WORDS_32 (swap_r_func_t)1 +#define SWAP_BYTES (swap_r_func_t)2 +#define SWAP_WRAPPER (swap_r_func_t)3 + +struct wrapper { + cmp_func_t cmp; + swap_func_t swap; +}; + +/* + * The function pointer is last to make tail calls most efficient if the + * compiler decides not to inline this function. + */ +static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv) +{ + if (swap_func == SWAP_WRAPPER) { + ((const struct wrapper *)priv)->swap(a, b, (int)size); + return; + } + + if (swap_func == SWAP_WORDS_64) + swap_words_64(a, b, size); + else if (swap_func == SWAP_WORDS_32) + swap_words_32(a, b, size); + else if (swap_func == SWAP_BYTES) + swap_bytes(a, b, size); + else + swap_func(a, b, (int)size, priv); +} + +#define _CMP_WRAPPER ((cmp_r_func_t)0L) + +static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) +{ + if (cmp == _CMP_WRAPPER) + return ((const struct wrapper *)priv)->cmp(a, b); + return cmp(a, b, priv); +} + +static inline int eytzinger0_do_cmp(void *base, size_t n, size_t size, + cmp_r_func_t cmp_func, const void *priv, + size_t l, size_t r) +{ + return do_cmp(base + inorder_to_eytzinger0(l, n) * size, + base + inorder_to_eytzinger0(r, n) * size, + cmp_func, priv); +} + +static inline void eytzinger0_do_swap(void *base, size_t n, size_t size, + swap_r_func_t swap_func, const void *priv, + size_t l, size_t r) +{ + do_swap(base + inorder_to_eytzinger0(l, n) * size, + base + inorder_to_eytzinger0(r, n) * size, + size, swap_func, priv); +} + +void eytzinger0_sort_r(void *base, size_t n, size_t size, + cmp_r_func_t cmp_func, + swap_r_func_t swap_func, + const void *priv) +{ + int i, c, r; + + /* called from 'sort' without swap function, let's pick the default */ + if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap) + swap_func = NULL; + + if (!swap_func) { + if (is_aligned(base, size, 8)) + swap_func = SWAP_WORDS_64; + else if (is_aligned(base, size, 4)) + swap_func = SWAP_WORDS_32; + else + swap_func = SWAP_BYTES; + } + + /* heapify */ + for (i = n / 2 - 1; i >= 0; --i) { + for (r = i; r * 2 + 1 < n; r = c) { + c = r * 2 + 1; + + if (c + 1 < n && + eytzinger0_do_cmp(base, n, size, cmp_func, priv, c, c + 1) < 0) + c++; + + if (eytzinger0_do_cmp(base, n, size, cmp_func, priv, r, c) >= 0) + break; + + eytzinger0_do_swap(base, n, size, swap_func, priv, r, c); + } + } + + /* sort */ + for (i = n - 1; i > 0; --i) { + eytzinger0_do_swap(base, n, size, swap_func, priv, 0, i); + + for (r = 0; r * 2 + 1 < i; r = c) { + c = r * 2 + 1; + + if (c + 1 < i && + eytzinger0_do_cmp(base, n, size, cmp_func, priv, c, c + 1) < 0) + c++; + + if (eytzinger0_do_cmp(base, n, size, cmp_func, priv, r, c) >= 0) + break; + + eytzinger0_do_swap(base, n, size, swap_func, priv, r, c); + } + } +} + +void eytzinger0_sort(void *base, size_t n, size_t size, + cmp_func_t cmp_func, + swap_func_t swap_func) +{ + struct wrapper w = { + .cmp = cmp_func, + .swap = swap_func, + }; + + return eytzinger0_sort_r(base, n, size, _CMP_WRAPPER, SWAP_WRAPPER, &w); +} diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h index b04750dbf870..ee0e2df33322 100644 --- a/fs/bcachefs/eytzinger.h +++ b/fs/bcachefs/eytzinger.h @@ -5,23 +5,33 @@ #include <linux/bitops.h> #include <linux/log2.h> -#include "util.h" +#ifdef EYTZINGER_DEBUG +#define EYTZINGER_BUG_ON(cond) BUG_ON(cond) +#else +#define EYTZINGER_BUG_ON(cond) +#endif /* * Traversal for trees in eytzinger layout - a full binary tree layed out in an - * array - */ - -/* - * One based indexing version: + * array. * - * With one based indexing each level of the tree starts at a power of two - - * good for cacheline alignment: + * Consider using an eytzinger tree any time you would otherwise be doing binary + * search over an array. Binary search is a worst case scenario for branch + * prediction and prefetching, but in an eytzinger tree every node's children + * are adjacent in memory, thus we can prefetch children before knowing the + * result of the comparison, assuming multiple nodes fit on a cacheline. + * + * Two variants are provided, for one based indexing and zero based indexing. + * + * Zero based indexing is more convenient, but one based indexing has better + * alignment and thus better performance because each new level of the tree + * starts at a power of two, and thus if element 0 was cacheline aligned, each + * new level will be as well. */ static inline unsigned eytzinger1_child(unsigned i, unsigned child) { - EBUG_ON(child > 1); + EYTZINGER_BUG_ON(child > 1); return (i << 1) + child; } @@ -58,7 +68,7 @@ static inline unsigned eytzinger1_last(unsigned size) static inline unsigned eytzinger1_next(unsigned i, unsigned size) { - EBUG_ON(i > size); + EYTZINGER_BUG_ON(i > size); if (eytzinger1_right_child(i) <= size) { i = eytzinger1_right_child(i); @@ -74,7 +84,7 @@ static inline unsigned eytzinger1_next(unsigned i, unsigned size) static inline unsigned eytzinger1_prev(unsigned i, unsigned size) { - EBUG_ON(i > size); + EYTZINGER_BUG_ON(i > size); if (eytzinger1_left_child(i) <= size) { i = eytzinger1_left_child(i) + 1; @@ -101,7 +111,7 @@ static inline unsigned __eytzinger1_to_inorder(unsigned i, unsigned size, unsigned shift = __fls(size) - b; int s; - EBUG_ON(!i || i > size); + EYTZINGER_BUG_ON(!i || i > size); i ^= 1U << b; i <<= 1; @@ -126,7 +136,7 @@ static inline unsigned __inorder_to_eytzinger1(unsigned i, unsigned size, unsigned shift; int s; - EBUG_ON(!i || i > size); + EYTZINGER_BUG_ON(!i || i > size); /* * sign bit trick: @@ -164,7 +174,7 @@ static inline unsigned inorder_to_eytzinger1(unsigned i, unsigned size) static inline unsigned eytzinger0_child(unsigned i, unsigned child) { - EBUG_ON(child > 1); + EYTZINGER_BUG_ON(child > 1); return (i << 1) + 1 + child; } @@ -231,11 +241,9 @@ static inline unsigned inorder_to_eytzinger0(unsigned i, unsigned size) (_i) != -1; \ (_i) = eytzinger0_next((_i), (_size))) -typedef int (*eytzinger_cmp_fn)(const void *l, const void *r, size_t size); - /* return greatest node <= @search, or -1 if not found */ static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size, - eytzinger_cmp_fn cmp, const void *search) + cmp_func_t cmp, const void *search) { unsigned i, n = 0; @@ -244,21 +252,24 @@ static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size, do { i = n; - n = eytzinger0_child(i, cmp(search, base + i * size, size) >= 0); + n = eytzinger0_child(i, cmp(base + i * size, search) <= 0); } while (n < nr); if (n & 1) { /* @i was greater than @search, return previous node: */ - - if (i == eytzinger0_first(nr)) - return -1; - return eytzinger0_prev(i, nr); } else { return i; } } +static inline ssize_t eytzinger0_find_gt(void *base, size_t nr, size_t size, + cmp_func_t cmp, const void *search) +{ + ssize_t idx = eytzinger0_find_le(base, nr, size, cmp, search); + return eytzinger0_next(idx, size); +} + #define eytzinger0_find(base, nr, size, _cmp, search) \ ({ \ void *_base = (base); \ @@ -269,13 +280,13 @@ static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size, int _res; \ \ while (_i < _nr && \ - (_res = _cmp(_search, _base + _i * _size, _size))) \ + (_res = _cmp(_search, _base + _i * _size))) \ _i = eytzinger0_child(_i, _res > 0); \ _i; \ }) -void eytzinger0_sort(void *, size_t, size_t, - int (*cmp_func)(const void *, const void *, size_t), - void (*swap_func)(void *, void *, size_t)); +void eytzinger0_sort_r(void *, size_t, size_t, + cmp_r_func_t, swap_r_func_t, const void *); +void eytzinger0_sort(void *, size_t, size_t, cmp_func_t, swap_func_t); #endif /* _EYTZINGER_H */ diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index 33cb6da3a5ad..f49e6c0f0f68 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -536,7 +536,7 @@ static __always_inline long bch2_dio_write_loop(struct dio_write *dio) if (likely(!dio->iter.count) || dio->op.error) break; - bio_reset(bio, NULL, REQ_OP_WRITE); + bio_reset(bio, NULL, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE); } out: return bch2_dio_write_done(dio); @@ -618,7 +618,7 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) bio = bio_alloc_bioset(NULL, bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS), - REQ_OP_WRITE, + REQ_OP_WRITE | REQ_SYNC | REQ_IDLE, GFP_KERNEL, &c->dio_write_bioset); dio = container_of(bio, struct dio_write, op.wbio.bio); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 0ccee05f6887..b5ea9fa1259d 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1997,6 +1997,7 @@ out: return dget(sb->s_root); err_put_super: + __bch2_fs_stop(c); deactivate_locked_super(sb); return ERR_PTR(bch2_err_class(ret)); } diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 47d4eefaba7b..8e2010212cc3 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -12,7 +12,7 @@ #include "fsck.h" #include "inode.h" #include "keylist.h" -#include "recovery.h" +#include "recovery_passes.h" #include "snapshot.h" #include "super.h" #include "xattr.h" @@ -63,9 +63,7 @@ static int subvol_lookup(struct btree_trans *trans, u32 subvol, u32 *snapshot, u64 *inum) { struct bch_subvolume s; - int ret; - - ret = bch2_subvolume_get(trans, subvol, false, 0, &s); + int ret = bch2_subvolume_get(trans, subvol, false, 0, &s); *snapshot = le32_to_cpu(s.snapshot); *inum = le64_to_cpu(s.inode); @@ -158,9 +156,10 @@ static int __remove_dirent(struct btree_trans *trans, struct bpos pos) bch2_trans_iter_init(trans, &iter, BTREE_ID_dirents, pos, BTREE_ITER_INTENT); - ret = bch2_hash_delete_at(trans, bch2_dirent_hash_desc, - &dir_hash_info, &iter, - BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE); + ret = bch2_btree_iter_traverse(&iter) ?: + bch2_hash_delete_at(trans, bch2_dirent_hash_desc, + &dir_hash_info, &iter, + BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE); bch2_trans_iter_exit(trans, &iter); err: bch_err_fn(c, ret); @@ -169,7 +168,8 @@ err: /* Get lost+found, create if it doesn't exist: */ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, - struct bch_inode_unpacked *lostfound) + struct bch_inode_unpacked *lostfound, + u64 reattaching_inum) { struct bch_fs *c = trans->c; struct qstr lostfound_str = QSTR("lost+found"); @@ -184,19 +184,36 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, return ret; subvol_inum root_inum = { .subvol = le32_to_cpu(st.master_subvol) }; - u32 subvol_snapshot; - ret = subvol_lookup(trans, le32_to_cpu(st.master_subvol), - &subvol_snapshot, &root_inum.inum); - bch_err_msg(c, ret, "looking up root subvol"); + struct bch_subvolume subvol; + ret = bch2_subvolume_get(trans, le32_to_cpu(st.master_subvol), + false, 0, &subvol); + bch_err_msg(c, ret, "looking up root subvol %u for snapshot %u", + le32_to_cpu(st.master_subvol), snapshot); if (ret) return ret; + if (!subvol.inode) { + struct btree_iter iter; + struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &iter, + BTREE_ID_subvolumes, POS(0, le32_to_cpu(st.master_subvol)), + 0, subvolume); + ret = PTR_ERR_OR_ZERO(subvol); + if (ret) + return ret; + + subvol->v.inode = cpu_to_le64(reattaching_inum); + bch2_trans_iter_exit(trans, &iter); + } + + root_inum.inum = le64_to_cpu(subvol.inode); + struct bch_inode_unpacked root_inode; struct bch_hash_info root_hash_info; u32 root_inode_snapshot = snapshot; ret = lookup_inode(trans, root_inum.inum, &root_inode, &root_inode_snapshot); - bch_err_msg(c, ret, "looking up root inode"); + bch_err_msg(c, ret, "looking up root inode %llu for subvol %u", + root_inum.inum, le32_to_cpu(st.master_subvol)); if (ret) return ret; @@ -292,7 +309,7 @@ static int reattach_inode(struct btree_trans *trans, snprintf(name_buf, sizeof(name_buf), "%llu", inode->bi_inum); } - ret = lookup_lostfound(trans, dirent_snapshot, &lostfound); + ret = lookup_lostfound(trans, dirent_snapshot, &lostfound, inode->bi_inum); if (ret) return ret; @@ -363,6 +380,112 @@ static int reattach_subvol(struct btree_trans *trans, struct bkey_s_c_subvolume return ret; } +static int reconstruct_subvol(struct btree_trans *trans, u32 snapshotid, u32 subvolid, u64 inum) +{ + struct bch_fs *c = trans->c; + + if (!bch2_snapshot_is_leaf(c, snapshotid)) { + bch_err(c, "need to reconstruct subvol, but have interior node snapshot"); + return -BCH_ERR_fsck_repair_unimplemented; + } + + /* + * If inum isn't set, that means we're being called from check_dirents, + * not check_inodes - the root of this subvolume doesn't exist or we + * would have found it there: + */ + if (!inum) { + struct btree_iter inode_iter = {}; + struct bch_inode_unpacked new_inode; + u64 cpu = raw_smp_processor_id(); + + bch2_inode_init_early(c, &new_inode); + bch2_inode_init_late(&new_inode, bch2_current_time(c), 0, 0, S_IFDIR|0755, 0, NULL); + + new_inode.bi_subvol = subvolid; + + int ret = bch2_inode_create(trans, &inode_iter, &new_inode, snapshotid, cpu) ?: + bch2_btree_iter_traverse(&inode_iter) ?: + bch2_inode_write(trans, &inode_iter, &new_inode); + bch2_trans_iter_exit(trans, &inode_iter); + if (ret) + return ret; + + inum = new_inode.bi_inum; + } + + bch_info(c, "reconstructing subvol %u with root inode %llu", subvolid, inum); + + struct bkey_i_subvolume *new_subvol = bch2_trans_kmalloc(trans, sizeof(*new_subvol)); + int ret = PTR_ERR_OR_ZERO(new_subvol); + if (ret) + return ret; + + bkey_subvolume_init(&new_subvol->k_i); + new_subvol->k.p.offset = subvolid; + new_subvol->v.snapshot = cpu_to_le32(snapshotid); + new_subvol->v.inode = cpu_to_le64(inum); + ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &new_subvol->k_i, 0); + if (ret) + return ret; + + struct btree_iter iter; + struct bkey_i_snapshot *s = bch2_bkey_get_mut_typed(trans, &iter, + BTREE_ID_snapshots, POS(0, snapshotid), + 0, snapshot); + ret = PTR_ERR_OR_ZERO(s); + bch_err_msg(c, ret, "getting snapshot %u", snapshotid); + if (ret) + return ret; + + u32 snapshot_tree = le32_to_cpu(s->v.tree); + + s->v.subvol = cpu_to_le32(subvolid); + SET_BCH_SNAPSHOT_SUBVOL(&s->v, true); + bch2_trans_iter_exit(trans, &iter); + + struct bkey_i_snapshot_tree *st = bch2_bkey_get_mut_typed(trans, &iter, + BTREE_ID_snapshot_trees, POS(0, snapshot_tree), + 0, snapshot_tree); + ret = PTR_ERR_OR_ZERO(st); + bch_err_msg(c, ret, "getting snapshot tree %u", snapshot_tree); + if (ret) + return ret; + + if (!st->v.master_subvol) + st->v.master_subvol = cpu_to_le32(subvolid); + + bch2_trans_iter_exit(trans, &iter); + return 0; +} + +static int reconstruct_inode(struct btree_trans *trans, u32 snapshot, u64 inum, u64 size, unsigned mode) +{ + struct bch_fs *c = trans->c; + struct bch_inode_unpacked new_inode; + + bch2_inode_init_early(c, &new_inode); + bch2_inode_init_late(&new_inode, bch2_current_time(c), 0, 0, mode|0755, 0, NULL); + new_inode.bi_size = size; + new_inode.bi_inum = inum; + + return __bch2_fsck_write_inode(trans, &new_inode, snapshot); +} + +static int reconstruct_reg_inode(struct btree_trans *trans, u32 snapshot, u64 inum) +{ + struct btree_iter iter = {}; + + bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(inum, U64_MAX, snapshot), 0); + struct bkey_s_c k = bch2_btree_iter_peek_prev(&iter); + bch2_trans_iter_exit(trans, &iter); + int ret = bkey_err(k); + if (ret) + return ret; + + return reconstruct_inode(trans, snapshot, inum, k.k->p.offset << 9, S_IFREG); +} + struct snapshots_seen_entry { u32 id; u32 equiv; @@ -1064,6 +1187,11 @@ static int check_inode(struct btree_trans *trans, if (ret && !bch2_err_matches(ret, ENOENT)) goto err; + if (ret && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) { + ret = reconstruct_subvol(trans, k.k->p.snapshot, u.bi_subvol, u.bi_inum); + goto do_update; + } + if (fsck_err_on(ret, c, inode_bi_subvol_missing, "inode %llu:%u bi_subvol points to missing subvolume %u", @@ -1081,7 +1209,7 @@ static int check_inode(struct btree_trans *trans, do_update = true; } } - +do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u, iter->pos.snapshot); bch_err_msg(c, ret, "in fsck updating inode"); @@ -1130,8 +1258,8 @@ static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_wal i->count = count2; if (i->count != count2) { - bch_err(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu", - w->last_pos.inode, i->snapshot, i->count, count2); + bch_err_ratelimited(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu", + w->last_pos.inode, i->snapshot, i->count, count2); return -BCH_ERR_internal_fsck_err; } @@ -1371,10 +1499,6 @@ static int check_overlapping_extents(struct btree_trans *trans, goto err; } - ret = extent_ends_at(c, extent_ends, seen, k); - if (ret) - goto err; - extent_ends->last_pos = k.k->p; err: return ret; @@ -1438,6 +1562,17 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, goto err; if (k.k->type != KEY_TYPE_whiteout) { + if (!i && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) { + ret = reconstruct_reg_inode(trans, k.k->p.snapshot, k.k->p.inode) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + inode->last_pos.inode--; + ret = -BCH_ERR_transaction_restart_nested; + goto err; + } + if (fsck_err_on(!i, c, extent_in_missing_inode, "extent in missing inode:\n %s", (printbuf_reset(&buf), @@ -1504,6 +1639,12 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, i->seen_this_pos = true; } + + if (k.k->type != KEY_TYPE_whiteout) { + ret = extent_ends_at(c, extent_ends, s, k); + if (ret) + goto err; + } out: err: fsck_err: @@ -1584,8 +1725,8 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_ return count2; if (i->count != count2) { - bch_err(c, "fsck counted subdirectories wrong: got %llu should be %llu", - i->count, count2); + bch_err_ratelimited(c, "fsck counted subdirectories wrong for inum %llu:%u: got %llu should be %llu", + w->last_pos.inode, i->snapshot, i->count, count2); i->count = count2; if (i->inode.bi_nlink == i->count) continue; @@ -1782,6 +1923,7 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * u32 parent_subvol = le32_to_cpu(d.v->d_parent_subvol); u32 target_subvol = le32_to_cpu(d.v->d_child_subvol); u32 parent_snapshot; + u32 new_parent_subvol = 0; u64 parent_inum; struct printbuf buf = PRINTBUF; int ret = 0; @@ -1790,6 +1932,27 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * if (ret && !bch2_err_matches(ret, ENOENT)) return ret; + if (ret || + (!ret && !bch2_snapshot_is_ancestor(c, parent_snapshot, d.k->p.snapshot))) { + int ret2 = find_snapshot_subvol(trans, d.k->p.snapshot, &new_parent_subvol); + if (ret2 && !bch2_err_matches(ret, ENOENT)) + return ret2; + } + + if (ret && + !new_parent_subvol && + (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) { + /* + * Couldn't find a subvol for dirent's snapshot - but we lost + * subvols, so we need to reconstruct: + */ + ret = reconstruct_subvol(trans, d.k->p.snapshot, parent_subvol, 0); + if (ret) + return ret; + + parent_snapshot = d.k->p.snapshot; + } + if (fsck_err_on(ret, c, dirent_to_missing_parent_subvol, "dirent parent_subvol points to missing subvolume\n%s", (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf)) || @@ -1798,10 +1961,10 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * "dirent not visible in parent_subvol (not an ancestor of subvol snap %u)\n%s", parent_snapshot, (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) { - u32 new_parent_subvol; - ret = find_snapshot_subvol(trans, d.k->p.snapshot, &new_parent_subvol); - if (ret) - goto err; + if (!new_parent_subvol) { + bch_err(c, "could not find a subvol for snapshot %u", d.k->p.snapshot); + return -BCH_ERR_fsck_repair_unimplemented; + } struct bkey_i_dirent *new_dirent = bch2_bkey_make_mut_typed(trans, iter, &d.s_c, 0, dirent); ret = PTR_ERR_OR_ZERO(new_dirent); @@ -1847,9 +2010,16 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * ret = lookup_inode(trans, target_inum, &subvol_root, &target_snapshot); if (ret && !bch2_err_matches(ret, ENOENT)) - return ret; + goto err; + + if (ret) { + bch_err(c, "subvol %u points to missing inode root %llu", target_subvol, target_inum); + ret = -BCH_ERR_fsck_repair_unimplemented; + ret = 0; + goto err; + } - if (fsck_err_on(parent_subvol != subvol_root.bi_parent_subvol, + if (fsck_err_on(!ret && parent_subvol != subvol_root.bi_parent_subvol, c, inode_bi_parent_wrong, "subvol root %llu has wrong bi_parent_subvol: got %u, should be %u", target_inum, @@ -1857,13 +2027,13 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter * subvol_root.bi_parent_subvol = parent_subvol; ret = __bch2_fsck_write_inode(trans, &subvol_root, target_snapshot); if (ret) - return ret; + goto err; } ret = check_dirent_target(trans, iter, d, &subvol_root, target_snapshot); if (ret) - return ret; + goto err; out: err: fsck_err: @@ -1880,7 +2050,6 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, struct snapshots_seen *s) { struct bch_fs *c = trans->c; - struct bkey_s_c_dirent d; struct inode_walker_entry *i; struct printbuf buf = PRINTBUF; struct bpos equiv; @@ -1919,6 +2088,17 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, *hash_info = bch2_hash_info_init(c, &dir->inodes.data[0].inode); dir->first_this_inode = false; + if (!i && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) { + ret = reconstruct_inode(trans, k.k->p.snapshot, k.k->p.inode, 0, S_IFDIR) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + dir->last_pos.inode--; + ret = -BCH_ERR_transaction_restart_nested; + goto err; + } + if (fsck_err_on(!i, c, dirent_in_missing_dir_inode, "dirent in nonexisting directory:\n%s", (printbuf_reset(&buf), @@ -1953,7 +2133,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (k.k->type != KEY_TYPE_dirent) goto out; - d = bkey_s_c_to_dirent(k); + struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); if (d.v->d_type == DT_SUBVOL) { ret = check_dirent_to_subvol(trans, iter, d); @@ -2098,17 +2278,21 @@ static int check_root_trans(struct btree_trans *trans) if (mustfix_fsck_err_on(ret, c, root_subvol_missing, "root subvol missing")) { - struct bkey_i_subvolume root_subvol; + struct bkey_i_subvolume *root_subvol = + bch2_trans_kmalloc(trans, sizeof(*root_subvol)); + ret = PTR_ERR_OR_ZERO(root_subvol); + if (ret) + goto err; snapshot = U32_MAX; inum = BCACHEFS_ROOT_INO; - bkey_subvolume_init(&root_subvol.k_i); - root_subvol.k.p.offset = BCACHEFS_ROOT_SUBVOL; - root_subvol.v.flags = 0; - root_subvol.v.snapshot = cpu_to_le32(snapshot); - root_subvol.v.inode = cpu_to_le64(inum); - ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &root_subvol.k_i, 0); + bkey_subvolume_init(&root_subvol->k_i); + root_subvol->k.p.offset = BCACHEFS_ROOT_SUBVOL; + root_subvol->v.flags = 0; + root_subvol->v.snapshot = cpu_to_le32(snapshot); + root_subvol->v.inode = cpu_to_le64(inum); + ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &root_subvol->k_i, 0); bch_err_msg(c, ret, "writing root subvol"); if (ret) goto err; diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index 2b5e06770ab3..ca4a066e9a54 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -552,8 +552,8 @@ static void __bch2_inode_unpacked_to_text(struct printbuf *out, prt_printf(out, "bi_sectors=%llu", inode->bi_sectors); prt_newline(out); - prt_newline(out); prt_printf(out, "bi_version=%llu", inode->bi_version); + prt_newline(out); #define x(_name, _bits) \ prt_printf(out, #_name "=%llu", (u64) inode->_name); \ diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c index 1baf78594cca..82f9170dab3f 100644 --- a/fs/bcachefs/io_misc.c +++ b/fs/bcachefs/io_misc.c @@ -264,6 +264,7 @@ static int __bch2_resume_logged_op_truncate(struct btree_trans *trans, ret = 0; err: bch2_logged_op_finish(trans, op_k); + bch_err_fn(c, ret); return ret; } @@ -476,6 +477,7 @@ case LOGGED_OP_FINSERT_finish: break; } err: + bch_err_fn(c, ret); bch2_logged_op_finish(trans, op_k); bch2_trans_iter_exit(trans, &iter); return ret; diff --git a/fs/bcachefs/journal_seq_blacklist.c b/fs/bcachefs/journal_seq_blacklist.c index b5303874fc35..37a024e034d4 100644 --- a/fs/bcachefs/journal_seq_blacklist.c +++ b/fs/bcachefs/journal_seq_blacklist.c @@ -95,8 +95,7 @@ out: return ret ?: bch2_blacklist_table_initialize(c); } -static int journal_seq_blacklist_table_cmp(const void *_l, - const void *_r, size_t size) +static int journal_seq_blacklist_table_cmp(const void *_l, const void *_r) { const struct journal_seq_blacklist_table_entry *l = _l; const struct journal_seq_blacklist_table_entry *r = _r; diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c index 9fac838d123e..b82f8209041f 100644 --- a/fs/bcachefs/logged_ops.c +++ b/fs/bcachefs/logged_ops.c @@ -37,7 +37,6 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter, const struct bch_logged_op_fn *fn = logged_op_fn(k.k->type); struct bkey_buf sk; u32 restart_count = trans->restart_count; - int ret; if (!fn) return 0; @@ -45,11 +44,11 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter, bch2_bkey_buf_init(&sk); bch2_bkey_buf_reassemble(&sk, c, k); - ret = drop_locks_do(trans, (bch2_fs_lazy_rw(c), 0)) ?: - fn->resume(trans, sk.k) ?: trans_was_restarted(trans, restart_count); + fn->resume(trans, sk.k); bch2_bkey_buf_exit(&sk, c); - return ret; + + return trans_was_restarted(trans, restart_count); } int bch2_resume_logged_ops(struct bch_fs *c) diff --git a/fs/bcachefs/mean_and_variance_test.c b/fs/bcachefs/mean_and_variance_test.c index db63b3f3b338..4c298e74723d 100644 --- a/fs/bcachefs/mean_and_variance_test.c +++ b/fs/bcachefs/mean_and_variance_test.c @@ -136,20 +136,8 @@ static void mean_and_variance_test_1(struct kunit *test) d, mean, stddev, weighted_mean, weighted_stddev); } -static void mean_and_variance_test_2(struct kunit *test) -{ - s64 d[] = { 100, 10, 10, 10, 10, 10, 10 }; - s64 mean[] = { 10, 10, 10, 10, 10, 10, 10 }; - s64 stddev[] = { 9, 9, 9, 9, 9, 9, 9 }; - s64 weighted_mean[] = { 32, 27, 22, 19, 17, 15, 14 }; - s64 weighted_stddev[] = { 38, 35, 31, 27, 24, 21, 18 }; - - do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2, - d, mean, stddev, weighted_mean, weighted_stddev); -} - /* Test behaviour where we switch from one steady state to another: */ -static void mean_and_variance_test_3(struct kunit *test) +static void mean_and_variance_test_2(struct kunit *test) { s64 d[] = { 100, 100, 100, 100, 100 }; s64 mean[] = { 22, 32, 40, 46, 50 }; @@ -161,18 +149,6 @@ static void mean_and_variance_test_3(struct kunit *test) d, mean, stddev, weighted_mean, weighted_stddev); } -static void mean_and_variance_test_4(struct kunit *test) -{ - s64 d[] = { 100, 100, 100, 100, 100 }; - s64 mean[] = { 10, 11, 12, 13, 14 }; - s64 stddev[] = { 9, 13, 15, 17, 19 }; - s64 weighted_mean[] = { 32, 49, 61, 71, 78 }; - s64 weighted_stddev[] = { 38, 44, 44, 41, 38 }; - - do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2, - d, mean, stddev, weighted_mean, weighted_stddev); -} - static void mean_and_variance_fast_divpow2(struct kunit *test) { s64 i; @@ -230,8 +206,6 @@ static struct kunit_case mean_and_variance_test_cases[] = { KUNIT_CASE(mean_and_variance_weighted_advanced_test), KUNIT_CASE(mean_and_variance_test_1), KUNIT_CASE(mean_and_variance_test_2), - KUNIT_CASE(mean_and_variance_test_3), - KUNIT_CASE(mean_and_variance_test_4), {} }; diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c index 08ea0cfc4aef..e1800c4119b5 100644 --- a/fs/bcachefs/opts.c +++ b/fs/bcachefs/opts.c @@ -7,6 +7,7 @@ #include "disk_groups.h" #include "error.h" #include "opts.h" +#include "recovery_passes.h" #include "super-io.h" #include "util.h" @@ -205,6 +206,9 @@ const struct bch_option bch2_opt_table[] = { #define OPT_STR(_choices) .type = BCH_OPT_STR, \ .min = 0, .max = ARRAY_SIZE(_choices), \ .choices = _choices +#define OPT_STR_NOLIMIT(_choices) .type = BCH_OPT_STR, \ + .min = 0, .max = U64_MAX, \ + .choices = _choices #define OPT_FN(_fn) .type = BCH_OPT_FN, .fn = _fn #define x(_name, _bits, _flags, _type, _sb_opt, _default, _hint, _help) \ diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 136083c11f3a..1ac4135cca1c 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -362,12 +362,17 @@ enum fsck_err_opts { OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ - NULL, "Don't replay the journal") \ - x(keep_journal, u8, \ + NULL, "Exit recovery immediately prior to journal replay")\ + x(recovery_pass_last, u8, \ + OPT_FS|OPT_MOUNT, \ + OPT_STR_NOLIMIT(bch2_recovery_passes), \ + BCH2_NO_SB_OPT, 0, \ + NULL, "Exit recovery after specified pass") \ + x(retain_recovery_info, u8, \ 0, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ - NULL, "Don't free journal entries/keys after startup")\ + NULL, "Don't free journal entries/keys, scanned btree nodes after startup")\ x(read_entire_journal, u8, \ 0, \ OPT_BOOL(), \ diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 03f9d6afe467..b76c16152579 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -1,35 +1,31 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" -#include "backpointers.h" -#include "bkey_buf.h" #include "alloc_background.h" -#include "btree_gc.h" +#include "bkey_buf.h" #include "btree_journal_iter.h" +#include "btree_node_scan.h" #include "btree_update.h" #include "btree_update_interior.h" #include "btree_io.h" #include "buckets.h" #include "dirent.h" -#include "ec.h" #include "errcode.h" #include "error.h" #include "fs-common.h" -#include "fsck.h" #include "journal_io.h" #include "journal_reclaim.h" #include "journal_seq_blacklist.h" -#include "lru.h" #include "logged_ops.h" #include "move.h" #include "quota.h" #include "rebalance.h" #include "recovery.h" +#include "recovery_passes.h" #include "replicas.h" #include "sb-clean.h" #include "sb-downgrade.h" #include "snapshot.h" -#include "subvolume.h" #include "super-io.h" #include <linux/sort.h> @@ -37,6 +33,20 @@ #define QSTR(n) { { { .len = strlen(n) } }, .name = n } +void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) +{ + u64 b = BIT_ULL(btree); + + if (!(c->sb.btrees_lost_data & b)) { + bch_err(c, "flagging btree %s lost data", bch2_btree_id_str(btree)); + + mutex_lock(&c->sb_lock); + bch2_sb_field_get(c->disk_sb.sb, ext)->btrees_lost_data |= cpu_to_le64(b); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); + } +} + static bool btree_id_is_alloc(enum btree_id id) { switch (id) { @@ -52,7 +62,7 @@ static bool btree_id_is_alloc(enum btree_id id) } /* for -o reconstruct_alloc: */ -static void do_reconstruct_alloc(struct bch_fs *c) +static void bch2_reconstruct_alloc(struct bch_fs *c) { bch2_journal_log_msg(c, "dropping alloc info"); bch_info(c, "dropping and reconstructing all alloc info"); @@ -87,15 +97,17 @@ static void do_reconstruct_alloc(struct bch_fs *c) c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); - struct journal_keys *keys = &c->journal_keys; - size_t src, dst; - move_gap(keys, keys->nr); - - for (src = 0, dst = 0; src < keys->nr; src++) - if (!btree_id_is_alloc(keys->data[src].btree_id)) - keys->data[dst++] = keys->data[src]; - keys->nr = keys->gap = dst; + bch2_shoot_down_journal_keys(c, BTREE_ID_alloc, + 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + bch2_shoot_down_journal_keys(c, BTREE_ID_backpointers, + 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + bch2_shoot_down_journal_keys(c, BTREE_ID_need_discard, + 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + bch2_shoot_down_journal_keys(c, BTREE_ID_freespace, + 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); + bch2_shoot_down_journal_keys(c, BTREE_ID_bucket_gens, + 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); } /* @@ -186,7 +198,7 @@ static int journal_sort_seq_cmp(const void *_l, const void *_r) return cmp_int(l->journal_seq, r->journal_seq); } -static int bch2_journal_replay(struct bch_fs *c) +int bch2_journal_replay(struct bch_fs *c) { struct journal_keys *keys = &c->journal_keys; DARRAY(struct journal_key *) keys_sorted = { 0 }; @@ -194,6 +206,7 @@ static int bch2_journal_replay(struct bch_fs *c) u64 start_seq = c->journal_replay_seq_start; u64 end_seq = c->journal_replay_seq_start; struct btree_trans *trans = bch2_trans_get(c); + bool immediate_flush = false; int ret = 0; if (keys->nr) { @@ -215,6 +228,13 @@ static int bch2_journal_replay(struct bch_fs *c) darray_for_each(*keys, k) { cond_resched(); + /* + * k->allocated means the key wasn't read in from the journal, + * rather it was from early repair code + */ + if (k->allocated) + immediate_flush = true; + /* Skip fastpath if we're low on space in the journal */ ret = c->journal.watermark ? -1 : commit_do(trans, NULL, NULL, @@ -266,7 +286,8 @@ static int bch2_journal_replay(struct bch_fs *c) bch2_trans_put(trans); trans = NULL; - if (!c->opts.keep_journal) + if (!c->opts.retain_recovery_info && + c->recovery_pass_done >= BCH_RECOVERY_PASS_journal_replay) bch2_journal_keys_put_initial(c); replay_now_at(j, j->replay_journal_seq_end); @@ -274,6 +295,12 @@ static int bch2_journal_replay(struct bch_fs *c) bch2_journal_set_replay_done(j); + /* if we did any repair, flush it immediately */ + if (immediate_flush) { + bch2_journal_flush_all_pins(&c->journal); + ret = bch2_journal_meta(&c->journal); + } + if (keys->nr) bch2_journal_log_msg(c, "journal replay finished"); err: @@ -423,10 +450,9 @@ static int journal_replay_early(struct bch_fs *c, static int read_btree_roots(struct bch_fs *c) { - unsigned i; int ret = 0; - for (i = 0; i < btree_id_nr_alive(c); i++) { + for (unsigned i = 0; i < btree_id_nr_alive(c); i++) { struct btree_root *r = bch2_btree_id_root(c, i); if (!r->alive) @@ -435,186 +461,46 @@ static int read_btree_roots(struct bch_fs *c) if (btree_id_is_alloc(i) && c->opts.reconstruct_alloc) continue; - if (r->error) { - __fsck_err(c, - btree_id_is_alloc(i) - ? FSCK_CAN_IGNORE : 0, - btree_root_bkey_invalid, - "invalid btree root %s", - bch2_btree_id_str(i)); - if (i == BTREE_ID_alloc) + if (mustfix_fsck_err_on((ret = r->error), + c, btree_root_bkey_invalid, + "invalid btree root %s", + bch2_btree_id_str(i)) || + mustfix_fsck_err_on((ret = r->error = bch2_btree_root_read(c, i, &r->key, r->level)), + c, btree_root_read_error, + "error reading btree root %s l=%u: %s", + bch2_btree_id_str(i), r->level, bch2_err_str(ret))) { + if (btree_id_is_alloc(i)) { + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_allocations); + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_info); + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_lrus); + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers); + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_to_lru_refs); c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info); - } + r->error = 0; + } else if (!(c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes))) { + bch_info(c, "will run btree node scan"); + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes); + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); + } - ret = bch2_btree_root_read(c, i, &r->key, r->level); - if (ret) { - fsck_err(c, - btree_root_read_error, - "error reading btree root %s", - bch2_btree_id_str(i)); - if (btree_id_is_alloc(i)) - c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info); ret = 0; + bch2_btree_lost_data(c, i); } } - for (i = 0; i < BTREE_ID_NR; i++) { + for (unsigned i = 0; i < BTREE_ID_NR; i++) { struct btree_root *r = bch2_btree_id_root(c, i); - if (!r->b) { + if (!r->b && !r->error) { r->alive = false; r->level = 0; - bch2_btree_root_alloc(c, i); + bch2_btree_root_alloc_fake(c, i, 0); } } fsck_err: return ret; } -static int bch2_initialize_subvolumes(struct bch_fs *c) -{ - struct bkey_i_snapshot_tree root_tree; - struct bkey_i_snapshot root_snapshot; - struct bkey_i_subvolume root_volume; - int ret; - - bkey_snapshot_tree_init(&root_tree.k_i); - root_tree.k.p.offset = 1; - root_tree.v.master_subvol = cpu_to_le32(1); - root_tree.v.root_snapshot = cpu_to_le32(U32_MAX); - - bkey_snapshot_init(&root_snapshot.k_i); - root_snapshot.k.p.offset = U32_MAX; - root_snapshot.v.flags = 0; - root_snapshot.v.parent = 0; - root_snapshot.v.subvol = cpu_to_le32(BCACHEFS_ROOT_SUBVOL); - root_snapshot.v.tree = cpu_to_le32(1); - SET_BCH_SNAPSHOT_SUBVOL(&root_snapshot.v, true); - - bkey_subvolume_init(&root_volume.k_i); - root_volume.k.p.offset = BCACHEFS_ROOT_SUBVOL; - root_volume.v.flags = 0; - root_volume.v.snapshot = cpu_to_le32(U32_MAX); - root_volume.v.inode = cpu_to_le64(BCACHEFS_ROOT_INO); - - ret = bch2_btree_insert(c, BTREE_ID_snapshot_trees, &root_tree.k_i, NULL, 0) ?: - bch2_btree_insert(c, BTREE_ID_snapshots, &root_snapshot.k_i, NULL, 0) ?: - bch2_btree_insert(c, BTREE_ID_subvolumes, &root_volume.k_i, NULL, 0); - bch_err_fn(c, ret); - return ret; -} - -static int __bch2_fs_upgrade_for_subvolumes(struct btree_trans *trans) -{ - struct btree_iter iter; - struct bkey_s_c k; - struct bch_inode_unpacked inode; - int ret; - - k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, - SPOS(0, BCACHEFS_ROOT_INO, U32_MAX), 0); - ret = bkey_err(k); - if (ret) - return ret; - - if (!bkey_is_inode(k.k)) { - bch_err(trans->c, "root inode not found"); - ret = -BCH_ERR_ENOENT_inode; - goto err; - } - - ret = bch2_inode_unpack(k, &inode); - BUG_ON(ret); - - inode.bi_subvol = BCACHEFS_ROOT_SUBVOL; - - ret = bch2_inode_write(trans, &iter, &inode); -err: - bch2_trans_iter_exit(trans, &iter); - return ret; -} - -/* set bi_subvol on root inode */ -noinline_for_stack -static int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c) -{ - int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw, - __bch2_fs_upgrade_for_subvolumes(trans)); - bch_err_fn(c, ret); - return ret; -} - -const char * const bch2_recovery_passes[] = { -#define x(_fn, ...) #_fn, - BCH_RECOVERY_PASSES() -#undef x - NULL -}; - -static int bch2_check_allocations(struct bch_fs *c) -{ - return bch2_gc(c, true, c->opts.norecovery); -} - -static int bch2_set_may_go_rw(struct bch_fs *c) -{ - struct journal_keys *keys = &c->journal_keys; - - /* - * After we go RW, the journal keys buffer can't be modified (except for - * setting journal_key->overwritten: it will be accessed by multiple - * threads - */ - move_gap(keys, keys->nr); - - set_bit(BCH_FS_may_go_rw, &c->flags); - - if (keys->nr || c->opts.fsck || !c->sb.clean) - return bch2_fs_read_write_early(c); - return 0; -} - -struct recovery_pass_fn { - int (*fn)(struct bch_fs *); - unsigned when; -}; - -static struct recovery_pass_fn recovery_pass_fns[] = { -#define x(_fn, _id, _when) { .fn = bch2_##_fn, .when = _when }, - BCH_RECOVERY_PASSES() -#undef x -}; - -u64 bch2_recovery_passes_to_stable(u64 v) -{ - static const u8 map[] = { -#define x(n, id, ...) [BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n, - BCH_RECOVERY_PASSES() -#undef x - }; - - u64 ret = 0; - for (unsigned i = 0; i < ARRAY_SIZE(map); i++) - if (v & BIT_ULL(i)) - ret |= BIT_ULL(map[i]); - return ret; -} - -u64 bch2_recovery_passes_from_stable(u64 v) -{ - static const u8 map[] = { -#define x(n, id, ...) [BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n, - BCH_RECOVERY_PASSES() -#undef x - }; - - u64 ret = 0; - for (unsigned i = 0; i < ARRAY_SIZE(map); i++) - if (v & BIT_ULL(i)) - ret |= BIT_ULL(map[i]); - return ret; -} - static bool check_version_upgrade(struct bch_fs *c) { unsigned latest_version = bcachefs_metadata_version_current; @@ -687,96 +573,6 @@ static bool check_version_upgrade(struct bch_fs *c) return false; } -u64 bch2_fsck_recovery_passes(void) -{ - u64 ret = 0; - - for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) - if (recovery_pass_fns[i].when & PASS_FSCK) - ret |= BIT_ULL(i); - return ret; -} - -static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass) -{ - struct recovery_pass_fn *p = recovery_pass_fns + pass; - - if (c->opts.norecovery && pass > BCH_RECOVERY_PASS_snapshots_read) - return false; - if (c->recovery_passes_explicit & BIT_ULL(pass)) - return true; - if ((p->when & PASS_FSCK) && c->opts.fsck) - return true; - if ((p->when & PASS_UNCLEAN) && !c->sb.clean) - return true; - if (p->when & PASS_ALWAYS) - return true; - return false; -} - -static int bch2_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass) -{ - struct recovery_pass_fn *p = recovery_pass_fns + pass; - int ret; - - if (!(p->when & PASS_SILENT)) - bch2_print(c, KERN_INFO bch2_log_msg(c, "%s..."), - bch2_recovery_passes[pass]); - ret = p->fn(c); - if (ret) - return ret; - if (!(p->when & PASS_SILENT)) - bch2_print(c, KERN_CONT " done\n"); - - return 0; -} - -static int bch2_run_recovery_passes(struct bch_fs *c) -{ - int ret = 0; - - while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) { - if (should_run_recovery_pass(c, c->curr_recovery_pass)) { - unsigned pass = c->curr_recovery_pass; - - ret = bch2_run_recovery_pass(c, c->curr_recovery_pass); - if (bch2_err_matches(ret, BCH_ERR_restart_recovery) || - (ret && c->curr_recovery_pass < pass)) - continue; - if (ret) - break; - - c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass); - } - c->curr_recovery_pass++; - c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass); - } - - return ret; -} - -int bch2_run_online_recovery_passes(struct bch_fs *c) -{ - int ret = 0; - - for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) { - struct recovery_pass_fn *p = recovery_pass_fns + i; - - if (!(p->when & PASS_ONLINE)) - continue; - - ret = bch2_run_recovery_pass(c, i); - if (bch2_err_matches(ret, BCH_ERR_restart_recovery)) { - i = c->curr_recovery_pass; - continue; - } - if (ret) - break; - } - - return ret; -} - int bch2_fs_recovery(struct bch_fs *c) { struct bch_sb_field_clean *clean = NULL; @@ -809,24 +605,14 @@ int bch2_fs_recovery(struct bch_fs *c) goto err; } - if (c->opts.fsck && c->opts.norecovery) { - bch_err(c, "cannot select both norecovery and fsck"); - ret = -EINVAL; - goto err; - } + if (c->opts.norecovery) + c->opts.recovery_pass_last = BCH_RECOVERY_PASS_journal_replay - 1; if (!c->opts.nochanges) { mutex_lock(&c->sb_lock); + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); bool write_sb = false; - struct bch_sb_field_ext *ext = - bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(*ext) / sizeof(u64)); - if (!ext) { - ret = -BCH_ERR_ENOSPC_sb; - mutex_unlock(&c->sb_lock); - goto err; - } - if (BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb)) { ext->recovery_passes_required[0] |= cpu_to_le64(bch2_recovery_passes_to_stable(BIT_ULL(BCH_RECOVERY_PASS_check_topology))); @@ -885,7 +671,7 @@ int bch2_fs_recovery(struct bch_fs *c) goto err; } - if (!c->sb.clean || c->opts.fsck || c->opts.keep_journal) { + if (!c->sb.clean || c->opts.fsck || c->opts.retain_recovery_info) { struct genradix_iter iter; struct journal_replay **i; @@ -965,7 +751,7 @@ use_clean: c->journal_replay_seq_end = blacklist_seq - 1; if (c->opts.reconstruct_alloc) - do_reconstruct_alloc(c); + bch2_reconstruct_alloc(c); zero_out_btree_mem_ptr(&c->journal_keys); @@ -1017,6 +803,12 @@ use_clean: clear_bit(BCH_FS_fsck_running, &c->flags); + /* fsync if we fixed errors */ + if (test_bit(BCH_FS_errors_fixed, &c->flags)) { + bch2_journal_flush_all_pins(&c->journal); + bch2_journal_meta(&c->journal); + } + /* If we fixed errors, verify that fs is actually clean now: */ if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) && test_bit(BCH_FS_errors_fixed, &c->flags) && @@ -1051,6 +843,7 @@ use_clean: } mutex_lock(&c->sb_lock); + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); bool write_sb = false; if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != le16_to_cpu(c->disk_sb.sb->version)) { @@ -1064,15 +857,18 @@ use_clean: write_sb = true; } - if (!test_bit(BCH_FS_error, &c->flags)) { - struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); - if (ext && - (!bch2_is_zero(ext->recovery_passes_required, sizeof(ext->recovery_passes_required)) || - !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent)))) { - memset(ext->recovery_passes_required, 0, sizeof(ext->recovery_passes_required)); - memset(ext->errors_silent, 0, sizeof(ext->errors_silent)); - write_sb = true; - } + if (!test_bit(BCH_FS_error, &c->flags) && + !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent))) { + memset(ext->errors_silent, 0, sizeof(ext->errors_silent)); + write_sb = true; + } + + if (c->opts.fsck && + !test_bit(BCH_FS_error, &c->flags) && + c->recovery_pass_done == BCH_RECOVERY_PASS_NR - 1 && + ext->btrees_lost_data) { + ext->btrees_lost_data = 0; + write_sb = true; } if (c->opts.fsck && @@ -1113,9 +909,10 @@ use_clean: out: bch2_flush_fsck_errs(c); - if (!c->opts.keep_journal && - test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) + if (!c->opts.retain_recovery_info) { bch2_journal_keys_put_initial(c); + bch2_find_btree_nodes_exit(&c->found_btree_nodes); + } kfree(clean); if (!ret && @@ -1141,6 +938,7 @@ int bch2_fs_initialize(struct bch_fs *c) int ret; bch_notice(c, "initializing new filesystem"); + set_bit(BCH_FS_new_fs, &c->flags); mutex_lock(&c->sb_lock); c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done); @@ -1155,11 +953,11 @@ int bch2_fs_initialize(struct bch_fs *c) } mutex_unlock(&c->sb_lock); - c->curr_recovery_pass = ARRAY_SIZE(recovery_pass_fns); + c->curr_recovery_pass = BCH_RECOVERY_PASS_NR; set_bit(BCH_FS_may_go_rw, &c->flags); for (unsigned i = 0; i < BTREE_ID_NR; i++) - bch2_btree_root_alloc(c, i); + bch2_btree_root_alloc_fake(c, i, 0); for_each_member_device(c, ca) bch2_dev_usage_init(ca); @@ -1230,7 +1028,7 @@ int bch2_fs_initialize(struct bch_fs *c) if (ret) goto err; - c->recovery_pass_done = ARRAY_SIZE(recovery_pass_fns) - 1; + c->recovery_pass_done = BCH_RECOVERY_PASS_NR - 1; if (enabled_qtypes(c)) { ret = bch2_fs_quota_read(c); diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h index 4e9d24719b2e..4bf818de1f2f 100644 --- a/fs/bcachefs/recovery.h +++ b/fs/bcachefs/recovery.h @@ -2,37 +2,9 @@ #ifndef _BCACHEFS_RECOVERY_H #define _BCACHEFS_RECOVERY_H -extern const char * const bch2_recovery_passes[]; +void bch2_btree_lost_data(struct bch_fs *, enum btree_id); -u64 bch2_recovery_passes_to_stable(u64 v); -u64 bch2_recovery_passes_from_stable(u64 v); - -/* - * For when we need to rewind recovery passes and run a pass we skipped: - */ -static inline int bch2_run_explicit_recovery_pass(struct bch_fs *c, - enum bch_recovery_pass pass) -{ - if (c->recovery_passes_explicit & BIT_ULL(pass)) - return 0; - - bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)", - bch2_recovery_passes[pass], pass, - bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass); - - c->recovery_passes_explicit |= BIT_ULL(pass); - - if (c->curr_recovery_pass >= pass) { - c->curr_recovery_pass = pass; - c->recovery_passes_complete &= (1ULL << pass) >> 1; - return -BCH_ERR_restart_recovery; - } else { - return 0; - } -} - -int bch2_run_online_recovery_passes(struct bch_fs *); -u64 bch2_fsck_recovery_passes(void); +int bch2_journal_replay(struct bch_fs *); int bch2_fs_recovery(struct bch_fs *); int bch2_fs_initialize(struct bch_fs *); diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c new file mode 100644 index 000000000000..cb501460d615 --- /dev/null +++ b/fs/bcachefs/recovery_passes.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "bcachefs.h" +#include "alloc_background.h" +#include "backpointers.h" +#include "btree_gc.h" +#include "btree_node_scan.h" +#include "ec.h" +#include "fsck.h" +#include "inode.h" +#include "journal.h" +#include "lru.h" +#include "logged_ops.h" +#include "rebalance.h" +#include "recovery.h" +#include "recovery_passes.h" +#include "snapshot.h" +#include "subvolume.h" +#include "super.h" +#include "super-io.h" + +const char * const bch2_recovery_passes[] = { +#define x(_fn, ...) #_fn, + BCH_RECOVERY_PASSES() +#undef x + NULL +}; + +static int bch2_check_allocations(struct bch_fs *c) +{ + return bch2_gc(c, true, false); +} + +static int bch2_set_may_go_rw(struct bch_fs *c) +{ + struct journal_keys *keys = &c->journal_keys; + + /* + * After we go RW, the journal keys buffer can't be modified (except for + * setting journal_key->overwritten: it will be accessed by multiple + * threads + */ + move_gap(keys, keys->nr); + + set_bit(BCH_FS_may_go_rw, &c->flags); + + if (keys->nr || c->opts.fsck || !c->sb.clean) + return bch2_fs_read_write_early(c); + return 0; +} + +struct recovery_pass_fn { + int (*fn)(struct bch_fs *); + unsigned when; +}; + +static struct recovery_pass_fn recovery_pass_fns[] = { +#define x(_fn, _id, _when) { .fn = bch2_##_fn, .when = _when }, + BCH_RECOVERY_PASSES() +#undef x +}; + +static const u8 passes_to_stable_map[] = { +#define x(n, id, ...) [BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n, + BCH_RECOVERY_PASSES() +#undef x +}; + +static enum bch_recovery_pass_stable bch2_recovery_pass_to_stable(enum bch_recovery_pass pass) +{ + return passes_to_stable_map[pass]; +} + +u64 bch2_recovery_passes_to_stable(u64 v) +{ + u64 ret = 0; + for (unsigned i = 0; i < ARRAY_SIZE(passes_to_stable_map); i++) + if (v & BIT_ULL(i)) + ret |= BIT_ULL(passes_to_stable_map[i]); + return ret; +} + +u64 bch2_recovery_passes_from_stable(u64 v) +{ + static const u8 map[] = { +#define x(n, id, ...) [BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n, + BCH_RECOVERY_PASSES() +#undef x + }; + + u64 ret = 0; + for (unsigned i = 0; i < ARRAY_SIZE(map); i++) + if (v & BIT_ULL(i)) + ret |= BIT_ULL(map[i]); + return ret; +} + +/* + * For when we need to rewind recovery passes and run a pass we skipped: + */ +int bch2_run_explicit_recovery_pass(struct bch_fs *c, + enum bch_recovery_pass pass) +{ + if (c->recovery_passes_explicit & BIT_ULL(pass)) + return 0; + + bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)", + bch2_recovery_passes[pass], pass, + bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass); + + c->recovery_passes_explicit |= BIT_ULL(pass); + + if (c->curr_recovery_pass >= pass) { + c->curr_recovery_pass = pass; + c->recovery_passes_complete &= (1ULL << pass) >> 1; + return -BCH_ERR_restart_recovery; + } else { + return 0; + } +} + +int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *c, + enum bch_recovery_pass pass) +{ + enum bch_recovery_pass_stable s = bch2_recovery_pass_to_stable(pass); + + mutex_lock(&c->sb_lock); + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + + if (!test_bit_le64(s, ext->recovery_passes_required)) { + __set_bit_le64(s, ext->recovery_passes_required); + bch2_write_super(c); + } + mutex_unlock(&c->sb_lock); + + return bch2_run_explicit_recovery_pass(c, pass); +} + +static void bch2_clear_recovery_pass_required(struct bch_fs *c, + enum bch_recovery_pass pass) +{ + enum bch_recovery_pass_stable s = bch2_recovery_pass_to_stable(pass); + + mutex_lock(&c->sb_lock); + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + + if (test_bit_le64(s, ext->recovery_passes_required)) { + __clear_bit_le64(s, ext->recovery_passes_required); + bch2_write_super(c); + } + mutex_unlock(&c->sb_lock); +} + +u64 bch2_fsck_recovery_passes(void) +{ + u64 ret = 0; + + for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) + if (recovery_pass_fns[i].when & PASS_FSCK) + ret |= BIT_ULL(i); + return ret; +} + +static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass) +{ + struct recovery_pass_fn *p = recovery_pass_fns + pass; + + if (c->recovery_passes_explicit & BIT_ULL(pass)) + return true; + if ((p->when & PASS_FSCK) && c->opts.fsck) + return true; + if ((p->when & PASS_UNCLEAN) && !c->sb.clean) + return true; + if (p->when & PASS_ALWAYS) + return true; + return false; +} + +static int bch2_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass) +{ + struct recovery_pass_fn *p = recovery_pass_fns + pass; + int ret; + + if (!(p->when & PASS_SILENT)) + bch2_print(c, KERN_INFO bch2_log_msg(c, "%s..."), + bch2_recovery_passes[pass]); + ret = p->fn(c); + if (ret) + return ret; + if (!(p->when & PASS_SILENT)) + bch2_print(c, KERN_CONT " done\n"); + + return 0; +} + +int bch2_run_online_recovery_passes(struct bch_fs *c) +{ + int ret = 0; + + for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) { + struct recovery_pass_fn *p = recovery_pass_fns + i; + + if (!(p->when & PASS_ONLINE)) + continue; + + ret = bch2_run_recovery_pass(c, i); + if (bch2_err_matches(ret, BCH_ERR_restart_recovery)) { + i = c->curr_recovery_pass; + continue; + } + if (ret) + break; + } + + return ret; +} + +int bch2_run_recovery_passes(struct bch_fs *c) +{ + int ret = 0; + + while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) { + if (c->opts.recovery_pass_last && + c->curr_recovery_pass > c->opts.recovery_pass_last) + break; + + if (should_run_recovery_pass(c, c->curr_recovery_pass)) { + unsigned pass = c->curr_recovery_pass; + + ret = bch2_run_recovery_pass(c, c->curr_recovery_pass); + if (bch2_err_matches(ret, BCH_ERR_restart_recovery) || + (ret && c->curr_recovery_pass < pass)) + continue; + if (ret) + break; + + c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass); + } + + c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass); + + if (!test_bit(BCH_FS_error, &c->flags)) + bch2_clear_recovery_pass_required(c, c->curr_recovery_pass); + + c->curr_recovery_pass++; + } + + return ret; +} diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h new file mode 100644 index 000000000000..99b464e127b8 --- /dev/null +++ b/fs/bcachefs/recovery_passes.h @@ -0,0 +1,17 @@ +#ifndef _BCACHEFS_RECOVERY_PASSES_H +#define _BCACHEFS_RECOVERY_PASSES_H + +extern const char * const bch2_recovery_passes[]; + +u64 bch2_recovery_passes_to_stable(u64 v); +u64 bch2_recovery_passes_from_stable(u64 v); + +u64 bch2_fsck_recovery_passes(void); + +int bch2_run_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass); +int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *, enum bch_recovery_pass); + +int bch2_run_online_recovery_passes(struct bch_fs *); +int bch2_run_recovery_passes(struct bch_fs *); + +#endif /* _BCACHEFS_RECOVERY_PASSES_H */ diff --git a/fs/bcachefs/recovery_types.h b/fs/bcachefs/recovery_passes_types.h index 4959e95e7c74..773aea9a0080 100644 --- a/fs/bcachefs/recovery_types.h +++ b/fs/bcachefs/recovery_passes_types.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _BCACHEFS_RECOVERY_TYPES_H -#define _BCACHEFS_RECOVERY_TYPES_H +#ifndef _BCACHEFS_RECOVERY_PASSES_TYPES_H +#define _BCACHEFS_RECOVERY_PASSES_TYPES_H #define PASS_SILENT BIT(0) #define PASS_FSCK BIT(1) @@ -13,6 +13,7 @@ * must never change: */ #define BCH_RECOVERY_PASSES() \ + x(scan_for_btree_nodes, 37, 0) \ x(check_topology, 4, 0) \ x(alloc_read, 0, PASS_ALWAYS) \ x(stripes_read, 1, PASS_ALWAYS) \ @@ -31,13 +32,13 @@ x(check_alloc_to_lru_refs, 15, PASS_ONLINE|PASS_FSCK) \ x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \ x(bucket_gens_init, 17, 0) \ + x(reconstruct_snapshots, 38, 0) \ x(check_snapshot_trees, 18, PASS_ONLINE|PASS_FSCK) \ x(check_snapshots, 19, PASS_ONLINE|PASS_FSCK) \ x(check_subvols, 20, PASS_ONLINE|PASS_FSCK) \ x(check_subvol_children, 35, PASS_ONLINE|PASS_FSCK) \ x(delete_dead_snapshots, 21, PASS_ONLINE|PASS_FSCK) \ x(fs_upgrade_for_subvolumes, 22, 0) \ - x(resume_logged_ops, 23, PASS_ALWAYS) \ x(check_inodes, 24, PASS_FSCK) \ x(check_extents, 25, PASS_FSCK) \ x(check_indirect_extents, 26, PASS_FSCK) \ @@ -47,6 +48,7 @@ x(check_subvolume_structure, 36, PASS_ONLINE|PASS_FSCK) \ x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \ x(check_nlinks, 31, PASS_FSCK) \ + x(resume_logged_ops, 23, PASS_ALWAYS) \ x(delete_dead_inodes, 32, PASS_FSCK|PASS_UNCLEAN) \ x(fix_reflink_p, 33, 0) \ x(set_fs_needs_rebalance, 34, 0) \ @@ -56,6 +58,7 @@ enum bch_recovery_pass { #define x(n, id, when) BCH_RECOVERY_PASS_##n, BCH_RECOVERY_PASSES() #undef x + BCH_RECOVERY_PASS_NR }; /* But we also need stable identifiers that can be used in the superblock */ @@ -65,4 +68,4 @@ enum bch_recovery_pass_stable { #undef x }; -#endif /* _BCACHEFS_RECOVERY_TYPES_H */ +#endif /* _BCACHEFS_RECOVERY_PASSES_TYPES_H */ diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index c47c66c2b394..ff7864731a07 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -185,8 +185,7 @@ not_found: } else { bkey_error_init(update); update->k.p = p.k->p; - update->k.p.offset = next_idx; - update->k.size = next_idx - *idx; + update->k.size = p.k->size; set_bkey_val_u64s(&update->k, 0); } diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c index cc2672c12031..678b9c20e251 100644 --- a/fs/bcachefs/replicas.c +++ b/fs/bcachefs/replicas.c @@ -6,12 +6,15 @@ #include "replicas.h" #include "super-io.h" +#include <linux/sort.h> + static int bch2_cpu_replicas_to_sb_replicas(struct bch_fs *, struct bch_replicas_cpu *); /* Some (buggy!) compilers don't allow memcmp to be passed as a pointer */ -static int bch2_memcmp(const void *l, const void *r, size_t size) +static int bch2_memcmp(const void *l, const void *r, const void *priv) { + size_t size = (size_t) priv; return memcmp(l, r, size); } @@ -39,7 +42,8 @@ void bch2_replicas_entry_sort(struct bch_replicas_entry_v1 *e) static void bch2_cpu_replicas_sort(struct bch_replicas_cpu *r) { - eytzinger0_sort(r->entries, r->nr, r->entry_size, bch2_memcmp, NULL); + eytzinger0_sort_r(r->entries, r->nr, r->entry_size, + bch2_memcmp, NULL, (void *)(size_t)r->entry_size); } static void bch2_replicas_entry_v0_to_text(struct printbuf *out, @@ -228,7 +232,7 @@ static inline int __replicas_entry_idx(struct bch_replicas_cpu *r, verify_replicas_entry(search); -#define entry_cmp(_l, _r, size) memcmp(_l, _r, entry_size) +#define entry_cmp(_l, _r) memcmp(_l, _r, entry_size) idx = eytzinger0_find(r->entries, r->nr, r->entry_size, entry_cmp, search); #undef entry_cmp @@ -824,10 +828,11 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r, { unsigned i; - sort_cmp_size(cpu_r->entries, - cpu_r->nr, - cpu_r->entry_size, - bch2_memcmp, NULL); + sort_r(cpu_r->entries, + cpu_r->nr, + cpu_r->entry_size, + bch2_memcmp, NULL, + (void *)(size_t)cpu_r->entry_size); for (i = 0; i < cpu_r->nr; i++) { struct bch_replicas_entry_v1 *e = diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index e4396cb0bacb..d6f81179c3a2 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -7,7 +7,7 @@ #include "bcachefs.h" #include "darray.h" -#include "recovery.h" +#include "recovery_passes.h" #include "sb-downgrade.h" #include "sb-errors.h" #include "super-io.h" diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index 5178bf579f7c..d7d609131030 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -265,7 +265,12 @@ x(subvol_children_bad, 257) \ x(subvol_loop, 258) \ x(subvol_unreachable, 259) \ - x(btree_node_bkey_bad_u64s, 260) + x(btree_node_bkey_bad_u64s, 260) \ + x(btree_node_topology_empty_interior_node, 261) \ + x(btree_ptr_v2_min_key_bad, 262) \ + x(btree_root_unreadable_and_scan_found_nothing, 263) \ + x(snapshot_node_missing, 264) \ + x(dup_backpointer_to_bad_csum_extent, 265) enum bch_sb_error_id { #define x(t, n) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 39debe814bf3..0e806f04f3d7 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -8,6 +8,7 @@ #include "errcode.h" #include "error.h" #include "fs.h" +#include "recovery_passes.h" #include "snapshot.h" #include <linux/random.h> @@ -93,8 +94,10 @@ static int bch2_snapshot_tree_create(struct btree_trans *trans, static bool __bch2_snapshot_is_ancestor_early(struct snapshot_table *t, u32 id, u32 ancestor) { - while (id && id < ancestor) - id = __snapshot_t(t, id)->parent; + while (id && id < ancestor) { + const struct snapshot_t *s = __snapshot_t(t, id); + id = s ? s->parent : 0; + } return id == ancestor; } @@ -110,6 +113,8 @@ static bool bch2_snapshot_is_ancestor_early(struct bch_fs *c, u32 id, u32 ancest static inline u32 get_ancestor_below(struct snapshot_table *t, u32 id, u32 ancestor) { const struct snapshot_t *s = __snapshot_t(t, id); + if (!s) + return 0; if (s->skip[2] <= ancestor) return s->skip[2]; @@ -127,7 +132,7 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor) rcu_read_lock(); struct snapshot_table *t = rcu_dereference(c->snapshots); - if (unlikely(c->recovery_pass_done <= BCH_RECOVERY_PASS_check_snapshots)) { + if (unlikely(c->recovery_pass_done < BCH_RECOVERY_PASS_check_snapshots)) { ret = __bch2_snapshot_is_ancestor_early(t, id, ancestor); goto out; } @@ -151,36 +156,39 @@ out: static noinline struct snapshot_t *__snapshot_t_mut(struct bch_fs *c, u32 id) { size_t idx = U32_MAX - id; - size_t new_size; struct snapshot_table *new, *old; - new_size = max(16UL, roundup_pow_of_two(idx + 1)); + size_t new_bytes = kmalloc_size_roundup(struct_size(new, s, idx + 1)); + size_t new_size = (new_bytes - sizeof(*new)) / sizeof(new->s[0]); - new = kvzalloc(struct_size(new, s, new_size), GFP_KERNEL); + new = kvzalloc(new_bytes, GFP_KERNEL); if (!new) return NULL; + new->nr = new_size; + old = rcu_dereference_protected(c->snapshots, true); if (old) - memcpy(new->s, - rcu_dereference_protected(c->snapshots, true)->s, - sizeof(new->s[0]) * c->snapshot_table_size); + memcpy(new->s, old->s, sizeof(old->s[0]) * old->nr); rcu_assign_pointer(c->snapshots, new); - c->snapshot_table_size = new_size; - kvfree_rcu_mightsleep(old); + kvfree_rcu(old, rcu); - return &rcu_dereference_protected(c->snapshots, true)->s[idx]; + return &rcu_dereference_protected(c->snapshots, + lockdep_is_held(&c->snapshot_table_lock))->s[idx]; } static inline struct snapshot_t *snapshot_t_mut(struct bch_fs *c, u32 id) { size_t idx = U32_MAX - id; + struct snapshot_table *table = + rcu_dereference_protected(c->snapshots, + lockdep_is_held(&c->snapshot_table_lock)); lockdep_assert_held(&c->snapshot_table_lock); - if (likely(idx < c->snapshot_table_size)) - return &rcu_dereference_protected(c->snapshots, true)->s[idx]; + if (likely(table && idx < table->nr)) + return &table->s[idx]; return __snapshot_t_mut(c, id); } @@ -567,6 +575,13 @@ static int check_snapshot_tree(struct btree_trans *trans, u32 subvol_id; ret = bch2_snapshot_tree_master_subvol(trans, root_id, &subvol_id); + bch_err_fn(c, ret); + + if (bch2_err_matches(ret, ENOENT)) { /* nothing to be done here */ + ret = 0; + goto err; + } + if (ret) goto err; @@ -724,7 +739,6 @@ static int check_snapshot(struct btree_trans *trans, u32 parent_id = bch2_snapshot_parent_early(c, k.k->p.offset); u32 real_depth; struct printbuf buf = PRINTBUF; - bool should_have_subvol; u32 i, id; int ret = 0; @@ -770,7 +784,7 @@ static int check_snapshot(struct btree_trans *trans, } } - should_have_subvol = BCH_SNAPSHOT_SUBVOL(&s) && + bool should_have_subvol = BCH_SNAPSHOT_SUBVOL(&s) && !BCH_SNAPSHOT_DELETED(&s); if (should_have_subvol) { @@ -872,6 +886,154 @@ int bch2_check_snapshots(struct bch_fs *c) return ret; } +static int check_snapshot_exists(struct btree_trans *trans, u32 id) +{ + struct bch_fs *c = trans->c; + + if (bch2_snapshot_equiv(c, id)) + return 0; + + u32 tree_id; + int ret = bch2_snapshot_tree_create(trans, id, 0, &tree_id); + if (ret) + return ret; + + struct bkey_i_snapshot *snapshot = bch2_trans_kmalloc(trans, sizeof(*snapshot)); + ret = PTR_ERR_OR_ZERO(snapshot); + if (ret) + return ret; + + bkey_snapshot_init(&snapshot->k_i); + snapshot->k.p = POS(0, id); + snapshot->v.tree = cpu_to_le32(tree_id); + snapshot->v.btime.lo = cpu_to_le64(bch2_current_time(c)); + + return bch2_btree_insert_trans(trans, BTREE_ID_snapshots, &snapshot->k_i, 0) ?: + bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0, + bkey_s_c_null, bkey_i_to_s(&snapshot->k_i), 0) ?: + bch2_snapshot_set_equiv(trans, bkey_i_to_s_c(&snapshot->k_i)); +} + +/* Figure out which snapshot nodes belong in the same tree: */ +struct snapshot_tree_reconstruct { + enum btree_id btree; + struct bpos cur_pos; + snapshot_id_list cur_ids; + DARRAY(snapshot_id_list) trees; +}; + +static void snapshot_tree_reconstruct_exit(struct snapshot_tree_reconstruct *r) +{ + darray_for_each(r->trees, i) + darray_exit(i); + darray_exit(&r->trees); + darray_exit(&r->cur_ids); +} + +static inline bool same_snapshot(struct snapshot_tree_reconstruct *r, struct bpos pos) +{ + return r->btree == BTREE_ID_inodes + ? r->cur_pos.offset == pos.offset + : r->cur_pos.inode == pos.inode; +} + +static inline bool snapshot_id_lists_have_common(snapshot_id_list *l, snapshot_id_list *r) +{ + darray_for_each(*l, i) + if (snapshot_list_has_id(r, *i)) + return true; + return false; +} + +static void snapshot_id_list_to_text(struct printbuf *out, snapshot_id_list *s) +{ + bool first = true; + darray_for_each(*s, i) { + if (!first) + prt_char(out, ' '); + first = false; + prt_printf(out, "%u", *i); + } +} + +static int snapshot_tree_reconstruct_next(struct bch_fs *c, struct snapshot_tree_reconstruct *r) +{ + if (r->cur_ids.nr) { + darray_for_each(r->trees, i) + if (snapshot_id_lists_have_common(i, &r->cur_ids)) { + int ret = snapshot_list_merge(c, i, &r->cur_ids); + if (ret) + return ret; + goto out; + } + darray_push(&r->trees, r->cur_ids); + darray_init(&r->cur_ids); + } +out: + r->cur_ids.nr = 0; + return 0; +} + +static int get_snapshot_trees(struct bch_fs *c, struct snapshot_tree_reconstruct *r, struct bpos pos) +{ + if (!same_snapshot(r, pos)) + snapshot_tree_reconstruct_next(c, r); + r->cur_pos = pos; + return snapshot_list_add_nodup(c, &r->cur_ids, pos.snapshot); +} + +int bch2_reconstruct_snapshots(struct bch_fs *c) +{ + struct btree_trans *trans = bch2_trans_get(c); + struct printbuf buf = PRINTBUF; + struct snapshot_tree_reconstruct r = {}; + int ret = 0; + + for (unsigned btree = 0; btree < BTREE_ID_NR; btree++) { + if (btree_type_has_snapshots(btree)) { + r.btree = btree; + + ret = for_each_btree_key(trans, iter, btree, POS_MIN, + BTREE_ITER_ALL_SNAPSHOTS|BTREE_ITER_PREFETCH, k, ({ + get_snapshot_trees(c, &r, k.k->p); + })); + if (ret) + goto err; + + snapshot_tree_reconstruct_next(c, &r); + } + } + + darray_for_each(r.trees, t) { + printbuf_reset(&buf); + snapshot_id_list_to_text(&buf, t); + + darray_for_each(*t, id) { + if (fsck_err_on(!bch2_snapshot_equiv(c, *id), + c, snapshot_node_missing, + "snapshot node %u from tree %s missing", *id, buf.buf)) { + if (t->nr > 1) { + bch_err(c, "cannot reconstruct snapshot trees with multiple nodes"); + ret = -BCH_ERR_fsck_repair_unimplemented; + goto err; + } + + ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, + check_snapshot_exists(trans, *id)); + if (ret) + goto err; + } + } + } +fsck_err: +err: + bch2_trans_put(trans); + snapshot_tree_reconstruct_exit(&r); + printbuf_exit(&buf); + bch_err_fn(c, ret); + return ret; +} + /* * Mark a snapshot as deleted, for future cleanup: */ @@ -1682,6 +1844,20 @@ int bch2_snapshots_read(struct bch_fs *c) POS_MIN, 0, k, (set_is_ancestor_bitmap(c, k.k->p.offset), 0))); bch_err_fn(c, ret); + + /* + * It's important that we check if we need to reconstruct snapshots + * before going RW, so we mark that pass as required in the superblock - + * otherwise, we could end up deleting keys with missing snapshot nodes + * instead + */ + BUG_ON(!test_bit(BCH_FS_new_fs, &c->flags) && + test_bit(BCH_FS_may_go_rw, &c->flags)); + + if (bch2_err_matches(ret, EIO) || + (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_snapshots))) + ret = bch2_run_explicit_recovery_pass_persistent(c, BCH_RECOVERY_PASS_reconstruct_snapshots); + return ret; } diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h index 7c66ffc06385..b7d2fed37c4f 100644 --- a/fs/bcachefs/snapshot.h +++ b/fs/bcachefs/snapshot.h @@ -33,7 +33,11 @@ int bch2_mark_snapshot(struct btree_trans *, enum btree_id, unsigned, static inline struct snapshot_t *__snapshot_t(struct snapshot_table *t, u32 id) { - return &t->s[U32_MAX - id]; + u32 idx = U32_MAX - id; + + return likely(t && idx < t->nr) + ? &t->s[idx] + : NULL; } static inline const struct snapshot_t *snapshot_t(struct bch_fs *c, u32 id) @@ -44,7 +48,8 @@ static inline const struct snapshot_t *snapshot_t(struct bch_fs *c, u32 id) static inline u32 bch2_snapshot_tree(struct bch_fs *c, u32 id) { rcu_read_lock(); - id = snapshot_t(c, id)->tree; + const struct snapshot_t *s = snapshot_t(c, id); + id = s ? s->tree : 0; rcu_read_unlock(); return id; @@ -52,7 +57,8 @@ static inline u32 bch2_snapshot_tree(struct bch_fs *c, u32 id) static inline u32 __bch2_snapshot_parent_early(struct bch_fs *c, u32 id) { - return snapshot_t(c, id)->parent; + const struct snapshot_t *s = snapshot_t(c, id); + return s ? s->parent : 0; } static inline u32 bch2_snapshot_parent_early(struct bch_fs *c, u32 id) @@ -66,19 +72,19 @@ static inline u32 bch2_snapshot_parent_early(struct bch_fs *c, u32 id) static inline u32 __bch2_snapshot_parent(struct bch_fs *c, u32 id) { -#ifdef CONFIG_BCACHEFS_DEBUG - u32 parent = snapshot_t(c, id)->parent; + const struct snapshot_t *s = snapshot_t(c, id); + if (!s) + return 0; - if (parent && - snapshot_t(c, id)->depth != snapshot_t(c, parent)->depth + 1) + u32 parent = s->parent; + if (IS_ENABLED(CONFIG_BCACHEFS_DEBU) && + parent && + s->depth != snapshot_t(c, parent)->depth + 1) panic("id %u depth=%u parent %u depth=%u\n", id, snapshot_t(c, id)->depth, parent, snapshot_t(c, parent)->depth); return parent; -#else - return snapshot_t(c, id)->parent; -#endif } static inline u32 bch2_snapshot_parent(struct bch_fs *c, u32 id) @@ -116,7 +122,8 @@ static inline u32 bch2_snapshot_root(struct bch_fs *c, u32 id) static inline u32 __bch2_snapshot_equiv(struct bch_fs *c, u32 id) { - return snapshot_t(c, id)->equiv; + const struct snapshot_t *s = snapshot_t(c, id); + return s ? s->equiv : 0; } static inline u32 bch2_snapshot_equiv(struct bch_fs *c, u32 id) @@ -133,38 +140,22 @@ static inline bool bch2_snapshot_is_equiv(struct bch_fs *c, u32 id) return id == bch2_snapshot_equiv(c, id); } -static inline bool bch2_snapshot_is_internal_node(struct bch_fs *c, u32 id) +static inline int bch2_snapshot_is_internal_node(struct bch_fs *c, u32 id) { - const struct snapshot_t *s; - bool ret; - rcu_read_lock(); - s = snapshot_t(c, id); - ret = s->children[0]; + const struct snapshot_t *s = snapshot_t(c, id); + int ret = s ? s->children[0] : -BCH_ERR_invalid_snapshot_node; rcu_read_unlock(); return ret; } -static inline u32 bch2_snapshot_is_leaf(struct bch_fs *c, u32 id) -{ - return !bch2_snapshot_is_internal_node(c, id); -} - -static inline u32 bch2_snapshot_sibling(struct bch_fs *c, u32 id) +static inline int bch2_snapshot_is_leaf(struct bch_fs *c, u32 id) { - const struct snapshot_t *s; - u32 parent = __bch2_snapshot_parent(c, id); - - if (!parent) - return 0; - - s = snapshot_t(c, __bch2_snapshot_parent(c, id)); - if (id == s->children[0]) - return s->children[1]; - if (id == s->children[1]) - return s->children[0]; - return 0; + int ret = bch2_snapshot_is_internal_node(c, id); + if (ret < 0) + return ret; + return !ret; } static inline u32 bch2_snapshot_depth(struct bch_fs *c, u32 parent) @@ -218,15 +209,34 @@ static inline bool snapshot_list_has_ancestor(struct bch_fs *c, snapshot_id_list static inline int snapshot_list_add(struct bch_fs *c, snapshot_id_list *s, u32 id) { - int ret; - BUG_ON(snapshot_list_has_id(s, id)); - ret = darray_push(s, id); + int ret = darray_push(s, id); if (ret) bch_err(c, "error reallocating snapshot_id_list (size %zu)", s->size); return ret; } +static inline int snapshot_list_add_nodup(struct bch_fs *c, snapshot_id_list *s, u32 id) +{ + int ret = snapshot_list_has_id(s, id) + ? 0 + : darray_push(s, id); + if (ret) + bch_err(c, "error reallocating snapshot_id_list (size %zu)", s->size); + return ret; +} + +static inline int snapshot_list_merge(struct bch_fs *c, snapshot_id_list *dst, snapshot_id_list *src) +{ + darray_for_each(*src, i) { + int ret = snapshot_list_add_nodup(c, dst, *i); + if (ret) + return ret; + } + + return 0; +} + int bch2_snapshot_lookup(struct btree_trans *trans, u32 id, struct bch_snapshot *s); int bch2_snapshot_get_subvol(struct btree_trans *, u32, @@ -238,6 +248,7 @@ int bch2_snapshot_node_create(struct btree_trans *, u32, int bch2_check_snapshot_trees(struct bch_fs *); int bch2_check_snapshots(struct bch_fs *); +int bch2_reconstruct_snapshots(struct bch_fs *); int bch2_snapshot_node_set_deleted(struct btree_trans *, u32); void bch2_delete_dead_snapshots_work(struct work_struct *); @@ -249,7 +260,7 @@ static inline int bch2_key_has_snapshot_overwrites(struct btree_trans *trans, struct bpos pos) { if (!btree_type_has_snapshots(id) || - bch2_snapshot_is_leaf(trans->c, pos.snapshot)) + bch2_snapshot_is_leaf(trans->c, pos.snapshot) > 0) return 0; return __bch2_key_has_snapshot_overwrites(trans, id, pos); diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index ce7aed121942..88a79c823276 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -595,6 +595,78 @@ err: return ret; } +int bch2_initialize_subvolumes(struct bch_fs *c) +{ + struct bkey_i_snapshot_tree root_tree; + struct bkey_i_snapshot root_snapshot; + struct bkey_i_subvolume root_volume; + int ret; + + bkey_snapshot_tree_init(&root_tree.k_i); + root_tree.k.p.offset = 1; + root_tree.v.master_subvol = cpu_to_le32(1); + root_tree.v.root_snapshot = cpu_to_le32(U32_MAX); + + bkey_snapshot_init(&root_snapshot.k_i); + root_snapshot.k.p.offset = U32_MAX; + root_snapshot.v.flags = 0; + root_snapshot.v.parent = 0; + root_snapshot.v.subvol = cpu_to_le32(BCACHEFS_ROOT_SUBVOL); + root_snapshot.v.tree = cpu_to_le32(1); + SET_BCH_SNAPSHOT_SUBVOL(&root_snapshot.v, true); + + bkey_subvolume_init(&root_volume.k_i); + root_volume.k.p.offset = BCACHEFS_ROOT_SUBVOL; + root_volume.v.flags = 0; + root_volume.v.snapshot = cpu_to_le32(U32_MAX); + root_volume.v.inode = cpu_to_le64(BCACHEFS_ROOT_INO); + + ret = bch2_btree_insert(c, BTREE_ID_snapshot_trees, &root_tree.k_i, NULL, 0) ?: + bch2_btree_insert(c, BTREE_ID_snapshots, &root_snapshot.k_i, NULL, 0) ?: + bch2_btree_insert(c, BTREE_ID_subvolumes, &root_volume.k_i, NULL, 0); + bch_err_fn(c, ret); + return ret; +} + +static int __bch2_fs_upgrade_for_subvolumes(struct btree_trans *trans) +{ + struct btree_iter iter; + struct bkey_s_c k; + struct bch_inode_unpacked inode; + int ret; + + k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, + SPOS(0, BCACHEFS_ROOT_INO, U32_MAX), 0); + ret = bkey_err(k); + if (ret) + return ret; + + if (!bkey_is_inode(k.k)) { + bch_err(trans->c, "root inode not found"); + ret = -BCH_ERR_ENOENT_inode; + goto err; + } + + ret = bch2_inode_unpack(k, &inode); + BUG_ON(ret); + + inode.bi_subvol = BCACHEFS_ROOT_SUBVOL; + + ret = bch2_inode_write(trans, &iter, &inode); +err: + bch2_trans_iter_exit(trans, &iter); + return ret; +} + +/* set bi_subvol on root inode */ +int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c) +{ + int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw, + __bch2_fs_upgrade_for_subvolumes(trans)); + bch_err_fn(c, ret); + return ret; +} + int bch2_fs_subvolumes_init(struct bch_fs *c) { INIT_WORK(&c->snapshot_delete_work, bch2_delete_dead_snapshots_work); diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h index 903c05162c06..d2015d549bd2 100644 --- a/fs/bcachefs/subvolume.h +++ b/fs/bcachefs/subvolume.h @@ -37,6 +37,9 @@ void bch2_delete_dead_snapshots_async(struct bch_fs *); int bch2_subvolume_unlink(struct btree_trans *, u32); int bch2_subvolume_create(struct btree_trans *, u64, u32, u32, u32 *, u32 *, bool); +int bch2_initialize_subvolumes(struct bch_fs *); +int bch2_fs_upgrade_for_subvolumes(struct bch_fs *); + int bch2_fs_subvolumes_init(struct bch_fs *); #endif /* _BCACHEFS_SUBVOLUME_H */ diff --git a/fs/bcachefs/subvolume_types.h b/fs/bcachefs/subvolume_types.h index ae644adfc391..9b10c8947828 100644 --- a/fs/bcachefs/subvolume_types.h +++ b/fs/bcachefs/subvolume_types.h @@ -20,6 +20,8 @@ struct snapshot_t { }; struct snapshot_table { + struct rcu_head rcu; + size_t nr; #ifndef RUST_BINDGEN DECLARE_FLEX_ARRAY(struct snapshot_t, s); #else diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index ad28e370b640..5eee055ee272 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -8,7 +8,7 @@ #include "journal.h" #include "journal_sb.h" #include "journal_seq_blacklist.h" -#include "recovery.h" +#include "recovery_passes.h" #include "replicas.h" #include "quota.h" #include "sb-clean.h" @@ -143,7 +143,7 @@ void bch2_free_super(struct bch_sb_handle *sb) { kfree(sb->bio); if (!IS_ERR_OR_NULL(sb->s_bdev_file)) - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); kfree(sb->holder); kfree(sb->sb_name); @@ -527,9 +527,11 @@ static void bch2_sb_update(struct bch_fs *c) memset(c->sb.errors_silent, 0, sizeof(c->sb.errors_silent)); struct bch_sb_field_ext *ext = bch2_sb_field_get(src, ext); - if (ext) + if (ext) { le_bitvector_to_cpu(c->sb.errors_silent, (void *) ext->errors_silent, sizeof(c->sb.errors_silent) * 8); + c->sb.btrees_lost_data = le64_to_cpu(ext->btrees_lost_data); + } for_each_member_device(c, ca) { struct bch_member m = bch2_sb_member_get(src, ca->dev_idx); @@ -1162,6 +1164,11 @@ static void bch2_sb_ext_to_text(struct printbuf *out, struct bch_sb *sb, kfree(errors_silent); } + + prt_printf(out, "Btrees with missing data:"); + prt_tab(out); + prt_bitflags(out, __bch2_btree_ids, le64_to_cpu(e->btrees_lost_data)); + prt_newline(out); } static const struct bch_sb_field_ops bch_sb_field_ops_ext = { diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 1ad6e5cd9476..ed63018f21be 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -15,6 +15,7 @@ #include "btree_gc.h" #include "btree_journal_iter.h" #include "btree_key_cache.h" +#include "btree_node_scan.h" #include "btree_update_interior.h" #include "btree_io.h" #include "btree_write_buffer.h" @@ -365,7 +366,7 @@ void bch2_fs_read_only(struct bch_fs *c) !test_bit(BCH_FS_emergency_ro, &c->flags) && test_bit(BCH_FS_started, &c->flags) && test_bit(BCH_FS_clean_shutdown, &c->flags) && - !c->opts.norecovery) { + c->recovery_pass_done >= BCH_RECOVERY_PASS_journal_replay) { BUG_ON(c->journal.last_empty_seq != journal_cur_seq(&c->journal)); BUG_ON(atomic_read(&c->btree_cache.dirty)); BUG_ON(atomic_long_read(&c->btree_key_cache.nr_dirty)); @@ -510,7 +511,8 @@ err: int bch2_fs_read_write(struct bch_fs *c) { - if (c->opts.norecovery) + if (c->opts.recovery_pass_last && + c->opts.recovery_pass_last < BCH_RECOVERY_PASS_journal_replay) return -BCH_ERR_erofs_norecovery; if (c->opts.nochanges) @@ -535,6 +537,7 @@ static void __bch2_fs_free(struct bch_fs *c) for (i = 0; i < BCH_TIME_STAT_NR; i++) bch2_time_stats_exit(&c->times[i]); + bch2_find_btree_nodes_exit(&c->found_btree_nodes); bch2_free_pending_node_rewrites(c); bch2_fs_sb_errors_exit(c); bch2_fs_counters_exit(c); @@ -559,6 +562,7 @@ static void __bch2_fs_free(struct bch_fs *c) bch2_io_clock_exit(&c->io_clock[READ]); bch2_fs_compress_exit(c); bch2_journal_keys_put_initial(c); + bch2_find_btree_nodes_exit(&c->found_btree_nodes); BUG_ON(atomic_read(&c->journal_keys.ref)); bch2_fs_btree_write_buffer_exit(c); percpu_free_rwsem(&c->mark_lock); @@ -1015,8 +1019,16 @@ int bch2_fs_start(struct bch_fs *c) for_each_online_member(c, ca) bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx)->last_mount = cpu_to_le64(now); + struct bch_sb_field_ext *ext = + bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(*ext) / sizeof(u64)); mutex_unlock(&c->sb_lock); + if (!ext) { + bch_err(c, "insufficient space in superblock for sb_field_ext"); + ret = -BCH_ERR_ENOSPC_sb; + goto err; + } + for_each_rw_member(c, ca) bch2_dev_allocator_add(c, ca); bch2_recalc_capacity(c); diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c index 216fadf16928..92c6ad75e702 100644 --- a/fs/bcachefs/util.c +++ b/fs/bcachefs/util.c @@ -707,149 +707,6 @@ void memcpy_from_bio(void *dst, struct bio *src, struct bvec_iter src_iter) } } -static int alignment_ok(const void *base, size_t align) -{ - return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || - ((unsigned long)base & (align - 1)) == 0; -} - -static void u32_swap(void *a, void *b, size_t size) -{ - u32 t = *(u32 *)a; - *(u32 *)a = *(u32 *)b; - *(u32 *)b = t; -} - -static void u64_swap(void *a, void *b, size_t size) -{ - u64 t = *(u64 *)a; - *(u64 *)a = *(u64 *)b; - *(u64 *)b = t; -} - -static void generic_swap(void *a, void *b, size_t size) -{ - char t; - - do { - t = *(char *)a; - *(char *)a++ = *(char *)b; - *(char *)b++ = t; - } while (--size > 0); -} - -static inline int do_cmp(void *base, size_t n, size_t size, - int (*cmp_func)(const void *, const void *, size_t), - size_t l, size_t r) -{ - return cmp_func(base + inorder_to_eytzinger0(l, n) * size, - base + inorder_to_eytzinger0(r, n) * size, - size); -} - -static inline void do_swap(void *base, size_t n, size_t size, - void (*swap_func)(void *, void *, size_t), - size_t l, size_t r) -{ - swap_func(base + inorder_to_eytzinger0(l, n) * size, - base + inorder_to_eytzinger0(r, n) * size, - size); -} - -void eytzinger0_sort(void *base, size_t n, size_t size, - int (*cmp_func)(const void *, const void *, size_t), - void (*swap_func)(void *, void *, size_t)) -{ - int i, c, r; - - if (!swap_func) { - if (size == 4 && alignment_ok(base, 4)) - swap_func = u32_swap; - else if (size == 8 && alignment_ok(base, 8)) - swap_func = u64_swap; - else - swap_func = generic_swap; - } - - /* heapify */ - for (i = n / 2 - 1; i >= 0; --i) { - for (r = i; r * 2 + 1 < n; r = c) { - c = r * 2 + 1; - - if (c + 1 < n && - do_cmp(base, n, size, cmp_func, c, c + 1) < 0) - c++; - - if (do_cmp(base, n, size, cmp_func, r, c) >= 0) - break; - - do_swap(base, n, size, swap_func, r, c); - } - } - - /* sort */ - for (i = n - 1; i > 0; --i) { - do_swap(base, n, size, swap_func, 0, i); - - for (r = 0; r * 2 + 1 < i; r = c) { - c = r * 2 + 1; - - if (c + 1 < i && - do_cmp(base, n, size, cmp_func, c, c + 1) < 0) - c++; - - if (do_cmp(base, n, size, cmp_func, r, c) >= 0) - break; - - do_swap(base, n, size, swap_func, r, c); - } - } -} - -void sort_cmp_size(void *base, size_t num, size_t size, - int (*cmp_func)(const void *, const void *, size_t), - void (*swap_func)(void *, void *, size_t size)) -{ - /* pre-scale counters for performance */ - int i = (num/2 - 1) * size, n = num * size, c, r; - - if (!swap_func) { - if (size == 4 && alignment_ok(base, 4)) - swap_func = u32_swap; - else if (size == 8 && alignment_ok(base, 8)) - swap_func = u64_swap; - else - swap_func = generic_swap; - } - - /* heapify */ - for ( ; i >= 0; i -= size) { - for (r = i; r * 2 + size < n; r = c) { - c = r * 2 + size; - if (c < n - size && - cmp_func(base + c, base + c + size, size) < 0) - c += size; - if (cmp_func(base + r, base + c, size) >= 0) - break; - swap_func(base + r, base + c, size); - } - } - - /* sort */ - for (i = n - size; i > 0; i -= size) { - swap_func(base, base + i, size); - for (r = 0; r * 2 + size < i; r = c) { - c = r * 2 + size; - if (c < i - size && - cmp_func(base + c, base + c + size, size) < 0) - c += size; - if (cmp_func(base + r, base + c, size) >= 0) - break; - swap_func(base + r, base + c, size); - } - } -} - #if 0 void eytzinger1_test(void) { diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index 175aee3074c7..b7e7c29278fc 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -631,10 +631,6 @@ static inline void memset_u64s_tail(void *s, int c, unsigned bytes) memset(s + bytes, c, rem); } -void sort_cmp_size(void *base, size_t num, size_t size, - int (*cmp_func)(const void *, const void *, size_t), - void (*swap_func)(void *, void *, size_t)); - /* just the memmove, doesn't update @_nr */ #define __array_insert_item(_array, _nr, _pos) \ memmove(&(_array)[(_pos) + 1], \ @@ -797,4 +793,14 @@ static inline void __set_bit_le64(size_t bit, __le64 *addr) addr[bit / 64] |= cpu_to_le64(BIT_ULL(bit % 64)); } +static inline void __clear_bit_le64(size_t bit, __le64 *addr) +{ + addr[bit / 64] &= !cpu_to_le64(BIT_ULL(bit % 64)); +} + +static inline bool test_bit_le64(size_t bit, __le64 *addr) +{ + return (addr[bit / 64] & cpu_to_le64(BIT_ULL(bit % 64))) != 0; +} + #endif /* _BCACHEFS_UTIL_H */ diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 39e75131fd5a..9901057a15ba 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -495,7 +495,7 @@ static void cramfs_kill_sb(struct super_block *sb) sb->s_mtd = NULL; } else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) { sync_blockdev(sb->s_bdev); - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); } kfree(sbi); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cfb8449c731f..044135796f2b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5668,7 +5668,7 @@ failed_mount: brelse(sbi->s_sbh); if (sbi->s_journal_bdev_file) { invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); - fput(sbi->s_journal_bdev_file); + bdev_fput(sbi->s_journal_bdev_file); } out_fail: invalidate_bdev(sb->s_bdev); @@ -5913,7 +5913,7 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb, out_bh: brelse(bh); out_bdev: - fput(bdev_file); + bdev_fput(bdev_file); return ERR_PTR(errno); } @@ -5952,7 +5952,7 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, out_journal: jbd2_journal_destroy(journal); out_bdev: - fput(bdev_file); + bdev_fput(bdev_file); return ERR_PTR(errno); } @@ -7327,7 +7327,7 @@ static void ext4_kill_sb(struct super_block *sb) kill_block_super(sb); if (bdev_file) - fput(bdev_file); + bdev_fput(bdev_file); } static struct file_system_type ext4_fs_type = { diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index a6867f26f141..a4bc26dfdb1a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1558,7 +1558,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) for (i = 0; i < sbi->s_ndevs; i++) { if (i > 0) - fput(FDEV(i).bdev_file); + bdev_fput(FDEV(i).bdev_file); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); #endif diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 73389c68e251..9609349e92e5 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1141,7 +1141,7 @@ journal_found: lbmLogShutdown(log); close: /* close external log device */ - fput(bdev_file); + bdev_fput(bdev_file); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); @@ -1485,7 +1485,7 @@ int lmLogClose(struct super_block *sb) bdev_file = log->bdev_file; rc = lmLogShutdown(log); - fput(bdev_file); + bdev_fput(bdev_file); kfree(log); diff --git a/fs/namei.c b/fs/namei.c index ceb9ddf8dfdd..c5b2a25be7d0 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4050,6 +4050,8 @@ retry: case 0: case S_IFREG: error = vfs_create(idmap, path.dentry->d_inode, dentry, mode, true); + if (!error) + security_path_post_mknod(idmap, dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(idmap, path.dentry->d_inode, @@ -4060,11 +4062,6 @@ retry: dentry, mode, 0); break; } - - if (error) - goto out2; - - security_path_post_mknod(idmap, dentry); out2: done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2391ab3c3231..84d4093ca713 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3042,12 +3042,9 @@ static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - spin_lock(&nn->client_lock); clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); - put_client_renew_locked(clp); - spin_unlock(&nn->client_lock); + drop_client(clp); } static int @@ -6616,7 +6613,7 @@ deleg_reaper(struct nfsd_net *nn) list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ - atomic_inc(&clp->cl_rpc_users); + kref_get(&clp->cl_nfsdfs.cl_ref); set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); clp->cl_ra_time = ktime_get_boottime_seconds(); } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 6474529c4253..e539ccd39e1e 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2589,7 +2589,7 @@ static void journal_list_init(struct super_block *sb) static void release_journal_dev(struct reiserfs_journal *journal) { if (journal->j_bdev_file) { - fput(journal->j_bdev_file); + bdev_fput(journal->j_bdev_file); journal->j_bdev_file = NULL; } } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 2be227532f39..2cbb92462074 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -594,7 +594,7 @@ static void romfs_kill_sb(struct super_block *sb) #ifdef CONFIG_ROMFS_ON_BLOCK if (sb->s_bdev) { sync_blockdev(sb->s_bdev); - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); } #endif } diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index a0017724d523..13a9d7acf8f8 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -417,6 +417,7 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); + int rc; spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->on_list) { @@ -430,9 +431,10 @@ smb2_close_cached_fid(struct kref *ref) cfid->dentry = NULL; if (cfid->is_open) { - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); - atomic_dec(&cfid->tcon->num_remote_opens); + if (rc != -EBUSY && rc != -EAGAIN) + atomic_dec(&cfid->tcon->num_remote_opens); } free_cached_dir(cfid); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 226d4835c92d..c71ae5c04306 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -250,6 +250,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { @@ -676,6 +678,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, } #endif /* CONFIG_CIFS_STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { atomic_set(&tcon->num_smbs_sent, 0); spin_lock(&tcon->stat_lock); @@ -755,6 +759,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) } #endif /* STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { i++; seq_printf(m, "\n%d) %s", i, tcon->tree_name); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index aa6f1ecb7c0e..d41eedbff674 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -156,6 +156,7 @@ struct workqueue_struct *decrypt_wq; struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; struct workqueue_struct *deferredclose_wq; +struct workqueue_struct *serverclose_wq; __u32 cifs_lock_secret; /* @@ -1888,6 +1889,13 @@ init_cifs(void) goto out_destroy_cifsoplockd_wq; } + serverclose_wq = alloc_workqueue("serverclose", + WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + if (!serverclose_wq) { + rc = -ENOMEM; + goto out_destroy_serverclose_wq; + } + rc = cifs_init_inodecache(); if (rc) goto out_destroy_deferredclose_wq; @@ -1962,6 +1970,8 @@ out_destroy_decrypt_wq: destroy_workqueue(decrypt_wq); out_destroy_cifsiod_wq: destroy_workqueue(cifsiod_wq); +out_destroy_serverclose_wq: + destroy_workqueue(serverclose_wq); out_clean_proc: cifs_proc_clean(); return rc; @@ -1991,6 +2001,7 @@ exit_cifs(void) destroy_workqueue(cifsoplockd_wq); destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); + destroy_workqueue(serverclose_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 7ed9d05f6890..f6a302205f89 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -442,10 +442,10 @@ struct smb_version_operations { /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ - void (*close)(const unsigned int, struct cifs_tcon *, + int (*close)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* close a file, returning file attributes and timestamps */ - void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, + int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *pfile_info); /* send a flush request to the server */ int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); @@ -1281,7 +1281,6 @@ struct cifs_tcon { struct cached_fids *cfids; /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - struct list_head dfs_ses_list; struct delayed_work dfs_cache_work; #endif struct delayed_work query_interfaces; /* query interfaces workqueue job */ @@ -1440,6 +1439,7 @@ struct cifsFileInfo { bool swapfile:1; bool oplock_break_cancelled:1; bool status_file_deleted:1; /* file has been deleted */ + bool offload:1; /* offload final part of _put to a wq */ unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ int count; @@ -1448,6 +1448,7 @@ struct cifsFileInfo { struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ struct work_struct put; /* work for the final part of _put */ + struct work_struct serverclose; /* work for serverclose */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ char *symlink_target; @@ -1804,7 +1805,6 @@ struct cifs_mount_ctx { struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct list_head dfs_ses_list; }; static inline void __free_dfs_info_param(struct dfs_info3_param *param) @@ -2105,6 +2105,7 @@ extern struct workqueue_struct *decrypt_wq; extern struct workqueue_struct *fileinfo_put_wq; extern struct workqueue_struct *cifsoplockd_wq; extern struct workqueue_struct *deferredclose_wq; +extern struct workqueue_struct *serverclose_wq; extern __u32 cifs_lock_secret; extern mempool_t *cifs_sm_req_poolp; @@ -2324,4 +2325,14 @@ struct smb2_compound_vars { struct kvec ea_iov; }; +static inline bool cifs_ses_exiting(struct cifs_ses *ses) +{ + bool ret; + + spin_lock(&ses->ses_lock); + ret = ses->ses_status == SES_EXITING; + spin_unlock(&ses->ses_lock); + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 0723e1b57256..8e0a348f1f66 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -725,31 +725,31 @@ struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon); void cifs_put_tcon_super(struct super_block *sb); int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry); -/* Put references of @ses and @ses->dfs_root_ses */ +/* Put references of @ses and its children */ static inline void cifs_put_smb_ses(struct cifs_ses *ses) { - struct cifs_ses *rses = ses->dfs_root_ses; + struct cifs_ses *next; - __cifs_put_smb_ses(ses); - if (rses) - __cifs_put_smb_ses(rses); + do { + next = ses->dfs_root_ses; + __cifs_put_smb_ses(ses); + } while ((ses = next)); } -/* Get an active reference of @ses and @ses->dfs_root_ses. +/* Get an active reference of @ses and its children. * * NOTE: make sure to call this function when incrementing reference count of * @ses to ensure that any DFS root session attached to it (@ses->dfs_root_ses) * will also get its reference count incremented. * - * cifs_put_smb_ses() will put both references, so call it when you're done. + * cifs_put_smb_ses() will put all references, so call it when you're done. */ static inline void cifs_smb_ses_inc_refcount(struct cifs_ses *ses) { lockdep_assert_held(&cifs_tcp_ses_lock); - ses->ses_count++; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; + for (; ses; ses = ses->dfs_root_ses) + ses->ses_count++; } static inline bool dfs_src_pathname_equal(const char *s1, const char *s2) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 5aee55551573..23b5709ddc31 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -5854,10 +5854,8 @@ SetEARetry: parm_data->list.EA_flags = 0; /* we checked above that name len is less than 255 */ parm_data->list.name_len = (__u8)name_len; - /* EA names are always ASCII */ - if (ea_name) - strncpy(parm_data->list.name, ea_name, name_len); - parm_data->list.name[name_len] = '\0'; + /* EA names are always ASCII and NUL-terminated */ + strscpy(parm_data->list.name, ea_name ?: "", name_len + 1); parm_data->list.value_len = cpu_to_le16(ea_value_len); /* caller ensures that ea_value_len is less than 64K but we need to ensure that it fits within the smb */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 9b85b5341822..85679ae106fd 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -175,6 +175,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { if (!ses->chans[i].server) @@ -232,7 +234,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { - /* check if iface is still active */ + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + continue; + } + spin_unlock(&ses->ses_lock); + spin_lock(&ses->chan_lock); if (cifs_ses_get_chan_index(ses, server) == CIFS_INVAL_CHAN_INDEX) { @@ -1860,6 +1868,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) ctx->sectype != ses->sectype) return 0; + if (ctx->dfs_root_ses != ses->dfs_root_ses) + return 0; + /* * If an existing session is limited to less channels than * requested, it should not be reused @@ -1963,31 +1974,6 @@ out: return rc; } -/** - * cifs_free_ipc - helper to release the session IPC tcon - * @ses: smb session to unmount the IPC from - * - * Needs to be called everytime a session is destroyed. - * - * On session close, the IPC is closed and the server must release all tcons of the session. - * No need to send a tree disconnect here. - * - * Besides, it will make the server to not close durable and resilient files on session close, as - * specified in MS-SMB2 3.3.5.6 Receiving an SMB2 LOGOFF Request. - */ -static int -cifs_free_ipc(struct cifs_ses *ses) -{ - struct cifs_tcon *tcon = ses->tcon_ipc; - - if (tcon == NULL) - return 0; - - tconInfoFree(tcon); - ses->tcon_ipc = NULL; - return 0; -} - static struct cifs_ses * cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { @@ -2019,48 +2005,52 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) void __cifs_put_smb_ses(struct cifs_ses *ses) { struct TCP_Server_Info *server = ses->server; + struct cifs_tcon *tcon; unsigned int xid; size_t i; + bool do_logoff; int rc; + spin_lock(&cifs_tcp_ses_lock); spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING) { + cifs_dbg(FYI, "%s: id=0x%llx ses_count=%d ses_status=%u ipc=%s\n", + __func__, ses->Suid, ses->ses_count, ses->ses_status, + ses->tcon_ipc ? ses->tcon_ipc->tree_name : "none"); + if (ses->ses_status == SES_EXITING || --ses->ses_count > 0) { spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } - spin_unlock(&ses->ses_lock); + /* ses_count can never go negative */ + WARN_ON(ses->ses_count < 0); - cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); - cifs_dbg(FYI, - "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->tree_name : "NONE"); + spin_lock(&ses->chan_lock); + cifs_chan_clear_need_reconnect(ses, server); + spin_unlock(&ses->chan_lock); - spin_lock(&cifs_tcp_ses_lock); - if (--ses->ses_count > 0) { - spin_unlock(&cifs_tcp_ses_lock); - return; - } - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_GOOD) - ses->ses_status = SES_EXITING; + do_logoff = ses->ses_status == SES_GOOD && server->ops->logoff; + ses->ses_status = SES_EXITING; + tcon = ses->tcon_ipc; + ses->tcon_ipc = NULL; spin_unlock(&ses->ses_lock); spin_unlock(&cifs_tcp_ses_lock); - /* ses_count can never go negative */ - WARN_ON(ses->ses_count < 0); - - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING && server->ops->logoff) { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); + /* + * On session close, the IPC is closed and the server must release all + * tcons of the session. No need to send a tree disconnect here. + * + * Besides, it will make the server to not close durable and resilient + * files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an + * SMB2 LOGOFF Request. + */ + tconInfoFree(tcon); + if (do_logoff) { xid = get_xid(); rc = server->ops->logoff(xid, ses); if (rc) cifs_server_dbg(VFS, "%s: Session Logoff failure rc=%d\n", __func__, rc); _free_xid(xid); - } else { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); } spin_lock(&cifs_tcp_ses_lock); @@ -2373,9 +2363,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) * need to lock before changing something in the session. */ spin_lock(&cifs_tcp_ses_lock); + if (ctx->dfs_root_ses) + cifs_smb_ses_inc_refcount(ctx->dfs_root_ses); ses->dfs_root_ses = ctx->dfs_root_ses; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -3326,6 +3316,9 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) cifs_put_smb_ses(mnt_ctx->ses); else if (mnt_ctx->server) cifs_put_tcp_session(mnt_ctx->server, 0); + mnt_ctx->ses = NULL; + mnt_ctx->tcon = NULL; + mnt_ctx->server = NULL; mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; free_xid(mnt_ctx->xid); } @@ -3604,8 +3597,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) bool isdfs; int rc; - INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list); - rc = dfs_mount_share(&mnt_ctx, &isdfs); if (rc) goto error; @@ -3636,7 +3627,6 @@ out: return rc; error: - dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list); cifs_mount_put_conns(&mnt_ctx); return rc; } @@ -3651,6 +3641,18 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; rc = cifs_mount_get_tcon(&mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx.server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx.ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx.tcon)) + rc = -ENOENT; + } if (rc) goto error; @@ -3988,13 +3990,14 @@ cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) } static struct cifs_tcon * -cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +__cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) { int rc; struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb); struct cifs_ses *ses; struct cifs_tcon *tcon = NULL; struct smb3_fs_context *ctx; + char *origin_fullpath = NULL; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (ctx == NULL) @@ -4018,6 +4021,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->sign = master_tcon->ses->sign; ctx->seal = master_tcon->seal; ctx->witness = master_tcon->use_witness; + ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; rc = cifs_set_vol_auth(ctx, master_tcon->ses); if (rc) { @@ -4037,12 +4041,39 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + spin_lock(&master_tcon->tc_lock); + if (master_tcon->origin_fullpath) { + spin_unlock(&master_tcon->tc_lock); + origin_fullpath = dfs_get_path(cifs_sb, cifs_sb->ctx->source); + if (IS_ERR(origin_fullpath)) { + tcon = ERR_CAST(origin_fullpath); + origin_fullpath = NULL; + cifs_put_smb_ses(ses); + goto out; + } + } else { + spin_unlock(&master_tcon->tc_lock); + } +#endif + tcon = cifs_get_tcon(ses, ctx); if (IS_ERR(tcon)) { cifs_put_smb_ses(ses); goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + if (origin_fullpath) { + spin_lock(&tcon->tc_lock); + tcon->origin_fullpath = origin_fullpath; + spin_unlock(&tcon->tc_lock); + origin_fullpath = NULL; + queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, + dfs_cache_get_ttl() * HZ); + } +#endif + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(ses)) reset_cifs_unix_caps(0, tcon, NULL, ctx); @@ -4051,11 +4082,23 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) out: kfree(ctx->username); kfree_sensitive(ctx->password); + kfree(origin_fullpath); kfree(ctx); return tcon; } +static struct cifs_tcon * +cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +{ + struct cifs_tcon *ret; + + cifs_mount_lock(); + ret = __cifs_construct_tcon(cifs_sb, fsuid); + cifs_mount_unlock(); + return ret; +} + struct cifs_tcon * cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) { diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 449c59830039..3ec965547e3d 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -66,33 +66,20 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) } /* - * Track individual DFS referral servers used by new DFS mount. - * - * On success, their lifetime will be shared by final tcon (dfs_ses_list). - * Otherwise, they will be put by dfs_put_root_smb_sessions() in cifs_mount(). + * Get an active reference of @ses so that next call to cifs_put_tcon() won't + * release it as any new DFS referrals must go through its IPC tcon. */ -static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) +static void add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - struct dfs_root_ses *root_ses; struct cifs_ses *ses = mnt_ctx->ses; if (ses) { - root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL); - if (!root_ses) - return -ENOMEM; - - INIT_LIST_HEAD(&root_ses->list); - spin_lock(&cifs_tcp_ses_lock); cifs_smb_ses_inc_refcount(ses); spin_unlock(&cifs_tcp_ses_lock); - root_ses->ses = ses; - list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list); } - /* Select new DFS referral server so that new referrals go through it */ ctx->dfs_root_ses = ses; - return 0; } static inline int parse_dfs_target(struct smb3_fs_context *ctx, @@ -185,11 +172,8 @@ again: continue; } - if (is_refsrv) { - rc = add_root_smb_session(mnt_ctx); - if (rc) - goto out; - } + if (is_refsrv) + add_root_smb_session(mnt_ctx); rc = ref_walk_advance(rw); if (!rc) { @@ -232,6 +216,7 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_tcon *tcon; char *origin_fullpath; + bool new_tcon = true; int rc; origin_fullpath = dfs_get_path(cifs_sb, ctx->source); @@ -239,6 +224,18 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) return PTR_ERR(origin_fullpath); rc = dfs_referral_walk(mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx->server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx->ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx->tcon)) + rc = -ENOENT; + } if (rc) goto out; @@ -247,15 +244,14 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) if (!tcon->origin_fullpath) { tcon->origin_fullpath = origin_fullpath; origin_fullpath = NULL; + } else { + new_tcon = false; } spin_unlock(&tcon->tc_lock); - if (list_empty(&tcon->dfs_ses_list)) { - list_replace_init(&mnt_ctx->dfs_ses_list, &tcon->dfs_ses_list); + if (new_tcon) { queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, dfs_cache_get_ttl() * HZ); - } else { - dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list); } out: @@ -298,7 +294,6 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) if (rc) return rc; - ctx->dfs_root_ses = mnt_ctx->ses; /* * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally * try to get an DFS referral (even cached) to determine whether it is an DFS mount. @@ -324,7 +319,9 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) *isdfs = true; add_root_smb_session(mnt_ctx); - return __dfs_mount_share(mnt_ctx); + rc = __dfs_mount_share(mnt_ctx); + dfs_put_root_smb_sessions(mnt_ctx); + return rc; } /* Update dfs referral path of superblock */ diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h index 875ab7ae57fc..e5c4dcf83750 100644 --- a/fs/smb/client/dfs.h +++ b/fs/smb/client/dfs.h @@ -7,7 +7,9 @@ #define _CIFS_DFS_H #include "cifsglob.h" +#include "cifsproto.h" #include "fs_context.h" +#include "dfs_cache.h" #include "cifs_unicode.h" #include <linux/namei.h> @@ -114,11 +116,6 @@ static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw) ref_walk_tit(rw)); } -struct dfs_root_ses { - struct list_head list; - struct cifs_ses *ses; -}; - int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs); @@ -133,20 +130,32 @@ static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *p { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses; - return dfs_cache_find(mnt_ctx->xid, ctx->dfs_root_ses, cifs_sb->local_nls, + return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls, cifs_remap(cifs_sb), path, ref, tl); } -static inline void dfs_put_root_smb_sessions(struct list_head *head) +/* + * cifs_get_smb_ses() already guarantees an active reference of + * @ses->dfs_root_ses when a new session is created, so we need to put extra + * references of all DFS root sessions that were used across the mount process + * in dfs_mount_share(). + */ +static inline void dfs_put_root_smb_sessions(struct cifs_mount_ctx *mnt_ctx) { - struct dfs_root_ses *root, *tmp; + const struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct cifs_ses *ses = ctx->dfs_root_ses; + struct cifs_ses *cur; + + if (!ses) + return; - list_for_each_entry_safe(root, tmp, head, list) { - list_del_init(&root->list); - cifs_put_smb_ses(root->ses); - kfree(root); + for (cur = ses; cur; cur = cur->dfs_root_ses) { + if (cur->dfs_root_ses) + cifs_put_smb_ses(cur->dfs_root_ses); } + cifs_put_smb_ses(ses); } #endif /* _CIFS_DFS_H */ diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 508d831fabe3..11c8efecf7aa 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1172,8 +1172,8 @@ static bool is_ses_good(struct cifs_ses *ses) return ret; } -/* Refresh dfs referral of tcon and mark it for reconnect if needed */ -static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_refresh) +/* Refresh dfs referral of @ses and mark it for reconnect if needed */ +static void __refresh_ses_referral(struct cifs_ses *ses, bool force_refresh) { struct TCP_Server_Info *server = ses->server; DFS_CACHE_TGT_LIST(old_tl); @@ -1181,10 +1181,21 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref bool needs_refresh = false; struct cache_entry *ce; unsigned int xid; + char *path = NULL; int rc = 0; xid = get_xid(); + mutex_lock(&server->refpath_lock); + if (server->leaf_fullpath) { + path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC); + if (!path) + rc = -ENOMEM; + } + mutex_unlock(&server->refpath_lock); + if (!path) + goto out; + down_read(&htable_rw_lock); ce = lookup_cache_entry(path); needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce); @@ -1218,19 +1229,17 @@ out: free_xid(xid); dfs_cache_free_tgts(&old_tl); dfs_cache_free_tgts(&new_tl); - return rc; + kfree(path); } -static int refresh_tcon(struct cifs_tcon *tcon, bool force_refresh) +static inline void refresh_ses_referral(struct cifs_ses *ses) { - struct TCP_Server_Info *server = tcon->ses->server; - struct cifs_ses *ses = tcon->ses; + __refresh_ses_referral(ses, false); +} - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, force_refresh); - mutex_unlock(&server->refpath_lock); - return 0; +static inline void force_refresh_ses_referral(struct cifs_ses *ses) +{ + __refresh_ses_referral(ses, true); } /** @@ -1271,34 +1280,20 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) */ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - return refresh_tcon(tcon, true); + force_refresh_ses_referral(tcon->ses); + return 0; } /* Refresh all DFS referrals related to DFS tcon */ void dfs_cache_refresh(struct work_struct *work) { - struct TCP_Server_Info *server; - struct dfs_root_ses *rses; struct cifs_tcon *tcon; struct cifs_ses *ses; tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work); - ses = tcon->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - - list_for_each_entry(rses, &tcon->dfs_ses_list, list) { - ses = rses->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - } + for (ses = tcon->ses; ses; ses = ses->dfs_root_ses) + refresh_ses_referral(ses); queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, atomic_read(&dfs_cache_ttl) * HZ); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index d11dc3aa458b..864b194dbaa0 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -189,6 +189,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; *oplock = 0; if (tcon->ses->server->oplocks) @@ -200,6 +201,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned return PTR_ERR(full_path); } + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -276,6 +281,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned desired_access |= GENERIC_READ; /* is this too little? */ if (OPEN_FMODE(oflags) & FMODE_WRITE) desired_access |= GENERIC_WRITE; + if (rdwr_for_fscache == 1) + desired_access |= GENERIC_READ; disposition = FILE_OVERWRITE_IF; if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) @@ -304,6 +311,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -317,8 +325,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) { cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc); + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access &= ~GENERIC_READ; + rdwr_for_fscache = 2; + goto retry_open; + } goto out; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 16aadce492b2..9be37d0fe724 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -206,12 +206,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) */ } -static inline int cifs_convert_flags(unsigned int flags) +static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache) { if ((flags & O_ACCMODE) == O_RDONLY) return GENERIC_READ; else if ((flags & O_ACCMODE) == O_WRONLY) - return GENERIC_WRITE; + return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE; else if ((flags & O_ACCMODE) == O_RDWR) { /* GENERIC_ALL is too much permission to request can cause unnecessary access denied on create */ @@ -348,11 +348,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ int create_options = CREATE_NOT_DIR; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; if (!server->ops->open) return -ENOSYS; - desired_access = cifs_convert_flags(f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache); /********************************************************************* * open flag mapping table: @@ -389,6 +394,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ if (f_flags & O_DIRECT) create_options |= CREATE_NO_BUFFER; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -400,8 +406,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ }; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) + if (rc) { + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } return rc; + } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -445,6 +459,7 @@ cifs_down_write(struct rw_semaphore *sem) } static void cifsFileInfo_put_work(struct work_struct *work); +void serverclose_work(struct work_struct *work); struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock, @@ -491,6 +506,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); INIT_WORK(&cfile->put, cifsFileInfo_put_work); + INIT_WORK(&cfile->serverclose, serverclose_work); INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close); mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); @@ -582,6 +598,40 @@ static void cifsFileInfo_put_work(struct work_struct *work) cifsFileInfo_put_final(cifs_file); } +void serverclose_work(struct work_struct *work) +{ + struct cifsFileInfo *cifs_file = container_of(work, + struct cifsFileInfo, serverclose); + + struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); + + struct TCP_Server_Info *server = tcon->ses->server; + int rc = 0; + int retries = 0; + int MAX_RETRIES = 4; + + do { + if (server->ops->close_getattr) + rc = server->ops->close_getattr(0, tcon, cifs_file); + else if (server->ops->close) + rc = server->ops->close(0, tcon, &cifs_file->fid); + + if (rc == -EBUSY || rc == -EAGAIN) { + retries++; + msleep(250); + } + } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES) + ); + + if (retries == MAX_RETRIES) + pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES); + + if (cifs_file->offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); +} + /** * cifsFileInfo_put - release a reference of file priv data * @@ -622,10 +672,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; + bool serverclose_offloaded = false; spin_lock(&tcon->open_file_lock); spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); + + cifs_file->offload = offload; if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); spin_unlock(&cifsi->open_file_lock); @@ -667,13 +720,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; + int rc = 0; xid = get_xid(); if (server->ops->close_getattr) - server->ops->close_getattr(xid, tcon, cifs_file); + rc = server->ops->close_getattr(xid, tcon, cifs_file); else if (server->ops->close) - server->ops->close(xid, tcon, &cifs_file->fid); + rc = server->ops->close(xid, tcon, &cifs_file->fid); _free_xid(xid); + + if (rc == -EBUSY || rc == -EAGAIN) { + // Server close failed, hence offloading it as an async op + queue_work(serverclose_wq, &cifs_file->serverclose); + serverclose_offloaded = true; + } } if (oplock_break_cancelled) @@ -681,10 +741,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, cifs_del_pending_open(&open); - if (offload) - queue_work(fileinfo_put_wq, &cifs_file->put); - else - cifsFileInfo_put_final(cifs_file); + // if serverclose has been offloaded to wq (on failure), it will + // handle offloading put as well. If serverclose not offloaded, + // we need to handle offloading put here. + if (!serverclose_offloaded) { + if (offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); + } } int cifs_open(struct inode *inode, struct file *file) @@ -834,11 +899,11 @@ int cifs_open(struct inode *inode, struct file *file) use_cache: fscache_use_cookie(cifs_inode_cookie(file_inode(file)), file->f_mode & FMODE_WRITE); - if (file->f_flags & O_DIRECT && - (!((file->f_flags & O_ACCMODE) != O_RDONLY) || - file->f_flags & O_APPEND)) - cifs_invalidate_cache(file_inode(file), - FSCACHE_INVAL_DIO_WRITE); + if (!(file->f_flags & O_DIRECT)) + goto out; + if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY) + goto out; + cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE); out: free_dentry_path(page); @@ -903,6 +968,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int disposition = FILE_OPEN; int create_options = CREATE_NOT_DIR; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; xid = get_xid(); mutex_lock(&cfile->fh_mutex); @@ -966,7 +1032,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - desired_access = cifs_convert_flags(cfile->f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (cfile->f_flags & O_SYNC) @@ -978,6 +1048,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -1003,6 +1074,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) /* indicate that we need to relock the file */ oparms.reconnect = true; } + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(cfile->f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } if (rc) { mutex_unlock(&cfile->fh_mutex); @@ -1011,6 +1087,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) goto reopen_error_exit; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY reopen_success: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index bdcbe6ff2739..b7bfe705b2c4 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -37,7 +37,7 @@ #include "rfc1002pdu.h" #include "fs_context.h" -static DEFINE_MUTEX(cifs_mount_mutex); +DEFINE_MUTEX(cifs_mount_mutex); static const match_table_t cifs_smb_version_tokens = { { Smb_1, SMB1_VERSION_STRING }, @@ -783,9 +783,9 @@ static int smb3_get_tree(struct fs_context *fc) if (err) return err; - mutex_lock(&cifs_mount_mutex); + cifs_mount_lock(); ret = smb3_get_tree_common(fc); - mutex_unlock(&cifs_mount_mutex); + cifs_mount_unlock(); return ret; } diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 7863f2248c4d..8a35645e0b65 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -304,4 +304,16 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); #define MAX_CACHED_FIDS 16 extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); +extern struct mutex cifs_mount_mutex; + +static inline void cifs_mount_lock(void) +{ + mutex_lock(&cifs_mount_mutex); +} + +static inline void cifs_mount_unlock(void) +{ + mutex_unlock(&cifs_mount_mutex); +} + #endif diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index a3d73720914f..1f2ea9f5cc9a 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -109,6 +109,11 @@ static inline void cifs_readahead_to_fscache(struct inode *inode, __cifs_readahead_to_fscache(inode, pos, len); } +static inline bool cifs_fscache_enabled(struct inode *inode) +{ + return fscache_cookie_enabled(cifs_inode_cookie(inode)); +} + #else /* CONFIG_CIFS_FSCACHE */ static inline void cifs_fscache_fill_coherency(struct inode *inode, @@ -124,6 +129,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {} static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {} static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {} +static inline bool cifs_fscache_enabled(struct inode *inode) { return false; } static inline int cifs_fscache_query_occupancy(struct inode *inode, pgoff_t first, unsigned int nr_pages, diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index c012dfdba80d..855ac5a62edf 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -247,7 +247,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { - if (ses_it->Suid == out.session_id) { + spin_lock(&ses_it->ses_lock); + if (ses_it->ses_status != SES_EXITING && + ses_it->Suid == out.session_id) { ses = ses_it; /* * since we are using the session outside the crit @@ -255,9 +257,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug * so increment its refcount */ cifs_smb_ses_inc_refcount(ses); + spin_unlock(&ses_it->ses_lock); found = true; goto search_end; } + spin_unlock(&ses_it->ses_lock); } } search_end: diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index c3771fc81328..33ac4f8f5050 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -138,9 +138,6 @@ tcon_info_alloc(bool dir_leases_enabled) atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); ret_buf->stats_from_time = ktime_get_real_seconds(); -#ifdef CONFIG_CIFS_DFS_UPCALL - INIT_LIST_HEAD(&ret_buf->dfs_ses_list); -#endif return ret_buf; } @@ -156,9 +153,6 @@ tconInfoFree(struct cifs_tcon *tcon) atomic_dec(&tconInfoAllocCount); kfree(tcon->nativeFileSystem); kfree_sensitive(tcon->password); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_put_root_smb_sessions(&tcon->dfs_ses_list); -#endif kfree(tcon->origin_fullpath); kfree(tcon); } @@ -487,6 +481,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index a9eaba8083b0..212ec6f66ec6 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -753,11 +753,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } -static void +static int cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - CIFSSMBClose(xid, tcon, fid->netfid); + return CIFSSMBClose(xid, tcon, fid->netfid); } static int diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 82b84a4941dd..cc72be5a93a9 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); cifs_stats_inc( @@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 2ed456948f34..b156eefa75d7 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1412,14 +1412,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) memcpy(cfile->fid.create_guid, fid->create_guid, 16); } -static void +static int smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); + return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } -static void +static int smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile) { @@ -1430,7 +1430,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, &file_inf); if (rc) - return; + return rc; inode = d_inode(cfile->dentry); @@ -1459,6 +1459,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* End of file and Attributes should not have to be updated on close */ spin_unlock(&inode->i_lock); + return rc; } static int @@ -2480,6 +2481,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); @@ -3913,7 +3916,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, strcat(message, "W"); } if (!new_oplock) - strncpy(message, "None", sizeof(message)); + strscpy(message, "None"); cinode->oplock = new_oplock; cifs_dbg(FYI, "%s Lease granted on inode %p\n", message, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 3ea688558e6c..c0c4933af5fc 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3628,9 +3628,9 @@ replay_again: memcpy(&pbuf->network_open_info, &rsp->network_open_info, sizeof(pbuf->network_open_info)); + atomic_dec(&tcon->num_remote_opens); } - atomic_dec(&tcon->num_remote_opens); close_exit: SMB2_close_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 5a3ca62d2f07..1d6e54f7879e 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -659,7 +659,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) } spin_unlock(&server->srv_lock); if (!is_binding && !server->session_estab) { - strncpy(shdr->Signature, "BSRSPYL", 8); + strscpy(shdr->Signature, "BSRSPYL"); return 0; } diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index 8ca8a45c4c62..686b321c5a8b 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -167,7 +167,8 @@ struct ksmbd_share_config_response { __u16 force_uid; __u16 force_gid; __s8 share_name[KSMBD_REQ_MAX_SHARE_NAME]; - __u32 reserved[112]; /* Reserved room */ + __u32 reserved[111]; /* Reserved room */ + __u32 payload_sz; __u32 veto_list_sz; __s8 ____payload[]; }; diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 328a412259dc..a2f0a2edceb8 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -158,7 +158,12 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, share->name = kstrdup(name, GFP_KERNEL); if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - share->path = kstrdup(ksmbd_share_config_path(resp), + int path_len = PATH_MAX; + + if (resp->payload_sz) + path_len = resp->payload_sz - resp->veto_list_sz; + + share->path = kstrndup(ksmbd_share_config_path(resp), path_len, GFP_KERNEL); if (share->path) share->path_sz = strlen(share->path); diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index a45f7dca482e..606aa3c5189a 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -228,6 +228,11 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || + (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && + conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; } @@ -278,11 +283,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || - (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && - conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d478fa0c57ab..5723bbf372d7 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -5857,8 +5857,9 @@ static int smb2_rename(struct ksmbd_work *work, if (!file_info->ReplaceIfExists) flags = RENAME_NOREPLACE; - smb_break_all_levII_oplock(work, fp, 0); rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags); + if (!rc) + smb_break_all_levII_oplock(work, fp, 0); out: kfree(new_name); return rc; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index f29bb03f0dc4..8752ac82c557 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -65,6 +65,7 @@ struct ipc_msg_table_entry { struct hlist_node ipc_table_hlist; void *response; + unsigned int msg_sz; }; static struct delayed_work ipc_timer_work; @@ -275,6 +276,7 @@ static int handle_response(int type, void *payload, size_t sz) } memcpy(entry->response, payload, sz); + entry->msg_sz = sz; wake_up_interruptible(&entry->wait); ret = 0; break; @@ -453,6 +455,34 @@ out: return ret; } +static int ipc_validate_msg(struct ipc_msg_table_entry *entry) +{ + unsigned int msg_sz = entry->msg_sz; + + if (entry->type == KSMBD_EVENT_RPC_REQUEST) { + struct ksmbd_rpc_command *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz; + } else if (entry->type == KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST) { + struct ksmbd_spnego_authen_response *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_spnego_authen_response) + + resp->session_key_len + resp->spnego_blob_len; + } else if (entry->type == KSMBD_EVENT_SHARE_CONFIG_REQUEST) { + struct ksmbd_share_config_response *resp = entry->response; + + if (resp->payload_sz) { + if (resp->payload_sz < resp->veto_list_sz) + return -EINVAL; + + msg_sz = sizeof(struct ksmbd_share_config_response) + + resp->payload_sz; + } + } + + return entry->msg_sz != msg_sz ? -EINVAL : 0; +} + static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle) { struct ipc_msg_table_entry entry; @@ -477,6 +507,13 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle ret = wait_event_interruptible_timeout(entry.wait, entry.response != NULL, IPC_WAIT_TIMEOUT); + if (entry.response) { + ret = ipc_validate_msg(&entry); + if (ret) { + kvfree(entry.response); + entry.response = NULL; + } + } out: down_write(&ipc_msg_table_lock); hash_del(&entry.ipc_table_hlist); diff --git a/fs/super.c b/fs/super.c index 71d9779c42b1..69ce6c600968 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1515,29 +1515,11 @@ static int fs_bdev_thaw(struct block_device *bdev) return error; } -static void fs_bdev_super_get(void *data) -{ - struct super_block *sb = data; - - spin_lock(&sb_lock); - sb->s_count++; - spin_unlock(&sb_lock); -} - -static void fs_bdev_super_put(void *data) -{ - struct super_block *sb = data; - - put_super(sb); -} - const struct blk_holder_ops fs_holder_ops = { .mark_dead = fs_bdev_mark_dead, .sync = fs_bdev_sync, .freeze = fs_bdev_freeze, .thaw = fs_bdev_thaw, - .get_holder = fs_bdev_super_get, - .put_holder = fs_bdev_super_put, }; EXPORT_SYMBOL_GPL(fs_holder_ops); @@ -1562,7 +1544,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, * writable from userspace even for a read-only block device. */ if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { - fput(bdev_file); + bdev_fput(bdev_file); return -EACCES; } @@ -1573,7 +1555,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, if (atomic_read(&bdev->bd_fsfreeze_count) > 0) { if (fc) warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); - fput(bdev_file); + bdev_fput(bdev_file); return -EBUSY; } spin_lock(&sb_lock); @@ -1693,7 +1675,7 @@ void kill_block_super(struct super_block *sb) generic_shutdown_super(sb); if (bdev) { sync_blockdev(bdev); - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); } } diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index 2307f8037efc..118dedef8ebe 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -218,6 +218,7 @@ const struct file_operations vboxsf_reg_fops = { .release = vboxsf_file_release, .fsync = noop_fsync, .splice_read = filemap_splice_read, + .setlease = simple_nosetlease, }; const struct inode_operations vboxsf_reg_iops = { diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index cabe8ac4fefc..ffb1d565da39 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -151,11 +151,11 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) if (!sbi->nls) { vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); err = -EINVAL; - goto fail_free; + goto fail_destroy_idr; } } - sbi->bdi_id = ida_simple_get(&vboxsf_bdi_ida, 0, 0, GFP_KERNEL); + sbi->bdi_id = ida_alloc(&vboxsf_bdi_ida, GFP_KERNEL); if (sbi->bdi_id < 0) { err = sbi->bdi_id; goto fail_free; @@ -221,9 +221,10 @@ fail_unmap: vboxsf_unmap_folder(sbi->root); fail_free: if (sbi->bdi_id >= 0) - ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); + ida_free(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); +fail_destroy_idr: idr_destroy(&sbi->ino_idr); kfree(sbi); return err; @@ -268,7 +269,7 @@ static void vboxsf_put_super(struct super_block *sb) vboxsf_unmap_folder(sbi->root); if (sbi->bdi_id >= 0) - ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); + ida_free(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c index 72ac9320e6a3..9515bbf0b54c 100644 --- a/fs/vboxsf/utils.c +++ b/fs/vboxsf/utils.c @@ -440,7 +440,6 @@ int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, { const char *in; char *out; - size_t out_len; size_t out_bound_len; size_t in_bound_len; @@ -448,7 +447,6 @@ int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, in_bound_len = utf8_len; out = name; - out_len = 0; /* Reserve space for terminating 0 */ out_bound_len = name_bound_len - 1; @@ -469,7 +467,6 @@ int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len, out += nb; out_bound_len -= nb; - out_len += nb; } *out = 0; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 1a18c381127e..f0fa02264eda 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2030,7 +2030,7 @@ xfs_free_buftarg( fs_put_dax(btp->bt_daxdev, btp->bt_mount); /* the main block device is closed by kill_block_super */ if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev) - fput(btp->bt_bdev_file); + bdev_fput(btp->bt_bdev_file); kfree(btp); } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ea48774f6b76..d55b42b2480d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1301,8 +1301,19 @@ xfs_link( */ if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) && tdp->i_projid != sip->i_projid)) { - error = -EXDEV; - goto error_return; + /* + * Project quota setup skips special files which can + * leave inodes in a PROJINHERIT directory without a + * project ID set. We need to allow links to be made + * to these "project-less" inodes because userspace + * expects them to succeed after project ID setup, + * but everything else should be rejected. + */ + if (!special_file(VFS_I(sip)->i_mode) || + sip->i_projid != 0) { + error = -EXDEV; + goto error_return; + } } if (!resblks) { diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index c21f10ab0f5d..bce020374c5e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -485,7 +485,7 @@ xfs_open_devices( mp->m_logdev_targp = mp->m_ddev_targp; /* Handle won't be used, drop it */ if (logdev_file) - fput(logdev_file); + bdev_fput(logdev_file); } return 0; @@ -497,10 +497,10 @@ xfs_open_devices( xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: if (rtdev_file) - fput(rtdev_file); + bdev_fput(rtdev_file); out_close_logdev: if (logdev_file) - fput(logdev_file); + bdev_fput(logdev_file); return error; } diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index eb4c369a79eb..35d4ca4f6122 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -86,7 +86,7 @@ void kvm_vcpu_pmu_resync_el0(void); */ #define kvm_pmu_update_vcpu_events(vcpu) \ do { \ - if (!has_vhe() && kvm_vcpu_has_pmu(vcpu)) \ + if (!has_vhe() && kvm_arm_support_pmu_v3()) \ vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ } while (0) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c3e8f7cf96be..172c91879999 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1505,16 +1505,6 @@ struct blk_holder_ops { * Thaw the file system mounted on the block device. */ int (*thaw)(struct block_device *bdev); - - /* - * If needed, get a reference to the holder. - */ - void (*get_holder)(void *holder); - - /* - * Release the holder. - */ - void (*put_holder)(void *holder); }; /* @@ -1585,6 +1575,7 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev) int bdev_freeze(struct block_device *bdev); int bdev_thaw(struct block_device *bdev); +void bdev_fput(struct file *bdev_file); struct io_comp_batch { struct request *req_list; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f20f62f9d63..890e152d553e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1574,12 +1574,26 @@ struct bpf_link { enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; - struct work_struct work; + /* rcu is used before freeing, work can be used to schedule that + * RCU-based freeing before that, so they never overlap + */ + union { + struct rcu_head rcu; + struct work_struct work; + }; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); + /* deallocate link resources callback, called without RCU grace period + * waiting + */ void (*dealloc)(struct bpf_link *link); + /* deallocate link resources callback, called after RCU grace period; + * if underlying BPF program is sleepable we go through tasks trace + * RCU GP and then "classic" RCU GP + */ + void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index cb0d6cd1c12f..60693a145894 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -90,6 +90,14 @@ enum cc_attr { * Examples include TDX Guest. */ CC_ATTR_HOTPLUG_DISABLED, + + /** + * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. + * + * The host kernel is running with the necessary features + * enabled to run SEV-SNP guests. + */ + CC_ATTR_HOST_SEV_SNP, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM @@ -107,10 +115,14 @@ enum cc_attr { * * FALSE - Specified Confidential Computing attribute is not active */ bool cc_platform_has(enum cc_attr attr); +void cc_platform_set(enum cc_attr attr); +void cc_platform_clear(enum cc_attr attr); #else /* !CONFIG_ARCH_HAS_CC_PLATFORM */ static inline bool cc_platform_has(enum cc_attr attr) { return false; } +static inline void cc_platform_set(enum cc_attr attr) { } +static inline void cc_platform_clear(enum cc_attr attr) { } #endif /* CONFIG_ARCH_HAS_CC_PLATFORM */ diff --git a/include/linux/device.h b/include/linux/device.h index 97c4b046c09d..b9f5464f44ed 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1247,6 +1247,7 @@ void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 770755df852f..70cd7258cd29 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -245,7 +245,6 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * max utilization to the allowed CPU capacity before calculating * effective performance. */ - max_util = map_util_perf(max_util); max_util = min(max_util, allowed_cpu_cap); /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 00fc429b0af0..8dfd53b52744 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -121,6 +121,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) +/* File writes are restricted (block device specific) */ +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index e24893625085..05df0e399d7c 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -294,7 +294,6 @@ struct io_ring_ctx { struct io_submit_state submit_state; - struct io_buffer_list *io_bl; struct xarray io_bl_xa; struct io_hash_table cancel_table_locked; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b743241cfb7c..d470303b1bbb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1230,6 +1230,7 @@ int regmap_multi_reg_write_bypassed(struct regmap *map, int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_noinc_read(struct regmap *map, unsigned int reg, @@ -1739,6 +1740,13 @@ static inline int regmap_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_read_bypassed(struct regmap *map, unsigned int reg, + unsigned int *val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 35f3a4a8ceb1..acf7e1a3f3de 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio) /* * Using folio_mapping() is quite slow because of the actual call * instruction. - * We know that secretmem pages are not compound and LRU so we can + * We know that secretmem pages are not compound, so we can * save a couple of cycles here. */ - if (folio_test_large(folio) || !folio_test_lru(folio)) + if (folio_test_large(folio)) return false; mapping = (struct address_space *) diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 3c6caa5abc7c..e9ec32fb97d4 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -44,10 +44,9 @@ typedef u32 depot_stack_handle_t; union handle_parts { depot_stack_handle_t handle; struct { - /* pool_index is offset by 1 */ - u32 pool_index : DEPOT_POOL_INDEX_BITS; - u32 offset : DEPOT_OFFSET_BITS; - u32 extra : STACK_DEPOT_EXTRA_BITS; + u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS; + u32 offset : DEPOT_OFFSET_BITS; + u32 extra : STACK_DEPOT_EXTRA_BITS; }; }; diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index c6540ceea143..0982d1d52b24 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -22,7 +22,7 @@ * * @read: returns the current cycle value * @mask: bitmask for two's complement - * subtraction of non 64 bit counters, + * subtraction of non-64-bit counters, * see CYCLECOUNTER_MASK() helper macro * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) @@ -35,7 +35,7 @@ struct cyclecounter { }; /** - * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds + * struct timecounter - layer above a &struct cyclecounter which counts nanoseconds * Contains the state needed by timecounter_read() to detect * cycle counter wrap around. Initialize with * timecounter_init(). Also used to convert cycle counts into the @@ -66,6 +66,8 @@ struct timecounter { * @cycles: Cycles * @mask: bit mask for maintaining the 'frac' field * @frac: pointer to storage for the fractional nanoseconds. + * + * Returns: cycle counter cycles converted to nanoseconds */ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, u64 cycles, u64 mask, u64 *frac) @@ -79,6 +81,7 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, /** * timecounter_adjtime - Shifts the time of the clock. + * @tc: The &struct timecounter to adjust * @delta: Desired change in nanoseconds. */ static inline void timecounter_adjtime(struct timecounter *tc, s64 delta) @@ -107,6 +110,8 @@ extern void timecounter_init(struct timecounter *tc, * * In other words, keeps track of time since the same epoch as * the function which generated the initial time stamp. + * + * Returns: nanoseconds since the initial time stamp */ extern u64 timecounter_read(struct timecounter *tc); @@ -123,6 +128,8 @@ extern u64 timecounter_read(struct timecounter *tc); * * This allows conversion of cycle counter values which were generated * in the past. + * + * Returns: cycle counter converted to nanoseconds since the initial time stamp */ extern u64 timecounter_cyc2time(const struct timecounter *tc, u64 cycle_tstamp); diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7e50cbd97f86..0ea7823b7f31 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -22,14 +22,14 @@ extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* - * ktime_get() family: read the current time in a multitude of ways, + * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * - * To get the time in a different format, use the ones wit + * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. @@ -74,6 +74,8 @@ extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format + * + * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { @@ -86,10 +88,12 @@ static inline ktime_t ktime_get_coarse_real(void) } /** - * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. + * + * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { @@ -102,7 +106,9 @@ static inline ktime_t ktime_get_coarse_boottime(void) } /** - * ktime_get_clocktai - Returns the TAI time of day in ktime_t format + * ktime_get_clocktai - Get the TAI time of day in ktime_t format + * + * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { @@ -144,32 +150,60 @@ static inline u64 ktime_get_coarse_clocktai_ns(void) /** * ktime_mono_to_real - Convert monotonic time to clock realtime + * @mono: monotonic time to convert + * + * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } +/** + * ktime_get_ns - Get the current time in nanoseconds + * + * Returns: current time converted to nanoseconds + */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } +/** + * ktime_get_real_ns - Get the current real/wall time in nanoseconds + * + * Returns: current real time converted to nanoseconds + */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } +/** + * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds + * + * Returns: current boottime converted to nanoseconds + */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } +/** + * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds + * + * Returns: current TAI time converted to nanoseconds + */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } +/** + * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds + * + * Returns: current raw monotonic time converted to nanoseconds + */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); @@ -224,8 +258,8 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/* - * struct ktime_timestanps - Simultaneous mono/boot/real timestamps +/** + * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp @@ -242,7 +276,8 @@ struct ktime_timestamps { * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time - * @clock_was_set_seq: The sequence number of clock was set events + * @cs_id: Clocksource ID + * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { diff --git a/include/linux/timer.h b/include/linux/timer.h index 14a633ba61d6..e67ecd1cbc97 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -22,7 +22,7 @@ #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif -/** +/* * @TIMER_DEFERRABLE: A deferrable timer will work normally when the * system is busy, but will not cause a CPU to come out of idle just * to service it; instead, the timer will be serviced when the CPU @@ -140,7 +140,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { } * or not. Callers must ensure serialization wrt. other operations done * to this timer, eg. interrupt contexts, or other CPUs on SMP. * - * return value: 1 if the timer is pending, 0 if not. + * Returns: 1 if the timer is pending, 0 if not. */ static inline int timer_pending(const struct timer_list * timer) { @@ -175,6 +175,10 @@ extern int timer_shutdown(struct timer_list *timer); * See timer_delete_sync() for detailed explanation. * * Do not use in new code. Use timer_delete_sync() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer_sync(struct timer_list *timer) { @@ -188,6 +192,10 @@ static inline int del_timer_sync(struct timer_list *timer) * See timer_delete() for detailed explanation. * * Do not use in new code. Use timer_delete() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer(struct timer_list *timer) { diff --git a/include/linux/udp.h b/include/linux/udp.h index 3748e82b627b..17539d089666 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -150,6 +150,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -163,6 +181,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8701ca5f31ee..5c12761cbc0e 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -176,6 +176,15 @@ enum { */ HCI_QUIRK_USE_BDADDR_PROPERTY, + /* When this quirk is set, the Bluetooth Device Address provided by + * the 'local-bd-address' fwnode property is incorrectly specified in + * big-endian order. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BDADDR_PROPERTY_BROKEN, + /* When this quirk is set, the duplicate filtering during * scanning is based on Bluetooth devices addresses. To allow * RSSI based updates, restart scanning if needed. diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 76147feb0d10..4eeedf14711b 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -39,7 +39,6 @@ enum TRI_STATE { #define COMP_ENTRY_SIZE 64 #define RX_BUFFERS_PER_QUEUE 512 -#define MANA_RX_DATA_ALIGN 64 #define MAX_SEND_BUFFERS_PER_QUEUE 256 diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index e0629699b563..1a3c6f66f620 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -267,6 +267,7 @@ struct cs35l56_base { bool fw_patched; bool secured; bool can_hibernate; + bool fw_owns_asp1; bool cal_data_valid; s8 cal_index; struct cirrus_amp_cal_data cal_data; @@ -283,6 +284,7 @@ extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC]; extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC]; int cs35l56_set_patch(struct cs35l56_base *cs35l56_base); +int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base); int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base); int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command); int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base); diff --git a/include/sound/tas2781-tlv.h b/include/sound/tas2781-tlv.h index 4038dd421150..1dc59005d241 100644 --- a/include/sound/tas2781-tlv.h +++ b/include/sound/tas2781-tlv.h @@ -15,7 +15,7 @@ #ifndef __TAS2781_TLV_H__ #define __TAS2781_TLV_H__ -static const DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 100, 0); +static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 100, 0); static const DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0); #endif diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index 5d5c0b8efff2..c71ddb6d4691 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -19,12 +19,6 @@ #include <vdso/time32.h> #include <vdso/time64.h> -#ifdef CONFIG_ARM64 -#include <asm/page-def.h> -#else -#include <asm/page.h> -#endif - #ifdef CONFIG_ARCH_HAS_VDSO_DATA #include <asm/vdso/data.h> #else @@ -132,7 +126,7 @@ extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden */ union vdso_data_store { struct vdso_data data[CS_BASES]; - u8 page[PAGE_SIZE]; + u8 page[1U << CONFIG_PAGE_SHIFT]; }; /* diff --git a/init/initramfs.c b/init/initramfs.c index 3127e0bf7bbd..a298a3854a80 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -367,7 +367,7 @@ static int __init do_name(void) if (S_ISREG(mode)) { int ml = maybe_link(); if (ml >= 0) { - int openflags = O_WRONLY|O_CREAT; + int openflags = O_WRONLY|O_CREAT|O_LARGEFILE; if (ml != 1) openflags |= O_TRUNC; wfile = filp_open(collected, openflags, mode); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 5d4b448fdc50..4521c2b66b98 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -147,6 +147,7 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, static void io_queue_sqe(struct io_kiocb *req); struct kmem_cache *req_cachep; +static struct workqueue_struct *iou_wq __ro_after_init; static int __read_mostly sysctl_io_uring_disabled; static int __read_mostly sysctl_io_uring_group = -1; @@ -350,7 +351,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) err: kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); - kfree(ctx->io_bl); xa_destroy(&ctx->io_bl_xa); kfree(ctx); return NULL; @@ -1982,10 +1982,15 @@ fail: err = -EBADFD; if (!io_file_can_poll(req)) goto fail; - err = -ECANCELED; - if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK) - goto fail; - return; + if (req->file->f_flags & O_NONBLOCK || + req->file->f_mode & FMODE_NOWAIT) { + err = -ECANCELED; + if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK) + goto fail; + return; + } else { + req->flags &= ~REQ_F_APOLL_MULTISHOT; + } } if (req->flags & REQ_F_FORCE_ASYNC) { @@ -2926,7 +2931,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_napi_free(ctx); kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); - kfree(ctx->io_bl); xa_destroy(&ctx->io_bl_xa); kfree(ctx); } @@ -3161,7 +3165,7 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) * noise and overhead, there's no discernable change in runtime * over using system_wq. */ - queue_work(system_unbound_wq, &ctx->exit_work); + queue_work(iou_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) @@ -3443,14 +3447,15 @@ static void *io_uring_validate_mmap_request(struct file *file, ptr = ctx->sq_sqes; break; case IORING_OFF_PBUF_RING: { + struct io_buffer_list *bl; unsigned int bgid; bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT; - rcu_read_lock(); - ptr = io_pbuf_get_address(ctx, bgid); - rcu_read_unlock(); - if (!ptr) - return ERR_PTR(-EINVAL); + bl = io_pbuf_get_bl(ctx, bgid); + if (IS_ERR(bl)) + return bl; + ptr = bl->buf_ring; + io_put_bl(ctx, bl); break; } default: @@ -4185,6 +4190,8 @@ static int __init io_uring_init(void) io_buf_cachep = KMEM_CACHE(io_buffer, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); + iou_wq = alloc_workqueue("iou_exit", WQ_UNBOUND, 64); + #ifdef CONFIG_SYSCTL register_sysctl_init("kernel", kernel_io_uring_disabled_table); #endif diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 693c26da4ee1..3aa16e27f509 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -17,8 +17,6 @@ #define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) -#define BGID_ARRAY 64 - /* BIDs are addressed by a 16-bit field in a CQE */ #define MAX_BIDS_PER_BGID (1 << 16) @@ -40,13 +38,9 @@ struct io_buf_free { int inuse; }; -static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, - struct io_buffer_list *bl, - unsigned int bgid) +static inline struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, + unsigned int bgid) { - if (bl && bgid < BGID_ARRAY) - return &bl[bgid]; - return xa_load(&ctx->io_bl_xa, bgid); } @@ -55,7 +49,7 @@ static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, { lockdep_assert_held(&ctx->uring_lock); - return __io_buffer_get_list(ctx, ctx->io_bl, bgid); + return __io_buffer_get_list(ctx, bgid); } static int io_buffer_add_list(struct io_ring_ctx *ctx, @@ -67,11 +61,7 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx, * always under the ->uring_lock, but the RCU lookup from mmap does. */ bl->bgid = bgid; - smp_store_release(&bl->is_ready, 1); - - if (bgid < BGID_ARRAY) - return 0; - + atomic_set(&bl->refs, 1); return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } @@ -208,24 +198,6 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len, return ret; } -static __cold int io_init_bl_list(struct io_ring_ctx *ctx) -{ - struct io_buffer_list *bl; - int i; - - bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL); - if (!bl) - return -ENOMEM; - - for (i = 0; i < BGID_ARRAY; i++) { - INIT_LIST_HEAD(&bl[i].buf_list); - bl[i].bgid = i; - } - - smp_store_release(&ctx->io_bl, bl); - return 0; -} - /* * Mark the given mapped range as free for reuse */ @@ -294,24 +266,24 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, return i; } +void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) +{ + if (atomic_dec_and_test(&bl->refs)) { + __io_remove_buffers(ctx, bl, -1U); + kfree_rcu(bl, rcu); + } +} + void io_destroy_buffers(struct io_ring_ctx *ctx) { struct io_buffer_list *bl; struct list_head *item, *tmp; struct io_buffer *buf; unsigned long index; - int i; - - for (i = 0; i < BGID_ARRAY; i++) { - if (!ctx->io_bl) - break; - __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); - } xa_for_each(&ctx->io_bl_xa, index, bl) { xa_erase(&ctx->io_bl_xa, bl->bgid); - __io_remove_buffers(ctx, bl, -1U); - kfree_rcu(bl, rcu); + io_put_bl(ctx, bl); } /* @@ -489,12 +461,6 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) io_ring_submit_lock(ctx, issue_flags); - if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { - ret = io_init_bl_list(ctx); - if (ret) - goto err; - } - bl = io_buffer_get_list(ctx, p->bgid); if (unlikely(!bl)) { bl = kzalloc(sizeof(*bl), GFP_KERNEL_ACCOUNT); @@ -507,14 +473,9 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) if (ret) { /* * Doesn't need rcu free as it was never visible, but - * let's keep it consistent throughout. Also can't - * be a lower indexed array group, as adding one - * where lookup failed cannot happen. + * let's keep it consistent throughout. */ - if (p->bgid >= BGID_ARRAY) - kfree_rcu(bl, rcu); - else - WARN_ON_ONCE(1); + kfree_rcu(bl, rcu); goto err; } } @@ -679,12 +640,6 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (reg.ring_entries >= 65536) return -EINVAL; - if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { - int ret = io_init_bl_list(ctx); - if (ret) - return ret; - } - bl = io_buffer_get_list(ctx, reg.bgid); if (bl) { /* if mapped buffer ring OR classic exists, don't allow */ @@ -733,11 +688,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (!bl->is_buf_ring) return -EINVAL; - __io_remove_buffers(ctx, bl, -1U); - if (bl->bgid >= BGID_ARRAY) { - xa_erase(&ctx->io_bl_xa, bl->bgid); - kfree_rcu(bl, rcu); - } + xa_erase(&ctx->io_bl_xa, bl->bgid); + io_put_bl(ctx, bl); return 0; } @@ -767,23 +719,35 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg) return 0; } -void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid) +struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx, + unsigned long bgid) { struct io_buffer_list *bl; + bool ret; - bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid); - - if (!bl || !bl->is_mmap) - return NULL; /* - * Ensure the list is fully setup. Only strictly needed for RCU lookup - * via mmap, and in that case only for the array indexed groups. For - * the xarray lookups, it's either visible and ready, or not at all. + * We have to be a bit careful here - we're inside mmap and cannot grab + * the uring_lock. This means the buffer_list could be simultaneously + * going away, if someone is trying to be sneaky. Look it up under rcu + * so we know it's not going away, and attempt to grab a reference to + * it. If the ref is already zero, then fail the mapping. If successful, + * the caller will call io_put_bl() to drop the the reference at at the + * end. This may then safely free the buffer_list (and drop the pages) + * at that point, vm_insert_pages() would've already grabbed the + * necessary vma references. */ - if (!smp_load_acquire(&bl->is_ready)) - return NULL; - - return bl->buf_ring; + rcu_read_lock(); + bl = xa_load(&ctx->io_bl_xa, bgid); + /* must be a mmap'able buffer ring and have pages */ + ret = false; + if (bl && bl->is_mmap) + ret = atomic_inc_not_zero(&bl->refs); + rcu_read_unlock(); + + if (ret) + return bl; + + return ERR_PTR(-EINVAL); } /* diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index 1c7b654ee726..df365b8860cf 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -25,12 +25,12 @@ struct io_buffer_list { __u16 head; __u16 mask; + atomic_t refs; + /* ring mapped provided buffers */ __u8 is_buf_ring; /* ring mapped provided buffers, but mmap'ed by application */ __u8 is_mmap; - /* bl is visible from an RCU point of view for lookup */ - __u8 is_ready; }; struct io_buffer { @@ -61,7 +61,9 @@ void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags); bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); -void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid); +void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl); +struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx, + unsigned long bgid); static inline bool io_kbuf_recycle_ring(struct io_kiocb *req) { diff --git a/io_uring/rw.c b/io_uring/rw.c index 0585ebcc9773..c8d48287439e 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -937,6 +937,13 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) ret = __io_read(req, issue_flags); /* + * If the file doesn't support proper NOWAIT, then disable multishot + * and stay in single shot mode. + */ + if (!io_file_supports_nowait(req)) + req->flags &= ~REQ_F_APOLL_MULTISHOT; + + /* * If we get -EAGAIN, recycle our buffer and just let normal poll * handling arm it. */ @@ -955,7 +962,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) /* * Any successful return value will keep the multishot read armed. */ - if (ret > 0) { + if (ret > 0 && req->flags & REQ_F_APOLL_MULTISHOT) { /* * Put our buffer and post a CQE. If we fail to post a CQE, then * jump to the termination path. This request is then done. diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ae2ff73bde7e..c287925471f6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3024,17 +3024,46 @@ void bpf_link_inc(struct bpf_link *link) atomic64_inc(&link->refcnt); } +static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) +{ + struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); + + /* free bpf_link and its containing memory */ + link->ops->dealloc_deferred(link); +} + +static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_link_defer_dealloc_rcu_gp(rcu); + else + call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); +} + /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { + bool sleepable = false; + bpf_link_free_id(link->id); if (link->prog) { + sleepable = link->prog->sleepable; /* detach BPF program, clean up used resources */ link->ops->release(link); bpf_prog_put(link->prog); } - /* free bpf_link and its containing memory */ - link->ops->dealloc(link); + if (link->ops->dealloc_deferred) { + /* schedule BPF link deallocation; if underlying BPF program + * is sleepable, we need to first wait for RCU tasks trace + * sync, then go through "classic" RCU grace period + */ + if (sleepable) + call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); + else + call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); + } + if (link->ops->dealloc) + link->ops->dealloc(link); } static void bpf_link_put_deferred(struct work_struct *work) @@ -3544,7 +3573,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, - .dealloc = bpf_raw_tp_link_dealloc, + .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 353985b2b6a2..98188379d5c7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18379,15 +18379,18 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) } if (!env->prog->jit_requested) { verbose(env, "JIT is required to use arena\n"); + fdput(f); return -EOPNOTSUPP; } if (!bpf_jit_supports_arena()) { verbose(env, "JIT doesn't support arena\n"); + fdput(f); return -EOPNOTSUPP; } env->prog->aux->arena = (void *)map; if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { verbose(env, "arena's user address must be set via map_extra or mmap()\n"); + fdput(f); return -EINVAL; } } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 269e21590df5..1331216a9cae 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -697,6 +697,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu) /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted + * @now: current ktime_t * * Called from interrupt entry when the CPU was idle * @@ -794,7 +795,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * This function returns -1 if NOHZ is not enabled. + * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { @@ -820,7 +821,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * This function returns -1 if NOHZ is not enabled. + * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { @@ -1287,6 +1288,8 @@ void tick_nohz_irq_exit(void) /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run + * + * Return: %true if the tick handler has run, otherwise %false */ bool tick_nohz_idle_got_tick(void) { @@ -1305,6 +1308,8 @@ bool tick_nohz_idle_got_tick(void) * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled + * + * Return: the next expiration time */ ktime_t tick_nohz_get_next_hrtimer(void) { @@ -1320,6 +1325,8 @@ ktime_t tick_nohz_get_next_hrtimer(void) * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. + * + * Return: the expected length of the current sleep */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { @@ -1357,8 +1364,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. + * @cpu: target CPU number * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for @cpu */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { @@ -1371,6 +1381,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for the current CPU */ unsigned long tick_nohz_get_idle_calls(void) { @@ -1559,7 +1571,7 @@ early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer - * @mode: tick_nohz_mode to setup for + * @hrtimer: whether to use the hrtimer or not */ void tick_setup_sched_timer(bool hrtimer) { diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index e11c4dc65bcb..b4a7822f495d 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -46,8 +46,8 @@ struct tick_device { * @next_tick: Next tick to be fired when in dynticks mode. * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_waketime: Time when the idle was interrupted + * @idle_sleeptime_seq: sequence counter for data consistency * @idle_entrytime: Time when the idle call was entered - * @nohz_mode: Mode - one state of tick_nohz_mode * @last_jiffies: Base jiffies snapshot when next event was last computed * @timer_expires_base: Base time clock monotonic for @timer_expires * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index dee29f1f5b75..3baf2fbe6848 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -64,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of - * LVL_SIZE buckets. Each level is driven by its own clock and therefor each + * LVL_SIZE buckets. Each level is driven by its own clock and therefore each * level has a different granularity. * - * The level granularity is: LVL_CLK_DIV ^ lvl + * The level granularity is: LVL_CLK_DIV ^ level * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and - * therefor the granularity becomes. + * therefore the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading @@ -207,7 +207,7 @@ EXPORT_SYMBOL(jiffies_64); * struct timer_base - Per CPU timer base (number of base depends on config) * @lock: Lock protecting the timer_base * @running_timer: When expiring timers, the lock is dropped. To make - * sure not to race agains deleting/modifying a + * sure not to race against deleting/modifying a * currently running timer, the pointer is set to the * timer, which expires at the moment. If no timer is * running, the pointer is NULL. @@ -737,7 +737,7 @@ static bool timer_is_static_object(void *addr) } /* - * fixup_init is called when: + * timer_fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) @@ -761,7 +761,7 @@ static void stub_timer(struct timer_list *unused) } /* - * fixup_activate is called when: + * timer_fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ @@ -783,7 +783,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) } /* - * fixup_free is called when: + * timer_fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) @@ -801,7 +801,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state) } /* - * fixup_assert_init is called when: + * timer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) @@ -914,7 +914,7 @@ static void do_init_timer(struct timer_list *timer, * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * - * init_timer_key() must be done to a timer prior calling *any* of the + * init_timer_key() must be done to a timer prior to calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, @@ -1417,7 +1417,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown) * If @shutdown is set then the lock has to be taken whether the * timer is pending or not to protect against a concurrent rearm * which might hit between the lockless pending check and the lock - * aquisition. By taking the lock it is ensured that such a newly + * acquisition. By taking the lock it is ensured that such a newly * enqueued timer is dequeued and cannot end up with * timer->function == NULL in the expiry code. * @@ -2306,7 +2306,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, /* * When timer base is not set idle, undo the effect of - * tmigr_cpu_deactivate() to prevent inconsitent states - active + * tmigr_cpu_deactivate() to prevent inconsistent states - active * timer base but inactive timer migration hierarchy. * * When timer base was already marked idle, nothing will be diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c63a0afdcebe..ccba875d2234 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -751,6 +751,33 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, first_childevt = evt = data->evt; + /* + * Walking the hierarchy is required in any case when a + * remote expiry was done before. This ensures to not lose + * already queued events in non active groups (see section + * "Required event and timerqueue update after a remote + * expiry" in the documentation at the top). + * + * The two call sites which are executed without a remote expiry + * before, are not prevented from propagating changes through + * the hierarchy by the return: + * - When entering this path by tmigr_new_timer(), @evt->ignore + * is never set. + * - tmigr_inactive_up() takes care of the propagation by + * itself and ignores the return value. But an immediate + * return is possible if there is a parent, sparing group + * locking at this level, because the upper walking call to + * the parent will take care about removing this event from + * within the group and update next_expiry accordingly. + * + * However if there is no parent, ie: the hierarchy has only a + * single level so @group is the top level group, make sure the + * first event information of the group is updated properly and + * also handled properly, so skip this fast return path. + */ + if (evt->ignore && !remote && group->parent) + return true; + raw_spin_lock(&group->lock); childstate.state = 0; @@ -762,8 +789,11 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, * queue when the expiry time changed only or when it could be ignored. */ if (timerqueue_node_queued(&evt->nextevt)) { - if ((evt->nextevt.expires == nextexp) && !evt->ignore) + if ((evt->nextevt.expires == nextexp) && !evt->ignore) { + /* Make sure not to miss a new CPU event with the same expiry */ + evt->cpu = first_childevt->cpu; goto check_toplvl; + } if (!timerqueue_del(&group->events, &evt->nextevt)) WRITE_ONCE(group->next_expiry, KTIME_MAX); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0a5c4efc73c3..9dc605f08a23 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2728,7 +2728,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, - .dealloc = bpf_kprobe_multi_link_dealloc, + .dealloc_deferred = bpf_kprobe_multi_link_dealloc, .fill_link_info = bpf_kprobe_multi_link_fill_link_info, }; @@ -3157,6 +3157,9 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link) umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt); + if (umulti_link->task) + put_task_struct(umulti_link->task); + path_put(&umulti_link->path); } static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) @@ -3164,9 +3167,6 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); - if (umulti_link->task) - put_task_struct(umulti_link->task); - path_put(&umulti_link->path); kvfree(umulti_link->uprobes); kfree(umulti_link); } @@ -3242,7 +3242,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { .release = bpf_uprobe_multi_link_release, - .dealloc = bpf_uprobe_multi_link_dealloc, + .dealloc_deferred = bpf_uprobe_multi_link_dealloc, .fill_link_info = bpf_uprobe_multi_link_fill_link_info, }; diff --git a/lib/stackdepot.c b/lib/stackdepot.c index af6cc19a2003..68c97387aa54 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -330,7 +330,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size) stack = current_pool + pool_offset; /* Pre-initialize handle once. */ - stack->handle.pool_index = pool_index + 1; + stack->handle.pool_index_plus_1 = pool_index + 1; stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; stack->handle.extra = 0; INIT_LIST_HEAD(&stack->hash_list); @@ -441,7 +441,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) const int pools_num_cached = READ_ONCE(pools_num); union handle_parts parts = { .handle = handle }; void *pool; - u32 pool_index = parts.pool_index - 1; + u32 pool_index = parts.pool_index_plus_1 - 1; size_t offset = parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; diff --git a/mm/memory.c b/mm/memory.c index 904f70b99498..d2155ced45f8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5973,6 +5973,10 @@ int follow_phys(struct vm_area_struct *vma, goto out; pte = ptep_get(ptep); + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_folio(vma, address, pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 22aa63f4ef63..68fa001648cc 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -989,6 +989,27 @@ unsigned long vmalloc_nr_pages(void) return atomic_long_read(&nr_vmalloc_pages); } +static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) +{ + struct rb_node *n = root->rb_node; + + addr = (unsigned long)kasan_reset_tag((void *)addr); + + while (n) { + struct vmap_area *va; + + va = rb_entry(n, struct vmap_area, rb_node); + if (addr < va->va_start) + n = n->rb_left; + else if (addr >= va->va_end) + n = n->rb_right; + else + return va; + } + + return NULL; +} + /* Look up the first VA which satisfies addr < va_end, NULL if none. */ static struct vmap_area * __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) @@ -1025,47 +1046,39 @@ __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) static struct vmap_node * find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) { - struct vmap_node *vn, *va_node = NULL; - struct vmap_area *va_lowest; + unsigned long va_start_lowest; + struct vmap_node *vn; int i; - for (i = 0; i < nr_vmap_nodes; i++) { +repeat: + for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); - va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root); - if (va_lowest) { - if (!va_node || va_lowest->va_start < (*va)->va_start) { - if (va_node) - spin_unlock(&va_node->busy.lock); - - *va = va_lowest; - va_node = vn; - continue; - } - } + *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); + + if (*va) + if (!va_start_lowest || (*va)->va_start < va_start_lowest) + va_start_lowest = (*va)->va_start; spin_unlock(&vn->busy.lock); } - return va_node; -} - -static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) -{ - struct rb_node *n = root->rb_node; + /* + * Check if found VA exists, it might have gone away. In this case we + * repeat the search because a VA has been removed concurrently and we + * need to proceed to the next one, which is a rare case. + */ + if (va_start_lowest) { + vn = addr_to_node(va_start_lowest); - addr = (unsigned long)kasan_reset_tag((void *)addr); + spin_lock(&vn->busy.lock); + *va = __find_vmap_area(va_start_lowest, &vn->busy.root); - while (n) { - struct vmap_area *va; + if (*va) + return vn; - va = rb_entry(n, struct vmap_area, rb_node); - if (addr < va->va_start) - n = n->rb_left; - else if (addr >= va->va_end) - n = n->rb_right; - else - return va; + spin_unlock(&vn->busy.lock); + goto repeat; } return NULL; @@ -2343,6 +2356,9 @@ struct vmap_area *find_vmap_area(unsigned long addr) struct vmap_area *va; int i, j; + if (unlikely(!vmap_initialized)) + return NULL; + /* * An addr_to_node_id(addr) converts an address to a node index * where a VA is located. If VA spans several zones and passed diff --git a/net/9p/client.c b/net/9p/client.c index e265a0ca6bdd..f7e90b4769bb 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1583,7 +1583,7 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, received = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received); if (non_zc) { int n = copy_to_iter(dataptr, received, to); @@ -1609,9 +1609,6 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) int total = 0; *err = 0; - p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n", - fid->fid, offset, iov_iter_count(from)); - while (iov_iter_count(from)) { int count = iov_iter_count(from); int rsize = fid->iounit; @@ -1623,6 +1620,9 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) if (count < rsize) rsize = count; + p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n", + fid->fid, offset, rsize, count); + /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0, @@ -1650,7 +1650,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) written = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written); p9_req_put(clnt, req); iov_iter_revert(from, count - written - iov_iter_count(from)); diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 1a3948b8c493..196060dc6138 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -95,7 +95,6 @@ struct p9_poll_wait { * @unsent_req_list: accounting for requests that haven't been sent * @rreq: read request * @wreq: write request - * @req: current request being processed (if any) * @tmp_buf: temporary buffer to read in header * @rc: temporary fcall for reading current frame * @wpos: write position for current frame diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index c5462486dbca..282ec581c072 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -105,7 +105,7 @@ void ax25_dev_device_down(struct net_device *dev) spin_lock_bh(&ax25_dev_lock); #ifdef CONFIG_AX25_DAMA_SLAVE - ax25_ds_del_timer(ax25_dev); + timer_shutdown_sync(&ax25_dev->dama.slave_timer); #endif /* diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 1690ae57a09d..a7028d38c1f5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2874,7 +2874,7 @@ static void hci_cancel_cmd_sync(struct hci_dev *hdev, int err) cancel_delayed_work_sync(&hdev->ncmd_timer); atomic_set(&hdev->cmd_cnt, 1); - hci_cmd_sync_cancel_sync(hdev, -err); + hci_cmd_sync_cancel_sync(hdev, err); } /* Suspend HCI device */ @@ -2894,7 +2894,7 @@ int hci_suspend_dev(struct hci_dev *hdev) return 0; /* Cancel potentially blocking sync operation before suspend */ - hci_cancel_cmd_sync(hdev, -EHOSTDOWN); + hci_cancel_cmd_sync(hdev, EHOSTDOWN); hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); @@ -4210,7 +4210,7 @@ static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) err = hci_send_frame(hdev, skb); if (err < 0) { - hci_cmd_sync_cancel_sync(hdev, err); + hci_cmd_sync_cancel_sync(hdev, -err); return; } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 233453807b50..ce3ff2fa72e5 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -218,10 +218,12 @@ static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val > hdev->conn_info_max_age) + hci_dev_lock(hdev); + if (val == 0 || val > hdev->conn_info_max_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_min_age = val; hci_dev_unlock(hdev); @@ -246,10 +248,12 @@ static int conn_info_max_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val < hdev->conn_info_min_age) + hci_dev_lock(hdev); + if (val == 0 || val < hdev->conn_info_min_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_max_age = val; hci_dev_unlock(hdev); @@ -567,10 +571,12 @@ static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val > hdev->sniff_max_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val > hdev->sniff_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_min_interval = val; hci_dev_unlock(hdev); @@ -595,10 +601,12 @@ static int sniff_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val < hdev->sniff_min_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val < hdev->sniff_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_max_interval = val; hci_dev_unlock(hdev); @@ -850,10 +858,12 @@ static int conn_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_min_interval = val; hci_dev_unlock(hdev); @@ -878,10 +888,12 @@ static int conn_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_max_interval = val; hci_dev_unlock(hdev); @@ -990,10 +1002,12 @@ static int adv_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); @@ -1018,10 +1032,12 @@ static int adv_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_max_interval = val; hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4ae224824012..a8b8cfebe018 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3208,6 +3208,31 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, if (test_bit(HCI_ENCRYPT, &hdev->flags)) set_bit(HCI_CONN_ENCRYPT, &conn->flags); + /* "Link key request" completed ahead of "connect request" completes */ + if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && + ev->link_type == ACL_LINK) { + struct link_key *key; + struct hci_cp_read_enc_key_size cp; + + key = hci_find_link_key(hdev, &ev->bdaddr); + if (key) { + set_bit(HCI_CONN_ENCRYPT, &conn->flags); + + if (!(hdev->commands[20] & 0x10)) { + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } else { + cp.handle = cpu_to_le16(conn->handle); + if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, + sizeof(cp), &cp)) { + bt_dev_err(hdev, "sending read key size failed"); + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } + } + + hci_encrypt_cfm(conn, ev->status); + } + } + /* Get remote features */ if (conn->type == ACL_LINK) { struct hci_cp_read_remote_features cp; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index f6b662369322..8fe02921adf1 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -617,7 +617,10 @@ void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err) bt_dev_dbg(hdev, "err 0x%2.2x", err); if (hdev->req_status == HCI_REQ_PEND) { - hdev->req_result = err; + /* req_result is __u32 so error must be positive to be properly + * propagated. + */ + hdev->req_result = err < 0 ? -err : err; hdev->req_status = HCI_REQ_CANCELED; wake_up_interruptible(&hdev->req_wait_q); @@ -3416,7 +3419,10 @@ static void hci_dev_get_bd_addr_from_property(struct hci_dev *hdev) if (ret < 0 || !bacmp(&ba, BDADDR_ANY)) return; - bacpy(&hdev->public_addr, &ba); + if (test_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks)) + baswap(&hdev->public_addr, &ba); + else + bacpy(&hdev->public_addr, &ba); } struct hci_init_stage { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 99d82676f780..cbd0e3586c3f 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1111,6 +1111,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) struct ebt_table_info *newinfo; struct ebt_replace tmp; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1423,6 +1425,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) { struct ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; @@ -2352,6 +2356,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, { struct compat_ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; diff --git a/net/core/dev.c b/net/core/dev.c index 9a67003e49db..984ff8b9d0e1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -429,7 +429,7 @@ EXPORT_PER_CPU_SYMBOL(softnet_data); * PP consumers must pay attention to run APIs in the appropriate context * (e.g. NAPI context). */ -static DEFINE_PER_CPU_ALIGNED(struct page_pool *, system_page_pool); +static DEFINE_PER_CPU(struct page_pool *, system_page_pool); #ifdef CONFIG_LOCKDEP /* diff --git a/net/core/gro.c b/net/core/gro.c index ee30d4f0c038..83f35d99a682 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -192,8 +192,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) } merge: - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 27d733c0f65e..8598466a3805 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -411,6 +411,9 @@ 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) @@ -933,6 +936,9 @@ 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); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index c98b5b71ad7c..e9d45133d641 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -132,30 +132,29 @@ static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; - char designation; + const char *designation = NULL; hsr = netdev_priv(dev); - designation = '\0'; hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: - designation = 'A'; + designation = "Slave A"; break; case HSR_PT_SLAVE_B: - designation = 'B'; + designation = "Slave B"; break; default: - designation = '?'; + designation = "Unknown"; } if (!is_slave_up(port->dev)) - netdev_warn(dev, "Slave %c (%s) is not up; please bring it up to get a fully working HSR network\n", + netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } - if (designation == '\0') + if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c038e28e2f1e..3b38610958ee 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -203,8 +203,15 @@ static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { - if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) - return false; + if (ipv6_only_sock(sk2)) { + if (sk->sk_family == AF_INET) + return false; + +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return false; +#endif + } return inet_bind_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok); @@ -287,6 +294,7 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; + bool conflict = false; bool reuseport_cb_ok; rcu_read_lock(); @@ -299,18 +307,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l spin_lock(&head2->lock); - inet_bind_bucket_for_each(tb2, &head2->chain) - if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) - break; + inet_bind_bucket_for_each(tb2, &head2->chain) { + if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) + continue; - if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) { - spin_unlock(&head2->lock); - return true; + if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok)) + continue; + + conflict = true; + break; } spin_unlock(&head2->lock); - return false; + + return conflict; } /* diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7b16c211b904..57ddcd8c62f6 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { + if (unlikely(!pskb_may_pull(skb, + gre_hdr_len + sizeof(*ershdr)))) + return PACKET_REJECT; + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; + iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 2407066b0fec..b150c9929b12 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -956,6 +956,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1254,6 +1256,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 7da1df4997d0..487670759578 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1108,6 +1108,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1492,6 +1494,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 661d0e0d273f..c02bf011d4a6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -582,6 +582,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b9880743765c..3498dd1d0694 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -449,8 +449,9 @@ static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) NAPI_GRO_CB(p)->count++; p->data_len += skb->len; - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; p->truesize += skb->truesize; p->len += skb->len; @@ -551,11 +552,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - /* we can do L4 aggregation only if the packet can't land in a tunnel - * otherwise we could corrupt the inner stream + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { + /* If the packet was locally encapsulated in a UDP tunnel that + * wasn't detected above, do not GRO. + */ + if (skb->encapsulation) + goto out; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; @@ -719,13 +728,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5c558dc1c683..7209419cfb0e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -651,19 +651,19 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (!w) { /* New dump: * - * 1. hook callback destructor. - */ - cb->args[3] = (long)cb->done; - cb->done = fib6_dump_done; - - /* - * 2. allocate and initialize walker. + * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_dump_node; cb->args[2] = (long)w; + + /* 2. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + } arg.skb = skb; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index ca7e77e84283..c89aef524df9 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -528,6 +528,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, struct ip6_tnl *tunnel; u8 ver; + if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) + return PACKET_REJECT; + ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index fd9f049d6d41..636b360311c5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1125,6 +1125,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1501,6 +1503,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7c1e6469d091..8b1dd7f51249 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -447,7 +447,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 312bcaeea96f..bbd347de00b4 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -174,13 +174,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3a1967bc7bad..7e74b812e366 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3937,8 +3937,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, mptcp_set_state(newsk, TCP_CLOSE); } } else { - MPTCP_INC_STATS(sock_net(ssk), - MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); tcpfallback: newsk->sk_kern_sock = kern; lock_sock(newsk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index dcd1c76d2a3b..73fdf423de44 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1493,6 +1493,10 @@ int mptcp_set_rcvlowat(struct sock *sk, int val) struct mptcp_subflow_context *subflow; int space, cap; + /* bpf can land here with a wrong sk type */ + if (sk->sk_protocol == IPPROTO_TCP) + return -EINVAL; + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 1626dd20c68f..6042a47da61b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -905,6 +905,8 @@ dispose_child: return child; fallback: + if (fallback) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); mptcp_subflow_drop_ctx(child); return child; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fd86f2720c9e..d89d77946719 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1209,10 +1209,11 @@ static bool nft_table_pending_update(const struct nft_ctx *ctx) return true; list_for_each_entry(trans, &nft_net->commit_list, list) { - if ((trans->msg_type == NFT_MSG_NEWCHAIN || - trans->msg_type == NFT_MSG_DELCHAIN) && - trans->ctx.table == ctx->table && - nft_trans_chain_update(trans)) + if (trans->ctx.table == ctx->table && + ((trans->msg_type == NFT_MSG_NEWCHAIN && + nft_trans_chain_update(trans)) || + (trans->msg_type == NFT_MSG_DELCHAIN && + nft_is_base_chain(trans->ctx.chain)))) return true; } @@ -2449,6 +2450,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook = {}; + if (table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; @@ -8293,11 +8297,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, return err; } +/* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; - list_for_each_entry(type, &nf_tables_flowtables, list) { + list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } @@ -8309,9 +8314,13 @@ nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; + rcu_read_lock(); type = __nft_flowtable_type_get(family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -10455,10 +10464,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; + int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) - return -EAGAIN; + err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { @@ -10650,12 +10660,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_abort_release(trans); } - if (action == NFNL_ABORT_AUTOLOAD) - nf_tables_module_autoload(net); - else - nf_tables_module_autoload_cleanup(net); - - return 0; + return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, @@ -10668,6 +10673,17 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, gc_seq = nft_gc_seq_begin(nft_net); ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); + + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + /* module autoload needs to happen after GC sequence update because it + * temporarily releases and grabs mutex again. + */ + if (action == NFNL_ABORT_AUTOLOAD) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + mutex_unlock(&nft_net->commit_mutex); return ret; @@ -11473,9 +11489,10 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nft_net->commit_list) || - !list_empty(&nft_net->module_list)) - __nf_tables_abort(net, NFNL_ABORT_NONE); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + if (!list_empty(&nft_net->module_list)) + nf_tables_module_autoload_cleanup(net); __nft_release_tables(net); @@ -11567,6 +11584,7 @@ static void __exit nf_tables_module_exit(void) unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); + nf_tables_trans_destroy_flush_work(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); diff --git a/net/rds/rdma.c b/net/rds/rdma.c index a4e3c5de998b..00dbcd4d28e6 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -302,7 +302,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, } ret = PTR_ERR(trans_private); /* Trigger connection so that its ready for the next retry */ - if (ret == -ENODEV) + if (ret == -ENODEV && cp) rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 39945b139c48..cd0accaf844a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -241,13 +241,13 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; - struct tc_skbmod opt = { - .index = d->tcf_index, - .refcnt = refcount_read(&d->tcf_refcnt) - ref, - .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - }; + struct tc_skbmod opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + opt.index = d->tcf_index; + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; p = rcu_dereference_protected(d->skbmod_p, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 65e05b0c98e4..60239378d43f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -809,7 +809,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) notify = !sch->q.qlen && !WARN_ON_ONCE(!n && !qdisc_is_offloaded); /* TODO: perform the search on a per txq basis */ - sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); + sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { WARN_ON_ONCE(parentid != TC_H_ROOT); break; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 545017a3daa4..6b3f01beb294 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1206,15 +1206,6 @@ err_noclose: * MSG_SPLICE_PAGES is used exclusively to reduce the number of * copy operations in this path. Therefore the caller must ensure * that the pages backing @xdr are unchanging. - * - * Note that the send is non-blocking. The caller has incremented - * the reference count on each page backing the RPC message, and - * the network layer will "put" these pages when transmission is - * complete. - * - * This is safe for our RPC services because the memory backing - * the head and tail components is never kmalloc'd. These always - * come from pages in the svc_rqst::rq_pages array. */ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, rpc_fraghdr marker, unsigned int *sentp) @@ -1244,6 +1235,7 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, 1 + count, sizeof(marker) + rqstp->rq_res.len); ret = sock_sendmsg(svsk->sk_sock, &msg); + page_frag_free(buf); if (ret < 0) return ret; *sentp += ret; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 1748268e0694..ee5d306a96d0 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -120,7 +120,6 @@ virtio_transport_send_pkt_work(struct work_struct *work) if (!skb) break; - virtio_transport_deliver_tap_pkt(skb); reply = virtio_vsock_skb_reply(skb); sgs = vsock->out_sgs; sg_init_one(sgs[out_sg], virtio_vsock_hdr(skb), @@ -170,6 +169,8 @@ virtio_transport_send_pkt_work(struct work_struct *work) break; } + virtio_transport_deliver_tap_pkt(skb); + if (reply) { struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; int val; diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 967f1abb0edb..cb1be22afc65 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1541,7 +1541,7 @@ sub create_parameterlist($$$$) { save_struct_actual($2); push_parameter($2, "$type $1", $arg, $file, $declaration_name); - } elsif ($param =~ m/(.*?):(\d+)/) { + } elsif ($param =~ m/(.*?):(\w+)/) { if ($type ne "") { # skip unnamed bit-fields save_struct_actual($1); push_parameter($1, "$type:$2", $arg, $file, $declaration_name) diff --git a/security/security.c b/security/security.c index 7e118858b545..0a9a0ac3f266 100644 --- a/security/security.c +++ b/security/security.c @@ -1793,11 +1793,11 @@ int security_path_mknod(const struct path *dir, struct dentry *dentry, EXPORT_SYMBOL(security_path_mknod); /** - * security_path_post_mknod() - Update inode security field after file creation + * security_path_post_mknod() - Update inode security after reg file creation * @idmap: idmap of the mount * @dentry: new file * - * Update inode security field after a file has been created. + * Update inode security field after a regular file has been created. */ void security_path_post_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 0619a1cbbfbe..074d6c2714eb 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -2123,7 +2123,6 @@ static struct file_system_type sel_fs_type = { .kill_sb = sel_kill_sb, }; -static struct vfsmount *selinuxfs_mount __ro_after_init; struct path selinux_null __ro_after_init; static int __init init_sel_fs(void) @@ -2145,18 +2144,21 @@ static int __init init_sel_fs(void) return err; } - selinux_null.mnt = selinuxfs_mount = kern_mount(&sel_fs_type); - if (IS_ERR(selinuxfs_mount)) { + selinux_null.mnt = kern_mount(&sel_fs_type); + if (IS_ERR(selinux_null.mnt)) { pr_err("selinuxfs: could not mount!\n"); - err = PTR_ERR(selinuxfs_mount); - selinuxfs_mount = NULL; + err = PTR_ERR(selinux_null.mnt); + selinux_null.mnt = NULL; + return err; } + selinux_null.dentry = d_hash_and_lookup(selinux_null.mnt->mnt_root, &null_name); if (IS_ERR(selinux_null.dentry)) { pr_err("selinuxfs: could not lookup null!\n"); err = PTR_ERR(selinux_null.dentry); selinux_null.dentry = NULL; + return err; } return err; diff --git a/sound/oss/dmasound/dmasound_paula.c b/sound/oss/dmasound/dmasound_paula.c index 0ba8f0c4cd99..3a593da09280 100644 --- a/sound/oss/dmasound/dmasound_paula.c +++ b/sound/oss/dmasound/dmasound_paula.c @@ -725,7 +725,13 @@ static void __exit amiga_audio_remove(struct platform_device *pdev) dmasound_deinit(); } -static struct platform_driver amiga_audio_driver = { +/* + * amiga_audio_remove() lives in .exit.text. For drivers registered via + * module_platform_driver_probe() this is ok because they cannot get unbound at + * runtime. So mark the driver struct with __refdata to prevent modpost + * triggering a section mismatch warning. + */ +static struct platform_driver amiga_audio_driver __refdata = { .remove_new = __exit_p(amiga_audio_remove), .driver = { .name = "amiga-audio", diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c index d36234b88fb4..941bfbf812ed 100644 --- a/sound/pci/emu10k1/emu10k1_callback.c +++ b/sound/pci/emu10k1/emu10k1_callback.c @@ -255,7 +255,7 @@ lookup_voices(struct snd_emux *emu, struct snd_emu10k1 *hw, /* check if sample is finished playing (non-looping only) */ if (bp != best + V_OFF && bp != best + V_FREE && (vp->reg.sample_mode & SNDRV_SFNT_SAMPLE_SINGLESHOT)) { - val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch) - 64; + val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch); if (val >= vp->reg.loopstart) bp = best + V_OFF; } @@ -362,7 +362,7 @@ start_voice(struct snd_emux_voice *vp) map = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); - addr = vp->reg.start + 64; + addr = vp->reg.start; temp = vp->reg.parm.filterQ; ccca = (temp << 28) | addr; if (vp->apitch < 0xe400) @@ -430,9 +430,6 @@ start_voice(struct snd_emux_voice *vp) /* Q & current address (Q 4bit value, MSB) */ CCCA, ccca, - /* cache */ - CCR, REG_VAL_PUT(CCR_CACHEINVALIDSIZE, 64), - /* reset volume */ VTFT, vtarget | vp->ftarget, CVCF, vtarget | CVCF_CURRENTFILTER_MASK, diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c index 72ec872afb8d..8fb688e41414 100644 --- a/sound/pci/hda/cs35l41_hda_property.c +++ b/sound/pci/hda/cs35l41_hda_property.c @@ -108,7 +108,10 @@ static const struct cs35l41_config cs35l41_config_table[] = { { "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, { "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 }, { "10431F62", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 }, + { "10433A60", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, { "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, + { "17AA3877", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, + { "17AA3878", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, { "17AA38A9", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, { "17AA38AB", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, { "17AA38B4", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, @@ -496,7 +499,10 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = { { "CSC3551", "10431F12", generic_dsd_config }, { "CSC3551", "10431F1F", generic_dsd_config }, { "CSC3551", "10431F62", generic_dsd_config }, + { "CSC3551", "10433A60", generic_dsd_config }, { "CSC3551", "17AA386F", generic_dsd_config }, + { "CSC3551", "17AA3877", generic_dsd_config }, + { "CSC3551", "17AA3878", generic_dsd_config }, { "CSC3551", "17AA38A9", generic_dsd_config }, { "CSC3551", "17AA38AB", generic_dsd_config }, { "CSC3551", "17AA38B4", generic_dsd_config }, diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 1a3f84599cb5..558c1f38fe97 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -644,6 +644,8 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56) ret = cs35l56_wait_for_firmware_boot(&cs35l56->base); if (ret) goto err_powered_up; + + regcache_cache_only(cs35l56->base.regmap, false); } /* Disable auto-hibernate so that runtime_pm has control */ @@ -1002,6 +1004,8 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) if (ret) goto err; + regcache_cache_only(cs35l56->base.regmap, false); + ret = cs35l56_set_patch(&cs35l56->base); if (ret) goto err; diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c index 13beee807308..40f2f97944d5 100644 --- a/sound/pci/hda/cs35l56_hda_i2c.c +++ b/sound/pci/hda/cs35l56_hda_i2c.c @@ -56,10 +56,19 @@ static const struct i2c_device_id cs35l56_hda_i2c_id[] = { {} }; +static const struct acpi_device_id cs35l56_acpi_hda_match[] = { + { "CSC3554", 0 }, + { "CSC3556", 0 }, + { "CSC3557", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match); + static struct i2c_driver cs35l56_hda_i2c_driver = { .driver = { - .name = "cs35l56-hda", - .pm = &cs35l56_hda_pm_ops, + .name = "cs35l56-hda", + .acpi_match_table = cs35l56_acpi_hda_match, + .pm = &cs35l56_hda_pm_ops, }, .id_table = cs35l56_hda_i2c_id, .probe = cs35l56_hda_i2c_probe, diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c index a3b2fa76663d..7f02155fe61e 100644 --- a/sound/pci/hda/cs35l56_hda_spi.c +++ b/sound/pci/hda/cs35l56_hda_spi.c @@ -56,10 +56,19 @@ static const struct spi_device_id cs35l56_hda_spi_id[] = { {} }; +static const struct acpi_device_id cs35l56_acpi_hda_match[] = { + { "CSC3554", 0 }, + { "CSC3556", 0 }, + { "CSC3557", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match); + static struct spi_driver cs35l56_hda_spi_driver = { .driver = { - .name = "cs35l56-hda", - .pm = &cs35l56_hda_pm_ops, + .name = "cs35l56-hda", + .acpi_match_table = cs35l56_acpi_hda_match, + .pm = &cs35l56_hda_pm_ops, }, .id_table = cs35l56_hda_spi_id, .probe = cs35l56_hda_spi_probe, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a17c36a36aa5..cdcb28aa9d7b 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6875,11 +6875,38 @@ static void alc287_fixup_legion_16ithg6_speakers(struct hda_codec *cdc, const st comp_generic_fixup(cdc, action, "i2c", "CLSA0101", "-%s:00-cs35l41-hda.%d", 2); } +static void cs35l56_fixup_i2c_two(struct hda_codec *cdc, const struct hda_fixup *fix, int action) +{ + comp_generic_fixup(cdc, action, "i2c", "CSC3556", "-%s:00-cs35l56-hda.%d", 2); +} + +static void cs35l56_fixup_i2c_four(struct hda_codec *cdc, const struct hda_fixup *fix, int action) +{ + comp_generic_fixup(cdc, action, "i2c", "CSC3556", "-%s:00-cs35l56-hda.%d", 4); +} + +static void cs35l56_fixup_spi_two(struct hda_codec *cdc, const struct hda_fixup *fix, int action) +{ + comp_generic_fixup(cdc, action, "spi", "CSC3556", "-%s:00-cs35l56-hda.%d", 2); +} + static void cs35l56_fixup_spi_four(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { comp_generic_fixup(cdc, action, "spi", "CSC3556", "-%s:00-cs35l56-hda.%d", 4); } +static void alc285_fixup_asus_ga403u(struct hda_codec *cdc, const struct hda_fixup *fix, int action) +{ + /* + * The same SSID has been re-used in different hardware, they have + * different codecs and the newer GA403U has a ALC285. + */ + if (cdc->core.vendor_id == 0x10ec0285) + cs35l56_fixup_i2c_two(cdc, fix, action); + else + alc_fixup_inv_dmic(cdc, fix, action); +} + static void tas2781_fixup_i2c(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { @@ -7436,6 +7463,10 @@ enum { ALC256_FIXUP_ACER_SFG16_MICMUTE_LED, ALC256_FIXUP_HEADPHONE_AMP_VOL, ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX, + ALC285_FIXUP_CS35L56_SPI_2, + ALC285_FIXUP_CS35L56_I2C_2, + ALC285_FIXUP_CS35L56_I2C_4, + ALC285_FIXUP_ASUS_GA403U, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9643,6 +9674,22 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc245_fixup_hp_spectre_x360_eu0xxx, }, + [ALC285_FIXUP_CS35L56_SPI_2] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l56_fixup_spi_two, + }, + [ALC285_FIXUP_CS35L56_I2C_2] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l56_fixup_i2c_two, + }, + [ALC285_FIXUP_CS35L56_I2C_4] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l56_fixup_i2c_four, + }, + [ALC285_FIXUP_ASUS_GA403U] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_asus_ga403u, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -10096,7 +10143,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), - SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), + SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U), SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2), @@ -10104,6 +10151,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_CS35L56_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), @@ -10115,11 +10163,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1df3, "ASUS UM5606", ALC285_FIXUP_CS35L56_I2C_4), SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS), + SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_CS35L56_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_CS35L56_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), @@ -10133,7 +10184,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC), @@ -10159,7 +10210,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x12cc, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x12f6, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), - SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), + SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP), @@ -10333,6 +10384,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), + SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x3878, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3881, "YB9 dual power mode2 YC", ALC287_FIXUP_TAS2781_I2C), @@ -10403,6 +10456,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index 00258ac2bea6..cb25c33cc9b9 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -1093,6 +1093,7 @@ static int cs35l41_handle_pdata(struct device *dev, struct cs35l41_hw_cfg *hw_cf static int cs35l41_dsp_init(struct cs35l41_private *cs35l41) { struct wm_adsp *dsp; + uint32_t dsp1rx5_src; int ret; dsp = &cs35l41->dsp; @@ -1112,16 +1113,29 @@ static int cs35l41_dsp_init(struct cs35l41_private *cs35l41) return ret; } - ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, - CS35L41_INPUT_SRC_VPMON); + switch (cs35l41->hw_cfg.bst_type) { + case CS35L41_INT_BOOST: + case CS35L41_SHD_BOOST_ACTV: + dsp1rx5_src = CS35L41_INPUT_SRC_VPMON; + break; + case CS35L41_EXT_BOOST: + case CS35L41_SHD_BOOST_PASS: + dsp1rx5_src = CS35L41_INPUT_SRC_VBSTMON; + break; + default: + dev_err(cs35l41->dev, "wm_halo_init failed - Invalid Boost Type: %d\n", + cs35l41->hw_cfg.bst_type); + goto err_dsp; + } + + ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, dsp1rx5_src); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_VPMON failed: %d\n", ret); + dev_err(cs35l41->dev, "Write DSP1RX5_SRC: %d failed: %d\n", dsp1rx5_src, ret); goto err_dsp; } - ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, - CS35L41_INPUT_SRC_CLASSH); + ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, CS35L41_INPUT_SRC_VBSTMON); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_CLASSH failed: %d\n", ret); + dev_err(cs35l41->dev, "Write CS35L41_INPUT_SRC_VBSTMON failed: %d\n", ret); goto err_dsp; } ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX7_SRC, diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c index 14a5f86019aa..70ff55c1517f 100644 --- a/sound/soc/codecs/cs35l56-sdw.c +++ b/sound/soc/codecs/cs35l56-sdw.c @@ -188,8 +188,6 @@ static void cs35l56_sdw_init(struct sdw_slave *peripheral) goto out; } - regcache_cache_only(cs35l56->base.regmap, false); - ret = cs35l56_init(cs35l56); if (ret < 0) { regcache_cache_only(cs35l56->base.regmap, true); diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index ac2a760aeae1..8af89a263594 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -41,16 +41,11 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_set_patch, SND_SOC_CS35L56_SHARED); static const struct reg_default cs35l56_reg_defaults[] = { /* no defaults for OTP_MEM - first read populates cache */ - { CS35L56_ASP1_ENABLES1, 0x00000000 }, - { CS35L56_ASP1_CONTROL1, 0x00000028 }, - { CS35L56_ASP1_CONTROL2, 0x18180200 }, - { CS35L56_ASP1_CONTROL3, 0x00000002 }, - { CS35L56_ASP1_FRAME_CONTROL1, 0x03020100 }, - { CS35L56_ASP1_FRAME_CONTROL5, 0x00020100 }, - { CS35L56_ASP1_DATA_CONTROL1, 0x00000018 }, - { CS35L56_ASP1_DATA_CONTROL5, 0x00000018 }, - - /* no defaults for ASP1TX mixer */ + /* + * No defaults for ASP1 control or ASP1TX mixer. See + * cs35l56_populate_asp1_register_defaults() and + * cs35l56_sync_asp1_mixer_widgets_with_firmware(). + */ { CS35L56_SWIRE_DP3_CH1_INPUT, 0x00000018 }, { CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 }, @@ -211,6 +206,36 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg) } } +static const struct reg_sequence cs35l56_asp1_defaults[] = { + REG_SEQ0(CS35L56_ASP1_ENABLES1, 0x00000000), + REG_SEQ0(CS35L56_ASP1_CONTROL1, 0x00000028), + REG_SEQ0(CS35L56_ASP1_CONTROL2, 0x18180200), + REG_SEQ0(CS35L56_ASP1_CONTROL3, 0x00000002), + REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL1, 0x03020100), + REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL5, 0x00020100), + REG_SEQ0(CS35L56_ASP1_DATA_CONTROL1, 0x00000018), + REG_SEQ0(CS35L56_ASP1_DATA_CONTROL5, 0x00000018), +}; + +/* + * The firmware can have control of the ASP so we don't provide regmap + * with defaults for these registers, to prevent a regcache_sync() from + * overwriting the firmware settings. But if the machine driver hooks up + * the ASP it means the driver is taking control of the ASP, so then the + * registers are populated with the defaults. + */ +int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base) +{ + if (!cs35l56_base->fw_owns_asp1) + return 0; + + cs35l56_base->fw_owns_asp1 = false; + + return regmap_multi_reg_write(cs35l56_base->regmap, cs35l56_asp1_defaults, + ARRAY_SIZE(cs35l56_asp1_defaults)); +} +EXPORT_SYMBOL_NS_GPL(cs35l56_init_asp1_regs_for_driver_control, SND_SOC_CS35L56_SHARED); + /* * The firmware boot sequence can overwrite the ASP1 config registers so that * they don't match regmap's view of their values. Rewrite the values from the @@ -218,19 +243,15 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg) */ int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base) { - struct reg_sequence asp1_regs[] = { - { .reg = CS35L56_ASP1_ENABLES1 }, - { .reg = CS35L56_ASP1_CONTROL1 }, - { .reg = CS35L56_ASP1_CONTROL2 }, - { .reg = CS35L56_ASP1_CONTROL3 }, - { .reg = CS35L56_ASP1_FRAME_CONTROL1 }, - { .reg = CS35L56_ASP1_FRAME_CONTROL5 }, - { .reg = CS35L56_ASP1_DATA_CONTROL1 }, - { .reg = CS35L56_ASP1_DATA_CONTROL5 }, - }; + struct reg_sequence asp1_regs[ARRAY_SIZE(cs35l56_asp1_defaults)]; int i, ret; - /* Read values from regmap cache into a write sequence */ + if (cs35l56_base->fw_owns_asp1) + return 0; + + memcpy(asp1_regs, cs35l56_asp1_defaults, sizeof(asp1_regs)); + + /* Read current values from regmap cache into the write sequence */ for (i = 0; i < ARRAY_SIZE(asp1_regs); ++i) { ret = regmap_read(cs35l56_base->regmap, asp1_regs[i].reg, &asp1_regs[i].def); if (ret) @@ -308,10 +329,10 @@ int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base) reg = CS35L56_DSP1_HALO_STATE; /* - * This can't be a regmap_read_poll_timeout() because cs35l56 will NAK - * I2C until it has booted which would terminate the poll + * The regmap must remain in cache-only until the chip has + * booted, so use a bypassed read of the status register. */ - poll_ret = read_poll_timeout(regmap_read, read_ret, + poll_ret = read_poll_timeout(regmap_read_bypassed, read_ret, (val < 0xFFFF) && (val >= CS35L56_HALO_STATE_BOOT_DONE), CS35L56_HALO_STATE_POLL_US, CS35L56_HALO_STATE_TIMEOUT_US, @@ -363,7 +384,8 @@ void cs35l56_system_reset(struct cs35l56_base *cs35l56_base, bool is_soundwire) return; cs35l56_wait_control_port_ready(); - regcache_cache_only(cs35l56_base->regmap, false); + + /* Leave in cache-only. This will be revoked when the chip has rebooted. */ } EXPORT_SYMBOL_NS_GPL(cs35l56_system_reset, SND_SOC_CS35L56_SHARED); @@ -578,14 +600,14 @@ int cs35l56_runtime_resume_common(struct cs35l56_base *cs35l56_base, bool is_sou cs35l56_issue_wake_event(cs35l56_base); out_sync: - regcache_cache_only(cs35l56_base->regmap, false); - ret = cs35l56_wait_for_firmware_boot(cs35l56_base); if (ret) { dev_err(cs35l56_base->dev, "Hibernate wake failed: %d\n", ret); goto err; } + regcache_cache_only(cs35l56_base->regmap, false); + ret = cs35l56_mbox_send(cs35l56_base, CS35L56_MBOX_CMD_PREVENT_AUTO_HIBERNATE); if (ret) goto err; @@ -685,7 +707,7 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_calibration_controls, SND_SOC_CS35L56_SHARED); int cs35l56_get_calibration(struct cs35l56_base *cs35l56_base) { - u64 silicon_uid; + u64 silicon_uid = 0; int ret; /* Driver can't apply calibration to a secured part, so skip */ @@ -758,7 +780,7 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) * devices so the REVID needs to be determined before waiting for the * firmware to boot. */ - ret = regmap_read(cs35l56_base->regmap, CS35L56_REVID, &revid); + ret = regmap_read_bypassed(cs35l56_base->regmap, CS35L56_REVID, &revid); if (ret < 0) { dev_err(cs35l56_base->dev, "Get Revision ID failed\n"); return ret; @@ -769,7 +791,7 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) if (ret) return ret; - ret = regmap_read(cs35l56_base->regmap, CS35L56_DEVID, &devid); + ret = regmap_read_bypassed(cs35l56_base->regmap, CS35L56_DEVID, &devid); if (ret < 0) { dev_err(cs35l56_base->dev, "Get Device ID failed\n"); return ret; @@ -788,6 +810,9 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) cs35l56_base->type = devid & 0xFF; + /* Silicon is now identified and booted so exit cache-only */ + regcache_cache_only(cs35l56_base->regmap, false); + ret = regmap_read(cs35l56_base->regmap, CS35L56_DSP_RESTRICT_STS1, &secured); if (ret) { dev_err(cs35l56_base->dev, "Get Secure status failed\n"); diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 5a0b55e31e3c..dfd703d9e12f 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -455,9 +455,14 @@ static int cs35l56_asp_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int f { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component); unsigned int val; + int ret; dev_dbg(cs35l56->base.dev, "%s: %#x\n", __func__, fmt); + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; + switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) { case SND_SOC_DAIFMT_CBC_CFC: break; @@ -531,6 +536,11 @@ static int cs35l56_asp_dai_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx unsigned int rx_mask, int slots, int slot_width) { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component); + int ret; + + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; if ((slots == 0) || (slot_width == 0)) { dev_dbg(cs35l56->base.dev, "tdm config cleared\n"); @@ -579,6 +589,11 @@ static int cs35l56_asp_dai_hw_params(struct snd_pcm_substream *substream, struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component); unsigned int rate = params_rate(params); u8 asp_width, asp_wl; + int ret; + + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; asp_wl = params_width(params); if (cs35l56->asp_slot_width) @@ -635,7 +650,11 @@ static int cs35l56_asp_dai_set_sysclk(struct snd_soc_dai *dai, int clk_id, unsigned int freq, int dir) { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component); - int freq_id; + int freq_id, ret; + + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; if (freq == 0) { cs35l56->sysclk_set = false; @@ -1404,6 +1423,9 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56) cs35l56->base.cal_index = -1; cs35l56->speaker_id = -ENOENT; + /* Assume that the firmware owns ASP1 until we know different */ + cs35l56->base.fw_owns_asp1 = true; + dev_set_drvdata(cs35l56->base.dev, cs35l56); cs35l56_fill_supply_names(cs35l56->supplies); @@ -1532,6 +1554,8 @@ post_soft_reset: return ret; dev_dbg(cs35l56->base.dev, "Firmware rebooted after soft reset\n"); + + regcache_cache_only(cs35l56->base.regmap, false); } /* Disable auto-hibernate so that runtime_pm has control */ diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index e3ba04484813..d0d24a53df74 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -444,6 +444,7 @@ struct rt5645_priv { struct regmap *regmap; struct i2c_client *i2c; struct gpio_desc *gpiod_hp_det; + struct gpio_desc *gpiod_cbj_sleeve; struct snd_soc_jack *hp_jack; struct snd_soc_jack *mic_jack; struct snd_soc_jack *btn_jack; @@ -3186,6 +3187,9 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse regmap_update_bits(rt5645->regmap, RT5645_IN1_CTRL2, RT5645_CBJ_MN_JD, 0); + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 1); + msleep(600); regmap_read(rt5645->regmap, RT5645_IN1_CTRL3, &val); val &= 0x7; @@ -3202,6 +3206,8 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse snd_soc_dapm_disable_pin(dapm, "Mic Det Power"); snd_soc_dapm_sync(dapm); rt5645->jack_type = SND_JACK_HEADPHONE; + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } if (rt5645->pdata.level_trigger_irq) regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2, @@ -3229,6 +3235,9 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse if (rt5645->pdata.level_trigger_irq) regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2, RT5645_JD_1_1_MASK, RT5645_JD_1_1_INV); + + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } return rt5645->jack_type; @@ -4012,6 +4021,16 @@ static int rt5645_i2c_probe(struct i2c_client *i2c) return ret; } + rt5645->gpiod_cbj_sleeve = devm_gpiod_get_optional(&i2c->dev, "cbj-sleeve", + GPIOD_OUT_LOW); + + if (IS_ERR(rt5645->gpiod_cbj_sleeve)) { + ret = PTR_ERR(rt5645->gpiod_cbj_sleeve); + dev_info(&i2c->dev, "failed to initialize gpiod, ret=%d\n", ret); + if (ret != -ENOENT) + return ret; + } + for (i = 0; i < ARRAY_SIZE(rt5645->supplies); i++) rt5645->supplies[i].supply = rt5645_supply_names[i]; @@ -4259,6 +4278,9 @@ static void rt5645_i2c_remove(struct i2c_client *i2c) cancel_delayed_work_sync(&rt5645->jack_detect_work); cancel_delayed_work_sync(&rt5645->rcclock_work); + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); + regulator_bulk_disable(ARRAY_SIZE(rt5645->supplies), rt5645->supplies); } @@ -4274,6 +4296,9 @@ static void rt5645_i2c_shutdown(struct i2c_client *i2c) 0); msleep(20); regmap_write(rt5645->regmap, RT5645_RESET, 0); + + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } static int __maybe_unused rt5645_sys_suspend(struct device *dev) diff --git a/sound/soc/codecs/rt715-sdca.c b/sound/soc/codecs/rt715-sdca.c index 3a6dfe1f6c48..7e10fd913812 100644 --- a/sound/soc/codecs/rt715-sdca.c +++ b/sound/soc/codecs/rt715-sdca.c @@ -316,7 +316,7 @@ static int rt715_sdca_set_amp_gain_8ch_get(struct snd_kcontrol *kcontrol, return 0; } -static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -17625, 375, 0); +static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -1725, 75, 0); static const DECLARE_TLV_DB_SCALE(mic_vol_tlv, 0, 1000, 0); static int rt715_sdca_get_volsw(struct snd_kcontrol *kcontrol, @@ -477,7 +477,7 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { RT715_SDCA_FU_VOL_CTRL, CH_01), SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC7_27_VOL, RT715_SDCA_FU_VOL_CTRL, CH_02), - 0x2f, 0x7f, 0, + 0x2f, 0x3f, 0, rt715_sdca_set_amp_gain_get, rt715_sdca_set_amp_gain_put, in_vol_tlv), RT715_SDCA_EXT_TLV("FU02 Capture Volume", @@ -485,13 +485,13 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { RT715_SDCA_FU_VOL_CTRL, CH_01), rt715_sdca_set_amp_gain_4ch_get, rt715_sdca_set_amp_gain_4ch_put, - in_vol_tlv, 4, 0x7f), + in_vol_tlv, 4, 0x3f), RT715_SDCA_EXT_TLV("FU06 Capture Volume", SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC10_11_VOL, RT715_SDCA_FU_VOL_CTRL, CH_01), rt715_sdca_set_amp_gain_4ch_get, rt715_sdca_set_amp_gain_4ch_put, - in_vol_tlv, 4, 0x7f), + in_vol_tlv, 4, 0x3f), /* MIC Boost Control */ RT715_SDCA_BOOST_EXT_TLV("FU0E Boost", SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_DMIC_GAIN_EN, diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c index 24b3443aeb02..ec255ada44e0 100644 --- a/sound/soc/codecs/rt715-sdw.c +++ b/sound/soc/codecs/rt715-sdw.c @@ -111,6 +111,7 @@ static bool rt715_readable_register(struct device *dev, unsigned int reg) case 0x839d: case 0x83a7: case 0x83a9: + case 0x752001: case 0x752039: return true; default: diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c index e0ea3a23f7cc..e5bd9ef812de 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1330,7 +1330,7 @@ static struct snd_soc_dai_driver rt722_sdca_dai[] = { .capture = { .stream_name = "DP6 DMic Capture", .channels_min = 1, - .channels_max = 2, + .channels_max = 4, .rates = RT722_STEREO_RATES, .formats = RT722_FORMATS, }, @@ -1439,9 +1439,12 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) int loop_check, chk_cnt = 100, ret; unsigned int calib_status = 0; - /* Read eFuse */ - rt722_sdca_index_write(rt722, RT722_VENDOR_SPK_EFUSE, RT722_DC_CALIB_CTRL, - 0x4808); + /* Config analog bias */ + rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_ANALOG_BIAS_CTL3, + 0xa081); + /* GE related settings */ + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_GE_RELATED_CTL2, + 0xa009); /* Button A, B, C, D bypass mode */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_UMP_HID_CTL4, 0xcf00); @@ -1475,9 +1478,6 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) if ((calib_status & 0x0040) == 0x0) break; } - /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */ - rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4, - 0x0010); /* Set ADC09 power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ADC0A_08_PDE_FLOAT_CTL, 0x2a12); @@ -1490,8 +1490,21 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) /* Set DAC03 and HP power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_DAC03_HP_PDE_FLOAT_CTL, 0x4040); + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ENT_FLOAT_CTRL_1, + 0x4141); + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_FLOAT_CTRL_1, + 0x0101); /* Fine tune PDE40 latency */ regmap_write(rt722->regmap, 0x2f58, 0x07); + regmap_write(rt722->regmap, 0x2f03, 0x06); + /* MIC VRefo */ + rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG, + RT722_COMBO_JACK_AUTO_CTL1, 0x0200, 0x0200); + rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG, + RT722_VREFO_GAT, 0x4000, 0x4000); + /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */ + rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4, + 0x0010); } int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave) diff --git a/sound/soc/codecs/rt722-sdca.h b/sound/soc/codecs/rt722-sdca.h index 44af8901352e..2464361a7958 100644 --- a/sound/soc/codecs/rt722-sdca.h +++ b/sound/soc/codecs/rt722-sdca.h @@ -69,6 +69,7 @@ struct rt722_sdca_dmic_kctrl_priv { #define RT722_COMBO_JACK_AUTO_CTL2 0x46 #define RT722_COMBO_JACK_AUTO_CTL3 0x47 #define RT722_DIGITAL_MISC_CTRL4 0x4a +#define RT722_VREFO_GAT 0x63 #define RT722_FSM_CTL 0x67 #define RT722_SDCA_INTR_REC 0x82 #define RT722_SW_CONFIG1 0x8a @@ -127,6 +128,8 @@ struct rt722_sdca_dmic_kctrl_priv { #define RT722_UMP_HID_CTL6 0x66 #define RT722_UMP_HID_CTL7 0x67 #define RT722_UMP_HID_CTL8 0x68 +#define RT722_FLOAT_CTRL_1 0x70 +#define RT722_ENT_FLOAT_CTRL_1 0x76 /* Parameter & Verb control 01 (0x1a)(NID:20h) */ #define RT722_HIDDEN_REG_SW_RESET (0x1 << 14) diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 3c025dabaf7a..1253695bebd8 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1155,6 +1155,7 @@ static int wsa881x_probe(struct sdw_slave *pdev, pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0); pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop; pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY; + pdev->prop.clk_stop_mode1 = true; gpiod_direction_output(wsa881x->sd_n, !wsa881x->sd_n_val); wsa881x->regmap = devm_regmap_init_sdw(pdev, &wsa881x_regmap_config); diff --git a/sound/soc/intel/avs/icl.c b/sound/soc/intel/avs/icl.c index e0880acf8050..3a96c4304ca6 100644 --- a/sound/soc/intel/avs/icl.c +++ b/sound/soc/intel/avs/icl.c @@ -66,7 +66,7 @@ static_assert(sizeof(struct avs_icl_memwnd2_desc) == 12); struct avs_icl_memwnd2 { union { struct avs_icl_memwnd2_desc slot_desc[AVS_ICL_MEMWND2_SLOTS_COUNT]; - u8 rsvd[PAGE_SIZE]; + u8 rsvd[SZ_4K]; }; u8 slot_array[AVS_ICL_MEMWND2_SLOTS_COUNT][SZ_4K]; } __packed; diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c index 13061bd1488b..42b42903ae9d 100644 --- a/sound/soc/intel/avs/topology.c +++ b/sound/soc/intel/avs/topology.c @@ -1582,6 +1582,8 @@ static int avs_widget_load(struct snd_soc_component *comp, int index, if (!le32_to_cpu(dw->priv.size)) return 0; + w->no_wname_in_kcontrol_name = true; + if (w->ignore_suspend && !AVS_S0IX_SUPPORTED) { dev_info_once(comp->dev, "Device does not support S0IX, check BIOS settings\n"); w->ignore_suspend = false; diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 05f38d1f7d82..b41a1147f1c3 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -636,28 +636,30 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_USE_AMCR0F28), }, { + /* Asus T100TAF, unlike other T100TA* models this one has a mono speaker */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | BYT_RT5640_OVCD_TH_2000UA | BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { + /* Asus T100TA and T100TAM, must come after T100TAF (mono spk) match */ .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | BYT_RT5640_OVCD_TH_2000UA | BYT_RT5640_OVCD_SF_0P75 | - BYT_RT5640_MONO_SPEAKER | - BYT_RT5640_DIFF_MIC | - BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index be7dc1e02284..c12c7f820529 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -704,6 +704,10 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev) goto unregister_dev; } + ret = acp_init(sdev); + if (ret < 0) + goto free_smn_dev; + sdev->ipc_irq = pci->irq; ret = request_threaded_irq(sdev->ipc_irq, acp_irq_handler, acp_irq_thread, IRQF_SHARED, "AudioDSP", sdev); @@ -713,10 +717,6 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev) goto free_smn_dev; } - ret = acp_init(sdev); - if (ret < 0) - goto free_ipc_irq; - /* scan SoundWire capabilities exposed by DSDT */ ret = acp_sof_scan_sdw_devices(sdev, chip->sdw_acpi_dev_addr); if (ret < 0) { diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 9b00ede2a486..238bda5f6b76 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -339,8 +339,7 @@ static int sof_init_environment(struct snd_sof_dev *sdev) ret = snd_sof_probe(sdev); if (ret < 0) { dev_err(sdev->dev, "failed to probe DSP %d\n", ret); - sof_ops_free(sdev); - return ret; + goto err_sof_probe; } /* check machine info */ @@ -351,22 +350,27 @@ static int sof_init_environment(struct snd_sof_dev *sdev) } ret = sof_select_ipc_and_paths(sdev); - if (!ret && plat_data->ipc_type != base_profile->ipc_type) { + if (ret) { + goto err_machine_check; + } else if (plat_data->ipc_type != base_profile->ipc_type) { /* IPC type changed, re-initialize the ops */ sof_ops_free(sdev); ret = validate_sof_ops(sdev); if (ret < 0) { snd_sof_remove(sdev); + snd_sof_remove_late(sdev); return ret; } } + return 0; + err_machine_check: - if (ret) { - snd_sof_remove(sdev); - sof_ops_free(sdev); - } + snd_sof_remove(sdev); +err_sof_probe: + snd_sof_remove_late(sdev); + sof_ops_free(sdev); return ret; } diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index 937e51b02a24..cf282c8b18af 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -311,14 +311,32 @@ EXPORT_SYMBOL_GPL(snd_sof_dbg_memory_info_init); int snd_sof_dbg_init(struct snd_sof_dev *sdev) { + struct snd_sof_pdata *plat_data = sdev->pdata; struct snd_sof_dsp_ops *ops = sof_ops(sdev); const struct snd_sof_debugfs_map *map; + struct dentry *fw_profile; int i; int err; /* use "sof" as top level debugFS dir */ sdev->debugfs_root = debugfs_create_dir("sof", NULL); + /* expose firmware/topology prefix/names for test purposes */ + fw_profile = debugfs_create_dir("fw_profile", sdev->debugfs_root); + + debugfs_create_str("fw_path", 0444, fw_profile, + (char **)&plat_data->fw_filename_prefix); + debugfs_create_str("fw_lib_path", 0444, fw_profile, + (char **)&plat_data->fw_lib_prefix); + debugfs_create_str("tplg_path", 0444, fw_profile, + (char **)&plat_data->tplg_filename_prefix); + debugfs_create_str("fw_name", 0444, fw_profile, + (char **)&plat_data->fw_filename); + debugfs_create_str("tplg_name", 0444, fw_profile, + (char **)&plat_data->tplg_filename); + debugfs_create_u32("ipc_type", 0444, fw_profile, + (u32 *)&plat_data->ipc_type); + /* init dfsentry list */ INIT_LIST_HEAD(&sdev->dfsentry_list); diff --git a/sound/soc/sof/intel/lnl.c b/sound/soc/sof/intel/lnl.c index ac64a9f9cf9d..82c975823ab3 100644 --- a/sound/soc/sof/intel/lnl.c +++ b/sound/soc/sof/intel/lnl.c @@ -32,15 +32,17 @@ static const struct snd_sof_debugfs_map lnl_dsp_debugfs[] = { }; /* this helps allows the DSP to setup DMIC/SSP */ -static int hdac_bus_offload_dmic_ssp(struct hdac_bus *bus) +static int hdac_bus_offload_dmic_ssp(struct hdac_bus *bus, bool enable) { int ret; - ret = hdac_bus_eml_enable_offload(bus, true, AZX_REG_ML_LEPTR_ID_INTEL_SSP, true); + ret = hdac_bus_eml_enable_offload(bus, true, + AZX_REG_ML_LEPTR_ID_INTEL_SSP, enable); if (ret < 0) return ret; - ret = hdac_bus_eml_enable_offload(bus, true, AZX_REG_ML_LEPTR_ID_INTEL_DMIC, true); + ret = hdac_bus_eml_enable_offload(bus, true, + AZX_REG_ML_LEPTR_ID_INTEL_DMIC, enable); if (ret < 0) return ret; @@ -55,7 +57,19 @@ static int lnl_hda_dsp_probe(struct snd_sof_dev *sdev) if (ret < 0) return ret; - return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev)); + return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), true); +} + +static void lnl_hda_dsp_remove(struct snd_sof_dev *sdev) +{ + int ret; + + ret = hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), false); + if (ret < 0) + dev_warn(sdev->dev, + "Failed to disable offload for DMIC/SSP: %d\n", ret); + + hda_dsp_remove(sdev); } static int lnl_hda_dsp_resume(struct snd_sof_dev *sdev) @@ -66,7 +80,7 @@ static int lnl_hda_dsp_resume(struct snd_sof_dev *sdev) if (ret < 0) return ret; - return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev)); + return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), true); } static int lnl_hda_dsp_runtime_resume(struct snd_sof_dev *sdev) @@ -77,7 +91,7 @@ static int lnl_hda_dsp_runtime_resume(struct snd_sof_dev *sdev) if (ret < 0) return ret; - return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev)); + return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), true); } static int lnl_dsp_post_fw_run(struct snd_sof_dev *sdev) @@ -104,9 +118,11 @@ int sof_lnl_ops_init(struct snd_sof_dev *sdev) /* common defaults */ memcpy(&sof_lnl_ops, &sof_hda_common_ops, sizeof(struct snd_sof_dsp_ops)); - /* probe */ - if (!sdev->dspless_mode_selected) + /* probe/remove */ + if (!sdev->dspless_mode_selected) { sof_lnl_ops.probe = lnl_hda_dsp_probe; + sof_lnl_ops.remove = lnl_hda_dsp_remove; + } /* shutdown */ sof_lnl_ops.shutdown = hda_dsp_shutdown; diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c index b26ffe767fab..b14e508f1f31 100644 --- a/sound/soc/sof/intel/pci-lnl.c +++ b/sound/soc/sof/intel/pci-lnl.c @@ -35,6 +35,9 @@ static const struct sof_dev_desc lnl_desc = { .default_fw_path = { [SOF_IPC_TYPE_4] = "intel/sof-ipc4/lnl", }, + .default_lib_path = { + [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/lnl", + }, .default_tplg_path = { [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg", }, diff --git a/sound/soc/sof/ipc3-pcm.c b/sound/soc/sof/ipc3-pcm.c index 35769dd7905e..af0bf354cb20 100644 --- a/sound/soc/sof/ipc3-pcm.c +++ b/sound/soc/sof/ipc3-pcm.c @@ -434,4 +434,5 @@ const struct sof_ipc_pcm_ops ipc3_pcm_ops = { .trigger = sof_ipc3_pcm_trigger, .dai_link_fixup = sof_ipc3_pcm_dai_link_fixup, .reset_hw_params_during_stop = true, + .d0i3_supported_in_s0ix = true, }; diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c index e915f9f87a6c..4594470ed08b 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -37,6 +37,25 @@ struct sof_ipc4_timestamp_info { snd_pcm_sframes_t delay; }; +/** + * struct sof_ipc4_pcm_stream_priv - IPC4 specific private data + * @time_info: pointer to time info struct if it is supported, otherwise NULL + * @chain_dma_allocated: indicates the ChainDMA allocation state + */ +struct sof_ipc4_pcm_stream_priv { + struct sof_ipc4_timestamp_info *time_info; + + bool chain_dma_allocated; +}; + +static inline struct sof_ipc4_timestamp_info * +sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps) +{ + struct sof_ipc4_pcm_stream_priv *stream_priv = sps->private; + + return stream_priv->time_info; +} + static int sof_ipc4_set_multi_pipeline_state(struct snd_sof_dev *sdev, u32 state, struct ipc4_pipeline_set_state_data *trigger_list) { @@ -253,14 +272,17 @@ sof_ipc4_update_pipeline_state(struct snd_sof_dev *sdev, int state, int cmd, */ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, - int direction, + struct snd_sof_pcm *spcm, int direction, struct snd_sof_pcm_stream_pipeline_list *pipeline_list, int state, int cmd) { struct sof_ipc4_fw_data *ipc4_data = sdev->private; + struct sof_ipc4_pcm_stream_priv *stream_priv; bool allocate, enable, set_fifo_size; struct sof_ipc4_msg msg = {{ 0 }}; - int i; + int ret, i; + + stream_priv = spcm->stream[direction].private; switch (state) { case SOF_IPC4_PIPE_RUNNING: /* Allocate and start chained dma */ @@ -281,6 +303,11 @@ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, set_fifo_size = false; break; case SOF_IPC4_PIPE_RESET: /* Disable and free chained DMA. */ + + /* ChainDMA can only be reset if it has been allocated */ + if (!stream_priv->chain_dma_allocated) + return 0; + allocate = false; enable = false; set_fifo_size = false; @@ -338,7 +365,12 @@ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, if (enable) msg.primary |= SOF_IPC4_GLB_CHAIN_DMA_ENABLE_MASK; - return sof_ipc_tx_message_no_reply(sdev->ipc, &msg, 0); + ret = sof_ipc_tx_message_no_reply(sdev->ipc, &msg, 0); + /* Update the ChainDMA allocation state */ + if (!ret) + stream_priv->chain_dma_allocated = allocate; + + return ret; } static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, @@ -378,7 +410,7 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, * trigger function that handles the rest for the substream. */ if (pipeline->use_chain_dma) - return sof_ipc4_chain_dma_trigger(sdev, substream->stream, + return sof_ipc4_chain_dma_trigger(sdev, spcm, substream->stream, pipeline_list, state, cmd); /* allocate memory for the pipeline data */ @@ -452,7 +484,7 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, * Invalidate the stream_start_offset to make sure that it is * going to be updated if the stream resumes */ - time_info = spcm->stream[substream->stream].private; + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); if (time_info) time_info->stream_start_offset = SOF_IPC4_INVALID_STREAM_POSITION; @@ -706,12 +738,16 @@ static int sof_ipc4_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd, static void sof_ipc4_pcm_free(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm) { struct snd_sof_pcm_stream_pipeline_list *pipeline_list; + struct sof_ipc4_pcm_stream_priv *stream_priv; int stream; for_each_pcm_streams(stream) { pipeline_list = &spcm->stream[stream].pipeline_list; kfree(pipeline_list->pipelines); pipeline_list->pipelines = NULL; + + stream_priv = spcm->stream[stream].private; + kfree(stream_priv->time_info); kfree(spcm->stream[stream].private); spcm->stream[stream].private = NULL; } @@ -721,7 +757,8 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm { struct snd_sof_pcm_stream_pipeline_list *pipeline_list; struct sof_ipc4_fw_data *ipc4_data = sdev->private; - struct sof_ipc4_timestamp_info *stream_info; + struct sof_ipc4_pcm_stream_priv *stream_priv; + struct sof_ipc4_timestamp_info *time_info; bool support_info = true; u32 abi_version; u32 abi_offset; @@ -749,33 +786,41 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm return -ENOMEM; } + stream_priv = kzalloc(sizeof(*stream_priv), GFP_KERNEL); + if (!stream_priv) { + sof_ipc4_pcm_free(sdev, spcm); + return -ENOMEM; + } + + spcm->stream[stream].private = stream_priv; + if (!support_info) continue; - stream_info = kzalloc(sizeof(*stream_info), GFP_KERNEL); - if (!stream_info) { + time_info = kzalloc(sizeof(*time_info), GFP_KERNEL); + if (!time_info) { sof_ipc4_pcm_free(sdev, spcm); return -ENOMEM; } - spcm->stream[stream].private = stream_info; + stream_priv->time_info = time_info; } return 0; } -static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *spcm) +static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *sps) { struct sof_ipc4_copier *host_copier = NULL; struct sof_ipc4_copier *dai_copier = NULL; struct sof_ipc4_llp_reading_slot llp_slot; - struct sof_ipc4_timestamp_info *info; + struct sof_ipc4_timestamp_info *time_info; struct snd_soc_dapm_widget *widget; struct snd_sof_dai *dai; int i; /* find host & dai to locate info in memory window */ - for_each_dapm_widgets(spcm->list, i, widget) { + for_each_dapm_widgets(sps->list, i, widget) { struct snd_sof_widget *swidget = widget->dobj.private; if (!swidget) @@ -795,44 +840,44 @@ static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pc return; } - info = spcm->private; - info->host_copier = host_copier; - info->dai_copier = dai_copier; - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_gpdma_reading_slots) + - sdev->fw_info_box.offset; + time_info = sof_ipc4_sps_to_time_info(sps); + time_info->host_copier = host_copier; + time_info->dai_copier = dai_copier; + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_gpdma_reading_slots) + sdev->fw_info_box.offset; /* find llp slot used by current dai */ for (i = 0; i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS; i++) { - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id) break; - info->llp_offset += sizeof(llp_slot); + time_info->llp_offset += sizeof(llp_slot); } if (i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS) return; /* if no llp gpdma slot is used, check aggregated sdw slot */ - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_sndw_reading_slots) + - sdev->fw_info_box.offset; + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_sndw_reading_slots) + sdev->fw_info_box.offset; for (i = 0; i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS; i++) { - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id) break; - info->llp_offset += sizeof(llp_slot); + time_info->llp_offset += sizeof(llp_slot); } if (i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS) return; /* check EVAD slot */ - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_evad_reading_slot) + - sdev->fw_info_box.offset; - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_evad_reading_slot) + sdev->fw_info_box.offset; + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id) - info->llp_offset = 0; + time_info->llp_offset = 0; } static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, @@ -849,7 +894,7 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, if (!spcm) return -EINVAL; - time_info = spcm->stream[substream->stream].private; + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); /* delay calculation is not supported by current fw_reg ABI */ if (!time_info) return 0; @@ -864,7 +909,7 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream, - struct snd_sof_pcm_stream *stream, + struct snd_sof_pcm_stream *sps, struct sof_ipc4_timestamp_info *time_info) { struct sof_ipc4_copier *host_copier = time_info->host_copier; @@ -918,7 +963,7 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, struct sof_ipc4_timestamp_info *time_info; struct sof_ipc4_llp_reading_slot llp; snd_pcm_uframes_t head_cnt, tail_cnt; - struct snd_sof_pcm_stream *stream; + struct snd_sof_pcm_stream *sps; u64 dai_cnt, host_cnt, host_ptr; struct snd_sof_pcm *spcm; int ret; @@ -927,8 +972,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, if (!spcm) return -EOPNOTSUPP; - stream = &spcm->stream[substream->stream]; - time_info = stream->private; + sps = &spcm->stream[substream->stream]; + time_info = sof_ipc4_sps_to_time_info(sps); if (!time_info) return -EOPNOTSUPP; @@ -938,7 +983,7 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, * the statistics is complete. And it will not change after the first initiailization. */ if (time_info->stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION) { - ret = sof_ipc4_get_stream_start_offset(sdev, substream, stream, time_info); + ret = sof_ipc4_get_stream_start_offset(sdev, substream, sps, time_info); if (ret < 0) return -EOPNOTSUPP; } @@ -1030,15 +1075,13 @@ static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component, { struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct sof_ipc4_timestamp_info *time_info; - struct snd_sof_pcm_stream *stream; struct snd_sof_pcm *spcm; spcm = snd_sof_find_spcm_dai(component, rtd); if (!spcm) return 0; - stream = &spcm->stream[substream->stream]; - time_info = stream->private; + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); /* * Report the stored delay value calculated in the pointer callback. * In the unlikely event that the calculation was skipped/aborted, the diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index 4e11df6b4823..8fca4b0d63de 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -312,14 +312,13 @@ static int sof_pcm_trigger(struct snd_soc_component *component, ipc_first = true; break; case SNDRV_PCM_TRIGGER_SUSPEND: - if (sdev->system_suspend_target == SOF_SUSPEND_S0IX && + /* + * If DSP D0I3 is allowed during S0iX, set the suspend_ignored flag for + * D0I3-compatible streams to keep the firmware pipeline running + */ + if (pcm_ops && pcm_ops->d0i3_supported_in_s0ix && + sdev->system_suspend_target == SOF_SUSPEND_S0IX && spcm->stream[substream->stream].d0i3_compatible) { - /* - * trap the event, not sending trigger stop to - * prevent the FW pipelines from being stopped, - * and mark the flag to ignore the upcoming DAPM - * PM events. - */ spcm->stream[substream->stream].suspend_ignored = true; return 0; } diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index f4134257789e..2aeb269af752 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -117,6 +117,7 @@ struct snd_sof_dai_config_data { * triggers. The FW keeps the host DMA running in this case and * therefore the host must do the same and should stop the DMA during * hw_free. + * @d0i3_supported_in_s0ix: Allow DSP D0I3 during S0iX */ struct sof_ipc_pcm_ops { int (*hw_params)(struct snd_soc_component *component, struct snd_pcm_substream *substream, @@ -136,6 +137,7 @@ struct sof_ipc_pcm_ops { bool reset_hw_params_during_stop; bool ipc_first_on_start; bool platform_stop_during_hw_free; + bool d0i3_supported_in_s0ix; }; /** diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index aa37c4ab0adb..21cd41fec7a9 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only +// SPDX-FileCopyrightText: Copyright (c) 2020-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved. // // tegra186_dspk.c - Tegra186 DSPK driver -// -// Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. #include <linux/clk.h> #include <linux/device.h> @@ -241,14 +240,14 @@ static int tegra186_dspk_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - cif_conf.client_bits = TEGRA_ACIF_BITS_24; - switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_16; + cif_conf.client_bits = TEGRA_ACIF_BITS_16; break; case SNDRV_PCM_FORMAT_S32_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_32; + cif_conf.client_bits = TEGRA_ACIF_BITS_24; break; default: dev_err(dev, "unsupported format!\n"); diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c index b892d66f7847..1e760c315521 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -2417,12 +2417,6 @@ static int davinci_mcasp_probe(struct platform_device *pdev) mcasp_reparent_fck(pdev); - ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, - &davinci_mcasp_dai[mcasp->op_mode], 1); - - if (ret != 0) - goto err; - ret = davinci_mcasp_get_dma_type(mcasp); switch (ret) { case PCM_EDMA: @@ -2449,6 +2443,12 @@ static int davinci_mcasp_probe(struct platform_device *pdev) goto err; } + ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, + &davinci_mcasp_dai[mcasp->op_mode], 1); + + if (ret != 0) + goto err; + no_audio: ret = davinci_mcasp_init_gpiochip(mcasp); if (ret) { diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index b67617b68e50..f4437015d43a 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -202,7 +202,7 @@ int line6_send_raw_message_async(struct usb_line6 *line6, const char *buffer, struct urb *urb; /* create message: */ - msg = kmalloc(sizeof(struct message), GFP_ATOMIC); + msg = kzalloc(sizeof(struct message), GFP_ATOMIC); if (msg == NULL) return -ENOMEM; @@ -688,7 +688,7 @@ static int line6_init_cap_control(struct usb_line6 *line6) int ret; /* initialize USB buffers: */ - line6->buffer_listen = kmalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL); + line6->buffer_listen = kzalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL); if (!line6->buffer_listen) return -ENOMEM; @@ -697,7 +697,7 @@ static int line6_init_cap_control(struct usb_line6 *line6) return -ENOMEM; if (line6->properties->capabilities & LINE6_CAP_CONTROL_MIDI) { - line6->buffer_message = kmalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL); + line6->buffer_message = kzalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL); if (!line6->buffer_message) return -ENOMEM; diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 72535f00572f..72ea363d434d 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include <linux/types.h> /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index ddba2c2fb5de..4eaba83cdcf3 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -135,8 +135,8 @@ static void guest_run_stage(struct test_vcpu_shared_data *shared_data, irq_iter = READ_ONCE(shared_data->nr_iter); __GUEST_ASSERT(config_iter + 1 == irq_iter, - "config_iter + 1 = 0x%lx, irq_iter = 0x%lx.\n" - " Guest timer interrupt was not trigged within the specified\n" + "config_iter + 1 = 0x%x, irq_iter = 0x%x.\n" + " Guest timer interrupt was not triggered within the specified\n" " interval, try to increase the error margin by [-e] option.\n", config_iter + 1, irq_iter); } diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 3bd03b088dda..81ce37ec407d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -1037,8 +1037,19 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_property property, uint32_t value); +void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); + +static inline bool vcpu_cpuid_has(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_feature feature) +{ + struct kvm_cpuid_entry2 *entry; + + entry = __vcpu_get_cpuid_entry(vcpu, feature.function, feature.index); + return *((&entry->eax) + feature.reg) & BIT(feature.bit); +} + void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_feature feature, bool set); diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index e22848f747c0..0f9cabd99fd4 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -60,7 +60,7 @@ static void guest_run(struct test_vcpu_shared_data *shared_data) irq_iter = READ_ONCE(shared_data->nr_iter); __GUEST_ASSERT(config_iter + 1 == irq_iter, "config_iter + 1 = 0x%x, irq_iter = 0x%x.\n" - " Guest timer interrupt was not trigged within the specified\n" + " Guest timer interrupt was not triggered within the specified\n" " interval, try to increase the error margin by [-e] option.\n", config_iter + 1, irq_iter); } diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index 9e2879af7c20..40cc59f4e650 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -133,6 +133,43 @@ static void enter_guest(struct kvm_vcpu *vcpu) } } +static void test_pv_unhalt(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_cpuid_entry2 *ent; + u32 kvm_sig_old; + + pr_info("testing KVM_FEATURE_PV_UNHALT\n"); + + TEST_REQUIRE(KVM_CAP_X86_DISABLE_EXITS); + + /* KVM_PV_UNHALT test */ + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT); + + TEST_ASSERT(vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "Enabling X86_FEATURE_KVM_PV_UNHALT had no effect"); + + /* Make sure KVM clears vcpu->arch.kvm_cpuid */ + ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); + kvm_sig_old = ent->ebx; + ent->ebx = 0xdeadbeef; + vcpu_set_cpuid(vcpu); + + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); + ent->ebx = kvm_sig_old; + vcpu_set_cpuid(vcpu); + + TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "KVM_FEATURE_PV_UNHALT is set with KVM_CAP_X86_DISABLE_EXITS"); + + /* FIXME: actually test KVM_FEATURE_PV_UNHALT feature */ + + kvm_vm_free(vm); +} + int main(void) { struct kvm_vcpu *vcpu; @@ -151,4 +188,6 @@ int main(void) enter_guest(vcpu); kvm_vm_free(vm); + + test_pv_unhalt(); } diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index c02990bbd56f..9007c420d52c 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -3,7 +3,7 @@ #include <stdbool.h> #include <sys/mman.h> #include <err.h> -#include <string.h> /* ffsl() */ +#include <strings.h> /* ffsl() */ #include <unistd.h> /* _SC_PAGESIZE */ #define BIT_ULL(nr) (1ULL << (nr)) diff --git a/tools/testing/selftests/net/bind_wildcard.c b/tools/testing/selftests/net/bind_wildcard.c index a2662348cdb1..b7b54d646b93 100644 --- a/tools/testing/selftests/net/bind_wildcard.c +++ b/tools/testing/selftests/net/bind_wildcard.c @@ -6,7 +6,9 @@ #include "../kselftest_harness.h" -struct in6_addr in6addr_v4mapped_any = { +static const __u32 in4addr_any = INADDR_ANY; +static const __u32 in4addr_loopback = INADDR_LOOPBACK; +static const struct in6_addr in6addr_v4mapped_any = { .s6_addr = { 0, 0, 0, 0, 0, 0, 0, 0, @@ -14,8 +16,7 @@ struct in6_addr in6addr_v4mapped_any = { 0, 0, 0, 0 } }; - -struct in6_addr in6addr_v4mapped_loopback = { +static const struct in6_addr in6addr_v4mapped_loopback = { .s6_addr = { 0, 0, 0, 0, 0, 0, 0, 0, @@ -24,137 +25,785 @@ struct in6_addr in6addr_v4mapped_loopback = { } }; +#define NR_SOCKETS 8 + FIXTURE(bind_wildcard) { - struct sockaddr_in addr4; - struct sockaddr_in6 addr6; + int fd[NR_SOCKETS]; + socklen_t addrlen[NR_SOCKETS]; + union { + struct sockaddr addr; + struct sockaddr_in addr4; + struct sockaddr_in6 addr6; + } addr[NR_SOCKETS]; }; FIXTURE_VARIANT(bind_wildcard) { - const __u32 addr4_const; - const struct in6_addr *addr6_const; - int expected_errno; + sa_family_t family[2]; + const void *addr[2]; + bool ipv6_only[2]; + + /* 6 bind() calls below follow two bind() for the defined 2 addresses: + * + * 0.0.0.0 + * 127.0.0.1 + * :: + * ::1 + * ::ffff:0.0.0.0 + * ::ffff:127.0.0.1 + */ + int expected_errno[NR_SOCKETS]; + int expected_reuse_errno[NR_SOCKETS]; +}; + +/* (IPv4, IPv4) */ +FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v4_local) +{ + .family = {AF_INET, AF_INET}, + .addr = {&in4addr_any, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v4_any) +{ + .family = {AF_INET, AF_INET}, + .addr = {&in4addr_loopback, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; +/* (IPv4, IPv6) */ FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_any) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_any_only) +{ + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_local) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_loopback, - .expected_errno = 0, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_v4mapped_any) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_v4mapped_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_v4mapped_local) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_v4mapped_loopback, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_any) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_any_only) +{ + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_local) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_loopback, - .expected_errno = 0, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_v4mapped_any) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_v4mapped_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_v4mapped_local) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_v4mapped_loopback, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +/* (IPv6, IPv4) */ +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_any}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_loopback}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_loopback, &in4addr_any}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_loopback, &in4addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_any, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_any, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_local_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_loopback, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_local_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_loopback, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +/* (IPv6, IPv6) */ +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .ipv6_only = {true, false}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .ipv6_only = {true, true}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_loopback}, + .ipv6_only = {true, false}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_any}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_loopback}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_v4mapped_any}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_v4mapped_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +static void setup_addr(FIXTURE_DATA(bind_wildcard) *self, int i, + int family, const void *addr_const) +{ + if (family == AF_INET) { + struct sockaddr_in *addr4 = &self->addr[i].addr4; + const __u32 *addr4_const = addr_const; + + addr4->sin_family = AF_INET; + addr4->sin_port = htons(0); + addr4->sin_addr.s_addr = htonl(*addr4_const); + + self->addrlen[i] = sizeof(struct sockaddr_in); + } else { + struct sockaddr_in6 *addr6 = &self->addr[i].addr6; + const struct in6_addr *addr6_const = addr_const; + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(0); + addr6->sin6_addr = *addr6_const; + + self->addrlen[i] = sizeof(struct sockaddr_in6); + } +} + FIXTURE_SETUP(bind_wildcard) { - self->addr4.sin_family = AF_INET; - self->addr4.sin_port = htons(0); - self->addr4.sin_addr.s_addr = htonl(variant->addr4_const); + setup_addr(self, 0, variant->family[0], variant->addr[0]); + setup_addr(self, 1, variant->family[1], variant->addr[1]); + + setup_addr(self, 2, AF_INET, &in4addr_any); + setup_addr(self, 3, AF_INET, &in4addr_loopback); - self->addr6.sin6_family = AF_INET6; - self->addr6.sin6_port = htons(0); - self->addr6.sin6_addr = *variant->addr6_const; + setup_addr(self, 4, AF_INET6, &in6addr_any); + setup_addr(self, 5, AF_INET6, &in6addr_loopback); + setup_addr(self, 6, AF_INET6, &in6addr_v4mapped_any); + setup_addr(self, 7, AF_INET6, &in6addr_v4mapped_loopback); } FIXTURE_TEARDOWN(bind_wildcard) { + int i; + + for (i = 0; i < NR_SOCKETS; i++) + close(self->fd[i]); } -void bind_sockets(struct __test_metadata *_metadata, - FIXTURE_DATA(bind_wildcard) *self, - int expected_errno, - struct sockaddr *addr1, socklen_t addrlen1, - struct sockaddr *addr2, socklen_t addrlen2) +void bind_socket(struct __test_metadata *_metadata, + FIXTURE_DATA(bind_wildcard) *self, + const FIXTURE_VARIANT(bind_wildcard) *variant, + int i, int reuse) { - int fd[2]; int ret; - fd[0] = socket(addr1->sa_family, SOCK_STREAM, 0); - ASSERT_GT(fd[0], 0); + self->fd[i] = socket(self->addr[i].addr.sa_family, SOCK_STREAM, 0); + ASSERT_GT(self->fd[i], 0); - ret = bind(fd[0], addr1, addrlen1); - ASSERT_EQ(ret, 0); + if (i < 2 && variant->ipv6_only[i]) { + ret = setsockopt(self->fd[i], SOL_IPV6, IPV6_V6ONLY, &(int){1}, sizeof(int)); + ASSERT_EQ(ret, 0); + } - ret = getsockname(fd[0], addr1, &addrlen1); - ASSERT_EQ(ret, 0); + if (i < 2 && reuse) { + ret = setsockopt(self->fd[i], SOL_SOCKET, reuse, &(int){1}, sizeof(int)); + ASSERT_EQ(ret, 0); + } - ((struct sockaddr_in *)addr2)->sin_port = ((struct sockaddr_in *)addr1)->sin_port; + self->addr[i].addr4.sin_port = self->addr[0].addr4.sin_port; - fd[1] = socket(addr2->sa_family, SOCK_STREAM, 0); - ASSERT_GT(fd[1], 0); + ret = bind(self->fd[i], &self->addr[i].addr, self->addrlen[i]); - ret = bind(fd[1], addr2, addrlen2); - if (expected_errno) { - ASSERT_EQ(ret, -1); - ASSERT_EQ(errno, expected_errno); + if (reuse) { + if (variant->expected_reuse_errno[i]) { + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, variant->expected_reuse_errno[i]); + } else { + ASSERT_EQ(ret, 0); + } } else { + if (variant->expected_errno[i]) { + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, variant->expected_errno[i]); + } else { + ASSERT_EQ(ret, 0); + } + } + + if (i == 0) { + ret = getsockname(self->fd[0], &self->addr[0].addr, &self->addrlen[0]); ASSERT_EQ(ret, 0); } +} - close(fd[1]); - close(fd[0]); +TEST_F(bind_wildcard, plain) +{ + int i; + + for (i = 0; i < NR_SOCKETS; i++) + bind_socket(_metadata, self, variant, i, 0); } -TEST_F(bind_wildcard, v4_v6) +TEST_F(bind_wildcard, reuseaddr) { - bind_sockets(_metadata, self, variant->expected_errno, - (struct sockaddr *)&self->addr4, sizeof(self->addr4), - (struct sockaddr *)&self->addr6, sizeof(self->addr6)); + int i; + + for (i = 0; i < NR_SOCKETS; i++) + bind_socket(_metadata, self, variant, i, SO_REUSEADDR); } -TEST_F(bind_wildcard, v6_v4) +TEST_F(bind_wildcard, reuseport) { - bind_sockets(_metadata, self, variant->expected_errno, - (struct sockaddr *)&self->addr6, sizeof(self->addr6), - (struct sockaddr *)&self->addr4, sizeof(self->addr4)); + int i; + + for (i = 0; i < NR_SOCKETS; i++) + bind_socket(_metadata, self, variant, i, SO_REUSEPORT); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 4c4248554826..4131f3263a48 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -383,12 +383,14 @@ do_transfer() local stat_cookierx_last local stat_csum_err_s local stat_csum_err_c + local stat_tcpfb_last_l stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -457,11 +459,13 @@ do_transfer() local stat_cookietx_now local stat_cookierx_now local stat_ooo_now + local stat_tcpfb_now_l stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -508,6 +512,11 @@ do_transfer() fi fi + if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + mptcp_lib_pr_fail "unexpected fallback to TCP" + rets=1 + fi + if [ $cookies -eq 2 ];then if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then extra+=" WARN: CookieSent: did not advance" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 5e9211e89825..e4403236f655 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -729,7 +729,7 @@ pm_nl_check_endpoint() [ -n "$_flags" ]; flags="flags $_flags" shift elif [ $1 = "dev" ]; then - [ -n "$2" ]; dev="dev $1" + [ -n "$2" ]; dev="dev $2" shift elif [ $1 = "id" ]; then _id=$2 @@ -3610,6 +3610,8 @@ endpoint_tests() local tests_pid=$! wait_mpj $ns2 + pm_nl_check_endpoint "creation" \ + $ns2 10.0.2.2 id 2 flags subflow dev ns2eth2 chk_subflow_nr "before delete" 2 chk_mptcp_info subflows 1 subflows 1 diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c index 7c5b12664b03..bfb07dc49518 100644 --- a/tools/testing/selftests/net/reuseaddr_conflict.c +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -109,6 +109,6 @@ int main(void) fd1 = open_port(0, 1); if (fd1 >= 0) error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); - fprintf(stderr, "Success"); + fprintf(stderr, "Success\n"); return 0; } diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index 380cb15e942e..83ed987cff34 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -244,7 +244,7 @@ for family in 4 6; do create_vxlan_pair ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on - run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1 + run_test "GRO frag list over UDP tunnel" $OL_NET$DST 10 10 cleanup # use NAT to circumvent GRO FWD check @@ -258,13 +258,7 @@ for family in 4 6; do # load arp cache before running the test to reduce the amount of # stray traffic on top of the UDP tunnel ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null - run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST - cleanup - - create_vxlan_pair - run_bench "UDP tunnel fwd perf" $OL_NET$DST - ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on - run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST + run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST cleanup done |