diff options
492 files changed, 5230 insertions, 2689 deletions
@@ -232,6 +232,8 @@ Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> John Crispin <john@phrozen.org> <blogic@openwrt.org> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> +<jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com> +<jon.toppins+linux@gmail.com> <jtoppins@redhat.com> Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org> <josh@joshtriplett.org> <josh@freedesktop.org> <josh@joshtriplett.org> <josh@kernel.org> @@ -265,7 +267,9 @@ Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com> Krzysztof Kozlowski <krzk@kernel.org> <krzysztof.kozlowski@canonical.com> Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Kuogee Hsieh <quic_khsieh@quicinc.com> <khsieh@codeaurora.org> +Leonard Crestez <leonard.crestez@nxp.com> Leonard Crestez <cdleonard@gmail.com> Leonardo Bras <leobras.c@gmail.com> <leonardo@linux.ibm.com> +Leonard Göhrs <l.goehrs@pengutronix.de> Leonid I Ananiev <leonid.i.ananiev@intel.com> Leon Romanovsky <leon@kernel.org> <leon@leon.nu> Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com> @@ -295,6 +299,8 @@ Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> Mathieu Othacehe <m.othacehe@gmail.com> +Mat Martineau <martineau@kernel.org> <mathew.j.martineau@linux.intel.com> +Mat Martineau <martineau@kernel.org> <mathewm@codeaurora.org> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> Matthew Wilcox <willy@infradead.org> <matthew@wil.cx> Matthew Wilcox <willy@infradead.org> <mawilcox@linuxonhyperv.com> diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst index 19600c50277b..6ae5f129fbca 100644 --- a/Documentation/admin-guide/kernel-parameters.rst +++ b/Documentation/admin-guide/kernel-parameters.rst @@ -128,6 +128,7 @@ parameter is applicable:: KVM Kernel Virtual Machine support is enabled. LIBATA Libata driver is enabled LP Printer support is enabled. + LOONGARCH LoongArch architecture is enabled. LOOP Loopback device support is enabled. M68k M68k architecture is enabled. These options have more detailed description inside of diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6221a1d057dd..7016cb12dc4e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6933,6 +6933,12 @@ When enabled, memory and cache locality will be impacted. + writecombine= [LOONGARCH] Control the MAT (Memory Access Type) of + ioremap_wc(). + + on - Enable writecombine, use WUC for ioremap_wc() + off - Disable writecombine, use SUC for ioremap_wc() + x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of default x2apic cluster mode on platforms supporting x2apic. diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,cpu-interrupt-controller.yaml index 2a1cf885c99d..adf989976dcc 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,cpu-interrupt-controller.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: http://devicetree.org/schemas/interrupt-controller/loongarch,cpu-interrupt-controller.yaml# +$id: http://devicetree.org/schemas/interrupt-controller/loongson,cpu-interrupt-controller.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: LoongArch CPU Interrupt Controller @@ -11,7 +11,7 @@ maintainers: properties: compatible: - const: loongarch,cpu-interrupt-controller + const: loongson,cpu-interrupt-controller '#interrupt-cells': const: 1 @@ -28,7 +28,7 @@ required: examples: - | interrupt-controller { - compatible = "loongarch,cpu-interrupt-controller"; + compatible = "loongson,cpu-interrupt-controller"; #interrupt-cells = <1>; interrupt-controller; }; diff --git a/Documentation/devicetree/bindings/serial/renesas,scif.yaml b/Documentation/devicetree/bindings/serial/renesas,scif.yaml index 1989bd67d04e..54e4f41be9b4 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scif.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scif.yaml @@ -92,7 +92,7 @@ properties: - description: Error interrupt - description: Receive buffer full interrupt - description: Transmit buffer empty interrupt - - description: Transmit End interrupt + - description: Break interrupt - items: - description: Error interrupt - description: Receive buffer full interrupt @@ -107,7 +107,7 @@ properties: - const: eri - const: rxi - const: txi - - const: tei + - const: bri - items: - const: eri - const: rxi diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index bfb51685073c..c3851fe1900d 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -171,6 +171,10 @@ Getting Help Getting LLVM ------------- +We provide prebuilt stable versions of LLVM on `kernel.org <https://kernel.org/pub/tools/llvm/>`_. +Below are links that may be useful for building LLVM from source or procuring +it through a distribution's package manager. + - https://releases.llvm.org/download.html - https://github.com/llvm/llvm-project - https://llvm.org/docs/GettingStarted.html diff --git a/Documentation/mm/zsmalloc.rst b/Documentation/mm/zsmalloc.rst index 64d127bfc221..a3c26d587752 100644 --- a/Documentation/mm/zsmalloc.rst +++ b/Documentation/mm/zsmalloc.rst @@ -39,13 +39,12 @@ With CONFIG_ZSMALLOC_STAT, we could see zsmalloc internal information via # cat /sys/kernel/debug/zsmalloc/zram0/classes - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage + class size 10% 20% 30% 40% 50% 60% 70% 80% 90% 99% 100% obj_allocated obj_used pages_used pages_per_zspage freeable ... ... - 9 176 0 1 186 129 8 4 - 10 192 1 0 2880 2872 135 3 - 11 208 0 1 819 795 42 2 - 12 224 0 1 219 159 12 4 + 30 512 0 12 4 1 0 1 0 0 1 0 414 3464 3346 433 1 14 + 31 528 2 7 2 2 1 0 1 0 0 2 117 4154 3793 536 4 44 + 32 544 6 3 4 1 2 1 0 0 0 1 260 4170 3965 556 2 26 ... ... @@ -54,10 +53,28 @@ class index size object size zspage stores -almost_empty - the number of ZS_ALMOST_EMPTY zspages(see below) -almost_full - the number of ZS_ALMOST_FULL zspages(see below) +10% + the number of zspages with usage ratio less than 10% (see below) +20% + the number of zspages with usage ratio between 10% and 20% +30% + the number of zspages with usage ratio between 20% and 30% +40% + the number of zspages with usage ratio between 30% and 40% +50% + the number of zspages with usage ratio between 40% and 50% +60% + the number of zspages with usage ratio between 50% and 60% +70% + the number of zspages with usage ratio between 60% and 70% +80% + the number of zspages with usage ratio between 70% and 80% +90% + the number of zspages with usage ratio between 80% and 90% +99% + the number of zspages with usage ratio between 90% and 99% +100% + the number of zspages with usage ratio 100% obj_allocated the number of objects allocated obj_used @@ -66,19 +83,14 @@ pages_used the number of pages allocated for the class pages_per_zspage the number of 0-order pages to make a zspage +freeable + the approximate number of pages class compaction can free -We assign a zspage to ZS_ALMOST_EMPTY fullness group when n <= N / f, where - -* n = number of allocated objects -* N = total number of objects zspage can store -* f = fullness_threshold_frac(ie, 4 at the moment) - -Similarly, we assign zspage to: - -* ZS_ALMOST_FULL when n > N / f -* ZS_EMPTY when n == 0 -* ZS_FULL when n == N - +Each zspage maintains inuse counter which keeps track of the number of +objects stored in the zspage. The inuse counter determines the zspage's +"fullness group" which is calculated as the ratio of the "inuse" objects to +the total number of objects the zspage can hold (objs_per_zspage). The +closer the inuse counter is to objs_per_zspage, the better. Internals ========= @@ -94,10 +106,10 @@ of objects that each zspage can store. For instance, consider the following size classes::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable ... - 94 1536 0 0 0 0 0 3 0 - 100 1632 0 0 0 0 0 2 0 + 94 1536 0 .... 0 0 0 0 3 0 + 100 1632 0 .... 0 0 0 0 2 0 ... @@ -134,10 +146,11 @@ reduces memory wastage. Let's take a closer look at the bottom of `/sys/kernel/debug/zsmalloc/zramX/classes`::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - 202 3264 0 0 0 0 0 4 0 - 254 4096 0 0 0 0 0 1 0 + 202 3264 0 .. 0 0 0 0 4 0 + 254 4096 0 .. 0 0 0 0 1 0 ... Size class #202 stores objects of size 3264 bytes and has a maximum of 4 pages @@ -151,40 +164,42 @@ efficient storage of large objects. For zspage chain size of 8, huge class watermark becomes 3632 bytes::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - 202 3264 0 0 0 0 0 4 0 - 211 3408 0 0 0 0 0 5 0 - 217 3504 0 0 0 0 0 6 0 - 222 3584 0 0 0 0 0 7 0 - 225 3632 0 0 0 0 0 8 0 - 254 4096 0 0 0 0 0 1 0 + 202 3264 0 .. 0 0 0 0 4 0 + 211 3408 0 .. 0 0 0 0 5 0 + 217 3504 0 .. 0 0 0 0 6 0 + 222 3584 0 .. 0 0 0 0 7 0 + 225 3632 0 .. 0 0 0 0 8 0 + 254 4096 0 .. 0 0 0 0 1 0 ... For zspage chain size of 16, huge class watermark becomes 3840 bytes::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - 202 3264 0 0 0 0 0 4 0 - 206 3328 0 0 0 0 0 13 0 - 207 3344 0 0 0 0 0 9 0 - 208 3360 0 0 0 0 0 14 0 - 211 3408 0 0 0 0 0 5 0 - 212 3424 0 0 0 0 0 16 0 - 214 3456 0 0 0 0 0 11 0 - 217 3504 0 0 0 0 0 6 0 - 219 3536 0 0 0 0 0 13 0 - 222 3584 0 0 0 0 0 7 0 - 223 3600 0 0 0 0 0 15 0 - 225 3632 0 0 0 0 0 8 0 - 228 3680 0 0 0 0 0 9 0 - 230 3712 0 0 0 0 0 10 0 - 232 3744 0 0 0 0 0 11 0 - 234 3776 0 0 0 0 0 12 0 - 235 3792 0 0 0 0 0 13 0 - 236 3808 0 0 0 0 0 14 0 - 238 3840 0 0 0 0 0 15 0 - 254 4096 0 0 0 0 0 1 0 + 202 3264 0 .. 0 0 0 0 4 0 + 206 3328 0 .. 0 0 0 0 13 0 + 207 3344 0 .. 0 0 0 0 9 0 + 208 3360 0 .. 0 0 0 0 14 0 + 211 3408 0 .. 0 0 0 0 5 0 + 212 3424 0 .. 0 0 0 0 16 0 + 214 3456 0 .. 0 0 0 0 11 0 + 217 3504 0 .. 0 0 0 0 6 0 + 219 3536 0 .. 0 0 0 0 13 0 + 222 3584 0 .. 0 0 0 0 7 0 + 223 3600 0 .. 0 0 0 0 15 0 + 225 3632 0 .. 0 0 0 0 8 0 + 228 3680 0 .. 0 0 0 0 9 0 + 230 3712 0 .. 0 0 0 0 10 0 + 232 3744 0 .. 0 0 0 0 11 0 + 234 3776 0 .. 0 0 0 0 12 0 + 235 3792 0 .. 0 0 0 0 13 0 + 236 3808 0 .. 0 0 0 0 14 0 + 238 3840 0 .. 0 0 0 0 15 0 + 254 4096 0 .. 0 0 0 0 1 0 ... Overall the combined zspage chain size effect on zsmalloc pool configuration::: @@ -214,9 +229,10 @@ zram as a build artifacts storage (Linux kernel compilation). zsmalloc classes stats::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - Total 13 51 413836 412973 159955 3 + Total 13 .. 51 413836 412973 159955 3 zram mm_stat::: @@ -227,9 +243,10 @@ zram as a build artifacts storage (Linux kernel compilation). zsmalloc classes stats::: - class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable + class size 10% .... 100% obj_allocated obj_used pages_used pages_per_zspage freeable + ... - Total 18 87 414852 412978 156666 0 + Total 18 .. 87 414852 412978 156666 0 zram mm_stat::: diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 10f282c2117c..2f60e34ab926 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -7,6 +7,21 @@ ice devlink support This document describes the devlink features implemented by the ``ice`` device driver. +Parameters +========== + +.. list-table:: Generic parameters implemented + + * - Name + - Mode + - Notes + * - ``enable_roce`` + - runtime + - mutually exclusive with ``enable_iwarp`` + * - ``enable_iwarp`` + - runtime + - mutually exclusive with ``enable_roce`` + Info versions ============= diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 87dd1c5283e6..58a78a316697 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -340,6 +340,8 @@ tcp_app_win - INTEGER Reserve max(window/2^tcp_app_win, mss) of window for application buffer. Value 0 is special, it means that nothing is reserved. + Possible values are [0, 31], inclusive. + Default: 31 tcp_autocorking - BOOLEAN diff --git a/Documentation/riscv/vm-layout.rst b/Documentation/riscv/vm-layout.rst index 3be44e74ec5d..5462c84f4723 100644 --- a/Documentation/riscv/vm-layout.rst +++ b/Documentation/riscv/vm-layout.rst @@ -47,7 +47,7 @@ RISC-V Linux Kernel SV39 | Kernel-space virtual memory, shared between all processes: ____________________________________________________________|___________________________________________________________ | | | | - ffffffc6fee00000 | -228 GB | ffffffc6feffffff | 2 MB | fixmap + ffffffc6fea00000 | -228 GB | ffffffc6feffffff | 6 MB | fixmap ffffffc6ff000000 | -228 GB | ffffffc6ffffffff | 16 MB | PCI io ffffffc700000000 | -228 GB | ffffffc7ffffffff | 4 GB | vmemmap ffffffc800000000 | -224 GB | ffffffd7ffffffff | 64 GB | vmalloc/ioremap space @@ -83,7 +83,7 @@ RISC-V Linux Kernel SV48 | Kernel-space virtual memory, shared between all processes: ____________________________________________________________|___________________________________________________________ | | | | - ffff8d7ffee00000 | -114.5 TB | ffff8d7ffeffffff | 2 MB | fixmap + ffff8d7ffea00000 | -114.5 TB | ffff8d7ffeffffff | 6 MB | fixmap ffff8d7fff000000 | -114.5 TB | ffff8d7fffffffff | 16 MB | PCI io ffff8d8000000000 | -114.5 TB | ffff8f7fffffffff | 2 TB | vmemmap ffff8f8000000000 | -112.5 TB | ffffaf7fffffffff | 32 TB | vmalloc/ioremap space @@ -119,7 +119,7 @@ RISC-V Linux Kernel SV57 | Kernel-space virtual memory, shared between all processes: ____________________________________________________________|___________________________________________________________ | | | | - ff1bfffffee00000 | -57 PB | ff1bfffffeffffff | 2 MB | fixmap + ff1bfffffea00000 | -57 PB | ff1bfffffeffffff | 6 MB | fixmap ff1bffffff000000 | -57 PB | ff1bffffffffffff | 16 MB | PCI io ff1c000000000000 | -57 PB | ff1fffffffffffff | 1 PB | vmemmap ff20000000000000 | -56 PB | ff5fffffffffffff | 16 PB | vmalloc/ioremap space diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst index 9b52f50a6854..120430450014 100644 --- a/Documentation/sound/hd-audio/models.rst +++ b/Documentation/sound/hd-audio/models.rst @@ -704,7 +704,7 @@ ref no-jd BIOS setup but without jack-detection intel - Intel DG45* mobos + Intel D*45* mobos dell-m6-amic Dell desktops/laptops with analog mics dell-m6-dmic diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 62de0768d6aa..a5c803f39832 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8296,11 +8296,11 @@ ENOSYS for the others. 8.35 KVM_CAP_PMU_CAPABILITY --------------------------- -:Capability KVM_CAP_PMU_CAPABILITY +:Capability: KVM_CAP_PMU_CAPABILITY :Architectures: x86 :Type: vm :Parameters: arg[0] is bitmask of PMU virtualization capabilities. -:Returns 0 on success, -EINVAL when arg[0] contains invalid bits +:Returns: 0 on success, -EINVAL when arg[0] contains invalid bits This capability alters PMU virtualization in KVM. diff --git a/MAINTAINERS b/MAINTAINERS index 90abe83c02f3..c6545eb54104 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -224,13 +224,13 @@ S: Orphan / Obsolete F: drivers/net/ethernet/8390/ 9P FILE SYSTEM -M: Eric Van Hensbergen <ericvh@gmail.com> +M: Eric Van Hensbergen <ericvh@kernel.org> M: Latchesar Ionkov <lucho@ionkov.net> M: Dominique Martinet <asmadeus@codewreck.org> R: Christian Schoenebeck <linux_oss@crudebyte.com> -L: v9fs-developer@lists.sourceforge.net +L: v9fs@lists.linux.dev S: Maintained -W: http://swik.net/v9fs +W: http://github.com/v9fs Q: http://patchwork.kernel.org/project/v9fs-devel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs.git T: git git://github.com/martinetd/linux.git @@ -4461,14 +4461,14 @@ F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt F: drivers/net/ieee802154/ca8210.c CANAAN/KENDRYTE K210 SOC FPIOA DRIVER -M: Damien Le Moal <damien.lemoal@wdc.com> +M: Damien Le Moal <dlemoal@kernel.org> L: linux-riscv@lists.infradead.org L: linux-gpio@vger.kernel.org (pinctrl driver) F: Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml F: drivers/pinctrl/pinctrl-k210.c CANAAN/KENDRYTE K210 SOC RESET CONTROLLER DRIVER -M: Damien Le Moal <damien.lemoal@wdc.com> +M: Damien Le Moal <dlemoal@kernel.org> L: linux-kernel@vger.kernel.org L: linux-riscv@lists.infradead.org S: Maintained @@ -4476,7 +4476,7 @@ F: Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml F: drivers/reset/reset-k210.c CANAAN/KENDRYTE K210 SOC SYSTEM CONTROLLER DRIVER -M: Damien Le Moal <damien.lemoal@wdc.com> +M: Damien Le Moal <dlemoal@kernel.org> L: linux-riscv@lists.infradead.org S: Maintained F: Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml @@ -11758,7 +11758,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git F: drivers/ata/sata_promise.* LIBATA SUBSYSTEM (Serial and Parallel ATA drivers) -M: Damien Le Moal <damien.lemoal@opensource.wdc.com> +M: Damien Le Moal <dlemoal@kernel.org> L: linux-ide@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata.git @@ -14594,6 +14594,7 @@ F: net/netlabel/ NETWORKING [MPTCP] M: Matthieu Baerts <matthieu.baerts@tessares.net> +M: Mat Martineau <martineau@kernel.org> L: netdev@vger.kernel.org L: mptcp@lists.linux.dev S: Maintained @@ -23115,7 +23116,7 @@ S: Maintained F: arch/x86/kernel/cpu/zhaoxin.c ZONEFS FILESYSTEM -M: Damien Le Moal <damien.lemoal@opensource.wdc.com> +M: Damien Le Moal <dlemoal@kernel.org> M: Naohiro Aota <naohiro.aota@wdc.com> R: Johannes Thumshirn <jth@kernel.org> L: linux-fsdevel@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/imx6ull-colibri.dtsi b/arch/arm/boot/dts/imx6ull-colibri.dtsi index bf64ba84b358..fde8a19aac0f 100644 --- a/arch/arm/boot/dts/imx6ull-colibri.dtsi +++ b/arch/arm/boot/dts/imx6ull-colibri.dtsi @@ -33,15 +33,9 @@ self-powered; type = "micro"; - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - usb_dr_connector: endpoint { - remote-endpoint = <&usb1_drd_sw>; - }; + port { + usb_dr_connector: endpoint { + remote-endpoint = <&usb1_drd_sw>; }; }; }; diff --git a/arch/arm/boot/dts/imx7d-remarkable2.dts b/arch/arm/boot/dts/imx7d-remarkable2.dts index 8b2f11e85e05..427f8d04ec89 100644 --- a/arch/arm/boot/dts/imx7d-remarkable2.dts +++ b/arch/arm/boot/dts/imx7d-remarkable2.dts @@ -118,8 +118,6 @@ reg = <0x62>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_epdpmic>; - #address-cells = <1>; - #size-cells = <0>; #thermal-sensor-cells = <0>; epd-pwr-good-gpios = <&gpio6 21 GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index 2ca76b69add7..511ca864c1b2 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -942,7 +942,7 @@ status = "disabled"; }; - spdif: sound@ff88b0000 { + spdif: sound@ff8b0000 { compatible = "rockchip,rk3288-spdif", "rockchip,rk3066-spdif"; reg = <0x0 0xff8b0000 0x0 0x10000>; #sound-dai-cells = <0>; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 6dc6fed12af8..8d002c6e6cb3 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -76,7 +76,7 @@ CONFIG_RFKILL=y CONFIG_RFKILL_INPUT=y CONFIG_PCI=y CONFIG_PCI_MSI=y -CONFIG_PCI_IMX6=y +CONFIG_PCI_IMX6_HOST=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 123a56f7f818..feb27a0ccfb4 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -1571,15 +1571,20 @@ dmc: bus@38000 { compatible = "simple-bus"; - reg = <0x0 0x38000 0x0 0x400>; #address-cells = <2>; #size-cells = <2>; - ranges = <0x0 0x0 0x0 0x38000 0x0 0x400>; + ranges = <0x0 0x0 0x0 0x38000 0x0 0x2000>; canvas: video-lut@48 { compatible = "amlogic,canvas"; reg = <0x0 0x48 0x0 0x14>; }; + + pmu: pmu@80 { + reg = <0x0 0x80 0x0 0x40>, + <0x0 0xc00 0x0 0x40>; + interrupts = <GIC_SPI 52 IRQ_TYPE_EDGE_RISING>; + }; }; usb2_phy1: phy@3a000 { @@ -1705,12 +1710,6 @@ }; }; - pmu: pmu@ff638000 { - reg = <0x0 0xff638000 0x0 0x100>, - <0x0 0xff638c00 0x0 0x100>; - interrupts = <GIC_SPI 52 IRQ_TYPE_EDGE_RISING>; - }; - aobus: bus@ff800000 { compatible = "simple-bus"; reg = <0x0 0xff800000 0x0 0x100000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi index d1a6390976a9..3f9dfd4d3884 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi @@ -194,7 +194,7 @@ rohm,reset-snvs-powered; #clock-cells = <0>; - clocks = <&osc_32k 0>; + clocks = <&osc_32k>; clock-output-names = "clk-32k-out"; regulators { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 88321b5b0693..6f0811587142 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -99,7 +99,7 @@ compatible = "regulator-fixed"; enable-active-high; gpio = <&gpio2 20 GPIO_ACTIVE_HIGH>; /* PMIC_EN_ETH */ - off-on-delay = <500000>; + off-on-delay-us = <500000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reg_eth>; regulator-always-on; @@ -139,7 +139,7 @@ enable-active-high; /* Verdin SD_1_PWR_EN (SODIMM 76) */ gpio = <&gpio3 5 GPIO_ACTIVE_HIGH>; - off-on-delay = <100000>; + off-on-delay-us = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usdhc2_pwr_en>; regulator-max-microvolt = <3300000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin-dev.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin-dev.dtsi index 361426c0da0a..c29622529200 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-verdin-dev.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin-dev.dtsi @@ -10,7 +10,7 @@ compatible = "regulator-fixed"; enable-active-high; gpio = <&gpio_expander_21 4 GPIO_ACTIVE_HIGH>; /* ETH_PWR_EN */ - off-on-delay = <500000>; + off-on-delay-us = <500000>; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <3300000>; regulator-name = "+V3.3_ETH"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi index 0dd6180a8e39..1608775da0ad 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi @@ -87,7 +87,7 @@ compatible = "regulator-fixed"; enable-active-high; gpio = <&gpio2 20 GPIO_ACTIVE_HIGH>; /* PMIC_EN_ETH */ - off-on-delay = <500000>; + off-on-delay-us = <500000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reg_eth>; regulator-always-on; @@ -128,7 +128,7 @@ enable-active-high; /* Verdin SD_1_PWR_EN (SODIMM 76) */ gpio = <&gpio4 22 GPIO_ACTIVE_HIGH>; - off-on-delay = <100000>; + off-on-delay-us = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usdhc2_pwr_en>; regulator-max-microvolt = <3300000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 2dd60e3252f3..a237275ee017 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1128,7 +1128,7 @@ lcdif2: display-controller@32e90000 { compatible = "fsl,imx8mp-lcdif"; - reg = <0x32e90000 0x238>; + reg = <0x32e90000 0x10000>; interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MP_CLK_MEDIA_DISP2_PIX_ROOT>, <&clk IMX8MP_CLK_MEDIA_APB_ROOT>, diff --git a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts index ca3f96646b90..5cf07caf4103 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts +++ b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts @@ -62,11 +62,11 @@ perst-gpios = <&tlmm 58 GPIO_ACTIVE_LOW>; }; -&pcie_phy0 { +&pcie_qmp0 { status = "okay"; }; -&pcie_phy1 { +&pcie_qmp1 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/ipq8074-hk10.dtsi b/arch/arm64/boot/dts/qcom/ipq8074-hk10.dtsi index 651a231554e0..1b8379ba87f9 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074-hk10.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074-hk10.dtsi @@ -48,11 +48,11 @@ perst-gpios = <&tlmm 61 GPIO_ACTIVE_LOW>; }; -&pcie_phy0 { +&pcie_qmp0 { status = "okay"; }; -&pcie_phy1 { +&pcie_qmp1 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts index aa0a7bd7307c..dd924331b0ee 100644 --- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts +++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts @@ -1012,7 +1012,7 @@ left_spkr: speaker@0,3 { compatible = "sdw10217211000"; reg = <0 3>; - powerdown-gpios = <&tlmm 130 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&tlmm 130 GPIO_ACTIVE_LOW>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrLeft"; #sound-dai-cells = <0>; @@ -1021,7 +1021,7 @@ right_spkr: speaker@0,4 { compatible = "sdw10217211000"; reg = <0 4>; - powerdown-gpios = <&tlmm 130 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&tlmm 130 GPIO_ACTIVE_LOW>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrRight"; #sound-dai-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi b/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi index b6137816f2f3..313083ec1f39 100644 --- a/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi @@ -464,7 +464,7 @@ ap_i2c_tpm: &i2c14 { &mdss_dp_out { data-lanes = <0 1>; - link-frequencies = /bits/ 64 <1620000000 2700000000 5400000000 8100000000>; + link-frequencies = /bits/ 64 <1620000000 2700000000 5400000000>; }; &mdss_mdp { diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi index df7d28f7ae60..be446eba4fa7 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi @@ -59,8 +59,9 @@ #size-cells = <0>; pmk8280_pon: pon@1300 { - compatible = "qcom,pm8998-pon"; - reg = <0x1300>; + compatible = "qcom,pmk8350-pon"; + reg = <0x1300>, <0x800>; + reg-names = "hlos", "pbs"; pmk8280_pon_pwrkey: pwrkey { compatible = "qcom,pmk8350-pwrkey"; diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 67d2a663ce75..5c688cb6a7ce 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -753,7 +753,7 @@ left_spkr: speaker@0,3 { compatible = "sdw10217211000"; reg = <0 3>; - powerdown-gpios = <&wcdgpio 1 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&wcdgpio 1 GPIO_ACTIVE_LOW>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrLeft"; #sound-dai-cells = <0>; @@ -761,7 +761,7 @@ right_spkr: speaker@0,4 { compatible = "sdw10217211000"; - powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_LOW>; reg = <0 4>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrRight"; diff --git a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts index 9850140514ba..41f59e32af64 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts @@ -662,7 +662,7 @@ left_spkr: speaker@0,3 { compatible = "sdw10217211000"; reg = <0 3>; - powerdown-gpios = <&wcdgpio 1 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&wcdgpio 1 GPIO_ACTIVE_LOW>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrLeft"; #sound-dai-cells = <0>; @@ -670,7 +670,7 @@ right_spkr: speaker@0,4 { compatible = "sdw10217211000"; - powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_LOW>; reg = <0 4>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrRight"; diff --git a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts index e54cdc8bc31f..4c9de236676d 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts @@ -764,7 +764,7 @@ left_spkr: speaker@0,3 { compatible = "sdw10217211000"; reg = <0 3>; - powerdown-gpios = <&tlmm 26 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&tlmm 26 GPIO_ACTIVE_LOW>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrLeft"; #sound-dai-cells = <0>; @@ -773,7 +773,7 @@ right_spkr: speaker@0,4 { compatible = "sdw10217211000"; reg = <0 4>; - powerdown-gpios = <&tlmm 127 GPIO_ACTIVE_HIGH>; + powerdown-gpios = <&tlmm 127 GPIO_ACTIVE_LOW>; #thermal-sensor-cells = <0>; sound-name-prefix = "SpkrRight"; #sound-dai-cells = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts index 61b31688b469..ce318e05f0a6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-anbernic-rg351m.dts @@ -24,6 +24,8 @@ &internal_display { compatible = "elida,kd35t133"; + iovcc-supply = <&vcc_lcd>; + vdd-supply = <&vcc_lcd>; }; &pwm0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go.dtsi b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go.dtsi index 04eba432fb0e..80fc53c807a4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go.dtsi @@ -235,10 +235,8 @@ internal_display: panel@0 { reg = <0>; backlight = <&backlight>; - iovcc-supply = <&vcc_lcd>; reset-gpios = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>; rotation = <270>; - vdd-supply = <&vcc_lcd>; port { mipi_in_panel: endpoint { diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2-v11.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2-v11.dts index 139c898e590e..d94ac81eb4e6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2-v11.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2-v11.dts @@ -83,6 +83,8 @@ &internal_display { compatible = "elida,kd35t133"; + iovcc-supply = <&vcc_lcd>; + vdd-supply = <&vcc_lcd>; }; &rk817 { diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts index 4702183b673c..aa6f5b12206b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts @@ -59,6 +59,8 @@ &internal_display { compatible = "elida,kd35t133"; + iovcc-supply = <&vcc_lcd>; + vdd-supply = <&vcc_lcd>; }; &rk817_charger { diff --git a/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi index 083452c67711..e47d1398aeca 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368-evb.dtsi @@ -61,7 +61,6 @@ pinctrl-names = "default"; pinctrl-0 = <&bl_en>; pwms = <&pwm0 0 1000000 PWM_POLARITY_INVERTED>; - pwm-delay-us = <10000>; }; emmc_pwrseq: emmc-pwrseq { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi index ee6095baba4d..5c1929d41cc0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi @@ -198,7 +198,6 @@ power-supply = <&pp3300_disp>; pinctrl-names = "default"; pinctrl-0 = <&bl_en>; - pwm-delay-us = <10000>; }; gpio_keys: gpio-keys { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi index a47d9f758611..c5e7de60c121 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi @@ -167,7 +167,6 @@ pinctrl-names = "default"; pinctrl-0 = <&bl_en>; pwms = <&pwm1 0 1000000 0>; - pwm-delay-us = <10000>; }; dmic: dmic { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 194e48c755f6..ddd45de97950 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -50,19 +50,9 @@ pinctrl-0 = <&panel_en_pin>; power-supply = <&vcc3v3_panel>; - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - #address-cells = <1>; - #size-cells = <0>; - - panel_in_edp: endpoint@0 { - reg = <0>; - remote-endpoint = <&edp_out_panel>; - }; + port { + panel_in_edp: endpoint { + remote-endpoint = <&edp_out_panel>; }; }; }; @@ -943,7 +933,7 @@ disable-wp; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_bus4>; - sd-uhs-sdr104; + sd-uhs-sdr50; vmmc-supply = <&vcc3v0_sd>; vqmmc-supply = <&vcc_sdio>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi index 78157521e944..bca2b50e0a93 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi @@ -647,16 +647,10 @@ avdd-supply = <&avdd>; backlight = <&backlight>; dvdd-supply = <&vcc3v3_s0>; - ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; - - mipi_in_panel: endpoint { - remote-endpoint = <&mipi_out_panel>; - }; + port { + mipi_in_panel: endpoint { + remote-endpoint = <&mipi_out_panel>; }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 1881b4b71f91..40e7c4a70055 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -552,7 +552,7 @@ <0x0 0xfff10000 0 0x10000>, /* GICH */ <0x0 0xfff20000 0 0x10000>; /* GICV */ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH 0>; - its: interrupt-controller@fee20000 { + its: msi-controller@fee20000 { compatible = "arm,gic-v3-its"; msi-controller; #msi-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi index 65a80d1f6d91..9a0e217f069f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi @@ -16,8 +16,10 @@ }; &cru { - assigned-clocks = <&cru PLL_GPLL>, <&pmucru PLL_PPLL>, <&cru PLL_VPLL>; - assigned-clock-rates = <1200000000>, <200000000>, <241500000>; + assigned-clocks = <&pmucru CLK_RTC_32K>, <&cru PLL_GPLL>, + <&pmucru PLL_PPLL>, <&cru PLL_VPLL>; + assigned-clock-rates = <32768>, <1200000000>, + <200000000>, <241500000>; }; &gpio_keys_control { diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts index b4b2df821cba..c763c7f3b1b3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts @@ -105,8 +105,10 @@ }; &cru { - assigned-clocks = <&cru PLL_GPLL>, <&pmucru PLL_PPLL>, <&cru PLL_VPLL>; - assigned-clock-rates = <1200000000>, <200000000>, <500000000>; + assigned-clocks = <&pmucru CLK_RTC_32K>, <&cru PLL_GPLL>, + <&pmucru PLL_PPLL>, <&cru PLL_VPLL>; + assigned-clock-rates = <32768>, <1200000000>, + <200000000>, <500000000>; }; &dsi_dphy0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi index ce7165d7f1a1..102e448bc026 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi @@ -598,7 +598,7 @@ non-removable; pinctrl-names = "default"; pinctrl-0 = <&sdmmc1_bus4 &sdmmc1_cmd &sdmmc1_clk>; - sd-uhs-sdr104; + sd-uhs-sdr50; vmmc-supply = <&vcc3v3_sys>; vqmmc-supply = <&vcc_1v8>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi index 005cde61b4b2..a506948b5572 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi @@ -222,6 +222,7 @@ cache-size = <131072>; cache-line-size = <64>; cache-sets = <512>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -230,6 +231,7 @@ cache-size = <131072>; cache-line-size = <64>; cache-sets = <512>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -238,6 +240,7 @@ cache-size = <131072>; cache-line-size = <64>; cache-sets = <512>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -246,6 +249,7 @@ cache-size = <131072>; cache-line-size = <64>; cache-sets = <512>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -254,6 +258,7 @@ cache-size = <524288>; cache-line-size = <64>; cache-sets = <1024>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -262,6 +267,7 @@ cache-size = <524288>; cache-line-size = <64>; cache-sets = <1024>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -270,6 +276,7 @@ cache-size = <524288>; cache-line-size = <64>; cache-sets = <1024>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -278,6 +285,7 @@ cache-size = <524288>; cache-line-size = <64>; cache-sets = <1024>; + cache-level = <2>; next-level-cache = <&l3_cache>; }; @@ -286,6 +294,7 @@ cache-size = <3145728>; cache-line-size = <64>; cache-sets = <4096>; + cache-level = <3>; }; }; diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c index 5edec2f49ec9..deff21bfa680 100644 --- a/arch/arm64/kernel/compat_alignment.c +++ b/arch/arm64/kernel/compat_alignment.c @@ -314,36 +314,32 @@ int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs) int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs); unsigned int type; u32 instr = 0; - u16 tinstr = 0; int isize = 4; int thumb2_32b = 0; - int fault; instrptr = instruction_pointer(regs); if (compat_thumb_mode(regs)) { __le16 __user *ptr = (__le16 __user *)(instrptr & ~1); + u16 tinstr, tinst2; - fault = alignment_get_thumb(regs, ptr, &tinstr); - if (!fault) { - if (IS_T32(tinstr)) { - /* Thumb-2 32-bit */ - u16 tinst2; - fault = alignment_get_thumb(regs, ptr + 1, &tinst2); - instr = ((u32)tinstr << 16) | tinst2; - thumb2_32b = 1; - } else { - isize = 2; - instr = thumb2arm(tinstr); - } + if (alignment_get_thumb(regs, ptr, &tinstr)) + return 1; + + if (IS_T32(tinstr)) { /* Thumb-2 32-bit */ + if (alignment_get_thumb(regs, ptr + 1, &tinst2)) + return 1; + instr = ((u32)tinstr << 16) | tinst2; + thumb2_32b = 1; + } else { + isize = 2; + instr = thumb2arm(tinstr); } } else { - fault = alignment_get_arm(regs, (__le32 __user *)instrptr, &instr); + if (alignment_get_arm(regs, (__le32 __user *)instrptr, &instr)) + return 1; } - if (fault) - return 1; - switch (CODING_BITS(instr)) { case 0x00000000: /* 3.13.4 load/store instruction extensions */ if (LDSTHD_I_BIT(instr)) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3bd732eaf087..4b2e16e696a8 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -220,6 +220,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: case KVM_CAP_ARM_SYSTEM_SUSPEND: + case KVM_CAP_IRQFD_RESAMPLE: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -1889,9 +1890,33 @@ static int __init do_pkvm_init(u32 hyp_va_bits) return ret; } +static u64 get_hyp_id_aa64pfr0_el1(void) +{ + /* + * Track whether the system isn't affected by spectre/meltdown in the + * hypervisor's view of id_aa64pfr0_el1, used for protected VMs. + * Although this is per-CPU, we make it global for simplicity, e.g., not + * to have to worry about vcpu migration. + * + * Unlike for non-protected VMs, userspace cannot override this for + * protected VMs. + */ + u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + + val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3)); + + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), + arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED); + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), + arm64_get_meltdown_state() == SPECTRE_UNAFFECTED); + + return val; +} + static void kvm_hyp_init_symbols(void) { - kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = get_hyp_id_aa64pfr0_el1(); kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h index 07edfc7524c9..37440e1dda93 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h +++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h @@ -33,11 +33,14 @@ * Allow for protected VMs: * - Floating-point and Advanced SIMD * - Data Independent Timing + * - Spectre/Meltdown Mitigation */ #define PVM_ID_AA64PFR0_ALLOW (\ ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_FP) | \ ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD) | \ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3) \ ) /* diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 08d2b004f4b7..edd969a1f36b 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -85,19 +85,12 @@ static u64 get_restricted_features_unsigned(u64 sys_reg_val, static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) { - const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); u64 set_mask = 0; u64 allow_mask = PVM_ID_AA64PFR0_ALLOW; set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val, PVM_ID_AA64PFR0_RESTRICT_UNSIGNED); - /* Spectre and Meltdown mitigation in KVM */ - set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), - (u64)kvm->arch.pfr0_csv2); - set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), - (u64)kvm->arch.pfr0_csv3); - return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index c243b10f3e15..5eca0cdd961d 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -558,6 +558,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } + kvm_vcpu_pmu_restore_guest(vcpu); } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 1b2c161120be..34688918c811 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -794,7 +794,6 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; kvm_pmu_handle_pmcr(vcpu, val); - kvm_vcpu_pmu_restore_guest(vcpu); } else { /* PMCR.P & PMCR.C are RAZ */ val = __vcpu_sys_reg(vcpu, PMCR_EL0) diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index a6acb94ea3d6..c2edadb8ec6a 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -281,4 +281,8 @@ /* DMB */ #define A64_DMB_ISH aarch64_insn_gen_dmb(AARCH64_INSN_MB_ISH) +/* ADR */ +#define A64_ADR(Rd, offset) \ + aarch64_insn_gen_adr(0, offset, Rd, AARCH64_INSN_ADR_TYPE_ADR) + #endif /* _BPF_JIT_H */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 62f805f427b7..b26da8efa616 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1900,7 +1900,8 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, restore_args(ctx, args_off, nargs); /* call original func */ emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx); - emit(A64_BLR(A64_R(10)), ctx); + emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx); + emit(A64_RET(A64_R(10)), ctx); /* store return value */ emit(A64_STR64I(A64_R(0), A64_SP, retval_off), ctx); /* reserve a nop for bpf_tramp_image_put */ diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 7fd51257e0ed..3ddde336e6a5 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -447,6 +447,22 @@ config ARCH_IOREMAP protection support. However, you can enable LoongArch DMW-based ioremap() for better performance. +config ARCH_WRITECOMBINE + bool "Enable WriteCombine (WUC) for ioremap()" + help + LoongArch maintains cache coherency in hardware, but when paired + with LS7A chipsets the WUC attribute (Weak-ordered UnCached, which + is similar to WriteCombine) is out of the scope of cache coherency + machanism for PCIe devices (this is a PCIe protocol violation, which + may be fixed in newer chipsets). + + This means WUC can only used for write-only memory regions now, so + this option is disabled by default, making WUC silently fallback to + SUC for ioremap(). You can enable this option if the kernel is ensured + to run on hardware without this bug. + + You can override this setting via writecombine=on/off boot parameter. + config ARCH_STRICT_ALIGN bool "Enable -mstrict-align to prevent unaligned accesses" if EXPERT default y diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h index 4198753aa1d0..976a810352c6 100644 --- a/arch/loongarch/include/asm/acpi.h +++ b/arch/loongarch/include/asm/acpi.h @@ -41,8 +41,11 @@ extern void loongarch_suspend_enter(void); static inline unsigned long acpi_get_wakeup_address(void) { +#ifdef CONFIG_SUSPEND extern void loongarch_wakeup_start(void); return (unsigned long)loongarch_wakeup_start; +#endif + return 0UL; } #endif /* _ASM_LOONGARCH_ACPI_H */ diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index 8fb699b4d40a..5c9c03bdf915 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -71,9 +71,9 @@ extern unsigned long vm_map_base; #define _ATYPE32_ int #define _ATYPE64_ __s64 #ifdef CONFIG_64BIT -#define _CONST64_(x) x ## L +#define _CONST64_(x) x ## UL #else -#define _CONST64_(x) x ## LL +#define _CONST64_(x) x ## ULL #endif #endif diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h index 0051b526ac6d..c60796869b2b 100644 --- a/arch/loongarch/include/asm/bootinfo.h +++ b/arch/loongarch/include/asm/bootinfo.h @@ -13,7 +13,6 @@ const char *get_system_type(void); extern void init_environ(void); extern void memblock_init(void); extern void platform_init(void); -extern void plat_swiotlb_setup(void); extern int __init init_numa_memory(void); struct loongson_board_info { diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h index b07974218393..f6177f133477 100644 --- a/arch/loongarch/include/asm/cpu-features.h +++ b/arch/loongarch/include/asm/cpu-features.h @@ -42,6 +42,7 @@ #define cpu_has_fpu cpu_opt(LOONGARCH_CPU_FPU) #define cpu_has_lsx cpu_opt(LOONGARCH_CPU_LSX) #define cpu_has_lasx cpu_opt(LOONGARCH_CPU_LASX) +#define cpu_has_crc32 cpu_opt(LOONGARCH_CPU_CRC32) #define cpu_has_complex cpu_opt(LOONGARCH_CPU_COMPLEX) #define cpu_has_crypto cpu_opt(LOONGARCH_CPU_CRYPTO) #define cpu_has_lvz cpu_opt(LOONGARCH_CPU_LVZ) diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index c3da91759472..88773d849e33 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -78,25 +78,26 @@ enum cpu_type_enum { #define CPU_FEATURE_FPU 3 /* CPU has FPU */ #define CPU_FEATURE_LSX 4 /* CPU has LSX (128-bit SIMD) */ #define CPU_FEATURE_LASX 5 /* CPU has LASX (256-bit SIMD) */ -#define CPU_FEATURE_COMPLEX 6 /* CPU has Complex instructions */ -#define CPU_FEATURE_CRYPTO 7 /* CPU has Crypto instructions */ -#define CPU_FEATURE_LVZ 8 /* CPU has Virtualization extension */ -#define CPU_FEATURE_LBT_X86 9 /* CPU has X86 Binary Translation */ -#define CPU_FEATURE_LBT_ARM 10 /* CPU has ARM Binary Translation */ -#define CPU_FEATURE_LBT_MIPS 11 /* CPU has MIPS Binary Translation */ -#define CPU_FEATURE_TLB 12 /* CPU has TLB */ -#define CPU_FEATURE_CSR 13 /* CPU has CSR */ -#define CPU_FEATURE_WATCH 14 /* CPU has watchpoint registers */ -#define CPU_FEATURE_VINT 15 /* CPU has vectored interrupts */ -#define CPU_FEATURE_CSRIPI 16 /* CPU has CSR-IPI */ -#define CPU_FEATURE_EXTIOI 17 /* CPU has EXT-IOI */ -#define CPU_FEATURE_PREFETCH 18 /* CPU has prefetch instructions */ -#define CPU_FEATURE_PMP 19 /* CPU has perfermance counter */ -#define CPU_FEATURE_SCALEFREQ 20 /* CPU supports cpufreq scaling */ -#define CPU_FEATURE_FLATMODE 21 /* CPU has flat mode */ -#define CPU_FEATURE_EIODECODE 22 /* CPU has EXTIOI interrupt pin decode mode */ -#define CPU_FEATURE_GUESTID 23 /* CPU has GuestID feature */ -#define CPU_FEATURE_HYPERVISOR 24 /* CPU has hypervisor (running in VM) */ +#define CPU_FEATURE_CRC32 6 /* CPU has CRC32 instructions */ +#define CPU_FEATURE_COMPLEX 7 /* CPU has Complex instructions */ +#define CPU_FEATURE_CRYPTO 8 /* CPU has Crypto instructions */ +#define CPU_FEATURE_LVZ 9 /* CPU has Virtualization extension */ +#define CPU_FEATURE_LBT_X86 10 /* CPU has X86 Binary Translation */ +#define CPU_FEATURE_LBT_ARM 11 /* CPU has ARM Binary Translation */ +#define CPU_FEATURE_LBT_MIPS 12 /* CPU has MIPS Binary Translation */ +#define CPU_FEATURE_TLB 13 /* CPU has TLB */ +#define CPU_FEATURE_CSR 14 /* CPU has CSR */ +#define CPU_FEATURE_WATCH 15 /* CPU has watchpoint registers */ +#define CPU_FEATURE_VINT 16 /* CPU has vectored interrupts */ +#define CPU_FEATURE_CSRIPI 17 /* CPU has CSR-IPI */ +#define CPU_FEATURE_EXTIOI 18 /* CPU has EXT-IOI */ +#define CPU_FEATURE_PREFETCH 19 /* CPU has prefetch instructions */ +#define CPU_FEATURE_PMP 20 /* CPU has perfermance counter */ +#define CPU_FEATURE_SCALEFREQ 21 /* CPU supports cpufreq scaling */ +#define CPU_FEATURE_FLATMODE 22 /* CPU has flat mode */ +#define CPU_FEATURE_EIODECODE 23 /* CPU has EXTIOI interrupt pin decode mode */ +#define CPU_FEATURE_GUESTID 24 /* CPU has GuestID feature */ +#define CPU_FEATURE_HYPERVISOR 25 /* CPU has hypervisor (running in VM) */ #define LOONGARCH_CPU_CPUCFG BIT_ULL(CPU_FEATURE_CPUCFG) #define LOONGARCH_CPU_LAM BIT_ULL(CPU_FEATURE_LAM) @@ -104,6 +105,7 @@ enum cpu_type_enum { #define LOONGARCH_CPU_FPU BIT_ULL(CPU_FEATURE_FPU) #define LOONGARCH_CPU_LSX BIT_ULL(CPU_FEATURE_LSX) #define LOONGARCH_CPU_LASX BIT_ULL(CPU_FEATURE_LASX) +#define LOONGARCH_CPU_CRC32 BIT_ULL(CPU_FEATURE_CRC32) #define LOONGARCH_CPU_COMPLEX BIT_ULL(CPU_FEATURE_COMPLEX) #define LOONGARCH_CPU_CRYPTO BIT_ULL(CPU_FEATURE_CRYPTO) #define LOONGARCH_CPU_LVZ BIT_ULL(CPU_FEATURE_LVZ) diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index 402a7d9e3a53..545e2708fbf7 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -54,8 +54,10 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, * @offset: bus address of the memory * @size: size of the resource to map */ +extern pgprot_t pgprot_wc; + #define ioremap_wc(offset, size) \ - ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_WUC)) + ioremap_prot((offset), (size), pgprot_val(pgprot_wc)) #define ioremap_cache(offset, size) \ ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL)) diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 65b7dcdea16d..83da5d29e2d1 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -117,7 +117,7 @@ static inline u32 read_cpucfg(u32 reg) #define CPUCFG1_EP BIT(22) #define CPUCFG1_RPLV BIT(23) #define CPUCFG1_HUGEPG BIT(24) -#define CPUCFG1_IOCSRBRD BIT(25) +#define CPUCFG1_CRC32 BIT(25) #define CPUCFG1_MSGINT BIT(26) #define LOONGARCH_CPUCFG2 0x2 @@ -423,9 +423,9 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define CSR_ASID_ASID_WIDTH 10 #define CSR_ASID_ASID (_ULCAST_(0x3ff) << CSR_ASID_ASID_SHIFT) -#define LOONGARCH_CSR_PGDL 0x19 /* Page table base address when VA[47] = 0 */ +#define LOONGARCH_CSR_PGDL 0x19 /* Page table base address when VA[VALEN-1] = 0 */ -#define LOONGARCH_CSR_PGDH 0x1a /* Page table base address when VA[47] = 1 */ +#define LOONGARCH_CSR_PGDH 0x1a /* Page table base address when VA[VALEN-1] = 1 */ #define LOONGARCH_CSR_PGD 0x1b /* Page table base */ diff --git a/arch/loongarch/include/asm/module.lds.h b/arch/loongarch/include/asm/module.lds.h index 438f09d4ccf4..88554f92e010 100644 --- a/arch/loongarch/include/asm/module.lds.h +++ b/arch/loongarch/include/asm/module.lds.h @@ -2,8 +2,8 @@ /* Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ SECTIONS { . = ALIGN(4); - .got : { BYTE(0) } - .plt : { BYTE(0) } - .plt.idx : { BYTE(0) } - .ftrace_trampoline : { BYTE(0) } + .got 0 : { BYTE(0) } + .plt 0 : { BYTE(0) } + .plt.idx 0 : { BYTE(0) } + .ftrace_trampoline 0 : { BYTE(0) } } diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index cc48ed262021..82d811b5c6e9 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -47,11 +47,12 @@ struct user_fp_state { }; struct user_watch_state { - uint16_t dbg_info; + uint64_t dbg_info; struct { uint64_t addr; uint64_t mask; uint32_t ctrl; + uint32_t pad; } dbg_regs[8]; }; diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 3a3fce2d7846..5adf0f736c6d 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -60,7 +60,7 @@ static inline void set_elf_platform(int cpu, const char *plat) /* MAP BASE */ unsigned long vm_map_base; -EXPORT_SYMBOL_GPL(vm_map_base); +EXPORT_SYMBOL(vm_map_base); static void cpu_probe_addrbits(struct cpuinfo_loongarch *c) { @@ -94,13 +94,18 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH; - elf_hwcap = HWCAP_LOONGARCH_CPUCFG | HWCAP_LOONGARCH_CRC32; + elf_hwcap = HWCAP_LOONGARCH_CPUCFG; config = read_cpucfg(LOONGARCH_CPUCFG1); if (config & CPUCFG1_UAL) { c->options |= LOONGARCH_CPU_UAL; elf_hwcap |= HWCAP_LOONGARCH_UAL; } + if (config & CPUCFG1_CRC32) { + c->options |= LOONGARCH_CPU_CRC32; + elf_hwcap |= HWCAP_LOONGARCH_CRC32; + } + config = read_cpucfg(LOONGARCH_CPUCFG2); if (config & CPUCFG2_LAM) { diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c index 5c67cc4fd56d..0d82907b5404 100644 --- a/arch/loongarch/kernel/proc.c +++ b/arch/loongarch/kernel/proc.c @@ -76,6 +76,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_fpu) seq_printf(m, " fpu"); if (cpu_has_lsx) seq_printf(m, " lsx"); if (cpu_has_lasx) seq_printf(m, " lasx"); + if (cpu_has_crc32) seq_printf(m, " crc32"); if (cpu_has_complex) seq_printf(m, " complex"); if (cpu_has_crypto) seq_printf(m, " crypto"); if (cpu_has_lvz) seq_printf(m, " lvz"); diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index 06bceae7d104..5fcffb452367 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -391,10 +391,10 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, return 0; } -static int ptrace_hbp_get_resource_info(unsigned int note_type, u16 *info) +static int ptrace_hbp_get_resource_info(unsigned int note_type, u64 *info) { u8 num; - u16 reg = 0; + u64 reg = 0; switch (note_type) { case NT_LOONGARCH_HW_BREAK: @@ -524,15 +524,16 @@ static int ptrace_hbp_set_addr(unsigned int note_type, return modify_user_hw_breakpoint(bp, &attr); } -#define PTRACE_HBP_CTRL_SZ sizeof(u32) #define PTRACE_HBP_ADDR_SZ sizeof(u64) #define PTRACE_HBP_MASK_SZ sizeof(u64) +#define PTRACE_HBP_CTRL_SZ sizeof(u32) +#define PTRACE_HBP_PAD_SZ sizeof(u32) static int hw_break_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { - u16 info; + u64 info; u32 ctrl; u64 addr, mask; int ret, idx = 0; @@ -545,7 +546,7 @@ static int hw_break_get(struct task_struct *target, membuf_write(&to, &info, sizeof(info)); - /* (address, ctrl) registers */ + /* (address, mask, ctrl) registers */ while (to.left) { ret = ptrace_hbp_get_addr(note_type, target, idx, &addr); if (ret) @@ -562,6 +563,7 @@ static int hw_break_get(struct task_struct *target, membuf_store(&to, addr); membuf_store(&to, mask); membuf_store(&to, ctrl); + membuf_zero(&to, sizeof(u32)); idx++; } @@ -582,7 +584,7 @@ static int hw_break_set(struct task_struct *target, offset = offsetof(struct user_watch_state, dbg_regs); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); - /* (address, ctrl) registers */ + /* (address, mask, ctrl) registers */ limit = regset->n * regset->size; while (count && offset < limit) { if (count < PTRACE_HBP_ADDR_SZ) @@ -602,7 +604,7 @@ static int hw_break_set(struct task_struct *target, break; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, - offset, offset + PTRACE_HBP_ADDR_SZ); + offset, offset + PTRACE_HBP_MASK_SZ); if (ret) return ret; @@ -611,8 +613,8 @@ static int hw_break_set(struct task_struct *target, return ret; offset += PTRACE_HBP_MASK_SZ; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, - offset, offset + PTRACE_HBP_MASK_SZ); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, + offset, offset + PTRACE_HBP_CTRL_SZ); if (ret) return ret; @@ -620,6 +622,11 @@ static int hw_break_set(struct task_struct *target, if (ret) return ret; offset += PTRACE_HBP_CTRL_SZ; + + user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, + offset, offset + PTRACE_HBP_PAD_SZ); + offset += PTRACE_HBP_PAD_SZ; + idx++; } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index bae84ccf6d36..4444b13418f0 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -160,6 +160,27 @@ static void __init smbios_parse(void) dmi_walk(find_tokens, NULL); } +#ifdef CONFIG_ARCH_WRITECOMBINE +pgprot_t pgprot_wc = PAGE_KERNEL_WUC; +#else +pgprot_t pgprot_wc = PAGE_KERNEL_SUC; +#endif + +EXPORT_SYMBOL(pgprot_wc); + +static int __init setup_writecombine(char *p) +{ + if (!strcmp(p, "on")) + pgprot_wc = PAGE_KERNEL_WUC; + else if (!strcmp(p, "off")) + pgprot_wc = PAGE_KERNEL_SUC; + else + pr_warn("Unknown writecombine setting \"%s\".\n", p); + + return 0; +} +early_param("writecombine", setup_writecombine); + static int usermem __initdata; static int __init early_parse_mem(char *p) @@ -368,8 +389,8 @@ static void __init arch_mem_init(char **cmdline_p) /* * In order to reduce the possibility of kernel panic when failed to * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate - * low memory as small as possible before plat_swiotlb_setup(), so - * make sparse_init() using top-down allocation. + * low memory as small as possible before swiotlb_init(), so make + * sparse_init() using top-down allocation. */ memblock_set_bottom_up(false); sparse_init(); diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c index 3a690f96f00c..2463d2fea21f 100644 --- a/arch/loongarch/kernel/stacktrace.c +++ b/arch/loongarch/kernel/stacktrace.c @@ -30,7 +30,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, regs->regs[1] = 0; for (unwind_start(&state, task, regs); - !unwind_done(&state); unwind_next_frame(&state)) { + !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || !consume_entry(cookie, addr)) break; diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c index a463d6961344..ba324ba76fa1 100644 --- a/arch/loongarch/kernel/unwind.c +++ b/arch/loongarch/kernel/unwind.c @@ -28,5 +28,6 @@ bool default_next_frame(struct unwind_state *state) } while (!get_stack_info(state->sp, state->task, info)); + state->error = true; return false; } diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index 9095fde8e55d..55afc27320e1 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -211,7 +211,7 @@ static bool next_frame(struct unwind_state *state) pc = regs->csr_era; if (user_mode(regs) || !__kernel_text_address(pc)) - return false; + goto out; state->first = true; state->pc = pc; @@ -226,6 +226,8 @@ static bool next_frame(struct unwind_state *state) } while (!get_stack_info(state->sp, state->task, info)); +out: + state->error = true; return false; } diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index e018aed34586..3b7d8129570b 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -41,7 +41,7 @@ * don't have to care about aliases on other CPUs. */ unsigned long empty_zero_page, zero_page_mask; -EXPORT_SYMBOL_GPL(empty_zero_page); +EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(zero_page_mask); void setup_zero_pages(void) @@ -270,7 +270,7 @@ pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss; #endif #ifndef __PAGETABLE_PMD_FOLDED pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned_bss; -EXPORT_SYMBOL_GPL(invalid_pmd_table); +EXPORT_SYMBOL(invalid_pmd_table); #endif pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss; EXPORT_SYMBOL(invalid_pte_table); diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 288003a9f0ca..d586df48ecc6 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1022,6 +1022,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext emit_atomic(insn, ctx); break; + /* Speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + default: pr_err("bpf_jit: unknown opcode %02x\n", code); return -EINVAL; diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S index 90da899c06a1..e2fc3b4e31f0 100644 --- a/arch/loongarch/power/suspend_asm.S +++ b/arch/loongarch/power/suspend_asm.S @@ -80,6 +80,10 @@ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL) JUMP_VIRT_ADDR t0, t1 + /* Enable PG */ + li.w t0, 0xb0 # PLV=0, IE=0, PG=1 + csrwr t0, LOONGARCH_CSR_CRMD + la.pcrel t0, acpi_saved_sp ld.d sp, t0, 0 SETUP_WAKEUP diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 4c5405fc5538..d23e25e8432d 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -576,6 +576,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif +#ifdef CONFIG_HAVE_KVM_IRQFD + case KVM_CAP_IRQFD_RESAMPLE: + r = !xive_enabled(); + break; +#endif + case KVM_CAP_PPC_ALLOC_HTAB: r = hv_enabled; break; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b44ce71917d7..16cfe56be05b 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -366,6 +366,7 @@ void update_numa_distance(struct device_node *node) WARN(numa_distance_table[nid][nid] == -1, "NUMA distance details for node %d not provided\n", nid); } +EXPORT_SYMBOL_GPL(update_numa_distance); /* * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN} diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 2f8385523a13..1a53e048ceb7 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -1428,6 +1428,13 @@ static int papr_scm_probe(struct platform_device *pdev) return -ENODEV; } + /* + * open firmware platform device create won't update the NUMA + * distance table. For PAPR SCM devices we use numa_map_to_online_node() + * to find the nearest online NUMA node and that requires correct + * distance table information. + */ + update_numa_distance(dn); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi index 07e2e2649604..f87c5164d9cf 100644 --- a/arch/riscv/boot/dts/canaan/k210.dtsi +++ b/arch/riscv/boot/dts/canaan/k210.dtsi @@ -259,7 +259,6 @@ <&sysclk K210_CLK_APB0>; clock-names = "ssi_clk", "pclk"; resets = <&sysrst K210_RST_SPI2>; - spi-max-frequency = <25000000>; }; i2s0: i2s@50250000 { diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h index 5c3e7b97fcc6..0a55099bb734 100644 --- a/arch/riscv/include/asm/fixmap.h +++ b/arch/riscv/include/asm/fixmap.h @@ -22,6 +22,14 @@ */ enum fixed_addresses { FIX_HOLE, + /* + * The fdt fixmap mapping must be PMD aligned and will be mapped + * using PMD entries in fixmap_pmd in 64-bit and a PGD entry in 32-bit. + */ + FIX_FDT_END, + FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1, + + /* Below fixmaps will be mapped using fixmap_pte */ FIX_PTE, FIX_PMD, FIX_PUD, diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index ab05f892d317..f641837ccf31 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -87,9 +87,13 @@ #define FIXADDR_TOP PCI_IO_START #ifdef CONFIG_64BIT -#define FIXADDR_SIZE PMD_SIZE +#define MAX_FDT_SIZE PMD_SIZE +#define FIX_FDT_SIZE (MAX_FDT_SIZE + SZ_2M) +#define FIXADDR_SIZE (PMD_SIZE + FIX_FDT_SIZE) #else -#define FIXADDR_SIZE PGDIR_SIZE +#define MAX_FDT_SIZE PGDIR_SIZE +#define FIX_FDT_SIZE MAX_FDT_SIZE +#define FIXADDR_SIZE (PGDIR_SIZE + FIX_FDT_SIZE) #endif #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 376d2827e736..a059b73f4ddb 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -278,12 +278,8 @@ void __init setup_arch(char **cmdline_p) #if IS_ENABLED(CONFIG_BUILTIN_DTB) unflatten_and_copy_device_tree(); #else - if (early_init_dt_verify(__va(XIP_FIXUP(dtb_early_pa)))) - unflatten_device_tree(); - else - pr_err("No DTB found in kernel mappings\n"); + unflatten_device_tree(); #endif - early_init_fdt_scan_reserved_mem(); misc_mem_init(); init_resources(); diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index bfb2afa4135f..dee66c9290cc 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -19,6 +19,7 @@ #include <asm/signal32.h> #include <asm/switch_to.h> #include <asm/csr.h> +#include <asm/cacheflush.h> extern u32 __user_rt_sigreturn[2]; @@ -181,6 +182,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, { struct rt_sigframe __user *frame; long err = 0; + unsigned long __maybe_unused addr; frame = get_sigframe(ksig, regs, sizeof(*frame)); if (!access_ok(frame, sizeof(*frame))) @@ -209,7 +211,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn, sizeof(frame->sigreturn_code))) return -EFAULT; - regs->ra = (unsigned long)&frame->sigreturn_code; + + addr = (unsigned long)&frame->sigreturn_code; + /* Make sure the two instructions are pushed to icache. */ + flush_icache_range(addr, addr + sizeof(frame->sigreturn_code)); + + regs->ra = addr; #endif /* CONFIG_MMU */ /* diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 478d6763a01a..0f14f4a8d179 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -57,7 +57,6 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] EXPORT_SYMBOL(empty_zero_page); extern char _start[]; -#define DTB_EARLY_BASE_VA PGDIR_SIZE void *_dtb_early_va __initdata; uintptr_t _dtb_early_pa __initdata; @@ -236,31 +235,22 @@ static void __init setup_bootmem(void) set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); reserve_initrd_mem(); + + /* + * No allocation should be done before reserving the memory as defined + * in the device tree, otherwise the allocation could end up in a + * reserved region. + */ + early_init_fdt_scan_reserved_mem(); + /* * If DTB is built in, no need to reserve its memblock. * Otherwise, do reserve it but avoid using * early_init_fdt_reserve_self() since __pa() does * not work for DTB pointers that are fixmap addresses */ - if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) { - /* - * In case the DTB is not located in a memory region we won't - * be able to locate it later on via the linear mapping and - * get a segfault when accessing it via __va(dtb_early_pa). - * To avoid this situation copy DTB to a memory region. - * Note that memblock_phys_alloc will also reserve DTB region. - */ - if (!memblock_is_memory(dtb_early_pa)) { - size_t fdt_size = fdt_totalsize(dtb_early_va); - phys_addr_t new_dtb_early_pa = memblock_phys_alloc(fdt_size, PAGE_SIZE); - void *new_dtb_early_va = early_memremap(new_dtb_early_pa, fdt_size); - - memcpy(new_dtb_early_va, dtb_early_va, fdt_size); - early_memunmap(new_dtb_early_va, fdt_size); - _dtb_early_pa = new_dtb_early_pa; - } else - memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); - } + if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); dma_contiguous_reserve(dma32_phys_limit); if (IS_ENABLED(CONFIG_64BIT)) @@ -279,9 +269,6 @@ pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss; static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss; pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); -static p4d_t __maybe_unused early_dtb_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE); -static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); #ifdef CONFIG_XIP_KERNEL #define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops)) @@ -626,9 +613,6 @@ static void __init create_p4d_mapping(p4d_t *p4dp, #define trampoline_pgd_next (pgtable_l5_enabled ? \ (uintptr_t)trampoline_p4d : (pgtable_l4_enabled ? \ (uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd)) -#define early_dtb_pgd_next (pgtable_l5_enabled ? \ - (uintptr_t)early_dtb_p4d : (pgtable_l4_enabled ? \ - (uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd)) #else #define pgd_next_t pte_t #define alloc_pgd_next(__va) pt_ops.alloc_pte(__va) @@ -636,7 +620,6 @@ static void __init create_p4d_mapping(p4d_t *p4dp, #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \ create_pte_mapping(__nextp, __va, __pa, __sz, __prot) #define fixmap_pgd_next ((uintptr_t)fixmap_pte) -#define early_dtb_pgd_next ((uintptr_t)early_dtb_pmd) #define create_p4d_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) #define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) #define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) @@ -860,32 +843,28 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early) * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR * entry. */ -static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa) +static void __init create_fdt_early_page_table(pgd_t *pgdir, + uintptr_t fix_fdt_va, + uintptr_t dtb_pa) { -#ifndef CONFIG_BUILTIN_DTB uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1); - create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, - IS_ENABLED(CONFIG_64BIT) ? early_dtb_pgd_next : pa, - PGDIR_SIZE, - IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL); - - if (pgtable_l5_enabled) - create_p4d_mapping(early_dtb_p4d, DTB_EARLY_BASE_VA, - (uintptr_t)early_dtb_pud, P4D_SIZE, PAGE_TABLE); - - if (pgtable_l4_enabled) - create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA, - (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE); +#ifndef CONFIG_BUILTIN_DTB + /* Make sure the fdt fixmap address is always aligned on PMD size */ + BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE)); - if (IS_ENABLED(CONFIG_64BIT)) { - create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, + /* In 32-bit only, the fdt lies in its own PGD */ + if (!IS_ENABLED(CONFIG_64BIT)) { + create_pgd_mapping(early_pg_dir, fix_fdt_va, + pa, MAX_FDT_SIZE, PAGE_KERNEL); + } else { + create_pmd_mapping(fixmap_pmd, fix_fdt_va, pa, PMD_SIZE, PAGE_KERNEL); - create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, + create_pmd_mapping(fixmap_pmd, fix_fdt_va + PMD_SIZE, pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); } - dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); + dtb_early_va = (void *)fix_fdt_va + (dtb_pa & (PMD_SIZE - 1)); #else /* * For 64-bit kernel, __va can't be used since it would return a linear @@ -1055,7 +1034,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) create_kernel_page_table(early_pg_dir, true); /* Setup early mapping for FDT early scan */ - create_fdt_early_page_table(early_pg_dir, dtb_pa); + create_fdt_early_page_table(early_pg_dir, + __fix_to_virt(FIX_FDT), dtb_pa); /* * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap @@ -1097,6 +1077,16 @@ static void __init setup_vm_final(void) u64 i; /* Setup swapper PGD for fixmap */ +#if !defined(CONFIG_64BIT) + /* + * In 32-bit, the device tree lies in a pgd entry, so it must be copied + * directly in swapper_pg_dir in addition to the pgd entry that points + * to fixmap_pte. + */ + unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT)); + + set_pgd(&swapper_pg_dir[idx], early_pg_dir[idx]); +#endif create_pgd_mapping(swapper_pg_dir, FIXADDR_START, __pa_symbol(fixmap_pgd_next), PGDIR_SIZE, PAGE_TABLE); diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index d16bf715a586..5730797a6b40 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -84,12 +84,7 @@ CFLAGS_string.o += $(PURGATORY_CFLAGS) CFLAGS_REMOVE_ctype.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_ctype.o += $(PURGATORY_CFLAGS) -AFLAGS_REMOVE_entry.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_memcpy.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_memset.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_strcmp.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_strlen.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_strncmp.o += -Wa,-gdwarf-2 +asflags-remove-y += $(foreach x, -g -gdwarf-4 -gdwarf-5, $(x) -Wa,$(x)) $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 0ee02dae14b2..2cda8d9d7c6e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -271,10 +271,18 @@ static int handle_prog(struct kvm_vcpu *vcpu) * handle_external_interrupt - used for external interruption interceptions * @vcpu: virtual cpu * - * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if - * the new PSW does not have external interrupts disabled. In the first case, - * we've got to deliver the interrupt manually, and in the second case, we - * drop to userspace to handle the situation there. + * This interception occurs if: + * - the CPUSTAT_EXT_INT bit was already set when the external interrupt + * occurred. In this case, the interrupt needs to be injected manually to + * preserve interrupt priority. + * - the external new PSW has external interrupts enabled, which will cause an + * interruption loop. We drop to userspace in this case. + * + * The latter case can be detected by inspecting the external mask bit in the + * external new psw. + * + * Under PV, only the latter case can occur, since interrupt priorities are + * handled in the ultravisor. */ static int handle_external_interrupt(struct kvm_vcpu *vcpu) { @@ -285,10 +293,18 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu) vcpu->stat.exit_external_interrupt++; - rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t)); - if (rc) - return rc; - /* We can not handle clock comparator or timer interrupt with bad PSW */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + newpsw = vcpu->arch.sie_block->gpsw; + } else { + rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t)); + if (rc) + return rc; + } + + /* + * Clock comparator or timer interrupt with external interrupt enabled + * will cause interrupt loop. Drop to userspace. + */ if ((eic == EXT_IRQ_CLK_COMP || eic == EXT_IRQ_CPU_TIMER) && (newpsw.mask & PSW_MASK_EXT)) return -EOPNOTSUPP; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 39b36562c043..1eeb9ae57879 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -573,6 +573,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_VCPU_RESETS: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_S390_DIAG318: + case KVM_CAP_IRQFD_RESAMPLE: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index d0846ba818ee..6b1876e4ad3f 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -539,7 +539,7 @@ static void bpf_jit_plt(void *plt, void *ret, void *target) { memcpy(plt, bpf_plt, BPF_PLT_SIZE); *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret; - *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target; + *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret; } /* @@ -2010,7 +2010,9 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, } __packed insn; char expected_plt[BPF_PLT_SIZE]; char current_plt[BPF_PLT_SIZE]; + char new_plt[BPF_PLT_SIZE]; char *plt; + char *ret; int err; /* Verify the branch to be patched. */ @@ -2032,12 +2034,15 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE); if (err < 0) return err; - bpf_jit_plt(expected_plt, (char *)ip + 6, old_addr); + ret = (char *)ip + 6; + bpf_jit_plt(expected_plt, ret, old_addr); if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE)) return -EINVAL; /* Adjust the call address. */ + bpf_jit_plt(new_plt, ret, new_addr); s390_kernel_write(plt + (bpf_plt_target - bpf_plt), - &new_addr, sizeof(void *)); + new_plt + (bpf_plt_target - bpf_plt), + sizeof(void *)); } /* Adjust the mask of the branch. */ diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index b70559b821df..2106a2bd152b 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -3,9 +3,14 @@ core-y += arch/x86/crypto/ # # Disable SSE and other FP/SIMD instructions to match normal x86 +# This is required to work around issues in older LLVM versions, but breaks +# GCC versions < 11. See: +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99652 # +ifeq ($(CONFIG_CC_IS_CLANG),y) KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 +endif ifeq ($(CONFIG_X86_32),y) START := 0x8048000 diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index cbaf174d8efd..b3af2d45bbbb 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -125,6 +125,8 @@ #define INTEL_FAM6_LUNARLAKE_M 0xBD +#define INTEL_FAM6_ARROWLAKE 0xC6 + /* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1c38174b5f01..0dac4ab5b55b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -146,7 +146,11 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) pr_debug("Local APIC address 0x%08x\n", madt->address); } - if (madt->header.revision >= 5) + + /* ACPI 6.3 and newer support the online capable bit. */ + if (acpi_gbl_FADT.header.revision > 6 || + (acpi_gbl_FADT.header.revision == 6 && + acpi_gbl_FADT.minor_revision >= 3)) acpi_support_online_capable = true; default_acpi_madt_oem_check(madt->header.oem_id, @@ -193,7 +197,8 @@ static bool __init acpi_is_processor_usable(u32 lapic_flags) if (lapic_flags & ACPI_MADT_ENABLED) return true; - if (acpi_support_online_capable && (lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) + if (!acpi_support_online_capable || + (lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) return true; return false; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f36dc2f796c5..f1197366a97d 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -358,12 +358,16 @@ static void __init ms_hyperv_init_platform(void) * To mirror what Windows does we should extract CPU management * features and use the ReservedIdentityBit to detect if Linux is the * root partition. But that requires negotiating CPU management - * interface (a process to be finalized). + * interface (a process to be finalized). For now, use the privilege + * flag as the indicator for running as root. * - * For now, use the privilege flag as the indicator for running as - * root. + * Hyper-V should never specify running as root and as a Confidential + * VM. But to protect against a compromised/malicious Hyper-V trying + * to exploit root behavior to expose Confidential VM memory, ignore + * the root partition setting if also a Confidential VM. */ - if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_CPU_MANAGEMENT) { + if ((ms_hyperv.priv_high & HV_CPU_MANAGEMENT) && + !(ms_hyperv.priv_high & HV_ISOLATION)) { hv_root_partition = true; pr_info("Hyper-V: running as root partition\n"); } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ef80d361b463..10622cf2b30f 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -33,8 +33,8 @@ static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } -static __init int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } -static __init void get_rtc_noop(struct timespec64 *now) { } +static int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } +static void get_rtc_noop(struct timespec64 *now) { } static __initconst const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818" }, diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 042dee556125..995eb5054360 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -368,9 +368,39 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) mask_after = e->fields.mask; if (mask_before != mask_after) kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after); - if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG - && ioapic->irr & (1 << index)) - ioapic_service(ioapic, index, false); + if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && + ioapic->irr & (1 << index) && !e->fields.mask && !e->fields.remote_irr) { + /* + * Pending status in irr may be outdated: the IRQ line may have + * already been deasserted by a device while the IRQ was masked. + * This occurs, for instance, if the interrupt is handled in a + * Linux guest as a oneshot interrupt (IRQF_ONESHOT). In this + * case the guest acknowledges the interrupt to the device in + * its threaded irq handler, i.e. after the EOI but before + * unmasking, so at the time of unmasking the IRQ line is + * already down but our pending irr bit is still set. In such + * cases, injecting this pending interrupt to the guest is + * buggy: the guest will receive an extra unwanted interrupt. + * + * So we need to check here if the IRQ is actually still pending. + * As we are generally not able to probe the IRQ line status + * directly, we do it through irqfd resampler. Namely, we clear + * the pending status and notify the resampler that this interrupt + * is done, without actually injecting it into the guest. If the + * IRQ line is actually already deasserted, we are done. If it is + * still asserted, a new interrupt will be shortly triggered + * through irqfd and injected into the guest. + * + * If, however, it's not possible to resample (no irqfd resampler + * registered for this irq), then unconditionally inject this + * pending interrupt into the guest, so the guest will not miss + * an interrupt, although may get an extra unwanted interrupt. + */ + if (kvm_notify_irqfd_resampler(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index)) + ioapic->irr &= ~(1 << index); + else + ioapic_service(ioapic, index, false); + } if (e->fields.delivery_mode == APIC_DM_FIXED) { struct kvm_lapic_irq irq; diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h index 287e98ef9df3..6272dabec02d 100644 --- a/arch/x86/kvm/kvm_onhyperv.h +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -12,6 +12,11 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, int hv_remote_flush_tlb(struct kvm *kvm); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp); #else /* !CONFIG_HYPERV */ +static inline int hv_remote_flush_tlb(struct kvm *kvm) +{ + return -EOPNOTSUPP; +} + static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) { } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 252e7f37e4e2..f25bc3cbb250 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3729,7 +3729,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); } -static void svm_flush_tlb_current(struct kvm_vcpu *vcpu) +static void svm_flush_tlb_asid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3753,6 +3753,37 @@ static void svm_flush_tlb_current(struct kvm_vcpu *vcpu) svm->current_vmcb->asid_generation--; } +static void svm_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + hpa_t root_tdp = vcpu->arch.mmu->root.hpa; + + /* + * When running on Hyper-V with EnlightenedNptTlb enabled, explicitly + * flush the NPT mappings via hypercall as flushing the ASID only + * affects virtual to physical mappings, it does not invalidate guest + * physical to host physical mappings. + */ + if (svm_hv_is_enlightened_tlb_enabled(vcpu) && VALID_PAGE(root_tdp)) + hyperv_flush_guest_mapping(root_tdp); + + svm_flush_tlb_asid(vcpu); +} + +static void svm_flush_tlb_all(struct kvm_vcpu *vcpu) +{ + /* + * When running on Hyper-V with EnlightenedNptTlb enabled, remote TLB + * flushes should be routed to hv_remote_flush_tlb() without requesting + * a "regular" remote flush. Reaching this point means either there's + * a KVM bug or a prior hv_remote_flush_tlb() call failed, both of + * which might be fatal to the guest. Yell, but try to recover. + */ + if (WARN_ON_ONCE(svm_hv_is_enlightened_tlb_enabled(vcpu))) + hv_remote_flush_tlb(vcpu->kvm); + + svm_flush_tlb_asid(vcpu); +} + static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4745,10 +4776,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_rflags = svm_set_rflags, .get_if_flag = svm_get_if_flag, - .flush_tlb_all = svm_flush_tlb_current, + .flush_tlb_all = svm_flush_tlb_all, .flush_tlb_current = svm_flush_tlb_current, .flush_tlb_gva = svm_flush_tlb_gva, - .flush_tlb_guest = svm_flush_tlb_current, + .flush_tlb_guest = svm_flush_tlb_asid, .vcpu_pre_run = svm_vcpu_pre_run, .vcpu_run = svm_vcpu_run, diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index cff838f15db5..786d46d73a8e 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -6,6 +6,8 @@ #ifndef __ARCH_X86_KVM_SVM_ONHYPERV_H__ #define __ARCH_X86_KVM_SVM_ONHYPERV_H__ +#include <asm/mshyperv.h> + #if IS_ENABLED(CONFIG_HYPERV) #include "kvm_onhyperv.h" @@ -15,6 +17,14 @@ static struct kvm_x86_ops svm_x86_ops; int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu); +static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu) +{ + struct hv_vmcb_enlightenments *hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments; + + return ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB && + !!hve->hv_enlightenments_control.enlightened_npt_tlb; +} + static inline void svm_hv_init_vmcb(struct vmcb *vmcb) { struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; @@ -80,6 +90,11 @@ static inline void svm_hv_update_vp_id(struct vmcb *vmcb, struct kvm_vcpu *vcpu) } #else +static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} + static inline void svm_hv_init_vmcb(struct vmcb *vmcb) { } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1bc2b80273c9..768487611db7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3868,7 +3868,12 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu) exit_qual = 0; } - if (ex->has_error_code) { + /* + * Unlike AMD's Paged Real Mode, which reports an error code on #PF + * VM-Exits even if the CPU is in Real Mode, Intel VMX never sets the + * "has error code" flags on VM-Exit if the CPU is in Real Mode. + */ + if (ex->has_error_code && is_protmode(vcpu)) { /* * Intel CPUs do not generate error codes with bits 31:16 set, * and more importantly VMX disallows setting bits 31:16 in the diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7713420abab0..3d852ce84920 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4432,6 +4432,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_VAPIC: case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: + case KVM_CAP_IRQFD_RESAMPLE: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -8903,6 +8904,8 @@ restart: } if (ctxt->have_exception) { + WARN_ON_ONCE(vcpu->mmio_needed && !vcpu->mmio_is_write); + vcpu->mmio_needed = false; r = 1; inject_emulated_exception(vcpu); } else if (vcpu->arch.pio.count) { @@ -9906,13 +9909,20 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu) static void kvm_inject_exception(struct kvm_vcpu *vcpu) { + /* + * Suppress the error code if the vCPU is in Real Mode, as Real Mode + * exceptions don't report error codes. The presence of an error code + * is carried with the exception and only stripped when the exception + * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do + * report an error code despite the CPU being in Real Mode. + */ + vcpu->arch.exception.has_error_code &= is_protmode(vcpu); + trace_kvm_inj_exception(vcpu->arch.exception.vector, vcpu->arch.exception.has_error_code, vcpu->arch.exception.error_code, vcpu->arch.exception.injected); - if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) - vcpu->arch.exception.error_code = false; static_call(kvm_x86_inject_exception)(vcpu); } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 615a76d70019..bf5161dcf89e 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -7,6 +7,7 @@ #include <linux/dmi.h> #include <linux/pci.h> #include <linux/vgaarb.h> +#include <asm/amd_nb.h> #include <asm/hpet.h> #include <asm/pci_x86.h> @@ -824,3 +825,23 @@ static void rs690_fix_64bit_dma(struct pci_dev *pdev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); #endif + +#ifdef CONFIG_AMD_NB + +#define AMD_15B8_RCC_DEV2_EPF0_STRAP2 0x10136008 +#define AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK 0x00000080L + +static void quirk_clear_strap_no_soft_reset_dev2_f0(struct pci_dev *dev) +{ + u32 data; + + if (!amd_smn_read(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, &data)) { + data &= ~AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK; + if (amd_smn_write(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, data)) + pci_err(dev, "Failed to write data 0x%x\n", data); + } else { + pci_err(dev, "Failed to read data\n"); + } +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b8, quirk_clear_strap_no_soft_reset_dev2_f0); +#endif diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 17f09dc26381..82fec66d46d2 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -69,8 +69,7 @@ CFLAGS_sha256.o += $(PURGATORY_CFLAGS) CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_string.o += $(PURGATORY_CFLAGS) -AFLAGS_REMOVE_setup-x86_$(BITS).o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_entry64.o += -Wa,-gdwarf-2 +asflags-remove-y += $(foreach x, -g -gdwarf-4 -gdwarf-5, $(x) -Wa,$(x)) $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) diff --git a/block/blk-mq.c b/block/blk-mq.c index cf1a39adf9a5..f0ea9dcfb966 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1359,8 +1359,6 @@ bool blk_rq_is_poll(struct request *rq) return false; if (rq->mq_hctx->type != HCTX_TYPE_POLL) return false; - if (WARN_ON_ONCE(!rq->bio)) - return false; return true; } EXPORT_SYMBOL_GPL(blk_rq_is_poll); @@ -1368,7 +1366,7 @@ EXPORT_SYMBOL_GPL(blk_rq_is_poll); static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { - bio_poll(rq->bio, NULL, 0); + blk_mq_poll(rq->q, blk_rq_to_qc(rq), NULL, 0); cond_resched(); } while (!completion_done(wait)); } diff --git a/block/genhd.c b/block/genhd.c index 02d9cfb9e077..7f874737af68 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -368,7 +368,6 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) if (disk->open_partitions) return -EBUSY; - set_bit(GD_NEED_PART_SCAN, &disk->state); /* * If the device is opened exclusively by current thread already, it's * safe to scan partitons, otherwise, use bd_prepare_to_claim() to @@ -381,12 +380,19 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) return ret; } + set_bit(GD_NEED_PART_SCAN, &disk->state); bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL); if (IS_ERR(bdev)) ret = PTR_ERR(bdev); else blkdev_put(bdev, mode & ~FMODE_EXCL); + /* + * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set, + * and this will cause that re-assemble partitioned raid device will + * creat partition for underlying disk. + */ + clear_bit(GD_NEED_PART_SCAN, &disk->state); if (!(mode & FMODE_EXCL)) bd_abort_claiming(disk->part0, disk_scan_partitions); return ret; diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 910301fae435..3c6f1e16cf2f 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -461,26 +461,22 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32 job->cmd_buf_vpu_addr = bo->vpu_addr + commands_offset; - ret = drm_gem_lock_reservations((struct drm_gem_object **)job->bos, buf_count, - &acquire_ctx); + ret = drm_gem_lock_reservations((struct drm_gem_object **)job->bos, 1, &acquire_ctx); if (ret) { ivpu_warn(vdev, "Failed to lock reservations: %d\n", ret); return ret; } - for (i = 0; i < buf_count; i++) { - ret = dma_resv_reserve_fences(job->bos[i]->base.resv, 1); - if (ret) { - ivpu_warn(vdev, "Failed to reserve fences: %d\n", ret); - goto unlock_reservations; - } + ret = dma_resv_reserve_fences(bo->base.resv, 1); + if (ret) { + ivpu_warn(vdev, "Failed to reserve fences: %d\n", ret); + goto unlock_reservations; } - for (i = 0; i < buf_count; i++) - dma_resv_add_fence(job->bos[i]->base.resv, job->done_fence, DMA_RESV_USAGE_WRITE); + dma_resv_add_fence(bo->base.resv, job->done_fence, DMA_RESV_USAGE_WRITE); unlock_reservations: - drm_gem_unlock_reservations((struct drm_gem_object **)job->bos, buf_count, &acquire_ctx); + drm_gem_unlock_reservations((struct drm_gem_object **)job->bos, 1, &acquire_ctx); wmb(); /* Flush write combining buffers */ diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 7df72fa8100f..bde42d6383da 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -140,32 +140,28 @@ int ivpu_pm_suspend_cb(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); struct ivpu_device *vdev = to_ivpu_device(drm); - int ret; + unsigned long timeout; ivpu_dbg(vdev, PM, "Suspend..\n"); - ret = ivpu_suspend(vdev); - if (ret && vdev->pm->suspend_reschedule_counter) { - ivpu_dbg(vdev, PM, "Failed to enter idle, rescheduling suspend, retries left %d\n", - vdev->pm->suspend_reschedule_counter); - pm_schedule_suspend(dev, vdev->timeout.reschedule_suspend); - vdev->pm->suspend_reschedule_counter--; - return -EBUSY; - } else if (!vdev->pm->suspend_reschedule_counter) { - ivpu_warn(vdev, "Failed to enter idle, force suspend\n"); - ivpu_pm_prepare_cold_boot(vdev); - } else { - ivpu_pm_prepare_warm_boot(vdev); + timeout = jiffies + msecs_to_jiffies(vdev->timeout.tdr); + while (!ivpu_hw_is_idle(vdev)) { + cond_resched(); + if (time_after_eq(jiffies, timeout)) { + ivpu_err(vdev, "Failed to enter idle on system suspend\n"); + return -EBUSY; + } } - vdev->pm->suspend_reschedule_counter = PM_RESCHEDULE_LIMIT; + ivpu_suspend(vdev); + ivpu_pm_prepare_warm_boot(vdev); pci_save_state(to_pci_dev(dev)); pci_set_power_state(to_pci_dev(dev), PCI_D3hot); ivpu_dbg(vdev, PM, "Suspend done.\n"); - return ret; + return 0; } int ivpu_pm_resume_cb(struct device *dev) diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 97b711e57bff..c7a6d0b69dab 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -1984,6 +1984,7 @@ static int instance; static int acpi_video_bus_add(struct acpi_device *device) { struct acpi_video_bus *video; + bool auto_detect; int error; acpi_status status; @@ -2045,10 +2046,20 @@ static int acpi_video_bus_add(struct acpi_device *device) mutex_unlock(&video_list_lock); /* - * The userspace visible backlight_device gets registered separately - * from acpi_video_register_backlight(). + * If backlight-type auto-detection is used then a native backlight may + * show up later and this may change the result from video to native. + * Therefor normally the userspace visible /sys/class/backlight device + * gets registered separately by the GPU driver calling + * acpi_video_register_backlight() when an internal panel is detected. + * Register the backlight now when not using auto-detection, so that + * when the kernel cmdline or DMI-quirks are used the backlight will + * get registered even if acpi_video_register_backlight() is not called. */ acpi_video_run_bcl_for_osi(video); + if (__acpi_video_get_backlight_type(false, &auto_detect) == acpi_backlight_video && + !auto_detect) + acpi_video_bus_register_backlight(video); + acpi_video_bus_add_notify_handler(video); return 0; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 7b4801ce62d6..e8492b3a393a 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -440,6 +440,13 @@ static const struct dmi_system_id asus_laptop[] = { }, }, { + .ident = "Asus ExpertBook B1502CBA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B1502CBA"), + }, + }, + { .ident = "Asus ExpertBook B2402CBA", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index fd7cbce8076e..e85729fc481f 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -277,6 +277,43 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, /* + * Models which need acpi_video backlight control where the GPU drivers + * do not call acpi_video_register_backlight() because no internal panel + * is detected. Typically these are all-in-ones (monitors with builtin + * PC) where the panel connection shows up as regular DP instead of eDP. + */ + { + .callback = video_detect_force_video, + /* Apple iMac14,1 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac14,1"), + }, + }, + { + .callback = video_detect_force_video, + /* Apple iMac14,2 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac14,2"), + }, + }, + + /* + * Older models with nvidia GPU which need acpi_video backlight + * control and where the old nvidia binary driver series does not + * call acpi_video_register_backlight(). + */ + { + .callback = video_detect_force_video, + /* ThinkPad W530 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W530"), + }, + }, + + /* * These models have a working acpi_video backlight control, and using * native backlight causes a regression where backlight does not work * when userspace is not handling brightness key events. Disable @@ -782,7 +819,7 @@ static bool prefer_native_over_acpi_video(void) * Determine which type of backlight interface to use on this system, * First check cmdline, then dmi quirks, then do autodetect. */ -static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) +enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto_detect) { static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; @@ -807,6 +844,9 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) native_available = true; mutex_unlock(&init_mutex); + if (auto_detect) + *auto_detect = false; + /* * The below heuristics / detection steps are in order of descending * presedence. The commandline takes presedence over anything else. @@ -818,6 +858,9 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) if (acpi_backlight_dmi != acpi_backlight_undef) return acpi_backlight_dmi; + if (auto_detect) + *auto_detect = true; + /* Special cases such as nvidia_wmi_ec and apple gmux. */ if (nvidia_wmi_ec_present) return acpi_backlight_nvidia_wmi_ec; @@ -837,15 +880,4 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) /* No ACPI video/native (old hw), use vendor specific fw methods. */ return acpi_backlight_vendor; } - -enum acpi_backlight_type acpi_video_get_backlight_type(void) -{ - return __acpi_video_get_backlight_type(false); -} -EXPORT_SYMBOL(acpi_video_get_backlight_type); - -bool acpi_video_backlight_use_native(void) -{ - return __acpi_video_get_backlight_type(true) == acpi_backlight_native; -} -EXPORT_SYMBOL(acpi_video_backlight_use_native); +EXPORT_SYMBOL(__acpi_video_get_backlight_type); diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index da5727069d85..ba420a28a4aa 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -213,6 +213,7 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s disk in the system. */ static const struct x86_cpu_id storage_d3_cpu_ids[] = { + X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL), /* Picasso */ X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */ X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */ X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL), /* Cezanne */ diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c73cc57ec547..604c1a13c76e 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -246,7 +246,7 @@ static int ublk_validate_params(const struct ublk_device *ub) if (ub->params.types & UBLK_PARAM_TYPE_BASIC) { const struct ublk_param_basic *p = &ub->params.basic; - if (p->logical_bs_shift > PAGE_SHIFT) + if (p->logical_bs_shift > PAGE_SHIFT || p->logical_bs_shift < 9) return -EINVAL; if (p->logical_bs_shift > p->physical_bs_shift) @@ -1261,9 +1261,10 @@ static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, ublk_queue_cmd(ubq, req); } -static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, + unsigned int issue_flags, + struct ublksrv_io_cmd *ub_cmd) { - struct ublksrv_io_cmd *ub_cmd = (struct ublksrv_io_cmd *)cmd->cmd; struct ublk_device *ub = cmd->file->private_data; struct ublk_queue *ubq; struct ublk_io *io; @@ -1362,6 +1363,23 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return -EIOCBQUEUED; } +static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct ublksrv_io_cmd *ub_src = (struct ublksrv_io_cmd *) cmd->cmd; + struct ublksrv_io_cmd ub_cmd; + + /* + * Not necessary for async retry, but let's keep it simple and always + * copy the values to avoid any potential reuse. + */ + ub_cmd.q_id = READ_ONCE(ub_src->q_id); + ub_cmd.tag = READ_ONCE(ub_src->tag); + ub_cmd.result = READ_ONCE(ub_src->result); + ub_cmd.addr = READ_ONCE(ub_src->addr); + + return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd); +} + static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, @@ -1952,6 +1970,8 @@ static int ublk_ctrl_set_params(struct ublk_device *ub, /* clear all we don't support yet */ ub->params.types &= UBLK_PARAM_TYPE_ALL; ret = ublk_validate_params(ub); + if (ret) + ub->params.types = 0; } mutex_unlock(&ub->mutex); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2723eede6f21..2b918e28acaa 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -96,16 +96,14 @@ struct virtblk_req { /* * The zone append command has an extended in header. - * The status field in zone_append_in_hdr must have - * the same offset in virtblk_req as the non-zoned - * status field above. + * The status field in zone_append_in_hdr must always + * be the last byte. */ struct { + __virtio64 sector; u8 status; - u8 reserved[7]; - __le64 append_sector; - } zone_append_in_hdr; - }; + } zone_append; + } in_hdr; size_t in_hdr_len; @@ -154,7 +152,7 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr) sgs[num_out + num_in++] = vbr->sg_table.sgl; } - sg_init_one(&in_hdr, &vbr->status, vbr->in_hdr_len); + sg_init_one(&in_hdr, &vbr->in_hdr.status, vbr->in_hdr_len); sgs[num_out + num_in++] = &in_hdr; return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC); @@ -242,11 +240,14 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, struct request *req, struct virtblk_req *vbr) { - size_t in_hdr_len = sizeof(vbr->status); + size_t in_hdr_len = sizeof(vbr->in_hdr.status); bool unmap = false; u32 type; u64 sector = 0; + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) && op_is_zone_mgmt(req_op(req))) + return BLK_STS_NOTSUPP; + /* Set fields for all request types */ vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req)); @@ -287,7 +288,7 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, case REQ_OP_ZONE_APPEND: type = VIRTIO_BLK_T_ZONE_APPEND; sector = blk_rq_pos(req); - in_hdr_len = sizeof(vbr->zone_append_in_hdr); + in_hdr_len = sizeof(vbr->in_hdr.zone_append); break; case REQ_OP_ZONE_RESET: type = VIRTIO_BLK_T_ZONE_RESET; @@ -297,7 +298,10 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, type = VIRTIO_BLK_T_ZONE_RESET_ALL; break; case REQ_OP_DRV_IN: - /* Out header already filled in, nothing to do */ + /* + * Out header has already been prepared by the caller (virtblk_get_id() + * or virtblk_submit_zone_report()), nothing to do here. + */ return 0; default: WARN_ON_ONCE(1); @@ -318,16 +322,28 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, return 0; } +/* + * The status byte is always the last byte of the virtblk request + * in-header. This helper fetches its value for all in-header formats + * that are currently defined. + */ +static inline u8 virtblk_vbr_status(struct virtblk_req *vbr) +{ + return *((u8 *)&vbr->in_hdr + vbr->in_hdr_len - 1); +} + static inline void virtblk_request_done(struct request *req) { struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); - blk_status_t status = virtblk_result(vbr->status); + blk_status_t status = virtblk_result(virtblk_vbr_status(vbr)); + struct virtio_blk *vblk = req->mq_hctx->queue->queuedata; virtblk_unmap_data(req, vbr); virtblk_cleanup_cmd(req); if (req_op(req) == REQ_OP_ZONE_APPEND) - req->__sector = le64_to_cpu(vbr->zone_append_in_hdr.append_sector); + req->__sector = virtio64_to_cpu(vblk->vdev, + vbr->in_hdr.zone_append.sector); blk_mq_end_request(req, status); } @@ -355,7 +371,7 @@ static int virtblk_handle_req(struct virtio_blk_vq *vq, if (likely(!blk_should_fake_timeout(req->q)) && !blk_mq_complete_request_remote(req) && - !blk_mq_add_to_batch(req, iob, vbr->status, + !blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr), virtblk_complete_batch)) virtblk_request_done(req); req_done++; @@ -550,7 +566,6 @@ static void virtio_queue_rqs(struct request **rqlist) #ifdef CONFIG_BLK_DEV_ZONED static void *virtblk_alloc_report_buffer(struct virtio_blk *vblk, unsigned int nr_zones, - unsigned int zone_sectors, size_t *buflen) { struct request_queue *q = vblk->disk->queue; @@ -558,7 +573,7 @@ static void *virtblk_alloc_report_buffer(struct virtio_blk *vblk, void *buf; nr_zones = min_t(unsigned int, nr_zones, - get_capacity(vblk->disk) >> ilog2(zone_sectors)); + get_capacity(vblk->disk) >> ilog2(vblk->zone_sectors)); bufsize = sizeof(struct virtio_blk_zone_report) + nr_zones * sizeof(struct virtio_blk_zone_descriptor); @@ -592,7 +607,7 @@ static int virtblk_submit_zone_report(struct virtio_blk *vblk, return PTR_ERR(req); vbr = blk_mq_rq_to_pdu(req); - vbr->in_hdr_len = sizeof(vbr->status); + vbr->in_hdr_len = sizeof(vbr->in_hdr.status); vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_ZONE_REPORT); vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, sector); @@ -601,7 +616,7 @@ static int virtblk_submit_zone_report(struct virtio_blk *vblk, goto out; blk_execute_rq(req, false); - err = blk_status_to_errno(virtblk_result(vbr->status)); + err = blk_status_to_errno(virtblk_result(vbr->in_hdr.status)); out: blk_mq_free_request(req); return err; @@ -609,29 +624,72 @@ out: static int virtblk_parse_zone(struct virtio_blk *vblk, struct virtio_blk_zone_descriptor *entry, - unsigned int idx, unsigned int zone_sectors, - report_zones_cb cb, void *data) + unsigned int idx, report_zones_cb cb, void *data) { struct blk_zone zone = { }; - if (entry->z_type != VIRTIO_BLK_ZT_SWR && - entry->z_type != VIRTIO_BLK_ZT_SWP && - entry->z_type != VIRTIO_BLK_ZT_CONV) { - dev_err(&vblk->vdev->dev, "invalid zone type %#x\n", - entry->z_type); - return -EINVAL; + zone.start = virtio64_to_cpu(vblk->vdev, entry->z_start); + if (zone.start + vblk->zone_sectors <= get_capacity(vblk->disk)) + zone.len = vblk->zone_sectors; + else + zone.len = get_capacity(vblk->disk) - zone.start; + zone.capacity = virtio64_to_cpu(vblk->vdev, entry->z_cap); + zone.wp = virtio64_to_cpu(vblk->vdev, entry->z_wp); + + switch (entry->z_type) { + case VIRTIO_BLK_ZT_SWR: + zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ; + break; + case VIRTIO_BLK_ZT_SWP: + zone.type = BLK_ZONE_TYPE_SEQWRITE_PREF; + break; + case VIRTIO_BLK_ZT_CONV: + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + break; + default: + dev_err(&vblk->vdev->dev, "zone %llu: invalid type %#x\n", + zone.start, entry->z_type); + return -EIO; } - zone.type = entry->z_type; - zone.cond = entry->z_state; - zone.len = zone_sectors; - zone.capacity = le64_to_cpu(entry->z_cap); - zone.start = le64_to_cpu(entry->z_start); - if (zone.cond == BLK_ZONE_COND_FULL) + switch (entry->z_state) { + case VIRTIO_BLK_ZS_EMPTY: + zone.cond = BLK_ZONE_COND_EMPTY; + break; + case VIRTIO_BLK_ZS_CLOSED: + zone.cond = BLK_ZONE_COND_CLOSED; + break; + case VIRTIO_BLK_ZS_FULL: + zone.cond = BLK_ZONE_COND_FULL; zone.wp = zone.start + zone.len; - else - zone.wp = le64_to_cpu(entry->z_wp); + break; + case VIRTIO_BLK_ZS_EOPEN: + zone.cond = BLK_ZONE_COND_EXP_OPEN; + break; + case VIRTIO_BLK_ZS_IOPEN: + zone.cond = BLK_ZONE_COND_IMP_OPEN; + break; + case VIRTIO_BLK_ZS_NOT_WP: + zone.cond = BLK_ZONE_COND_NOT_WP; + break; + case VIRTIO_BLK_ZS_RDONLY: + zone.cond = BLK_ZONE_COND_READONLY; + zone.wp = ULONG_MAX; + break; + case VIRTIO_BLK_ZS_OFFLINE: + zone.cond = BLK_ZONE_COND_OFFLINE; + zone.wp = ULONG_MAX; + break; + default: + dev_err(&vblk->vdev->dev, "zone %llu: invalid condition %#x\n", + zone.start, entry->z_state); + return -EIO; + } + /* + * The callback below checks the validity of the reported + * entry data, no need to further validate it here. + */ return cb(&zone, idx, data); } @@ -641,39 +699,47 @@ static int virtblk_report_zones(struct gendisk *disk, sector_t sector, { struct virtio_blk *vblk = disk->private_data; struct virtio_blk_zone_report *report; - unsigned int zone_sectors = vblk->zone_sectors; - unsigned int nz, i; - int ret, zone_idx = 0; + unsigned long long nz, i; size_t buflen; + unsigned int zone_idx = 0; + int ret; if (WARN_ON_ONCE(!vblk->zone_sectors)) return -EOPNOTSUPP; - report = virtblk_alloc_report_buffer(vblk, nr_zones, - zone_sectors, &buflen); + report = virtblk_alloc_report_buffer(vblk, nr_zones, &buflen); if (!report) return -ENOMEM; + mutex_lock(&vblk->vdev_mutex); + + if (!vblk->vdev) { + ret = -ENXIO; + goto fail_report; + } + while (zone_idx < nr_zones && sector < get_capacity(vblk->disk)) { memset(report, 0, buflen); ret = virtblk_submit_zone_report(vblk, (char *)report, buflen, sector); - if (ret) { - if (ret > 0) - ret = -EIO; - goto out_free; - } - nz = min((unsigned int)le64_to_cpu(report->nr_zones), nr_zones); + if (ret) + goto fail_report; + + nz = min_t(u64, virtio64_to_cpu(vblk->vdev, report->nr_zones), + nr_zones); if (!nz) break; for (i = 0; i < nz && zone_idx < nr_zones; i++) { ret = virtblk_parse_zone(vblk, &report->zones[i], - zone_idx, zone_sectors, cb, data); + zone_idx, cb, data); if (ret) - goto out_free; - sector = le64_to_cpu(report->zones[i].z_start) + zone_sectors; + goto fail_report; + + sector = virtio64_to_cpu(vblk->vdev, + report->zones[i].z_start) + + vblk->zone_sectors; zone_idx++; } } @@ -682,7 +748,8 @@ static int virtblk_report_zones(struct gendisk *disk, sector_t sector, ret = zone_idx; else ret = -EINVAL; -out_free: +fail_report: + mutex_unlock(&vblk->vdev_mutex); kvfree(report); return ret; } @@ -691,20 +758,28 @@ static void virtblk_revalidate_zones(struct virtio_blk *vblk) { u8 model; - if (!vblk->zone_sectors) - return; - virtio_cread(vblk->vdev, struct virtio_blk_config, zoned.model, &model); - if (!blk_revalidate_disk_zones(vblk->disk, NULL)) - set_capacity_and_notify(vblk->disk, 0); + switch (model) { + default: + dev_err(&vblk->vdev->dev, "unknown zone model %d\n", model); + fallthrough; + case VIRTIO_BLK_Z_NONE: + case VIRTIO_BLK_Z_HA: + disk_set_zoned(vblk->disk, BLK_ZONED_NONE); + return; + case VIRTIO_BLK_Z_HM: + WARN_ON_ONCE(!vblk->zone_sectors); + if (!blk_revalidate_disk_zones(vblk->disk, NULL)) + set_capacity_and_notify(vblk->disk, 0); + } } static int virtblk_probe_zoned_device(struct virtio_device *vdev, struct virtio_blk *vblk, struct request_queue *q) { - u32 v; + u32 v, wg; u8 model; int ret; @@ -713,16 +788,11 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, switch (model) { case VIRTIO_BLK_Z_NONE: + case VIRTIO_BLK_Z_HA: + /* Present the host-aware device as non-zoned */ return 0; case VIRTIO_BLK_Z_HM: break; - case VIRTIO_BLK_Z_HA: - /* - * Present the host-aware device as a regular drive. - * TODO It is possible to add an option to make it appear - * in the system as a zoned drive. - */ - return 0; default: dev_err(&vdev->dev, "unsupported zone model %d\n", model); return -EINVAL; @@ -735,32 +805,31 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, virtio_cread(vdev, struct virtio_blk_config, zoned.max_open_zones, &v); - disk_set_max_open_zones(vblk->disk, le32_to_cpu(v)); - - dev_dbg(&vdev->dev, "max open zones = %u\n", le32_to_cpu(v)); + disk_set_max_open_zones(vblk->disk, v); + dev_dbg(&vdev->dev, "max open zones = %u\n", v); virtio_cread(vdev, struct virtio_blk_config, zoned.max_active_zones, &v); - disk_set_max_active_zones(vblk->disk, le32_to_cpu(v)); - dev_dbg(&vdev->dev, "max active zones = %u\n", le32_to_cpu(v)); + disk_set_max_active_zones(vblk->disk, v); + dev_dbg(&vdev->dev, "max active zones = %u\n", v); virtio_cread(vdev, struct virtio_blk_config, - zoned.write_granularity, &v); - if (!v) { + zoned.write_granularity, &wg); + if (!wg) { dev_warn(&vdev->dev, "zero write granularity reported\n"); return -ENODEV; } - blk_queue_physical_block_size(q, le32_to_cpu(v)); - blk_queue_io_min(q, le32_to_cpu(v)); + blk_queue_physical_block_size(q, wg); + blk_queue_io_min(q, wg); - dev_dbg(&vdev->dev, "write granularity = %u\n", le32_to_cpu(v)); + dev_dbg(&vdev->dev, "write granularity = %u\n", wg); /* * virtio ZBD specification doesn't require zones to be a power of * two sectors in size, but the code in this driver expects that. */ - virtio_cread(vdev, struct virtio_blk_config, zoned.zone_sectors, &v); - vblk->zone_sectors = le32_to_cpu(v); + virtio_cread(vdev, struct virtio_blk_config, zoned.zone_sectors, + &vblk->zone_sectors); if (vblk->zone_sectors == 0 || !is_power_of_2(vblk->zone_sectors)) { dev_err(&vdev->dev, "zoned device with non power of two zone size %u\n", @@ -783,36 +852,46 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, dev_warn(&vdev->dev, "zero max_append_sectors reported\n"); return -ENODEV; } - blk_queue_max_zone_append_sectors(q, le32_to_cpu(v)); - dev_dbg(&vdev->dev, "max append sectors = %u\n", le32_to_cpu(v)); + if ((v << SECTOR_SHIFT) < wg) { + dev_err(&vdev->dev, + "write granularity %u exceeds max_append_sectors %u limit\n", + wg, v); + return -ENODEV; + } + + blk_queue_max_zone_append_sectors(q, v); + dev_dbg(&vdev->dev, "max append sectors = %u\n", v); } return ret; } -static inline bool virtblk_has_zoned_feature(struct virtio_device *vdev) -{ - return virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED); -} #else /* * Zoned block device support is not configured in this kernel. - * We only need to define a few symbols to avoid compilation errors. + * Host-managed zoned devices can't be supported, but others are + * good to go as regular block devices. */ #define virtblk_report_zones NULL + static inline void virtblk_revalidate_zones(struct virtio_blk *vblk) { } + static inline int virtblk_probe_zoned_device(struct virtio_device *vdev, struct virtio_blk *vblk, struct request_queue *q) { - return -EOPNOTSUPP; -} + u8 model; -static inline bool virtblk_has_zoned_feature(struct virtio_device *vdev) -{ - return false; + virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model); + if (model == VIRTIO_BLK_Z_HM) { + dev_err(&vdev->dev, + "virtio_blk: zoned devices are not supported"); + return -EOPNOTSUPP; + } + + return 0; } #endif /* CONFIG_BLK_DEV_ZONED */ @@ -831,7 +910,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) return PTR_ERR(req); vbr = blk_mq_rq_to_pdu(req); - vbr->in_hdr_len = sizeof(vbr->status); + vbr->in_hdr_len = sizeof(vbr->in_hdr.status); vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID); vbr->out_hdr.sector = 0; @@ -840,7 +919,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) goto out; blk_execute_rq(req, false); - err = blk_status_to_errno(virtblk_result(vbr->status)); + err = blk_status_to_errno(virtblk_result(vbr->in_hdr.status)); out: blk_mq_free_request(req); return err; @@ -1498,15 +1577,16 @@ static int virtblk_probe(struct virtio_device *vdev) virtblk_update_capacity(vblk, false); virtio_device_ready(vdev); - if (virtblk_has_zoned_feature(vdev)) { + /* + * All steps that follow use the VQs therefore they need to be + * placed after the virtio_device_ready() call above. + */ + if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) { err = virtblk_probe_zoned_device(vdev, vblk, q); if (err) goto out_cleanup_disk; } - dev_info(&vdev->dev, "blk config size: %zu\n", - sizeof(struct virtio_blk_config)); - err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups); if (err) goto out_cleanup_disk; @@ -1607,10 +1687,7 @@ static unsigned int features[] = { VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, - VIRTIO_BLK_F_SECURE_ERASE, -#ifdef CONFIG_BLK_DEV_ZONED - VIRTIO_BLK_F_ZONED, -#endif /* CONFIG_BLK_DEV_ZONED */ + VIRTIO_BLK_F_SECURE_ERASE, VIRTIO_BLK_F_ZONED, }; static struct virtio_driver virtio_blk = { diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 3006e2a0f37e..43e98a598bd9 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -511,7 +511,7 @@ static const char *btbcm_get_board_name(struct device *dev) len = strlen(tmp) + 1; board_type = devm_kzalloc(dev, len, GFP_KERNEL); strscpy(board_type, tmp, len); - for (i = 0; i < board_type[i]; i++) { + for (i = 0; i < len; i++) { if (board_type[i] == '/') board_type[i] = '-'; } diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 02893600db39..51000320e1ea 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -358,6 +358,7 @@ static void btsdio_remove(struct sdio_func *func) if (!data) return; + cancel_work_sync(&data->work); hdev = data->hdev; sdio_set_drvdata(func, NULL); diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 36d42484142a..cf463c1d2102 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -329,6 +329,12 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, "Failed to setup timing for '%pOF'\n", rd->dn); if (!of_node_check_flag(rd->dn, OF_POPULATED)) { + /* + * Clear the flag before adding the device so that + * fw_devlink doesn't skip adding consumers to this + * device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; if (!of_platform_device_create(rd->dn, NULL, &pdev->dev)) { dev_err(&pdev->dev, "Failed to create child device '%pOF'\n", diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index f91f30560820..ff3a52d48479 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -143,8 +143,9 @@ static int rs9_regmap_i2c_read(void *context, static const struct regmap_config rs9_regmap_config = { .reg_bits = 8, .val_bits = 8, - .cache_type = REGCACHE_NONE, + .cache_type = REGCACHE_FLAT, .max_register = RS9_REG_BCP, + .num_reg_defaults_raw = 0x8, .rd_table = &rs9_readable_table, .wr_table = &rs9_writeable_table, .reg_write = rs9_regmap_i2c_write, diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c index 2836adb817b7..e3696a88b5a3 100644 --- a/drivers/clk/imx/clk-imx6ul.c +++ b/drivers/clk/imx/clk-imx6ul.c @@ -95,14 +95,16 @@ static const struct clk_div_table video_div_table[] = { { } }; -static const char * enet1_ref_sels[] = { "enet1_ref_125m", "enet1_ref_pad", }; +static const char * enet1_ref_sels[] = { "enet1_ref_125m", "enet1_ref_pad", "dummy", "dummy"}; static const u32 enet1_ref_sels_table[] = { IMX6UL_GPR1_ENET1_TX_CLK_DIR, - IMX6UL_GPR1_ENET1_CLK_SEL }; + IMX6UL_GPR1_ENET1_CLK_SEL, 0, + IMX6UL_GPR1_ENET1_TX_CLK_DIR | IMX6UL_GPR1_ENET1_CLK_SEL }; static const u32 enet1_ref_sels_table_mask = IMX6UL_GPR1_ENET1_TX_CLK_DIR | IMX6UL_GPR1_ENET1_CLK_SEL; -static const char * enet2_ref_sels[] = { "enet2_ref_125m", "enet2_ref_pad", }; +static const char * enet2_ref_sels[] = { "enet2_ref_125m", "enet2_ref_pad", "dummy", "dummy"}; static const u32 enet2_ref_sels_table[] = { IMX6UL_GPR1_ENET2_TX_CLK_DIR, - IMX6UL_GPR1_ENET2_CLK_SEL }; + IMX6UL_GPR1_ENET2_CLK_SEL, 0, + IMX6UL_GPR1_ENET2_TX_CLK_DIR | IMX6UL_GPR1_ENET2_CLK_SEL }; static const u32 enet2_ref_sels_table_mask = IMX6UL_GPR1_ENET2_TX_CLK_DIR | IMX6UL_GPR1_ENET2_CLK_SEL; diff --git a/drivers/clk/sprd/common.c b/drivers/clk/sprd/common.c index ce81e4087a8f..2bfbab8db94b 100644 --- a/drivers/clk/sprd/common.c +++ b/drivers/clk/sprd/common.c @@ -17,7 +17,6 @@ static const struct regmap_config sprdclk_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0xffff, .fast_io = true, }; @@ -43,6 +42,8 @@ int sprd_clk_regmap_init(struct platform_device *pdev, struct device *dev = &pdev->dev; struct device_node *node = dev->of_node, *np; struct regmap *regmap; + struct resource *res; + struct regmap_config reg_config = sprdclk_regmap_config; if (of_find_property(node, "sprd,syscon", NULL)) { regmap = syscon_regmap_lookup_by_phandle(node, "sprd,syscon"); @@ -59,12 +60,14 @@ int sprd_clk_regmap_init(struct platform_device *pdev, return PTR_ERR(regmap); } } else { - base = devm_platform_ioremap_resource(pdev, 0); + base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(base)) return PTR_ERR(base); + reg_config.max_register = resource_size(res) - reg_config.reg_stride; + regmap = devm_regmap_init_mmio(&pdev->dev, base, - &sprdclk_regmap_config); + ®_config); if (IS_ERR(regmap)) { pr_err("failed to init regmap\n"); return PTR_ERR(regmap); diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index deed4afadb29..d9cb937665cf 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -97,10 +97,6 @@ struct quad8 { struct quad8_reg __iomem *reg; }; -/* Borrow Toggle flip-flop */ -#define QUAD8_FLAG_BT BIT(0) -/* Carry Toggle flip-flop */ -#define QUAD8_FLAG_CT BIT(1) /* Error flag */ #define QUAD8_FLAG_E BIT(4) /* Up/Down flag */ @@ -133,6 +129,9 @@ struct quad8 { #define QUAD8_CMR_QUADRATURE_X2 0x10 #define QUAD8_CMR_QUADRATURE_X4 0x18 +/* Each Counter is 24 bits wide */ +#define LS7267_CNTR_MAX GENMASK(23, 0) + static int quad8_signal_read(struct counter_device *counter, struct counter_signal *signal, enum counter_signal_level *level) @@ -156,18 +155,10 @@ static int quad8_count_read(struct counter_device *counter, { struct quad8 *const priv = counter_priv(counter); struct channel_reg __iomem *const chan = priv->reg->channel + count->id; - unsigned int flags; - unsigned int borrow; - unsigned int carry; unsigned long irqflags; int i; - flags = ioread8(&chan->control); - borrow = flags & QUAD8_FLAG_BT; - carry = !!(flags & QUAD8_FLAG_CT); - - /* Borrow XOR Carry effectively doubles count range */ - *val = (unsigned long)(borrow ^ carry) << 24; + *val = 0; spin_lock_irqsave(&priv->lock, irqflags); @@ -191,8 +182,7 @@ static int quad8_count_write(struct counter_device *counter, unsigned long irqflags; int i; - /* Only 24-bit values are supported */ - if (val > 0xFFFFFF) + if (val > LS7267_CNTR_MAX) return -ERANGE; spin_lock_irqsave(&priv->lock, irqflags); @@ -378,7 +368,7 @@ static int quad8_action_read(struct counter_device *counter, /* Handle Index signals */ if (synapse->signal->id >= 16) { - if (priv->preset_enable[count->id]) + if (!priv->preset_enable[count->id]) *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; else *action = COUNTER_SYNAPSE_ACTION_NONE; @@ -806,8 +796,7 @@ static int quad8_count_preset_write(struct counter_device *counter, struct quad8 *const priv = counter_priv(counter); unsigned long irqflags; - /* Only 24-bit values are supported */ - if (preset > 0xFFFFFF) + if (preset > LS7267_CNTR_MAX) return -ERANGE; spin_lock_irqsave(&priv->lock, irqflags); @@ -834,8 +823,7 @@ static int quad8_count_ceiling_read(struct counter_device *counter, *ceiling = priv->preset[count->id]; break; default: - /* By default 0x1FFFFFF (25 bits unsigned) is maximum count */ - *ceiling = 0x1FFFFFF; + *ceiling = LS7267_CNTR_MAX; break; } @@ -850,8 +838,7 @@ static int quad8_count_ceiling_write(struct counter_device *counter, struct quad8 *const priv = counter_priv(counter); unsigned long irqflags; - /* Only 24-bit values are supported */ - if (ceiling > 0xFFFFFF) + if (ceiling > LS7267_CNTR_MAX) return -ERANGE; spin_lock_irqsave(&priv->lock, irqflags); diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 73c7643b2697..8dd46fad151e 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -840,22 +840,20 @@ static int amd_pstate_update_status(const char *buf, size_t size) switch(mode_idx) { case AMD_PSTATE_DISABLE: - if (!current_pstate_driver) - return -EINVAL; - if (cppc_state == AMD_PSTATE_ACTIVE) - return -EBUSY; - cpufreq_unregister_driver(current_pstate_driver); - amd_pstate_driver_cleanup(); + if (current_pstate_driver) { + cpufreq_unregister_driver(current_pstate_driver); + amd_pstate_driver_cleanup(); + } break; case AMD_PSTATE_PASSIVE: if (current_pstate_driver) { if (current_pstate_driver == &amd_pstate_driver) return 0; cpufreq_unregister_driver(current_pstate_driver); - cppc_state = AMD_PSTATE_PASSIVE; - current_pstate_driver = &amd_pstate_driver; } + current_pstate_driver = &amd_pstate_driver; + cppc_state = AMD_PSTATE_PASSIVE; ret = cpufreq_register_driver(current_pstate_driver); break; case AMD_PSTATE_ACTIVE: @@ -863,10 +861,10 @@ static int amd_pstate_update_status(const char *buf, size_t size) if (current_pstate_driver == &amd_pstate_epp_driver) return 0; cpufreq_unregister_driver(current_pstate_driver); - current_pstate_driver = &amd_pstate_epp_driver; - cppc_state = AMD_PSTATE_ACTIVE; } + current_pstate_driver = &amd_pstate_epp_driver; + cppc_state = AMD_PSTATE_ACTIVE; ret = cpufreq_register_driver(current_pstate_driver); break; default: diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 45deda18ed32..02cc2c38b44b 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -101,25 +101,40 @@ static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb, BIT(CXL_CM_CAP_CAP_ID_HDM)); } -static struct cxl_hdm *devm_cxl_setup_emulated_hdm(struct cxl_port *port, - struct cxl_endpoint_dvsec_info *info) +static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info) { - struct device *dev = &port->dev; struct cxl_hdm *cxlhdm; + void __iomem *hdm; + u32 ctrl; + int i; - if (!info->mem_enabled) - return ERR_PTR(-ENODEV); + if (!info) + return false; - cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL); - if (!cxlhdm) - return ERR_PTR(-ENOMEM); + cxlhdm = dev_get_drvdata(&info->port->dev); + hdm = cxlhdm->regs.hdm_decoder; - cxlhdm->port = port; - cxlhdm->decoder_count = info->ranges; - cxlhdm->target_count = info->ranges; - dev_set_drvdata(&port->dev, cxlhdm); + if (!hdm) + return true; - return cxlhdm; + /* + * If HDM decoders are present and the driver is in control of + * Mem_Enable skip DVSEC based emulation + */ + if (!info->mem_enabled) + return false; + + /* + * If any decoders are committed already, there should not be any + * emulated DVSEC decoders. + */ + for (i = 0; i < cxlhdm->decoder_count; i++) { + ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i)); + if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl)) + return false; + } + + return true; } /** @@ -138,13 +153,14 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL); if (!cxlhdm) return ERR_PTR(-ENOMEM); - cxlhdm->port = port; - crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE); - if (!crb) { - if (info && info->mem_enabled) - return devm_cxl_setup_emulated_hdm(port, info); + dev_set_drvdata(dev, cxlhdm); + crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE); + if (!crb && info && info->mem_enabled) { + cxlhdm->decoder_count = info->ranges; + return cxlhdm; + } else if (!crb) { dev_err(dev, "No component registers mapped\n"); return ERR_PTR(-ENXIO); } @@ -160,7 +176,15 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, return ERR_PTR(-ENXIO); } - dev_set_drvdata(dev, cxlhdm); + /* + * Now that the hdm capability is parsed, decide if range + * register emulation is needed and fixup cxlhdm accordingly. + */ + if (should_emulate_decoders(info)) { + dev_dbg(dev, "Fallback map %d range register%s\n", info->ranges, + info->ranges > 1 ? "s" : ""); + cxlhdm->decoder_count = info->ranges; + } return cxlhdm; } @@ -714,14 +738,20 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) return 0; } -static int cxl_setup_hdm_decoder_from_dvsec(struct cxl_port *port, - struct cxl_decoder *cxld, int which, - struct cxl_endpoint_dvsec_info *info) +static int cxl_setup_hdm_decoder_from_dvsec( + struct cxl_port *port, struct cxl_decoder *cxld, u64 *dpa_base, + int which, struct cxl_endpoint_dvsec_info *info) { + struct cxl_endpoint_decoder *cxled; + u64 len; + int rc; + if (!is_cxl_endpoint(port)) return -EOPNOTSUPP; - if (!range_len(&info->dvsec_range[which])) + cxled = to_cxl_endpoint_decoder(&cxld->dev); + len = range_len(&info->dvsec_range[which]); + if (!len) return -ENOENT; cxld->target_type = CXL_DECODER_EXPANDER; @@ -736,40 +766,24 @@ static int cxl_setup_hdm_decoder_from_dvsec(struct cxl_port *port, cxld->flags |= CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK; port->commit_end = cxld->id; - return 0; -} - -static bool should_emulate_decoders(struct cxl_port *port) -{ - struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); - void __iomem *hdm = cxlhdm->regs.hdm_decoder; - u32 ctrl; - int i; - - if (!is_cxl_endpoint(cxlhdm->port)) - return false; - - if (!hdm) - return true; - - /* - * If any decoders are committed already, there should not be any - * emulated DVSEC decoders. - */ - for (i = 0; i < cxlhdm->decoder_count; i++) { - ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i)); - if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl)) - return false; + rc = devm_cxl_dpa_reserve(cxled, *dpa_base, len, 0); + if (rc) { + dev_err(&port->dev, + "decoder%d.%d: Failed to reserve DPA range %#llx - %#llx\n (%d)", + port->id, cxld->id, *dpa_base, *dpa_base + len - 1, rc); + return rc; } + *dpa_base += len; + cxled->state = CXL_DECODER_STATE_AUTO; - return true; + return 0; } static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, int *target_map, void __iomem *hdm, int which, u64 *dpa_base, struct cxl_endpoint_dvsec_info *info) { - struct cxl_endpoint_decoder *cxled = NULL; + struct cxl_endpoint_decoder *cxled; u64 size, base, skip, dpa_size; bool committed; u32 remainder; @@ -780,11 +794,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, unsigned char target_id[8]; } target_list; - if (should_emulate_decoders(port)) - return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info); - - if (is_endpoint_decoder(&cxld->dev)) - cxled = to_cxl_endpoint_decoder(&cxld->dev); + if (should_emulate_decoders(info)) + return cxl_setup_hdm_decoder_from_dvsec(port, cxld, dpa_base, + which, info); ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(which)); base = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(which)); @@ -806,9 +818,6 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, .end = base + size - 1, }; - if (cxled && !committed && range_len(&info->dvsec_range[which])) - return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info); - /* decoders are enabled if committed */ if (committed) { cxld->flags |= CXL_DECODER_F_ENABLE; @@ -846,7 +855,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, if (rc) return rc; - if (!cxled) { + if (!info) { target_list.value = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_TL_LOW(which)); for (i = 0; i < cxld->interleave_ways; i++) @@ -866,6 +875,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, return -ENXIO; } skip = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SKIP_LOW(which)); + cxled = to_cxl_endpoint_decoder(&cxld->dev); rc = devm_cxl_dpa_reserve(cxled, *dpa_base + skip, dpa_size, skip); if (rc) { dev_err(&port->dev, diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 7328a2552411..523d5b9fd7fc 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -462,7 +462,7 @@ static struct pci_doe_mb *find_cdat_doe(struct device *uport) return NULL; } -#define CDAT_DOE_REQ(entry_handle) \ +#define CDAT_DOE_REQ(entry_handle) cpu_to_le32 \ (FIELD_PREP(CXL_DOE_TABLE_ACCESS_REQ_CODE, \ CXL_DOE_TABLE_ACCESS_REQ_CODE_READ) | \ FIELD_PREP(CXL_DOE_TABLE_ACCESS_TABLE_TYPE, \ @@ -475,8 +475,8 @@ static void cxl_doe_task_complete(struct pci_doe_task *task) } struct cdat_doe_task { - u32 request_pl; - u32 response_pl[32]; + __le32 request_pl; + __le32 response_pl[32]; struct completion c; struct pci_doe_task task; }; @@ -510,10 +510,10 @@ static int cxl_cdat_get_length(struct device *dev, return rc; } wait_for_completion(&t.c); - if (t.task.rv < sizeof(u32)) + if (t.task.rv < 2 * sizeof(__le32)) return -EIO; - *length = t.response_pl[1]; + *length = le32_to_cpu(t.response_pl[1]); dev_dbg(dev, "CDAT length %zu\n", *length); return 0; @@ -524,13 +524,13 @@ static int cxl_cdat_read_table(struct device *dev, struct cxl_cdat *cdat) { size_t length = cdat->length; - u32 *data = cdat->table; + __le32 *data = cdat->table; int entry_handle = 0; do { DECLARE_CDAT_DOE_TASK(CDAT_DOE_REQ(entry_handle), t); + struct cdat_entry_header *entry; size_t entry_dw; - u32 *entry; int rc; rc = pci_doe_submit_task(cdat_doe, &t.task); @@ -539,26 +539,34 @@ static int cxl_cdat_read_table(struct device *dev, return rc; } wait_for_completion(&t.c); - /* 1 DW header + 1 DW data min */ - if (t.task.rv < (2 * sizeof(u32))) + + /* 1 DW Table Access Response Header + CDAT entry */ + entry = (struct cdat_entry_header *)(t.response_pl + 1); + if ((entry_handle == 0 && + t.task.rv != sizeof(__le32) + sizeof(struct cdat_header)) || + (entry_handle > 0 && + (t.task.rv < sizeof(__le32) + sizeof(*entry) || + t.task.rv != sizeof(__le32) + le16_to_cpu(entry->length)))) return -EIO; /* Get the CXL table access header entry handle */ entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, - t.response_pl[0]); - entry = t.response_pl + 1; - entry_dw = t.task.rv / sizeof(u32); + le32_to_cpu(t.response_pl[0])); + entry_dw = t.task.rv / sizeof(__le32); /* Skip Header */ entry_dw -= 1; - entry_dw = min(length / sizeof(u32), entry_dw); + entry_dw = min(length / sizeof(__le32), entry_dw); /* Prevent length < 1 DW from causing a buffer overflow */ if (entry_dw) { - memcpy(data, entry, entry_dw * sizeof(u32)); - length -= entry_dw * sizeof(u32); + memcpy(data, entry, entry_dw * sizeof(__le32)); + length -= entry_dw * sizeof(__le32); data += entry_dw; } } while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY); + /* Length in CDAT header may exceed concatenation of CDAT entries */ + cdat->length -= length; + return 0; } diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index c2e4b1093788..f8c38d997252 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -62,9 +62,9 @@ static int match_nvdimm_bridge(struct device *dev, void *data) return is_cxl_nvdimm_bridge(dev); } -struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct device *start) +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd) { - struct cxl_port *port = find_cxl_root(start); + struct cxl_port *port = find_cxl_root(dev_get_drvdata(&cxlmd->dev)); struct device *dev; if (!port) @@ -253,7 +253,7 @@ int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd) struct device *dev; int rc; - cxl_nvb = cxl_find_nvdimm_bridge(&cxlmd->dev); + cxl_nvb = cxl_find_nvdimm_bridge(cxlmd); if (!cxl_nvb) return -ENODEV; diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 8ee6b6e2e2a4..4d1f9c5b5029 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -823,41 +823,17 @@ static bool dev_is_cxl_root_child(struct device *dev) return false; } -/* Find a 2nd level CXL port that has a dport that is an ancestor of @match */ -static int match_root_child(struct device *dev, const void *match) +struct cxl_port *find_cxl_root(struct cxl_port *port) { - const struct device *iter = NULL; - struct cxl_dport *dport; - struct cxl_port *port; - - if (!dev_is_cxl_root_child(dev)) - return 0; - - port = to_cxl_port(dev); - iter = match; - while (iter) { - dport = cxl_find_dport_by_dev(port, iter); - if (dport) - break; - iter = iter->parent; - } - - return !!iter; -} + struct cxl_port *iter = port; -struct cxl_port *find_cxl_root(struct device *dev) -{ - struct device *port_dev; - struct cxl_port *root; + while (iter && !is_cxl_root(iter)) + iter = to_cxl_port(iter->dev.parent); - port_dev = bus_find_device(&cxl_bus_type, NULL, dev, match_root_child); - if (!port_dev) + if (!iter) return NULL; - - root = to_cxl_port(port_dev->parent); - get_device(&root->dev); - put_device(port_dev); - return root; + get_device(&iter->dev); + return iter; } EXPORT_SYMBOL_NS_GPL(find_cxl_root, CXL); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index f29028148806..b2fd67fcebfb 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -134,9 +134,13 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count) struct cxl_endpoint_decoder *cxled = p->targets[i]; struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); struct cxl_port *iter = cxled_to_port(cxled); + struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_ep *ep; int rc = 0; + if (cxlds->rcd) + goto endpoint_reset; + while (!is_cxl_root(to_cxl_port(iter->dev.parent))) iter = to_cxl_port(iter->dev.parent); @@ -153,6 +157,7 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count) return rc; } +endpoint_reset: rc = cxled->cxld.reset(&cxled->cxld); if (rc) return rc; @@ -1199,6 +1204,7 @@ static void cxl_region_teardown_targets(struct cxl_region *cxlr) { struct cxl_region_params *p = &cxlr->params; struct cxl_endpoint_decoder *cxled; + struct cxl_dev_state *cxlds; struct cxl_memdev *cxlmd; struct cxl_port *iter; struct cxl_ep *ep; @@ -1214,6 +1220,10 @@ static void cxl_region_teardown_targets(struct cxl_region *cxlr) for (i = 0; i < p->nr_targets; i++) { cxled = p->targets[i]; cxlmd = cxled_to_memdev(cxled); + cxlds = cxlmd->cxlds; + + if (cxlds->rcd) + continue; iter = cxled_to_port(cxled); while (!is_cxl_root(to_cxl_port(iter->dev.parent))) @@ -1229,14 +1239,24 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr) { struct cxl_region_params *p = &cxlr->params; struct cxl_endpoint_decoder *cxled; + struct cxl_dev_state *cxlds; + int i, rc, rch = 0, vh = 0; struct cxl_memdev *cxlmd; struct cxl_port *iter; struct cxl_ep *ep; - int i, rc; for (i = 0; i < p->nr_targets; i++) { cxled = p->targets[i]; cxlmd = cxled_to_memdev(cxled); + cxlds = cxlmd->cxlds; + + /* validate that all targets agree on topology */ + if (!cxlds->rcd) { + vh++; + } else { + rch++; + continue; + } iter = cxled_to_port(cxled); while (!is_cxl_root(to_cxl_port(iter->dev.parent))) @@ -1256,6 +1276,12 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr) } } + if (rch && vh) { + dev_err(&cxlr->dev, "mismatched CXL topologies detected\n"); + cxl_region_teardown_targets(cxlr); + return -ENXIO; + } + return 0; } @@ -1648,6 +1674,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (rc) goto err_decrement; p->state = CXL_CONFIG_ACTIVE; + set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); } cxled->cxld.interleave_ways = p->interleave_ways; @@ -1749,8 +1776,6 @@ static int attach_target(struct cxl_region *cxlr, down_read(&cxl_dpa_rwsem); rc = cxl_region_attach(cxlr, cxled, pos); - if (rc == 0) - set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags); up_read(&cxl_dpa_rwsem); up_write(&cxl_region_rwsem); return rc; @@ -2251,7 +2276,7 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) * bridge for one device is the same for all. */ if (i == 0) { - cxl_nvb = cxl_find_nvdimm_bridge(&cxlmd->dev); + cxl_nvb = cxl_find_nvdimm_bridge(cxlmd); if (!cxl_nvb) { cxlr_pmem = ERR_PTR(-ENODEV); goto out; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index f2b0962a552d..044a92d9813e 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -658,7 +658,7 @@ struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port); struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, resource_size_t component_reg_phys, struct cxl_dport *parent_dport); -struct cxl_port *find_cxl_root(struct device *dev); +struct cxl_port *find_cxl_root(struct cxl_port *port); int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd); void cxl_bus_rescan(void); void cxl_bus_drain(void); @@ -695,13 +695,15 @@ int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint) /** * struct cxl_endpoint_dvsec_info - Cached DVSEC info - * @mem_enabled: cached value of mem_enabled in the DVSEC, PCIE_DEVICE + * @mem_enabled: cached value of mem_enabled in the DVSEC at init time * @ranges: Number of active HDM ranges this device uses. + * @port: endpoint port associated with this info instance * @dvsec_range: cached attributes of the ranges in the DVSEC, PCIE_DEVICE */ struct cxl_endpoint_dvsec_info { bool mem_enabled; int ranges; + struct cxl_port *port; struct range dvsec_range[2]; }; @@ -758,7 +760,7 @@ struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm_bridge(struct device *dev); int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd); -struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct device *dev); +struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd); #ifdef CONFIG_CXL_REGION bool is_cxl_pmem_region(struct device *dev); diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h index be6a2ef3cce3..0465ef963cd6 100644 --- a/drivers/cxl/cxlpci.h +++ b/drivers/cxl/cxlpci.h @@ -68,6 +68,20 @@ enum cxl_regloc_type { CXL_REGLOC_RBI_TYPES }; +struct cdat_header { + __le32 length; + u8 revision; + u8 checksum; + u8 reserved[6]; + __le32 sequence; +} __packed; + +struct cdat_entry_header { + u8 type; + u8 reserved; + __le16 length; +} __packed; + int devm_cxl_port_enumerate_dports(struct cxl_port *port); struct cxl_dev_state; int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 1049bb5ea496..22a7ab2bae7c 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -78,8 +78,8 @@ static int cxl_switch_port_probe(struct cxl_port *port) static int cxl_endpoint_port_probe(struct cxl_port *port) { + struct cxl_endpoint_dvsec_info info = { .port = port }; struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport); - struct cxl_endpoint_dvsec_info info = { 0 }; struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_hdm *cxlhdm; struct cxl_port *root; @@ -119,7 +119,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) * This can't fail in practice as CXL root exit unregisters all * descendant ports and that in turn synchronizes with cxl_port_probe() */ - root = find_cxl_root(&cxlmd->dev); + root = find_cxl_root(port); /* * Now that all endpoint decoders are successfully enumerated, try to diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index 90f28bda29c8..4cf8da77bdd9 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -75,6 +75,7 @@ #define REG_TX_INTSTATE(idx) (0x0030 + (idx) * 4) #define REG_RX_INTSTATE(idx) (0x0040 + (idx) * 4) +#define REG_GLOBAL_INTSTATE(idx) (0x0050 + (idx) * 4) #define REG_CHAN_INTSTATUS(ch, idx) (0x8010 + (ch) * 0x200 + (idx) * 4) #define REG_CHAN_INTMASK(ch, idx) (0x8020 + (ch) * 0x200 + (idx) * 4) @@ -511,7 +512,10 @@ static int admac_terminate_all(struct dma_chan *chan) admac_stop_chan(adchan); admac_reset_rings(adchan); - adchan->current_tx = NULL; + if (adchan->current_tx) { + list_add_tail(&adchan->current_tx->node, &adchan->to_free); + adchan->current_tx = NULL; + } /* * Descriptors can only be freed after the tasklet * has been killed (in admac_synchronize). @@ -672,13 +676,14 @@ static void admac_handle_chan_int(struct admac_data *ad, int no) static irqreturn_t admac_interrupt(int irq, void *devid) { struct admac_data *ad = devid; - u32 rx_intstate, tx_intstate; + u32 rx_intstate, tx_intstate, global_intstate; int i; rx_intstate = readl_relaxed(ad->base + REG_RX_INTSTATE(ad->irq_index)); tx_intstate = readl_relaxed(ad->base + REG_TX_INTSTATE(ad->irq_index)); + global_intstate = readl_relaxed(ad->base + REG_GLOBAL_INTSTATE(ad->irq_index)); - if (!tx_intstate && !rx_intstate) + if (!tx_intstate && !rx_intstate && !global_intstate) return IRQ_NONE; for (i = 0; i < ad->nchannels; i += 2) { @@ -693,6 +698,12 @@ static irqreturn_t admac_interrupt(int irq, void *devid) rx_intstate >>= 1; } + if (global_intstate) { + dev_warn(ad->dev, "clearing unknown global interrupt flag: %x\n", + global_intstate); + writel_relaxed(~(u32) 0, ad->base + REG_GLOBAL_INTSTATE(ad->irq_index)); + } + return IRQ_HANDLED; } @@ -850,6 +861,9 @@ static int admac_probe(struct platform_device *pdev) dma->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); dma->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + dma->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); dma->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index c24bca210104..826b98284fa1 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1342,7 +1342,7 @@ int dmaenginem_async_device_register(struct dma_device *device) if (ret) return ret; - return devm_add_action(device->dev, dmaenginem_async_device_unregister, device); + return devm_add_action_or_reset(device->dev, dmaenginem_async_device_unregister, device); } EXPORT_SYMBOL(dmaenginem_async_device_register); diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 462109c61653..93ee298d52b8 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -277,7 +277,7 @@ failed: /** * xdma_xfer_start - Start DMA transfer - * @xdma_chan: DMA channel pointer + * @xchan: DMA channel pointer */ static int xdma_xfer_start(struct xdma_chan *xchan) { diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index 29619f49873a..d9629ff87861 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -167,7 +167,8 @@ int psci_set_osi_mode(bool enable) err = invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE, suspend_mode, 0, 0); if (err < 0) - pr_warn("failed to set %s mode: %d\n", enable ? "OSI" : "PC", err); + pr_info(FW_BUG "failed to set %s mode: %d\n", + enable ? "OSI" : "PC", err); return psci_to_linux_errno(err); } diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 13be729710f2..badbe0582318 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -100,7 +100,7 @@ config GPIO_GENERIC tristate config GPIO_REGMAP - depends on REGMAP + select REGMAP tristate # put drivers in the right section, in alphabetical order diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 26b1f7465e09..43b2dc8821e6 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -324,7 +324,7 @@ static struct irq_chip gpio_irqchip = { .irq_enable = gpio_irq_enable, .irq_disable = gpio_irq_disable, .irq_set_type = gpio_irq_type, - .flags = IRQCHIP_SET_TYPE_MASKED, + .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE, }; static void gpio_irq_handler(struct irq_desc *desc) @@ -641,9 +641,6 @@ static void davinci_gpio_save_context(struct davinci_gpio_controller *chips, context->set_falling = readl_relaxed(&g->set_falling); } - /* Clear Bank interrupt enable bit */ - writel_relaxed(0, base + BINTEN); - /* Clear all interrupt status registers */ writel_relaxed(GENMASK(31, 0), &g->intstat); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 1583157da355..efd025d8961e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -177,6 +177,40 @@ void dm_helpers_dp_update_branch_info( const struct dc_link *link) {} +static void dm_helpers_construct_old_payload( + struct dc_link *link, + int pbn_per_slot, + struct drm_dp_mst_atomic_payload *new_payload, + struct drm_dp_mst_atomic_payload *old_payload) +{ + struct link_mst_stream_allocation_table current_link_table = + link->mst_stream_alloc_table; + struct link_mst_stream_allocation *dc_alloc; + int i; + + *old_payload = *new_payload; + + /* Set correct time_slots/PBN of old payload. + * other fields (delete & dsc_enabled) in + * struct drm_dp_mst_atomic_payload are don't care fields + * while calling drm_dp_remove_payload() + */ + for (i = 0; i < current_link_table.stream_count; i++) { + dc_alloc = + ¤t_link_table.stream_allocations[i]; + + if (dc_alloc->vcp_id == new_payload->vcpi) { + old_payload->time_slots = dc_alloc->slot_count; + old_payload->pbn = dc_alloc->slot_count * pbn_per_slot; + break; + } + } + + /* make sure there is an old payload*/ + ASSERT(i != current_link_table.stream_count); + +} + /* * Writes payload allocation table in immediate downstream device. */ @@ -188,7 +222,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( { struct amdgpu_dm_connector *aconnector; struct drm_dp_mst_topology_state *mst_state; - struct drm_dp_mst_atomic_payload *payload; + struct drm_dp_mst_atomic_payload *target_payload, *new_payload, old_payload; struct drm_dp_mst_topology_mgr *mst_mgr; aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; @@ -204,17 +238,26 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( mst_state = to_drm_dp_mst_topology_state(mst_mgr->base.state); /* It's OK for this to fail */ - payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); - if (enable) - drm_dp_add_payload_part1(mst_mgr, mst_state, payload); - else - drm_dp_remove_payload(mst_mgr, mst_state, payload, payload); + new_payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); + + if (enable) { + target_payload = new_payload; + + drm_dp_add_payload_part1(mst_mgr, mst_state, new_payload); + } else { + /* construct old payload by VCPI*/ + dm_helpers_construct_old_payload(stream->link, mst_state->pbn_div, + new_payload, &old_payload); + target_payload = &old_payload; + + drm_dp_remove_payload(mst_mgr, mst_state, &old_payload, new_payload); + } /* mst_mgr->->payloads are VC payload notify MST branch using DPCD or * AUX message. The sequence is slot 1-63 allocated sequence for each * stream. AMD ASIC stream slot allocation should follow the same * sequence. copy DRM MST allocation to dc */ - fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table); + fill_dc_mst_payload_table_from_drm(stream->link, enable, target_payload, proposed_table); return true; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index f085cb97a620..85a090b9e3d9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -61,6 +61,12 @@ #define CTF_OFFSET_HOTSPOT 5 #define CTF_OFFSET_MEM 5 +static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5}; +static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; + +#define DECODE_GEN_SPEED(gen_speed_idx) (pmfw_decoded_link_speed[gen_speed_idx]) +#define DECODE_LANE_WIDTH(lane_width_idx) (pmfw_decoded_link_width[lane_width_idx]) + struct smu_13_0_max_sustainable_clocks { uint32_t display_clock; uint32_t phy_clock; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 27448ffe60a4..a5c97d61e92a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -1144,8 +1144,8 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - ((gen_speed - 1) == pcie_table->pcie_gen[i]) && - (lane_width == link_width[pcie_table->pcie_lane[i]]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(link_width[pcie_table->pcie_lane[i]])) ? "*" : ""); break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 9e1967d8049e..4399416dd9b8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -575,6 +575,14 @@ static int smu_v13_0_7_set_default_dpm_table(struct smu_context *smu) dpm_table); if (ret) return ret; + + if (skutable->DriverReportedClocks.GameClockAc && + (dpm_table->dpm_levels[dpm_table->count - 1].value > + skutable->DriverReportedClocks.GameClockAc)) { + dpm_table->dpm_levels[dpm_table->count - 1].value = + skutable->DriverReportedClocks.GameClockAc; + dpm_table->max = skutable->DriverReportedClocks.GameClockAc; + } } else { dpm_table->count = 1; dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.gfxclk / 100; @@ -828,6 +836,57 @@ static int smu_v13_0_7_get_smu_metrics_data(struct smu_context *smu, return ret; } +static int smu_v13_0_7_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + struct smu_13_0_dpm_context *dpm_context = + smu->smu_dpm.dpm_context; + struct smu_13_0_dpm_table *dpm_table; + + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + /* uclk dpm table */ + dpm_table = &dpm_context->dpm_tables.uclk_table; + break; + case SMU_GFXCLK: + case SMU_SCLK: + /* gfxclk dpm table */ + dpm_table = &dpm_context->dpm_tables.gfx_table; + break; + case SMU_SOCCLK: + /* socclk dpm table */ + dpm_table = &dpm_context->dpm_tables.soc_table; + break; + case SMU_FCLK: + /* fclk dpm table */ + dpm_table = &dpm_context->dpm_tables.fclk_table; + break; + case SMU_VCLK: + case SMU_VCLK1: + /* vclk dpm table */ + dpm_table = &dpm_context->dpm_tables.vclk_table; + break; + case SMU_DCLK: + case SMU_DCLK1: + /* dclk dpm table */ + dpm_table = &dpm_context->dpm_tables.dclk_table; + break; + default: + dev_err(smu->adev->dev, "Unsupported clock type!\n"); + return -EINVAL; + } + + if (min) + *min = dpm_table->min; + if (max) + *max = dpm_table->max; + + return 0; +} + static int smu_v13_0_7_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, void *data, @@ -1074,8 +1133,8 @@ static int smu_v13_0_7_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - (gen_speed == pcie_table->pcie_gen[i]) && - (lane_width == pcie_table->pcie_lane[i]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ? "*" : ""); break; @@ -1329,9 +1388,17 @@ static int smu_v13_0_7_populate_umd_state_clk(struct smu_context *smu) &dpm_context->dpm_tables.fclk_table; struct smu_umd_pstate_table *pstate_table = &smu->pstate_table; + struct smu_table_context *table_context = &smu->smu_table; + PPTable_t *pptable = table_context->driver_pptable; + DriverReportedClocks_t driver_clocks = + pptable->SkuTable.DriverReportedClocks; pstate_table->gfxclk_pstate.min = gfx_table->min; - pstate_table->gfxclk_pstate.peak = gfx_table->max; + if (driver_clocks.GameClockAc && + (driver_clocks.GameClockAc < gfx_table->max)) + pstate_table->gfxclk_pstate.peak = driver_clocks.GameClockAc; + else + pstate_table->gfxclk_pstate.peak = gfx_table->max; pstate_table->uclk_pstate.min = mem_table->min; pstate_table->uclk_pstate.peak = mem_table->max; @@ -1348,12 +1415,12 @@ static int smu_v13_0_7_populate_umd_state_clk(struct smu_context *smu) pstate_table->fclk_pstate.min = fclk_table->min; pstate_table->fclk_pstate.peak = fclk_table->max; - /* - * For now, just use the mininum clock frequency. - * TODO: update them when the real pstate settings available - */ - pstate_table->gfxclk_pstate.standard = gfx_table->min; - pstate_table->uclk_pstate.standard = mem_table->min; + if (driver_clocks.BaseClockAc && + driver_clocks.BaseClockAc < gfx_table->max) + pstate_table->gfxclk_pstate.standard = driver_clocks.BaseClockAc; + else + pstate_table->gfxclk_pstate.standard = gfx_table->max; + pstate_table->uclk_pstate.standard = mem_table->max; pstate_table->socclk_pstate.standard = soc_table->min; pstate_table->vclk_pstate.standard = vclk_table->min; pstate_table->dclk_pstate.standard = dclk_table->min; @@ -1676,7 +1743,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .dpm_set_jpeg_enable = smu_v13_0_set_jpeg_enable, .init_pptable_microcode = smu_v13_0_init_pptable_microcode, .populate_umd_state_clk = smu_v13_0_7_populate_umd_state_clk, - .get_dpm_ultimate_freq = smu_v13_0_get_dpm_ultimate_freq, + .get_dpm_ultimate_freq = smu_v13_0_7_get_dpm_ultimate_freq, .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .read_sensor = smu_v13_0_7_read_sensor, .feature_is_enabled = smu_cmn_feature_is_enabled, diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 0643887800b4..142668cd6d7c 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -99,7 +99,6 @@ static int armada_drm_bind(struct device *dev) if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); - kfree(priv); return ret; } diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 468a792e6a40..fc0eaf40dc94 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -300,9 +300,21 @@ static void configure_dual_link_mode(struct intel_encoder *encoder, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); + i915_reg_t dss_ctl1_reg, dss_ctl2_reg; u32 dss_ctl1; - dss_ctl1 = intel_de_read(dev_priv, DSS_CTL1); + /* FIXME: Move all DSS handling to intel_vdsc.c */ + if (DISPLAY_VER(dev_priv) >= 12) { + struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); + + dss_ctl1_reg = ICL_PIPE_DSS_CTL1(crtc->pipe); + dss_ctl2_reg = ICL_PIPE_DSS_CTL2(crtc->pipe); + } else { + dss_ctl1_reg = DSS_CTL1; + dss_ctl2_reg = DSS_CTL2; + } + + dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg); dss_ctl1 |= SPLITTER_ENABLE; dss_ctl1 &= ~OVERLAP_PIXELS_MASK; dss_ctl1 |= OVERLAP_PIXELS(intel_dsi->pixel_overlap); @@ -323,16 +335,16 @@ static void configure_dual_link_mode(struct intel_encoder *encoder, dss_ctl1 &= ~LEFT_DL_BUF_TARGET_DEPTH_MASK; dss_ctl1 |= LEFT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); - dss_ctl2 = intel_de_read(dev_priv, DSS_CTL2); + dss_ctl2 = intel_de_read(dev_priv, dss_ctl2_reg); dss_ctl2 &= ~RIGHT_DL_BUF_TARGET_DEPTH_MASK; dss_ctl2 |= RIGHT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); - intel_de_write(dev_priv, DSS_CTL2, dss_ctl2); + intel_de_write(dev_priv, dss_ctl2_reg, dss_ctl2); } else { /* Interleave */ dss_ctl1 |= DUAL_LINK_MODE_INTERLEAVE; } - intel_de_write(dev_priv, DSS_CTL1, dss_ctl1); + intel_de_write(dev_priv, dss_ctl1_reg, dss_ctl1); } /* aka DSI 8X clock */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 2106b3de225a..7c9b328bc2d7 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -232,7 +232,7 @@ static int intel_dp_dsc_mst_compute_link_config(struct intel_encoder *encoder, return slots; } - intel_link_compute_m_n(crtc_state->pipe_bpp, + intel_link_compute_m_n(crtc_state->dsc.compressed_bpp, crtc_state->lane_count, adjusted_mode->crtc_clock, crtc_state->port_clock, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 7420276827a5..4758f21c91e1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -1067,11 +1067,12 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) .interruptible = true, .no_wait_gpu = true, /* should be idle already */ }; + int err; GEM_BUG_ON(!bo->ttm || !(bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED)); - ret = ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx); - if (ret) { + err = ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx); + if (err) { dma_resv_unlock(bo->base.resv); return VM_FAULT_SIGBUS; } diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 1bbe6708d0a7..750326434677 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -2018,6 +2018,8 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive) * inspecting the queue to see if we need to resumbit. */ if (*prev != *execlists->active) { /* elide lite-restores */ + struct intel_context *prev_ce = NULL, *active_ce = NULL; + /* * Note the inherent discrepancy between the HW runtime, * recorded as part of the context switch, and the CPU @@ -2029,9 +2031,15 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive) * and correct overselves later when updating from HW. */ if (*prev) - lrc_runtime_stop((*prev)->context); + prev_ce = (*prev)->context; if (*execlists->active) - lrc_runtime_start((*execlists->active)->context); + active_ce = (*execlists->active)->context; + if (prev_ce != active_ce) { + if (prev_ce) + lrc_runtime_stop(prev_ce); + if (active_ce) + lrc_runtime_start(active_ce); + } new_timeslice(execlists); } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 410905da8e97..0c103ca160d1 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -235,6 +235,13 @@ static void delayed_huc_load_fini(struct intel_huc *huc) i915_sw_fence_fini(&huc->delayed_load.fence); } +int intel_huc_sanitize(struct intel_huc *huc) +{ + delayed_huc_load_complete(huc); + intel_uc_fw_sanitize(&huc->fw); + return 0; +} + static bool vcs_supported(struct intel_gt *gt) { intel_engine_mask_t mask = gt->info.engine_mask; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index 52db03620c60..db555b3c1f56 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -41,6 +41,7 @@ struct intel_huc { } delayed_load; }; +int intel_huc_sanitize(struct intel_huc *huc); void intel_huc_init_early(struct intel_huc *huc); int intel_huc_init(struct intel_huc *huc); void intel_huc_fini(struct intel_huc *huc); @@ -54,12 +55,6 @@ bool intel_huc_is_authenticated(struct intel_huc *huc); void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); -static inline int intel_huc_sanitize(struct intel_huc *huc) -{ - intel_uc_fw_sanitize(&huc->fw); - return 0; -} - static inline bool intel_huc_is_supported(struct intel_huc *huc) { return intel_uc_fw_is_supported(&huc->fw); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 283a4a3c6862..004074936300 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4638,13 +4638,13 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, err = oa_config->id; goto sysfs_err; } - - mutex_unlock(&perf->metrics_lock); + id = oa_config->id; drm_dbg(&perf->i915->drm, "Added config %s id=%i\n", oa_config->uuid, oa_config->id); + mutex_unlock(&perf->metrics_lock); - return oa_config->id; + return id; sysfs_err: mutex_unlock(&perf->metrics_lock); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index ed9d374147b8..5bb777ff1313 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -363,6 +363,35 @@ nv50_outp_atomic_check_view(struct drm_encoder *encoder, return 0; } +static void +nv50_outp_atomic_fix_depth(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state) +{ + struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); + struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); + struct drm_display_mode *mode = &asyh->state.adjusted_mode; + unsigned int max_rate, mode_rate; + + switch (nv_encoder->dcb->type) { + case DCB_OUTPUT_DP: + max_rate = nv_encoder->dp.link_nr * nv_encoder->dp.link_bw; + + /* we don't support more than 10 anyway */ + asyh->or.bpc = min_t(u8, asyh->or.bpc, 10); + + /* reduce the bpc until it works out */ + while (asyh->or.bpc > 6) { + mode_rate = DIV_ROUND_UP(mode->clock * asyh->or.bpc * 3, 8); + if (mode_rate <= max_rate) + break; + + asyh->or.bpc -= 2; + } + break; + default: + break; + } +} + static int nv50_outp_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, @@ -381,6 +410,9 @@ nv50_outp_atomic_check(struct drm_encoder *encoder, if (crtc_state->mode_changed || crtc_state->connectors_changed) asyh->or.bpc = connector->display_info.bpc; + /* We might have to reduce the bpc */ + nv50_outp_atomic_fix_depth(encoder, crtc_state); + return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index e00876f92aee..d49b4875fc3c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -263,8 +263,6 @@ nouveau_dp_irq(struct work_struct *work) } /* TODO: - * - Use the minimum possible BPC here, once we add support for the max bpc - * property. * - Validate against the DP caps advertised by the GPU (we don't check these * yet) */ @@ -276,7 +274,11 @@ nv50_dp_mode_valid(struct drm_connector *connector, { const unsigned int min_clock = 25000; unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock; - const u8 bpp = connector->display_info.bpc * 3; + /* Check with the minmum bpc always, so we can advertise better modes. + * In particlar not doing this causes modes to be dropped on HDR + * displays as we might check with a bpc of 16 even. + */ + const u8 bpp = 6 * 3; if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace) return MODE_NO_INTERLACE; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c index 76678dd60f93..c4c6f67af7cc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c @@ -31,6 +31,7 @@ gf108_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gf108_ram_new, .default_bigpage = 17, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c index f73442ccb424..433fa966ba23 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c @@ -77,6 +77,7 @@ gk104_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gk104_ram_new, .default_bigpage = 17, .clkgate_pack = gk104_fb_clkgate_pack, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c index 45d6cdffafee..4dc283dedf8b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c @@ -59,6 +59,7 @@ gk110_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gk104_ram_new, .default_bigpage = 17, .clkgate_pack = gk110_fb_clkgate_pack, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c index de52462a92bf..90bfff616d35 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c @@ -31,6 +31,7 @@ gm107_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gm107_ram_new, .default_bigpage = 17, }; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 666a5e53fe19..e961fa27702c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -504,6 +504,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, if (IS_ERR(pages[i])) { mutex_unlock(&bo->base.pages_lock); ret = PTR_ERR(pages[i]); + pages[i] = NULL; goto err_pages; } } diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 15d04a0ec623..e0a8890a62e2 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -507,12 +507,19 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) { struct drm_sched_entity *entity = sched_job->entity; bool first; + ktime_t submit_ts; trace_drm_sched_job(sched_job, entity); atomic_inc(entity->rq->sched->score); WRITE_ONCE(entity->last_user, current->group_leader); + + /* + * After the sched_job is pushed into the entity queue, it may be + * completed and freed up at any time. We can no longer access it. + * Make sure to set the submit_ts first, to avoid a race. + */ + sched_job->submit_ts = submit_ts = ktime_get(); first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node); - sched_job->submit_ts = ktime_get(); /* first job wakes up scheduler */ if (first) { @@ -529,7 +536,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) spin_unlock(&entity->rq_lock); if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) - drm_sched_rq_update_fifo(entity, sched_job->submit_ts); + drm_sched_rq_update_fifo(entity, submit_ts); drm_sched_wakeup(entity->rq->sched); } diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 82f64fb31fda..4ce012f83253 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1122,7 +1122,7 @@ config HID_TOPRE tristate "Topre REALFORCE keyboards" depends on HID help - Say Y for N-key rollover support on Topre REALFORCE R2 108 key keyboards. + Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key keyboards. config HID_THINGM tristate "ThingM blink(1) USB RGB LED" diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 63545cd307e5..c2e9b6d1fd7d 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -420,6 +420,9 @@ #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A #define I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN 0x2A1C #define I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN 0x279F +#define I2C_DEVICE_ID_HP_SPECTRE_X360_13T_AW100 0x29F5 +#define I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V1 0x2BED +#define I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V2 0x2BEE #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 @@ -1249,6 +1252,7 @@ #define USB_VENDOR_ID_TOPRE 0x0853 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_108 0x0148 +#define USB_DEVICE_ID_TOPRE_REALFORCE_R2_87 0x0146 #define USB_VENDOR_ID_TOPSEED 0x0766 #define USB_DEVICE_ID_TOPSEED_CYBERLINK 0x0204 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 7fc967964dd8..5c65a584b3fa 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -398,6 +398,12 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_13T_AW100), + HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V1), + HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V2), + HID_BATTERY_QUIRK_IGNORE }, {} }; diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index 3e3f89e01d81..d85398721659 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -940,7 +940,7 @@ hid_sensor_register_platform_device(struct platform_device *pdev, struct hid_sensor_hub_device *hsdev, const struct hid_sensor_custom_match *match) { - char real_usage[HID_SENSOR_USAGE_LENGTH]; + char real_usage[HID_SENSOR_USAGE_LENGTH] = { 0 }; struct platform_device *custom_pdev; const char *dev_name; char *c; diff --git a/drivers/hid/hid-topre.c b/drivers/hid/hid-topre.c index 88a91cdad5f8..d1d5ca310ead 100644 --- a/drivers/hid/hid-topre.c +++ b/drivers/hid/hid-topre.c @@ -36,6 +36,8 @@ static __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc, static const struct hid_device_id topre_id_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, USB_DEVICE_ID_TOPRE_REALFORCE_R2_108) }, + { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, + USB_DEVICE_ID_TOPRE_REALFORCE_R2_87) }, { } }; MODULE_DEVICE_TABLE(hid, topre_id_table); diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index 81385ab37fa9..7fc738a22375 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -241,8 +241,8 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv) struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv); - return guid_equal(&driver->id[0].guid, - &device->fw_client->props.protocol_name); + return(device->fw_client ? guid_equal(&driver->id[0].guid, + &device->fw_client->props.protocol_name) : 0); } /** diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 9dc27e5d367a..da51b50787df 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -409,6 +409,10 @@ void vmbus_disconnect(void) */ struct vmbus_channel *relid2channel(u32 relid) { + if (vmbus_connection.channels == NULL) { + pr_warn_once("relid2channel: relid=%d: No channels mapped!\n", relid); + return NULL; + } if (WARN_ON(relid >= MAX_CHANNEL_RELIDS)) return NULL; return READ_ONCE(vmbus_connection.channels[relid]); diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 1ea8f173cca0..4c15fae534f3 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -472,7 +472,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) if (etm4x_sspcicrn_present(drvdata, i)) etm4x_relaxed_write32(csa, config->ss_pe_cmp[i], TRCSSPCICRn(i)); } - for (i = 0; i < drvdata->nr_addr_cmp; i++) { + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { etm4x_relaxed_write64(csa, config->addr_val[i], TRCACVRn(i)); etm4x_relaxed_write64(csa, config->addr_acc[i], TRCACATRn(i)); } @@ -1070,25 +1070,21 @@ static bool etm4_init_iomem_access(struct etmv4_drvdata *drvdata, struct csdev_access *csa) { u32 devarch = readl_relaxed(drvdata->base + TRCDEVARCH); - u32 idr1 = readl_relaxed(drvdata->base + TRCIDR1); /* * All ETMs must implement TRCDEVARCH to indicate that - * the component is an ETMv4. To support any broken - * implementations we fall back to TRCIDR1 check, which - * is not really reliable. + * the component is an ETMv4. Even though TRCIDR1 also + * contains the information, it is part of the "Trace" + * register and must be accessed with the OSLK cleared, + * with MMIO. But we cannot touch the OSLK until we are + * sure this is an ETM. So rely only on the TRCDEVARCH. */ - if ((devarch & ETM_DEVARCH_ID_MASK) == ETM_DEVARCH_ETMv4x_ARCH) { - drvdata->arch = etm_devarch_to_arch(devarch); - } else { - pr_warn("CPU%d: ETM4x incompatible TRCDEVARCH: %x, falling back to TRCIDR1\n", - smp_processor_id(), devarch); - - if (ETM_TRCIDR1_ARCH_MAJOR(idr1) != ETM_TRCIDR1_ARCH_ETMv4) - return false; - drvdata->arch = etm_trcidr_to_arch(idr1); + if ((devarch & ETM_DEVARCH_ID_MASK) != ETM_DEVARCH_ETMv4x_ARCH) { + pr_warn_once("TRCDEVARCH doesn't match ETMv4 architecture\n"); + return false; } + drvdata->arch = etm_devarch_to_arch(devarch); *csa = CSDEV_ACCESS_IOMEM(drvdata->base); return true; } diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 434f4e95ee17..27c8a9901868 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -753,14 +753,12 @@ * TRCDEVARCH - CoreSight architected register * - Bits[15:12] - Major version * - Bits[19:16] - Minor version - * TRCIDR1 - ETM architected register - * - Bits[11:8] - Major version - * - Bits[7:4] - Minor version - * We must rely on TRCDEVARCH for the version information, - * however we don't want to break the support for potential - * old implementations which might not implement it. Thus - * we fall back to TRCIDR1 if TRCDEVARCH is not implemented - * for memory mapped components. + * + * We must rely only on TRCDEVARCH for the version information. Even though, + * TRCIDR1 also provides the architecture version, it is a "Trace" register + * and as such must be accessed only with Trace power domain ON. This may + * not be available at probe time. + * * Now to make certain decisions easier based on the version * we use an internal representation of the version in the * driver, as follows : @@ -786,12 +784,6 @@ static inline u8 etm_devarch_to_arch(u32 devarch) ETM_DEVARCH_REVISION(devarch)); } -static inline u8 etm_trcidr_to_arch(u32 trcidr1) -{ - return ETM_ARCH_VERSION(ETM_TRCIDR1_ARCH_MAJOR(trcidr1), - ETM_TRCIDR1_ARCH_MINOR(trcidr1)); -} - enum etm_impdef_type { ETM4_IMPDEF_HISI_CORE_COMMIT, ETM4_IMPDEF_FEATURE_MAX, diff --git a/drivers/i2c/busses/i2c-mchp-pci1xxxx.c b/drivers/i2c/busses/i2c-mchp-pci1xxxx.c index 09af75921147..b21ffd6df927 100644 --- a/drivers/i2c/busses/i2c-mchp-pci1xxxx.c +++ b/drivers/i2c/busses/i2c-mchp-pci1xxxx.c @@ -48,9 +48,9 @@ * SR_HOLD_TIME_XK_TICKS field will indicate the number of ticks of the * baud clock required to program 'Hold Time' at X KHz. */ -#define SR_HOLD_TIME_100K_TICKS 133 -#define SR_HOLD_TIME_400K_TICKS 20 -#define SR_HOLD_TIME_1000K_TICKS 11 +#define SR_HOLD_TIME_100K_TICKS 150 +#define SR_HOLD_TIME_400K_TICKS 20 +#define SR_HOLD_TIME_1000K_TICKS 12 #define SMB_CORE_COMPLETION_REG_OFF3 (SMBUS_MAST_CORE_ADDR_BASE + 0x23) @@ -65,17 +65,17 @@ * the baud clock required to program 'fair idle delay' at X KHz. Fair idle * delay establishes the MCTP T(IDLE_DELAY) period. */ -#define FAIR_BUS_IDLE_MIN_100K_TICKS 969 -#define FAIR_BUS_IDLE_MIN_400K_TICKS 157 -#define FAIR_BUS_IDLE_MIN_1000K_TICKS 157 +#define FAIR_BUS_IDLE_MIN_100K_TICKS 992 +#define FAIR_BUS_IDLE_MIN_400K_TICKS 500 +#define FAIR_BUS_IDLE_MIN_1000K_TICKS 500 /* * FAIR_IDLE_DELAY_XK_TICKS field will indicate the number of ticks of the * baud clock required to satisfy the fairness protocol at X KHz. */ -#define FAIR_IDLE_DELAY_100K_TICKS 1000 -#define FAIR_IDLE_DELAY_400K_TICKS 500 -#define FAIR_IDLE_DELAY_1000K_TICKS 500 +#define FAIR_IDLE_DELAY_100K_TICKS 963 +#define FAIR_IDLE_DELAY_400K_TICKS 156 +#define FAIR_IDLE_DELAY_1000K_TICKS 156 #define SMB_IDLE_SCALING_100K \ ((FAIR_IDLE_DELAY_100K_TICKS << 16) | FAIR_BUS_IDLE_MIN_100K_TICKS) @@ -105,7 +105,7 @@ */ #define BUS_CLK_100K_LOW_PERIOD_TICKS 156 #define BUS_CLK_400K_LOW_PERIOD_TICKS 41 -#define BUS_CLK_1000K_LOW_PERIOD_TICKS 15 +#define BUS_CLK_1000K_LOW_PERIOD_TICKS 15 /* * BUS_CLK_XK_HIGH_PERIOD_TICKS field defines the number of I2C Baud Clock @@ -131,7 +131,7 @@ */ #define CLK_SYNC_100K 4 #define CLK_SYNC_400K 4 -#define CLK_SYNC_1000K 4 +#define CLK_SYNC_1000K 4 #define SMB_CORE_DATA_TIMING_REG_OFF (SMBUS_MAST_CORE_ADDR_BASE + 0x40) @@ -142,25 +142,25 @@ * determines the SCLK hold time following SDAT driven low during the first * START bit in a transfer. */ -#define FIRST_START_HOLD_100K_TICKS 22 -#define FIRST_START_HOLD_400K_TICKS 16 -#define FIRST_START_HOLD_1000K_TICKS 6 +#define FIRST_START_HOLD_100K_TICKS 23 +#define FIRST_START_HOLD_400K_TICKS 8 +#define FIRST_START_HOLD_1000K_TICKS 12 /* * STOP_SETUP_XK_TICKS will indicate the number of ticks of the baud clock * required to program 'STOP_SETUP' timer at X KHz. This timer determines the * SDAT setup time from the rising edge of SCLK for a STOP condition. */ -#define STOP_SETUP_100K_TICKS 157 +#define STOP_SETUP_100K_TICKS 150 #define STOP_SETUP_400K_TICKS 20 -#define STOP_SETUP_1000K_TICKS 12 +#define STOP_SETUP_1000K_TICKS 12 /* * RESTART_SETUP_XK_TICKS will indicate the number of ticks of the baud clock * required to program 'RESTART_SETUP' timer at X KHz. This timer determines the * SDAT setup time from the rising edge of SCLK for a repeated START condition. */ -#define RESTART_SETUP_100K_TICKS 157 +#define RESTART_SETUP_100K_TICKS 156 #define RESTART_SETUP_400K_TICKS 20 #define RESTART_SETUP_1000K_TICKS 12 @@ -169,7 +169,7 @@ * required to program 'DATA_HOLD' timer at X KHz. This timer determines the * SDAT hold time following SCLK driven low. */ -#define DATA_HOLD_100K_TICKS 2 +#define DATA_HOLD_100K_TICKS 12 #define DATA_HOLD_400K_TICKS 2 #define DATA_HOLD_1000K_TICKS 2 @@ -190,35 +190,35 @@ * Bus Idle Minimum time = BUS_IDLE_MIN[7:0] x Baud_Clock_Period x * (BUS_IDLE_MIN_XK_TICKS[7] ? 4,1) */ -#define BUS_IDLE_MIN_100K_TICKS 167UL -#define BUS_IDLE_MIN_400K_TICKS 139UL -#define BUS_IDLE_MIN_1000K_TICKS 133UL +#define BUS_IDLE_MIN_100K_TICKS 36UL +#define BUS_IDLE_MIN_400K_TICKS 10UL +#define BUS_IDLE_MIN_1000K_TICKS 4UL /* * CTRL_CUM_TIME_OUT_XK_TICKS defines SMBus Controller Cumulative Time-Out. * SMBus Controller Cumulative Time-Out duration = * CTRL_CUM_TIME_OUT_XK_TICKS[7:0] x Baud_Clock_Period x 2048 */ -#define CTRL_CUM_TIME_OUT_100K_TICKS 159 -#define CTRL_CUM_TIME_OUT_400K_TICKS 159 -#define CTRL_CUM_TIME_OUT_1000K_TICKS 159 +#define CTRL_CUM_TIME_OUT_100K_TICKS 76 +#define CTRL_CUM_TIME_OUT_400K_TICKS 76 +#define CTRL_CUM_TIME_OUT_1000K_TICKS 76 /* * TARGET_CUM_TIME_OUT_XK_TICKS defines SMBus Target Cumulative Time-Out duration. * SMBus Target Cumulative Time-Out duration = TARGET_CUM_TIME_OUT_XK_TICKS[7:0] x * Baud_Clock_Period x 4096 */ -#define TARGET_CUM_TIME_OUT_100K_TICKS 199 -#define TARGET_CUM_TIME_OUT_400K_TICKS 199 -#define TARGET_CUM_TIME_OUT_1000K_TICKS 199 +#define TARGET_CUM_TIME_OUT_100K_TICKS 95 +#define TARGET_CUM_TIME_OUT_400K_TICKS 95 +#define TARGET_CUM_TIME_OUT_1000K_TICKS 95 /* * CLOCK_HIGH_TIME_OUT_XK defines Clock High time out period. * Clock High time out period = CLOCK_HIGH_TIME_OUT_XK[7:0] x Baud_Clock_Period x 8 */ -#define CLOCK_HIGH_TIME_OUT_100K_TICKS 204 -#define CLOCK_HIGH_TIME_OUT_400K_TICKS 204 -#define CLOCK_HIGH_TIME_OUT_1000K_TICKS 204 +#define CLOCK_HIGH_TIME_OUT_100K_TICKS 97 +#define CLOCK_HIGH_TIME_OUT_400K_TICKS 97 +#define CLOCK_HIGH_TIME_OUT_1000K_TICKS 97 #define TO_SCALING_100K \ ((BUS_IDLE_MIN_100K_TICKS << 24) | (CTRL_CUM_TIME_OUT_100K_TICKS << 16) | \ diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index a0af027db04c..2e575856c5cd 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -342,18 +342,18 @@ static int ocores_poll_wait(struct ocores_i2c *i2c) * ocores_isr(), we just add our polling code around it. * * It can run in atomic context + * + * Return: 0 on success, -ETIMEDOUT on timeout */ -static void ocores_process_polling(struct ocores_i2c *i2c) +static int ocores_process_polling(struct ocores_i2c *i2c) { - while (1) { - irqreturn_t ret; - int err; + irqreturn_t ret; + int err = 0; + while (1) { err = ocores_poll_wait(i2c); - if (err) { - i2c->state = STATE_ERROR; + if (err) break; /* timeout */ - } ret = ocores_isr(-1, i2c); if (ret == IRQ_NONE) @@ -364,13 +364,15 @@ static void ocores_process_polling(struct ocores_i2c *i2c) break; } } + + return err; } static int ocores_xfer_core(struct ocores_i2c *i2c, struct i2c_msg *msgs, int num, bool polling) { - int ret; + int ret = 0; u8 ctrl; ctrl = oc_getreg(i2c, OCI2C_CONTROL); @@ -388,15 +390,16 @@ static int ocores_xfer_core(struct ocores_i2c *i2c, oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_START); if (polling) { - ocores_process_polling(i2c); + ret = ocores_process_polling(i2c); } else { - ret = wait_event_timeout(i2c->wait, - (i2c->state == STATE_ERROR) || - (i2c->state == STATE_DONE), HZ); - if (ret == 0) { - ocores_process_timeout(i2c); - return -ETIMEDOUT; - } + if (wait_event_timeout(i2c->wait, + (i2c->state == STATE_ERROR) || + (i2c->state == STATE_DONE), HZ) == 0) + ret = -ETIMEDOUT; + } + if (ret) { + ocores_process_timeout(i2c); + return ret; } return (i2c->state == STATE_DONE) ? num : -EIO; diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index bce6b796e04c..545436b7dd53 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -178,6 +178,11 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_OK; } + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; client = of_i2c_register_device(adap, rd->dn); if (IS_ERR(client)) { dev_err(&adap->dev, "failed to create client for '%pOF'\n", diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index f866859855cd..1c3a72380fb8 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -864,7 +864,7 @@ static irqreturn_t kx022a_trigger_handler(int irq, void *p) if (ret < 0) goto err_read; - iio_push_to_buffers_with_timestamp(idev, data->buffer, pf->timestamp); + iio_push_to_buffers_with_timestamp(idev, data->buffer, data->timestamp); err_read: iio_trigger_notify_done(idev->trig); diff --git a/drivers/iio/adc/ad7791.c b/drivers/iio/adc/ad7791.c index fee8d129a5f0..86effe8501b4 100644 --- a/drivers/iio/adc/ad7791.c +++ b/drivers/iio/adc/ad7791.c @@ -253,7 +253,7 @@ static const struct ad_sigma_delta_info ad7791_sigma_delta_info = { .has_registers = true, .addr_shift = 4, .read_mask = BIT(3), - .irq_flags = IRQF_TRIGGER_LOW, + .irq_flags = IRQF_TRIGGER_FALLING, }; static int ad7791_read_raw(struct iio_dev *indio_dev, diff --git a/drivers/iio/adc/ltc2497.c b/drivers/iio/adc/ltc2497.c index 17370c5eb6fe..ec198c6f13d6 100644 --- a/drivers/iio/adc/ltc2497.c +++ b/drivers/iio/adc/ltc2497.c @@ -28,7 +28,6 @@ struct ltc2497_driverdata { struct ltc2497core_driverdata common_ddata; struct i2c_client *client; u32 recv_size; - u32 sub_lsb; /* * DMA (thus cache coherency maintenance) may require the * transfer buffers to live in their own cache lines. @@ -65,10 +64,10 @@ static int ltc2497_result_and_measure(struct ltc2497core_driverdata *ddata, * equivalent to a sign extension. */ if (st->recv_size == 3) { - *val = (get_unaligned_be24(st->data.d8) >> st->sub_lsb) + *val = (get_unaligned_be24(st->data.d8) >> 6) - BIT(ddata->chip_info->resolution + 1); } else { - *val = (be32_to_cpu(st->data.d32) >> st->sub_lsb) + *val = (be32_to_cpu(st->data.d32) >> 6) - BIT(ddata->chip_info->resolution + 1); } @@ -122,7 +121,6 @@ static int ltc2497_probe(struct i2c_client *client) st->common_ddata.chip_info = chip_info; resolution = chip_info->resolution; - st->sub_lsb = 31 - (resolution + 1); st->recv_size = BITS_TO_BYTES(resolution) + 1; return ltc2497core_probe(dev, indio_dev); diff --git a/drivers/iio/adc/max11410.c b/drivers/iio/adc/max11410.c index b74b689ee7de..f6895bc9fc4b 100644 --- a/drivers/iio/adc/max11410.c +++ b/drivers/iio/adc/max11410.c @@ -414,13 +414,17 @@ static int max11410_sample(struct max11410_state *st, int *sample_raw, if (!ret) return -ETIMEDOUT; } else { + int ret2; + /* Wait for status register Conversion Ready flag */ - ret = read_poll_timeout(max11410_read_reg, ret, - ret || (val & MAX11410_STATUS_CONV_READY_BIT), + ret = read_poll_timeout(max11410_read_reg, ret2, + ret2 || (val & MAX11410_STATUS_CONV_READY_BIT), 5000, MAX11410_CONVERSION_TIMEOUT_MS * 1000, true, st, MAX11410_REG_STATUS, &val); if (ret) return ret; + if (ret2) + return ret2; } /* Read ADC Data */ @@ -851,17 +855,21 @@ static int max11410_init_vref(struct device *dev, static int max11410_calibrate(struct max11410_state *st, u32 cal_type) { - int ret, val; + int ret, ret2, val; ret = max11410_write_reg(st, MAX11410_REG_CAL_START, cal_type); if (ret) return ret; /* Wait for status register Calibration Ready flag */ - return read_poll_timeout(max11410_read_reg, ret, - ret || (val & MAX11410_STATUS_CAL_READY_BIT), - 50000, MAX11410_CALIB_TIMEOUT_MS * 1000, true, - st, MAX11410_REG_STATUS, &val); + ret = read_poll_timeout(max11410_read_reg, ret2, + ret2 || (val & MAX11410_STATUS_CAL_READY_BIT), + 50000, MAX11410_CALIB_TIMEOUT_MS * 1000, true, + st, MAX11410_REG_STATUS, &val); + if (ret) + return ret; + + return ret2; } static int max11410_self_calibrate(struct max11410_state *st) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index fd000345ec5c..849a697a467e 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -639,7 +639,7 @@ out: static int palmas_gpadc_remove(struct platform_device *pdev) { - struct iio_dev *indio_dev = dev_to_iio_dev(&pdev->dev); + struct iio_dev *indio_dev = dev_get_drvdata(&pdev->dev); struct palmas_gpadc *adc = iio_priv(indio_dev); if (adc->wakeup1_enable || adc->wakeup2_enable) diff --git a/drivers/iio/adc/qcom-spmi-adc5.c b/drivers/iio/adc/qcom-spmi-adc5.c index e90c299c913a..c2d5e06f137a 100644 --- a/drivers/iio/adc/qcom-spmi-adc5.c +++ b/drivers/iio/adc/qcom-spmi-adc5.c @@ -628,12 +628,20 @@ static int adc5_get_fw_channel_data(struct adc5_chip *adc, struct fwnode_handle *fwnode, const struct adc5_data *data) { - const char *name = fwnode_get_name(fwnode), *channel_name; + const char *channel_name; + char *name; u32 chan, value, varr[2]; u32 sid = 0; int ret; struct device *dev = adc->dev; + name = devm_kasprintf(dev, GFP_KERNEL, "%pfwP", fwnode); + if (!name) + return -ENOMEM; + + /* Cut the address part */ + name[strchrnul(name, '@') - name] = '\0'; + ret = fwnode_property_read_u32(fwnode, "reg", &chan); if (ret) { dev_err(dev, "invalid channel number %s\n", name); diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c index 2cc9a9bd9db6..263fc3a1b87e 100644 --- a/drivers/iio/adc/ti-ads7950.c +++ b/drivers/iio/adc/ti-ads7950.c @@ -634,6 +634,7 @@ static int ti_ads7950_probe(struct spi_device *spi) st->chip.label = dev_name(&st->spi->dev); st->chip.parent = &st->spi->dev; st->chip.owner = THIS_MODULE; + st->chip.can_sleep = true; st->chip.base = -1; st->chip.ngpio = TI_ADS7950_NUM_GPIOS; st->chip.get_direction = ti_ads7950_get_direction; diff --git a/drivers/iio/dac/cio-dac.c b/drivers/iio/dac/cio-dac.c index 791dd999cf29..18a64f72fc18 100644 --- a/drivers/iio/dac/cio-dac.c +++ b/drivers/iio/dac/cio-dac.c @@ -66,8 +66,8 @@ static int cio_dac_write_raw(struct iio_dev *indio_dev, if (mask != IIO_CHAN_INFO_RAW) return -EINVAL; - /* DAC can only accept up to a 16-bit value */ - if ((unsigned int)val > 65535) + /* DAC can only accept up to a 12-bit value */ + if ((unsigned int)val > 4095) return -EINVAL; priv->chan_out_states[chan->channel] = val; diff --git a/drivers/iio/imu/Kconfig b/drivers/iio/imu/Kconfig index f1d7d4b5e222..c2f97629e9cd 100644 --- a/drivers/iio/imu/Kconfig +++ b/drivers/iio/imu/Kconfig @@ -47,6 +47,7 @@ config ADIS16480 depends on SPI select IIO_ADIS_LIB select IIO_ADIS_LIB_BUFFER if IIO_BUFFER + select CRC32 help Say yes here to build support for Analog Devices ADIS16375, ADIS16480, ADIS16485, ADIS16488 inertial sensors. diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 80c78bd6bbef..a7a080bed180 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -203,24 +203,27 @@ static ssize_t iio_buffer_write(struct file *filp, const char __user *buf, break; } + if (filp->f_flags & O_NONBLOCK) { + if (!written) + ret = -EAGAIN; + break; + } + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); continue; } ret = rb->access->write(rb, n - written, buf + written); - if (ret == 0 && (filp->f_flags & O_NONBLOCK)) - ret = -EAGAIN; + if (ret < 0) + break; - if (ret > 0) { - written += ret; - if (written != n && !(filp->f_flags & O_NONBLOCK)) - continue; - } - } while (ret == 0); + written += ret; + + } while (written != n); remove_wait_queue(&rb->pollq, &wait); - return ret < 0 ? ret : n; + return ret < 0 ? ret : written; } /** diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index b1674a5bfa36..d4a34a3bf00d 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -429,6 +429,14 @@ static const struct iio_info cm32181_info = { .attrs = &cm32181_attribute_group, }; +static void cm32181_unregister_dummy_client(void *data) +{ + struct i2c_client *client = data; + + /* Unregister the dummy client */ + i2c_unregister_device(client); +} + static int cm32181_probe(struct i2c_client *client) { struct device *dev = &client->dev; @@ -460,6 +468,10 @@ static int cm32181_probe(struct i2c_client *client) client = i2c_acpi_new_device(dev, 1, &board_info); if (IS_ERR(client)) return PTR_ERR(client); + + ret = devm_add_action_or_reset(dev, cm32181_unregister_dummy_client, client); + if (ret) + return ret; } cm32181 = iio_priv(indio_dev); diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c index 6bdfce9747f9..5c44a36ab5b3 100644 --- a/drivers/iio/light/vcnl4000.c +++ b/drivers/iio/light/vcnl4000.c @@ -208,7 +208,6 @@ static int vcnl4000_init(struct vcnl4000_data *data) data->rev = ret & 0xf; data->al_scale = 250000; - mutex_init(&data->vcnl4000_lock); return data->chip_spec->set_power_state(data, true); }; @@ -1367,6 +1366,8 @@ static int vcnl4000_probe(struct i2c_client *client) data->id = id->driver_data; data->chip_spec = &vcnl4000_chip_spec_cfg[data->id]; + mutex_init(&data->vcnl4000_lock); + ret = data->chip_spec->init(data); if (ret < 0) return ret; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 308155937713..6b9563d4f23c 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -624,22 +624,11 @@ static inline unsigned short cma_family(struct rdma_id_private *id_priv) return id_priv->id.route.addr.src_addr.ss_family; } -static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) +static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0; - if (id_priv->qkey) { - if (qkey && id_priv->qkey != qkey) - return -EINVAL; - return 0; - } - - if (qkey) { - id_priv->qkey = qkey; - return 0; - } - switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: @@ -659,6 +648,16 @@ static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) return ret; } +static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) +{ + if (!qkey || + (id_priv->qkey && (id_priv->qkey != qkey))) + return -EINVAL; + + id_priv->qkey = qkey; + return 0; +} + static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; @@ -1229,7 +1228,7 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { - ret = cma_set_qkey(id_priv, 0); + ret = cma_set_default_qkey(id_priv); if (ret) return ret; @@ -4569,7 +4568,10 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv, memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { - ret = cma_set_qkey(id_priv, qkey); + if (qkey) + ret = cma_set_qkey(id_priv, qkey); + else + ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; @@ -4774,9 +4776,7 @@ static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, enum ib_gid_type gid_type; struct net_device *ndev; - if (!status) - status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); - else + if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); @@ -4804,7 +4804,7 @@ static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, } event->param.ud.qp_num = 0xFFFFFF; - event->param.ud.qkey = be32_to_cpu(multicast->rec.qkey); + event->param.ud.qkey = id_priv->qkey; out: if (ndev) @@ -4823,8 +4823,11 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out; - cma_make_mc_event(status, id_priv, multicast, &event, mc); - ret = cma_cm_event_handler(id_priv, &event); + ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); + if (!ret) { + cma_make_mc_event(status, id_priv, multicast, &event, mc); + ret = cma_cm_event_handler(id_priv, &event); + } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret); @@ -4877,9 +4880,11 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, if (ret) return ret; - ret = cma_set_qkey(id_priv, 0); - if (ret) - return ret; + if (!id_priv->qkey) { + ret = cma_set_default_qkey(id_priv); + if (ret) + return ret; + } cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); @@ -4956,9 +4961,6 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); ib.rec.pkey = cpu_to_be16(0xffff); - if (id_priv->id.ps == RDMA_PS_UDP) - ib.rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); - if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) @@ -4984,6 +4986,9 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, if (err || !ib.rec.mtu) return err ?: -EINVAL; + if (!id_priv->qkey) + cma_set_default_qkey(id_priv); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); @@ -5009,6 +5014,9 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL; + if (id_priv->id.qp_type != IB_QPT_UD) + return -EINVAL; + mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 11b1c1603aeb..b99b3cc283b6 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -532,6 +532,8 @@ static struct ib_ah *_rdma_create_ah(struct ib_pd *pd, else ret = device->ops.create_ah(ah, &init_attr, NULL); if (ret) { + if (ah->sgid_attr) + rdma_put_gid_attr(ah->sgid_attr); kfree(ah); return ERR_PTR(ret); } diff --git a/drivers/infiniband/hw/erdma/erdma_cq.c b/drivers/infiniband/hw/erdma/erdma_cq.c index cabd8678b355..7bc354273d4e 100644 --- a/drivers/infiniband/hw/erdma/erdma_cq.c +++ b/drivers/infiniband/hw/erdma/erdma_cq.c @@ -65,7 +65,7 @@ static const enum ib_wc_opcode wc_mapping_table[ERDMA_NUM_OPCODES] = { [ERDMA_OP_LOCAL_INV] = IB_WC_LOCAL_INV, [ERDMA_OP_READ_WITH_INV] = IB_WC_RDMA_READ, [ERDMA_OP_ATOMIC_CAS] = IB_WC_COMP_SWAP, - [ERDMA_OP_ATOMIC_FAD] = IB_WC_FETCH_ADD, + [ERDMA_OP_ATOMIC_FAA] = IB_WC_FETCH_ADD, }; static const struct { diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h index 4c38d99c73f1..37ad1bb1917c 100644 --- a/drivers/infiniband/hw/erdma/erdma_hw.h +++ b/drivers/infiniband/hw/erdma/erdma_hw.h @@ -441,7 +441,7 @@ struct erdma_reg_mr_sqe { }; /* EQ related. */ -#define ERDMA_DEFAULT_EQ_DEPTH 256 +#define ERDMA_DEFAULT_EQ_DEPTH 4096 /* ceqe */ #define ERDMA_CEQE_HDR_DB_MASK BIT_ULL(63) @@ -491,7 +491,7 @@ enum erdma_opcode { ERDMA_OP_LOCAL_INV = 15, ERDMA_OP_READ_WITH_INV = 16, ERDMA_OP_ATOMIC_CAS = 17, - ERDMA_OP_ATOMIC_FAD = 18, + ERDMA_OP_ATOMIC_FAA = 18, ERDMA_NUM_OPCODES = 19, ERDMA_OP_INVALID = ERDMA_NUM_OPCODES + 1 }; diff --git a/drivers/infiniband/hw/erdma/erdma_main.c b/drivers/infiniband/hw/erdma/erdma_main.c index 5dc31e5df5cb..4a29a53a6652 100644 --- a/drivers/infiniband/hw/erdma/erdma_main.c +++ b/drivers/infiniband/hw/erdma/erdma_main.c @@ -56,7 +56,7 @@ done: static int erdma_enum_and_get_netdev(struct erdma_dev *dev) { struct net_device *netdev; - int ret = -ENODEV; + int ret = -EPROBE_DEFER; /* Already binded to a net_device, so we skip. */ if (dev->netdev) diff --git a/drivers/infiniband/hw/erdma/erdma_qp.c b/drivers/infiniband/hw/erdma/erdma_qp.c index d088d6bef431..44923c51a01b 100644 --- a/drivers/infiniband/hw/erdma/erdma_qp.c +++ b/drivers/infiniband/hw/erdma/erdma_qp.c @@ -405,7 +405,7 @@ static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi, FIELD_PREP(ERDMA_SQE_MR_MTT_CNT_MASK, mr->mem.mtt_nents); - if (mr->mem.mtt_nents < ERDMA_MAX_INLINE_MTT_ENTRIES) { + if (mr->mem.mtt_nents <= ERDMA_MAX_INLINE_MTT_ENTRIES) { attrs |= FIELD_PREP(ERDMA_SQE_MR_MTT_TYPE_MASK, 0); /* Copy SGLs to SQE content to accelerate */ memcpy(get_queue_entry(qp->kern_qp.sq_buf, idx + 1, @@ -439,7 +439,7 @@ static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi, cpu_to_le64(atomic_wr(send_wr)->compare_add); } else { wqe_hdr |= FIELD_PREP(ERDMA_SQE_HDR_OPCODE_MASK, - ERDMA_OP_ATOMIC_FAD); + ERDMA_OP_ATOMIC_FAA); atomic_sqe->fetchadd_swap_data = cpu_to_le64(atomic_wr(send_wr)->compare_add); } diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.h b/drivers/infiniband/hw/erdma/erdma_verbs.h index e0a993bc032a..131cf5f40982 100644 --- a/drivers/infiniband/hw/erdma/erdma_verbs.h +++ b/drivers/infiniband/hw/erdma/erdma_verbs.h @@ -11,7 +11,7 @@ /* RDMA Capability. */ #define ERDMA_MAX_PD (128 * 1024) -#define ERDMA_MAX_SEND_WR 4096 +#define ERDMA_MAX_SEND_WR 8192 #define ERDMA_MAX_ORD 128 #define ERDMA_MAX_IRD 128 #define ERDMA_MAX_SGE_RD 1 diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 195aa9ea18b6..8817864154af 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -1458,13 +1458,15 @@ static int irdma_send_fin(struct irdma_cm_node *cm_node) * irdma_find_listener - find a cm node listening on this addr-port pair * @cm_core: cm's core * @dst_addr: listener ip addr + * @ipv4: flag indicating IPv4 when true * @dst_port: listener tcp port num * @vlan_id: virtual LAN ID * @listener_state: state to match with listen node's */ static struct irdma_cm_listener * -irdma_find_listener(struct irdma_cm_core *cm_core, u32 *dst_addr, u16 dst_port, - u16 vlan_id, enum irdma_cm_listener_state listener_state) +irdma_find_listener(struct irdma_cm_core *cm_core, u32 *dst_addr, bool ipv4, + u16 dst_port, u16 vlan_id, + enum irdma_cm_listener_state listener_state) { struct irdma_cm_listener *listen_node; static const u32 ip_zero[4] = { 0, 0, 0, 0 }; @@ -1477,7 +1479,7 @@ irdma_find_listener(struct irdma_cm_core *cm_core, u32 *dst_addr, u16 dst_port, list_for_each_entry (listen_node, &cm_core->listen_list, list) { memcpy(listen_addr, listen_node->loc_addr, sizeof(listen_addr)); listen_port = listen_node->loc_port; - if (listen_port != dst_port || + if (listen_node->ipv4 != ipv4 || listen_port != dst_port || !(listener_state & listen_node->listener_state)) continue; /* compare node pair, return node handle if a match */ @@ -2902,9 +2904,10 @@ irdma_make_listen_node(struct irdma_cm_core *cm_core, unsigned long flags; /* cannot have multiple matching listeners */ - listener = irdma_find_listener(cm_core, cm_info->loc_addr, - cm_info->loc_port, cm_info->vlan_id, - IRDMA_CM_LISTENER_EITHER_STATE); + listener = + irdma_find_listener(cm_core, cm_info->loc_addr, cm_info->ipv4, + cm_info->loc_port, cm_info->vlan_id, + IRDMA_CM_LISTENER_EITHER_STATE); if (listener && listener->listener_state == IRDMA_CM_LISTENER_ACTIVE_STATE) { refcount_dec(&listener->refcnt); @@ -3153,6 +3156,7 @@ void irdma_receive_ilq(struct irdma_sc_vsi *vsi, struct irdma_puda_buf *rbuf) listener = irdma_find_listener(cm_core, cm_info.loc_addr, + cm_info.ipv4, cm_info.loc_port, cm_info.vlan_id, IRDMA_CM_LISTENER_ACTIVE_STATE); diff --git a/drivers/infiniband/hw/irdma/cm.h b/drivers/infiniband/hw/irdma/cm.h index 19c284975fc7..7feadb3e1eda 100644 --- a/drivers/infiniband/hw/irdma/cm.h +++ b/drivers/infiniband/hw/irdma/cm.h @@ -41,7 +41,7 @@ #define TCP_OPTIONS_PADDING 3 #define IRDMA_DEFAULT_RETRYS 64 -#define IRDMA_DEFAULT_RETRANS 8 +#define IRDMA_DEFAULT_RETRANS 32 #define IRDMA_DEFAULT_TTL 0x40 #define IRDMA_DEFAULT_RTT_VAR 6 #define IRDMA_DEFAULT_SS_THRESH 0x3fffffff diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 2e1e2bad0401..43dfa4761f06 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -41,6 +41,7 @@ static enum irdma_hmc_rsrc_type iw_hmc_obj_types[] = { IRDMA_HMC_IW_XFFL, IRDMA_HMC_IW_Q1, IRDMA_HMC_IW_Q1FL, + IRDMA_HMC_IW_PBLE, IRDMA_HMC_IW_TIMER, IRDMA_HMC_IW_FSIMC, IRDMA_HMC_IW_FSIAV, @@ -827,6 +828,8 @@ static int irdma_create_hmc_objs(struct irdma_pci_f *rf, bool privileged, info.entry_type = rf->sd_type; for (i = 0; i < IW_HMC_OBJ_TYPE_NUM; i++) { + if (iw_hmc_obj_types[i] == IRDMA_HMC_IW_PBLE) + continue; if (dev->hmc_info->hmc_obj[iw_hmc_obj_types[i]].cnt) { info.rsrc_type = iw_hmc_obj_types[i]; info.count = dev->hmc_info->hmc_obj[info.rsrc_type].cnt; diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 445e69e86409..7887230c867b 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -2595,7 +2595,10 @@ void irdma_generate_flush_completions(struct irdma_qp *iwqp) /* remove the SQ WR by moving SQ tail*/ IRDMA_RING_SET_TAIL(*sq_ring, sq_ring->tail + qp->sq_wrtrk_array[sq_ring->tail].quanta); - + if (cmpl->cpi.op_type == IRDMAQP_OP_NOP) { + kfree(cmpl); + continue; + } ibdev_dbg(iwqp->iwscq->ibcq.device, "DEV: %s: adding wr_id = 0x%llx SQ Completion to list qp_id=%d\n", __func__, cmpl->cpi.wr_id, qp->qp_id); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5b988db66b8f..5d45de223c43 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -442,6 +442,10 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u16 *active_speed, *active_width = IB_WIDTH_2X; *active_speed = IB_SPEED_NDR; break; + case MLX5E_PROT_MASK(MLX5E_400GAUI_8): + *active_width = IB_WIDTH_8X; + *active_speed = IB_SPEED_HDR; + break; case MLX5E_PROT_MASK(MLX5E_400GAUI_4_400GBASE_CR4_KR4): *active_width = IB_WIDTH_4X; *active_speed = IB_SPEED_NDR; diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index f8d92c9bb65b..3c47846cc5ef 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -294,9 +294,9 @@ static void batch_clear_carry(struct pfn_batch *batch, unsigned int keep_pfns) batch->npfns[batch->end - 1] < keep_pfns); batch->total_pfns = keep_pfns; - batch->npfns[0] = keep_pfns; batch->pfns[0] = batch->pfns[batch->end - 1] + (batch->npfns[batch->end - 1] - keep_pfns); + batch->npfns[0] = keep_pfns; batch->end = 0; } @@ -1142,6 +1142,7 @@ struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, bool writable) { struct iopt_pages *pages; + unsigned long end; /* * The iommu API uses size_t as the length, and protect the DIV_ROUND_UP @@ -1150,6 +1151,9 @@ struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, if (length > SIZE_MAX - PAGE_SIZE || length == 0) return ERR_PTR(-EINVAL); + if (check_add_overflow((unsigned long)uptr, length, &end)) + return ERR_PTR(-EOVERFLOW); + pages = kzalloc(sizeof(*pages), GFP_KERNEL_ACCOUNT); if (!pages) return ERR_PTR(-ENOMEM); @@ -1203,13 +1207,21 @@ iopt_area_unpin_domain(struct pfn_batch *batch, struct iopt_area *area, unsigned long start = max(start_index, *unmapped_end_index); + if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + batch->total_pfns) + WARN_ON(*unmapped_end_index - + batch->total_pfns != + start_index); batch_from_domain(batch, domain, area, start, last_index); - batch_last_index = start + batch->total_pfns - 1; + batch_last_index = start_index + batch->total_pfns - 1; } else { batch_last_index = last_index; } + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(batch_last_index > real_last_index); + /* * unmaps must always 'cut' at a place where the pfns are not * contiguous to pair with the maps that always install diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index bf7667845459..bbfaf6536903 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -410,6 +410,7 @@ static struct memstick_dev *memstick_alloc_card(struct memstick_host *host) return card; err_out: host->card = old_card; + kfree_const(card->dev.kobj.name); kfree(card); return NULL; } @@ -468,8 +469,10 @@ static void memstick_check(struct work_struct *work) put_device(&card->dev); host->card = NULL; } - } else + } else { + kfree_const(card->dev.kobj.name); kfree(card); + } } out_power_off: diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index 89953093e20c..672d37ea98d0 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -351,8 +351,6 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg) */ case MMC_TIMING_SD_HS: case MMC_TIMING_MMC_HS: - case MMC_TIMING_UHS_SDR12: - case MMC_TIMING_UHS_SDR25: val &= ~SDHCI_CTRL_HISPD; } } diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c index 1e94e7d10b8b..a0a1194dc1d9 100644 --- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -153,7 +153,7 @@ static int do_cached_write (struct mtdblk_dev *mtdblk, unsigned long pos, mtdblk->cache_state = STATE_EMPTY; ret = mtd_read(mtd, sect_start, sect_size, &retlen, mtdblk->cache_data); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != sect_size) return -EIO; @@ -188,8 +188,12 @@ static int do_cached_read (struct mtdblk_dev *mtdblk, unsigned long pos, pr_debug("mtdblock: read on \"%s\" at 0x%lx, size 0x%x\n", mtd->name, pos, len); - if (!sect_size) - return mtd_read(mtd, pos, len, &retlen, buf); + if (!sect_size) { + ret = mtd_read(mtd, pos, len, &retlen, buf); + if (ret && !mtd_is_bitflip(ret)) + return ret; + return 0; + } while (len > 0) { unsigned long sect_start = (pos/sect_size)*sect_size; @@ -209,7 +213,7 @@ static int do_cached_read (struct mtdblk_dev *mtdblk, unsigned long pos, memcpy (buf, mtdblk->cache_data + offset, size); } else { ret = mtd_read(mtd, pos, size, &retlen, buf); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != size) return -EIO; diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index a28574c00900..074e14225c06 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -280,7 +280,7 @@ static void meson_nfc_cmd_access(struct nand_chip *nand, int raw, bool dir, if (raw) { len = mtd->writesize + mtd->oobsize; - cmd = (len & GENMASK(5, 0)) | scrambler | DMA_DIR(dir); + cmd = (len & GENMASK(13, 0)) | scrambler | DMA_DIR(dir); writel(cmd, nfc->reg_base + NFC_REG_CMD); return; } @@ -544,7 +544,7 @@ static int meson_nfc_read_buf(struct nand_chip *nand, u8 *buf, int len) if (ret) goto out; - cmd = NFC_CMD_N2M | (len & GENMASK(5, 0)); + cmd = NFC_CMD_N2M | (len & GENMASK(13, 0)); writel(cmd, nfc->reg_base + NFC_REG_CMD); meson_nfc_drain_cmd(nfc); @@ -568,7 +568,7 @@ static int meson_nfc_write_buf(struct nand_chip *nand, u8 *buf, int len) if (ret) return ret; - cmd = NFC_CMD_M2N | (len & GENMASK(5, 0)); + cmd = NFC_CMD_M2N | (len & GENMASK(13, 0)); writel(cmd, nfc->reg_base + NFC_REG_CMD); meson_nfc_drain_cmd(nfc); diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 5d627048c420..9e74bcd90aaa 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1531,6 +1531,9 @@ static int stm32_fmc2_nfc_setup_interface(struct nand_chip *chip, int chipnr, if (IS_ERR(sdrt)) return PTR_ERR(sdrt); + if (conf->timings.mode > 3) + return -EOPNOTSUPP; + if (chipnr == NAND_DATA_IFACE_CHECK_ONLY) return 0; diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 0904eb40c95f..ad025b2ee417 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -666,12 +666,6 @@ static int io_init(struct ubi_device *ubi, int max_beb_per1024) ubi->ec_hdr_alsize = ALIGN(UBI_EC_HDR_SIZE, ubi->hdrs_min_io_size); ubi->vid_hdr_alsize = ALIGN(UBI_VID_HDR_SIZE, ubi->hdrs_min_io_size); - if (ubi->vid_hdr_offset && ((ubi->vid_hdr_offset + UBI_VID_HDR_SIZE) > - ubi->vid_hdr_alsize)) { - ubi_err(ubi, "VID header offset %d too large.", ubi->vid_hdr_offset); - return -EINVAL; - } - dbg_gen("min_io_size %d", ubi->min_io_size); dbg_gen("max_write_size %d", ubi->max_write_size); dbg_gen("hdrs_min_io_size %d", ubi->hdrs_min_io_size); @@ -689,6 +683,21 @@ static int io_init(struct ubi_device *ubi, int max_beb_per1024) ubi->vid_hdr_aloffset; } + /* + * Memory allocation for VID header is ubi->vid_hdr_alsize + * which is described in comments in io.c. + * Make sure VID header shift + UBI_VID_HDR_SIZE not exceeds + * ubi->vid_hdr_alsize, so that all vid header operations + * won't access memory out of bounds. + */ + if ((ubi->vid_hdr_shift + UBI_VID_HDR_SIZE) > ubi->vid_hdr_alsize) { + ubi_err(ubi, "Invalid VID header offset %d, VID header shift(%d)" + " + VID header size(%zu) > VID header aligned size(%d).", + ubi->vid_hdr_offset, ubi->vid_hdr_shift, + UBI_VID_HDR_SIZE, ubi->vid_hdr_alsize); + return -EINVAL; + } + /* Similar for the data offset */ ubi->leb_start = ubi->vid_hdr_offset + UBI_VID_HDR_SIZE; ubi->leb_start = ALIGN(ubi->leb_start, ubi->min_io_size); diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 40f39e5d6dfc..26a214f016c1 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -575,7 +575,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, * @vol_id: the volume ID that last used this PEB * @lnum: the last used logical eraseblock number for the PEB * @torture: if the physical eraseblock has to be tortured - * @nested: denotes whether the work_sem is already held in read mode + * @nested: denotes whether the work_sem is already held * * This function returns zero in case of success and a %-ENOMEM in case of * failure. @@ -1131,7 +1131,7 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) int err1; /* Re-schedule the LEB for erasure */ - err1 = schedule_erase(ubi, e, vol_id, lnum, 0, false); + err1 = schedule_erase(ubi, e, vol_id, lnum, 0, true); if (err1) { spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 236e5219c811..7a7d584f378a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1777,14 +1777,15 @@ void bond_lower_state_changed(struct slave *slave) /* The bonding driver uses ether_setup() to convert a master bond device * to ARPHRD_ETHER, that resets the target netdevice's flags so we always - * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE if it was set + * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP + * if they were set */ static void bond_ether_setup(struct net_device *bond_dev) { - unsigned int slave_flag = bond_dev->flags & IFF_SLAVE; + unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP); ether_setup(bond_dev); - bond_dev->flags |= IFF_MASTER | slave_flag; + bond_dev->flags |= IFF_MASTER | flags; bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; } @@ -3269,7 +3270,8 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || - combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT) + (combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && + combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) goto out; saddr = &combined->ip6.saddr; @@ -3291,7 +3293,7 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) - bond_validate_na(bond, slave, saddr, daddr); + bond_validate_na(bond, slave, daddr, saddr); else if (curr_arp_slave && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_na(bond, slave, saddr, daddr); diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 3fffd5da8d3b..ffcad057d065 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -96,7 +96,7 @@ static int ksz8795_change_mtu(struct ksz_device *dev, int frame_size) if (frame_size > KSZ8_LEGAL_PACKET_SIZE) ctrl2 |= SW_LEGAL_PACKET_DISABLE; - else if (frame_size > KSZ8863_NORMAL_PACKET_SIZE) + if (frame_size > KSZ8863_NORMAL_PACKET_SIZE) ctrl1 |= SW_HUGE_PACKET; ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_HUGE_PACKET, ctrl1); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 0de7b3611202..7108f745fbf0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -5601,7 +5601,7 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = { * .port_set_upstream_port method. */ .set_egress_port = mv88e6393x_set_egress_port, - .watchdog_ops = &mv88e6390_watchdog_ops, + .watchdog_ops = &mv88e6393x_watchdog_ops, .mgmt_rsvd2cpu = mv88e6393x_port_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index ed3b2f88e783..a7af3cebae97 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -943,6 +943,26 @@ const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops = { .irq_free = mv88e6390_watchdog_free, }; +static int mv88e6393x_watchdog_action(struct mv88e6xxx_chip *chip, int irq) +{ + mv88e6390_watchdog_action(chip, irq); + + /* Fix for clearing the force WD event bit. + * Unreleased erratum on mv88e6393x. + */ + mv88e6xxx_g2_write(chip, MV88E6390_G2_WDOG_CTL, + MV88E6390_G2_WDOG_CTL_UPDATE | + MV88E6390_G2_WDOG_CTL_PTR_EVENT); + + return IRQ_HANDLED; +} + +const struct mv88e6xxx_irq_ops mv88e6393x_watchdog_ops = { + .irq_action = mv88e6393x_watchdog_action, + .irq_setup = mv88e6390_watchdog_setup, + .irq_free = mv88e6390_watchdog_free, +}; + static irqreturn_t mv88e6xxx_g2_watchdog_thread_fn(int irq, void *dev_id) { struct mv88e6xxx_chip *chip = dev_id; diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index e973114d6890..7e091965582b 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -369,6 +369,7 @@ int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target, extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops; extern const struct mv88e6xxx_irq_ops mv88e6250_watchdog_ops; extern const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops; +extern const struct mv88e6xxx_irq_ops mv88e6393x_watchdog_ops; extern const struct mv88e6xxx_avb_ops mv88e6165_avb_ops; extern const struct mv88e6xxx_avb_ops mv88e6352_avb_ops; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c23e3b397bcf..651b79ce5d80 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2388,7 +2388,7 @@ static int bnxt_async_event_process(struct bnxt *bp, case ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE: { switch (BNXT_EVENT_PHC_EVENT_TYPE(data1)) { case ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE: - if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + if (BNXT_PTP_USE_RTC(bp)) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; u64 ns; @@ -7627,7 +7627,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) u8 flags; int rc; - if (bp->hwrm_spec_code < 0x10801) { + if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5_THOR(bp)) { rc = -ENODEV; goto no_ptp; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index e7b5e28ee29f..852eb449ccae 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -304,7 +304,7 @@ void bnxt_rdma_aux_device_uninit(struct bnxt *bp) struct auxiliary_device *adev; /* Skip if no auxiliary device init was done. */ - if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) + if (!bp->aux_priv) return; aux_priv = bp->aux_priv; @@ -324,6 +324,7 @@ static void bnxt_aux_dev_release(struct device *dev) bp->edev = NULL; kfree(aux_priv->edev); kfree(aux_priv); + bp->aux_priv = NULL; } static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp) @@ -359,19 +360,18 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp) if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) return; - bp->aux_priv = kzalloc(sizeof(*bp->aux_priv), GFP_KERNEL); - if (!bp->aux_priv) + aux_priv = kzalloc(sizeof(*bp->aux_priv), GFP_KERNEL); + if (!aux_priv) goto exit; - bp->aux_priv->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL); - if (bp->aux_priv->id < 0) { + aux_priv->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL); + if (aux_priv->id < 0) { netdev_warn(bp->dev, "ida alloc failed for ROCE auxiliary device\n"); - kfree(bp->aux_priv); + kfree(aux_priv); goto exit; } - aux_priv = bp->aux_priv; aux_dev = &aux_priv->aux_dev; aux_dev->id = aux_priv->id; aux_dev->name = "rdma"; @@ -380,10 +380,11 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp) rc = auxiliary_device_init(aux_dev); if (rc) { - ida_free(&bnxt_aux_dev_ids, bp->aux_priv->id); - kfree(bp->aux_priv); + ida_free(&bnxt_aux_dev_ids, aux_priv->id); + kfree(aux_priv); goto exit; } + bp->aux_priv = aux_priv; /* From this point, all cleanup will happen via the .release callback & * any error unwinding will need to include a call to diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 66e30561569e..e43d99ec50ba 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1064,6 +1064,10 @@ static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc) } #endif addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr)); +#ifdef CONFIG_MACB_USE_HWSTAMP + if (bp->hw_dma_cap & HW_DMA_CAP_PTP) + addr &= ~GEM_BIT(DMA_RXVALID); +#endif return addr; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index dd9be229819a..d3541159487d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -1135,7 +1135,7 @@ void cxgb4_cleanup_tc_flower(struct adapter *adap) return; if (adap->flower_stats_timer.function) - del_timer_sync(&adap->flower_stats_timer); + timer_shutdown_sync(&adap->flower_stats_timer); cancel_work_sync(&adap->flower_stats_work); rhashtable_destroy(&adap->flower_tbl); adap->tc_flower_initialized = false; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index da9d4b310fcd..838750a03cf6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -989,6 +989,20 @@ static int enetc_get_mm(struct net_device *ndev, struct ethtool_mm_state *state) return 0; } +/* FIXME: Workaround for the link partner's verification failing if ENETC + * priorly received too much express traffic. The documentation doesn't + * suggest this is needed. + */ +static void enetc_restart_emac_rx(struct enetc_si *si) +{ + u32 val = enetc_port_rd(&si->hw, ENETC_PM0_CMD_CFG); + + enetc_port_wr(&si->hw, ENETC_PM0_CMD_CFG, val & ~ENETC_PM0_RX_EN); + + if (val & ENETC_PM0_RX_EN) + enetc_port_wr(&si->hw, ENETC_PM0_CMD_CFG, val); +} + static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { @@ -1040,6 +1054,8 @@ static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, enetc_port_wr(hw, ENETC_MMCSR, val); + enetc_restart_emac_rx(priv->si); + mutex_unlock(&priv->mm_lock); return 0; diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 5ba1e0d71c68..9939ccafb556 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -507,6 +507,11 @@ struct bufdesc_ex { /* i.MX6Q adds pm_qos support */ #define FEC_QUIRK_HAS_PMQOS BIT(23) +/* Not all FEC hardware block MDIOs support accesses in C45 mode. + * Older blocks in the ColdFire parts do not support it. + */ +#define FEC_QUIRK_HAS_MDIO_C45 BIT(24) + struct bufdesc_prop { int qid; /* Address of Rx and Tx buffers */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f3b16a6673e2..160c1b3525f5 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -100,18 +100,19 @@ struct fec_devinfo { static const struct fec_devinfo fec_imx25_info = { .quirks = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR | - FEC_QUIRK_HAS_FRREG, + FEC_QUIRK_HAS_FRREG | FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_imx27_info = { - .quirks = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG, + .quirks = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG | + FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_imx28_info = { .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME | FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII | - FEC_QUIRK_NO_HARD_RESET, + FEC_QUIRK_NO_HARD_RESET | FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_imx6q_info = { @@ -119,11 +120,12 @@ static const struct fec_devinfo fec_imx6q_info = { FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 | FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII | - FEC_QUIRK_HAS_PMQOS, + FEC_QUIRK_HAS_PMQOS | FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_mvf600_info = { - .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC, + .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC | + FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_imx6x_info = { @@ -132,7 +134,8 @@ static const struct fec_devinfo fec_imx6x_info = { FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB | FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE | - FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES, + FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES | + FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_imx6ul_info = { @@ -140,7 +143,8 @@ static const struct fec_devinfo fec_imx6ul_info = { FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII, + FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII | + FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_imx8mq_info = { @@ -150,7 +154,8 @@ static const struct fec_devinfo fec_imx8mq_info = { FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES | - FEC_QUIRK_HAS_EEE | FEC_QUIRK_WAKEUP_FROM_INT2, + FEC_QUIRK_HAS_EEE | FEC_QUIRK_WAKEUP_FROM_INT2 | + FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_imx8qm_info = { @@ -160,14 +165,15 @@ static const struct fec_devinfo fec_imx8qm_info = { FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES | - FEC_QUIRK_DELAYED_CLKS_SUPPORT, + FEC_QUIRK_DELAYED_CLKS_SUPPORT | FEC_QUIRK_HAS_MDIO_C45, }; static const struct fec_devinfo fec_s32v234_info = { .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB | - FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE, + FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | + FEC_QUIRK_HAS_MDIO_C45, }; static struct platform_device_id fec_devtype[] = { @@ -2434,8 +2440,10 @@ static int fec_enet_mii_init(struct platform_device *pdev) fep->mii_bus->name = "fec_enet_mii_bus"; fep->mii_bus->read = fec_enet_mdio_read_c22; fep->mii_bus->write = fec_enet_mdio_write_c22; - fep->mii_bus->read_c45 = fec_enet_mdio_read_c45; - fep->mii_bus->write_c45 = fec_enet_mdio_write_c45; + if (fep->quirks & FEC_QUIRK_HAS_MDIO_C45) { + fep->mii_bus->read_c45 = fec_enet_mdio_read_c45; + fep->mii_bus->write_c45 = fec_enet_mdio_write_c45; + } snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", pdev->name, fep->dev_id + 1); fep->mii_bus->priv = fep; diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 64eb0442c82f..005cb9dfe078 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -47,6 +47,8 @@ #define GVE_RX_BUFFER_SIZE_DQO 2048 +#define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182 + /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */ struct gve_rx_desc_queue { struct gve_rx_desc *desc_ring; /* the descriptor ring */ diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 4888bf05fbed..5e11b8236754 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -284,8 +284,8 @@ static inline int gve_skb_fifo_bytes_required(struct gve_tx_ring *tx, int bytes; int hlen; - hlen = skb_is_gso(skb) ? skb_checksum_start_offset(skb) + - tcp_hdrlen(skb) : skb_headlen(skb); + hlen = skb_is_gso(skb) ? skb_checksum_start_offset(skb) + tcp_hdrlen(skb) : + min_t(int, GVE_GQ_TX_MIN_PKT_DESC_BYTES, skb->len); pad_bytes = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo, hlen); @@ -454,13 +454,11 @@ static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, st pkt_desc = &tx->desc[idx]; l4_hdr_offset = skb_checksum_start_offset(skb); - /* If the skb is gso, then we want the tcp header in the first segment - * otherwise we want the linear portion of the skb (which will contain - * the checksum because skb->csum_start and skb->csum_offset are given - * relative to skb->head) in the first segment. + /* If the skb is gso, then we want the tcp header alone in the first segment + * otherwise we want the minimum required by the gVNIC spec. */ hlen = is_gso ? l4_hdr_offset + tcp_hdrlen(skb) : - skb_headlen(skb); + min_t(int, GVE_GQ_TX_MIN_PKT_DESC_BYTES, skb->len); info->skb = skb; /* We don't want to split the header, so if necessary, pad to the end diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e1eb1de88bf9..e14d1e45318f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5288,31 +5288,6 @@ static void e1000_watchdog_task(struct work_struct *work) ew32(TARC(0), tarc0); } - /* disable TSO for pcie and 10/100 speeds, to avoid - * some hardware issues - */ - if (!(adapter->flags & FLAG_TSO_FORCE)) { - switch (adapter->link_speed) { - case SPEED_10: - case SPEED_100: - e_info("10/100 speed: disabling TSO\n"); - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - break; - case SPEED_1000: - netdev->features |= NETIF_F_TSO; - netdev->features |= NETIF_F_TSO6; - break; - default: - /* oops */ - break; - } - if (hw->mac.type == e1000_pch_spt) { - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - } - } - /* enable transmits in the hardware, need to do this * after setting TARC(0) */ @@ -7526,6 +7501,32 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_RXCSUM | NETIF_F_HW_CSUM); + /* disable TSO for pcie and 10/100 speeds to avoid + * some hardware issues and for i219 to fix transfer + * speed being capped at 60% + */ + if (!(adapter->flags & FLAG_TSO_FORCE)) { + switch (adapter->link_speed) { + case SPEED_10: + case SPEED_100: + e_info("10/100 speed: disabling TSO\n"); + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + break; + case SPEED_1000: + netdev->features |= NETIF_F_TSO; + netdev->features |= NETIF_F_TSO6; + break; + default: + /* oops */ + break; + } + if (hw->mac.type == e1000_pch_spt) { + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + } + } + /* Set user-changeable features (subset of all device features) */ netdev->hw_features = netdev->features; netdev->hw_features |= NETIF_F_RXFCS; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 228cd502bb48..7c30abd0dfc2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11059,8 +11059,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) pf->hw.aq.asq_last_status)); } /* reinit the misc interrupt */ - if (pf->flags & I40E_FLAG_MSIX_ENABLED) + if (pf->flags & I40E_FLAG_MSIX_ENABLED) { ret = i40e_setup_misc_vector(pf); + if (ret) + goto end_unlock; + } /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -14133,15 +14136,15 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->id = ctxt.vsi_number; } - vsi->active_filters = 0; - clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); spin_lock_bh(&vsi->mac_filter_hash_lock); + vsi->active_filters = 0; /* If macvlan filters already exist, force them to get loaded */ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { f->state = I40E_FILTER_NEW; f_count++; } spin_unlock_bh(&vsi->mac_filter_hash_lock); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 232bc61d9eee..746ff76f2fb1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -59,8 +59,6 @@ enum iavf_vsi_state_t { struct iavf_vsi { struct iavf_adapter *back; struct net_device *netdev; - unsigned long active_cvlans[BITS_TO_LONGS(VLAN_N_VID)]; - unsigned long active_svlans[BITS_TO_LONGS(VLAN_N_VID)]; u16 seid; u16 id; DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); @@ -158,15 +156,20 @@ struct iavf_vlan { u16 tpid; }; +enum iavf_vlan_state_t { + IAVF_VLAN_INVALID, + IAVF_VLAN_ADD, /* filter needs to be added */ + IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ + IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ + IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ + IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ + IAVF_VLAN_REMOVE, /* filter needs to be removed from list */ +}; + struct iavf_vlan_filter { struct list_head list; struct iavf_vlan vlan; - struct { - u8 is_new_vlan:1; /* filter is new, wait for PF answer */ - u8 remove:1; /* filter needs to be removed */ - u8 add:1; /* filter needs to be added */ - u8 padding:5; - }; + enum iavf_vlan_state_t state; }; #define IAVF_MAX_TRAFFIC_CLASS 4 @@ -258,6 +261,7 @@ struct iavf_adapter { wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; + int num_vlan_filters; struct list_head mac_filter_list; struct mutex crit_lock; struct mutex client_lock; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 095201e83c9d..2de4baff4c20 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -791,7 +791,8 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->vlan = vlan; list_add_tail(&f->list, &adapter->vlan_filter_list); - f->add = true; + f->state = IAVF_VLAN_ADD; + adapter->num_vlan_filters++; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -813,7 +814,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->remove = true; + f->state = IAVF_VLAN_REMOVE; adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; } @@ -828,14 +829,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) **/ static void iavf_restore_filters(struct iavf_adapter *adapter) { - u16 vid; + struct iavf_vlan_filter *f; /* re-add all VLAN filters */ - for_each_set_bit(vid, adapter->vsi.active_cvlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021Q)); + spin_lock_bh(&adapter->mac_vlan_list_lock); - for_each_set_bit(vid, adapter->vsi.active_svlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021AD)); + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_INACTIVE) + f->state = IAVF_VLAN_ADD; + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } /** @@ -844,8 +849,7 @@ static void iavf_restore_filters(struct iavf_adapter *adapter) */ u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter) { - return bitmap_weight(adapter->vsi.active_cvlans, VLAN_N_VID) + - bitmap_weight(adapter->vsi.active_svlans, VLAN_N_VID); + return adapter->num_vlan_filters; } /** @@ -928,11 +932,6 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, return 0; iavf_del_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto))); - if (proto == cpu_to_be16(ETH_P_8021Q)) - clear_bit(vid, adapter->vsi.active_cvlans); - else - clear_bit(vid, adapter->vsi.active_svlans); - return 0; } @@ -1293,16 +1292,11 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) } } - /* remove all VLAN filters */ + /* disable all VLAN filters */ list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, - list) { - if (vlf->add) { - list_del(&vlf->list); - kfree(vlf); - } else { - vlf->remove = true; - } - } + list) + vlf->state = IAVF_VLAN_DISABLE; + spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -2914,6 +2908,7 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) list_del(&fv->list); kfree(fv); } + adapter->num_vlan_filters = 0; spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -3131,9 +3126,6 @@ continue_reset: adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); - bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID); - bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2); /* We were running when the reset started, so we need to restore some diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 4e17d006c52d..9afbbdac3590 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -642,16 +642,10 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - if (f->vlan.tpid == ETH_P_8021Q) - clear_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - clear_bit(f->vlan.vid, - adapter->vsi.active_svlans); - + if (f->state == IAVF_VLAN_IS_NEW) { list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -679,7 +673,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) + if (f->state == IAVF_VLAN_ADD) count++; } if (!count || !VLAN_FILTERING_ALLOWED(adapter)) { @@ -710,11 +704,10 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; if (i == count) break; } @@ -760,7 +753,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -778,8 +771,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; } } @@ -822,10 +814,16 @@ void iavf_del_vlans(struct iavf_adapter *adapter) * filters marked for removal to enable bailing out before * sending a virtchnl message */ - if (f->remove && !VLAN_FILTERING_ALLOWED(adapter)) { + if (f->state == IAVF_VLAN_REMOVE && + !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); - } else if (f->remove) { + adapter->num_vlan_filters--; + } else if (f->state == IAVF_VLAN_DISABLE && + !VLAN_FILTERING_ALLOWED(adapter)) { + f->state = IAVF_VLAN_INACTIVE; + } else if (f->state == IAVF_VLAN_REMOVE || + f->state == IAVF_VLAN_DISABLE) { count++; } } @@ -857,11 +855,18 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE) { vvfl->vlan_id[i] = f->vlan.vid; + f->state = IAVF_VLAN_INACTIVE; i++; + if (i == count) + break; + } else if (f->state == IAVF_VLAN_REMOVE) { + vvfl->vlan_id[i] = f->vlan.vid; list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; + i++; if (i == count) break; } @@ -901,7 +906,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE || + f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -915,8 +921,13 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - list_del(&f->list); - kfree(f); + if (f->state == IAVF_VLAN_DISABLE) { + f->state = IAVF_VLAN_INACTIVE; + } else { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } i++; if (i == count) break; @@ -2192,7 +2203,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; @@ -2260,7 +2271,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -2444,15 +2455,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - f->is_new_vlan = false; - if (f->vlan.tpid == ETH_P_8021Q) - set_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - set_bit(f->vlan.vid, - adapter->vsi.active_svlans); - } + if (f->state == IAVF_VLAN_IS_NEW) + f->state = IAVF_VLAN_ACTIVE; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index 5fd75e75772e..daa6a1e894cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -542,6 +542,21 @@ static void ice_vc_fdir_rem_prof_all(struct ice_vf *vf) } /** + * ice_vc_fdir_reset_cnt_all - reset all FDIR counters for this VF FDIR + * @fdir: pointer to the VF FDIR structure + */ +static void ice_vc_fdir_reset_cnt_all(struct ice_vf_fdir *fdir) +{ + enum ice_fltr_ptype flow; + + for (flow = ICE_FLTR_PTYPE_NONF_NONE; + flow < ICE_FLTR_PTYPE_MAX; flow++) { + fdir->fdir_fltr_cnt[flow][0] = 0; + fdir->fdir_fltr_cnt[flow][1] = 0; + } +} + +/** * ice_vc_fdir_has_prof_conflict * @vf: pointer to the VF structure * @conf: FDIR configuration for each filter @@ -1871,7 +1886,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) v_ret = VIRTCHNL_STATUS_SUCCESS; stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; dev_dbg(dev, "VF %d: set FDIR context failed\n", vf->vf_id); - goto err_free_conf; + goto err_rem_entry; } ret = ice_vc_fdir_write_fltr(vf, conf, true, is_tun); @@ -1880,15 +1895,16 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; dev_err(dev, "VF %d: writing FDIR rule failed, ret:%d\n", vf->vf_id, ret); - goto err_rem_entry; + goto err_clr_irq; } exit: kfree(stat); return ret; -err_rem_entry: +err_clr_irq: ice_vc_fdir_clear_irq_ctx(vf); +err_rem_entry: ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); err_free_conf: devm_kfree(dev, conf); @@ -1997,6 +2013,7 @@ void ice_vf_fdir_init(struct ice_vf *vf) spin_lock_init(&fdir->ctx_lock); fdir->ctx_irq.flags = 0; fdir->ctx_done.flags = 0; + ice_vc_fdir_reset_cnt_all(fdir); } /** diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 282f9435d5ff..e14050e17862 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -753,6 +753,7 @@ static void mtk_mac_link_up(struct phylink_config *config, MAC_MCR_FORCE_RX_FC); /* Configure speed */ + mac->speed = speed; switch (speed) { case SPEED_2500: case SPEED_1000: @@ -3235,6 +3236,9 @@ found: if (dp->index >= MTK_QDMA_NUM_QUEUES) return NOTIFY_DONE; + if (mac->speed > 0 && mac->speed <= s.base.speed) + s.base.speed = 0; + mtk_set_queue_speed(eth, dp->index + 3, s.base.speed); return NOTIFY_DONE; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 4b5e459b6d49..332472fe4990 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -681,14 +681,32 @@ int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { struct mlx4_en_xdp_buff *_ctx = (void *)ctx; + struct mlx4_cqe *cqe = _ctx->cqe; + enum xdp_rss_hash_type xht = 0; + __be16 status; if (unlikely(!(_ctx->dev->features & NETIF_F_RXHASH))) return -ENODATA; - *hash = be32_to_cpu(_ctx->cqe->immed_rss_invalid); + *hash = be32_to_cpu(cqe->immed_rss_invalid); + status = cqe->status; + if (status & cpu_to_be16(MLX4_CQE_STATUS_TCP)) + xht = XDP_RSS_L4_TCP; + if (status & cpu_to_be16(MLX4_CQE_STATUS_UDP)) + xht = XDP_RSS_L4_UDP; + if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV4F)) + xht |= XDP_RSS_L3_IPV4; + if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) { + xht |= XDP_RSS_L3_IPV6; + if (cqe->ipv6_ext_mask) + xht |= XDP_RSS_L3_DYNHDR; + } + *rss_type = xht; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 544e09b97483..4ac4d883047b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -798,7 +798,8 @@ int mlx4_en_netdev_event(struct notifier_block *this, struct xdp_md; int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp); -int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash); +int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); /* * Functions for time stamping diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 445fe30c3d0b..2e7806001fdc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -59,9 +59,6 @@ bool mlx5_eth_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_CORE_EN)) return false; - if (mlx5_core_is_management_pf(dev)) - return false; - if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return false; @@ -201,9 +198,6 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev) if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return false; - if (mlx5_core_is_management_pf(dev)) - return false; - if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 7c9c4e40c019..d000236ddbac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -75,10 +75,6 @@ int mlx5_ec_init(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return 0; - /* Management PF don't have a peer PF */ - if (mlx5_core_is_management_pf(dev)) - return 0; - return mlx5_host_pf_init(dev); } @@ -89,10 +85,6 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) if (!mlx5_core_is_ecpf(dev)) return; - /* Management PF don't have a peer PF */ - if (mlx5_core_is_management_pf(dev)) - return; - mlx5_host_pf_cleanup(dev); err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index c5dae48b7932..d9d3b9e1f15a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -34,6 +34,7 @@ #include <net/xdp_sock_drv.h> #include "en/xdp.h" #include "en/params.h" +#include <linux/bitfield.h> int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { @@ -169,14 +170,72 @@ static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +/* Mapping HW RSS Type bits CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 into 4-bits*/ +#define RSS_TYPE_MAX_TABLE 16 /* 4-bits max 16 entries */ +#define RSS_L4 GENMASK(1, 0) +#define RSS_L3 GENMASK(3, 2) /* Same as CQE_RSS_HTYPE_IP */ + +/* Valid combinations of CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 sorted numerical */ +enum mlx5_rss_hash_type { + RSS_TYPE_NO_HASH = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IP_NONE) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L3_IPV4 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L4_IPV4_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)), + RSS_TYPE_L4_IPV4_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)), + RSS_TYPE_L4_IPV4_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)), + RSS_TYPE_L3_IPV6 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L4_IPV6_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)), + RSS_TYPE_L4_IPV6_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)), + RSS_TYPE_L4_IPV6_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)), +}; + +/* Invalid combinations will simply return zero, allows no boundary checks */ +static const enum xdp_rss_hash_type mlx5_xdp_rss_type[RSS_TYPE_MAX_TABLE] = { + [RSS_TYPE_NO_HASH] = XDP_RSS_TYPE_NONE, + [1] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [2] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [3] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [RSS_TYPE_L3_IPV4] = XDP_RSS_TYPE_L3_IPV4, + [RSS_TYPE_L4_IPV4_TCP] = XDP_RSS_TYPE_L4_IPV4_TCP, + [RSS_TYPE_L4_IPV4_UDP] = XDP_RSS_TYPE_L4_IPV4_UDP, + [RSS_TYPE_L4_IPV4_IPSEC] = XDP_RSS_TYPE_L4_IPV4_IPSEC, + [RSS_TYPE_L3_IPV6] = XDP_RSS_TYPE_L3_IPV6, + [RSS_TYPE_L4_IPV6_TCP] = XDP_RSS_TYPE_L4_IPV6_TCP, + [RSS_TYPE_L4_IPV6_UDP] = XDP_RSS_TYPE_L4_IPV6_UDP, + [RSS_TYPE_L4_IPV6_IPSEC] = XDP_RSS_TYPE_L4_IPV6_IPSEC, + [12] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [13] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [14] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [15] = XDP_RSS_TYPE_NONE, /* Implicit zero */ +}; + +static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { const struct mlx5e_xdp_buff *_ctx = (void *)ctx; + const struct mlx5_cqe64 *cqe = _ctx->cqe; + u32 hash_type, l4_type, ip_type, lookup; if (unlikely(!(_ctx->xdp.rxq->dev->features & NETIF_F_RXHASH))) return -ENODATA; - *hash = be32_to_cpu(_ctx->cqe->rss_hash_result); + *hash = be32_to_cpu(cqe->rss_hash_result); + + hash_type = cqe->rss_hash_type; + BUILD_BUG_ON(CQE_RSS_HTYPE_IP != RSS_L3); /* same mask */ + ip_type = hash_type & CQE_RSS_HTYPE_IP; + l4_type = FIELD_GET(CQE_RSS_HTYPE_L4, hash_type); + lookup = ip_type | l4_type; + *rss_type = mlx5_xdp_rss_type[lookup]; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8bdf28762f41..19fed514fc17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1488,7 +1488,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 * void *hca_caps; int err; - if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_management_pf(dev)) { + if (!mlx5_core_is_ecpf(dev)) { *max_sfs = 0; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c index 017d68f1e123..972c571b4158 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c @@ -31,6 +31,8 @@ mlxfw_mfa2_tlv_next(const struct mlxfw_mfa2_file *mfa2_file, if (tlv->type == MLXFW_MFA2_TLV_MULTI_PART) { multi = mlxfw_mfa2_tlv_multi_get(mfa2_file, tlv); + if (!multi) + return NULL; tlv_len = NLA_ALIGN(tlv_len + be16_to_cpu(multi->total_len)); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index 48dbfea0a2a1..7cdf0ce24f28 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -26,7 +26,7 @@ #define MLXSW_PCI_CIR_TIMEOUT_MSECS 1000 #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 -#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 +#define MLXSW_PCI_SW_RESET_WAIT_MSECS 400 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF #define MLXSW_PCI_FW_READY_MAGIC 0x5E diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index 87f76bac2e46..eb827b86ecae 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -628,7 +628,13 @@ int qlcnic_fw_create_ctx(struct qlcnic_adapter *dev) int i, err, ring; if (dev->flags & QLCNIC_NEED_FLR) { - pci_reset_function(dev->pdev); + err = pci_reset_function(dev->pdev); + if (err) { + dev_err(&dev->pdev->dev, + "Adapter reset failed (%d). Please reboot\n", + err); + return err; + } dev->flags &= ~QLCNIC_NEED_FLR; } diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 884d8d168862..1eceffa02b55 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -541,7 +541,6 @@ int efx_net_open(struct net_device *net_dev) else efx->state = STATE_NET_UP; - efx_selftest_async_start(efx); return 0; } diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index cc30524c2fe4..361687de308d 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -544,6 +544,8 @@ void efx_start_all(struct efx_nic *efx) /* Start the hardware monitor if there is one */ efx_start_monitor(efx); + efx_selftest_async_start(efx); + /* Link state detection is normally event-driven; we have * to poll now because we could have missed a change */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 13aa919633b4..ab9f876b6df7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -251,7 +251,6 @@ static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data) priv->plat->mdio_bus_data->xpcs_an_inband = false; } else { priv->plat->max_speed = 1000; - priv->plat->mdio_bus_data->xpcs_an_inband = true; } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 17310ade88dd..d7fcab057032 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1134,20 +1134,26 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) static int stmmac_init_phy(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + struct fwnode_handle *phy_fwnode; struct fwnode_handle *fwnode; int ret; + if (!phylink_expects_phy(priv->phylink)) + return 0; + fwnode = of_fwnode_handle(priv->plat->phylink_node); if (!fwnode) fwnode = dev_fwnode(priv->device); if (fwnode) - ret = phylink_fwnode_phy_connect(priv->phylink, fwnode, 0); + phy_fwnode = fwnode_get_phy_node(fwnode); + else + phy_fwnode = NULL; /* Some DT bindings do not set-up the PHY handle. Let's try to * manually parse it */ - if (!fwnode || ret) { + if (!phy_fwnode || IS_ERR(phy_fwnode)) { int addr = priv->plat->phy_addr; struct phy_device *phydev; @@ -1163,6 +1169,9 @@ static int stmmac_init_phy(struct net_device *dev) } ret = phylink_connect_phy(priv->phylink, phydev); + } else { + fwnode_handle_put(phy_fwnode); + ret = phylink_fwnode_phy_connect(priv->phylink, fwnode, 0); } if (!priv->plat->pmt) { @@ -6622,6 +6631,8 @@ int stmmac_xdp_open(struct net_device *dev) goto init_error; } + stmmac_reset_queues_param(priv); + /* DMA CSR Channel configuration */ for (chan = 0; chan < dma_csr_ch; chan++) { stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan); @@ -6948,7 +6959,7 @@ static void stmmac_napi_del(struct net_device *dev) int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) { struct stmmac_priv *priv = netdev_priv(dev); - int ret = 0; + int ret = 0, i; if (netif_running(dev)) stmmac_release(dev); @@ -6957,6 +6968,10 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) priv->plat->rx_queues_to_use = rx_cnt; priv->plat->tx_queues_to_use = tx_cnt; + if (!netif_is_rxfh_configured(dev)) + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = ethtool_rxfh_indir_default(i, + rx_cnt); stmmac_napi_add(dev); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index ab8b09a9ef61..7a2e76776297 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -4522,7 +4522,7 @@ static int niu_alloc_channels(struct niu *np) err = niu_rbr_fill(np, rp, GFP_KERNEL); if (err) - return err; + goto out_err; } tx_rings = kcalloc(num_tx_rings, sizeof(struct tx_ring_info), diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 4e3861c47708..bcea87b7151c 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2926,7 +2926,8 @@ err_free_phylink: am65_cpsw_nuss_phylink_cleanup(common); am65_cpts_release(common->cpts); err_of_clear: - of_platform_device_destroy(common->mdio_dev, NULL); + if (common->mdio_dev) + of_platform_device_destroy(common->mdio_dev, NULL); err_pm_clear: pm_runtime_put_sync(dev); pm_runtime_disable(dev); @@ -2956,7 +2957,8 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) am65_cpts_release(common->cpts); am65_cpsw_disable_serdes_phy(common); - of_platform_device_destroy(common->mdio_dev, NULL); + if (common->mdio_dev) + of_platform_device_destroy(common->mdio_dev, NULL); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 37f0b62ec5d6..f9cd566d1c9b 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -27,7 +27,7 @@ #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/of_device.h> +#include <linux/of_platform.h> #include <linux/if_vlan.h> #include <linux/kmemleak.h> #include <linux/sys_soc.h> diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 35128dd45ffc..c61e4e44a78f 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -7,6 +7,7 @@ #include <linux/io.h> #include <linux/clk.h> +#include <linux/platform_device.h> #include <linux/timer.h> #include <linux/module.h> #include <linux/irqreturn.h> @@ -23,7 +24,7 @@ #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/of_device.h> +#include <linux/of_platform.h> #include <linux/if_vlan.h> #include <linux/kmemleak.h> #include <linux/sys_soc.h> diff --git a/drivers/net/hamradio/Kconfig b/drivers/net/hamradio/Kconfig index a9c44f08199d..a94c7bd5db2e 100644 --- a/drivers/net/hamradio/Kconfig +++ b/drivers/net/hamradio/Kconfig @@ -47,7 +47,7 @@ config BPQETHER config SCC tristate "Z8530 SCC driver" - depends on ISA && AX25 && ISA_DMA_API + depends on ISA && AX25 help These cards are used to connect your Linux box to an amateur radio in order to communicate with other computers. If you want to use diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 5813b07242ce..029875a59ff8 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -191,7 +191,7 @@ #define MAX_ID_PS 2260U #define DEFAULT_ID_PS 2000U -#define PPM_TO_SUBNS_INC(ppb) div_u64(GENMASK(31, 0) * (ppb) * \ +#define PPM_TO_SUBNS_INC(ppb) div_u64(GENMASK_ULL(31, 0) * (ppb) * \ PTP_CLK_PERIOD_100BT1, NSEC_PER_SEC) #define NXP_C45_SKB_CB(skb) ((struct nxp_c45_skb_cb *)(skb)->cb) @@ -1337,6 +1337,17 @@ no_ptp_support: return ret; } +static void nxp_c45_remove(struct phy_device *phydev) +{ + struct nxp_c45_phy *priv = phydev->priv; + + if (priv->ptp_clock) + ptp_clock_unregister(priv->ptp_clock); + + skb_queue_purge(&priv->tx_queue); + skb_queue_purge(&priv->rx_queue); +} + static struct phy_driver nxp_c45_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103), @@ -1359,6 +1370,7 @@ static struct phy_driver nxp_c45_driver[] = { .set_loopback = genphy_c45_loopback, .get_sqi = nxp_c45_get_sqi, .get_sqi_max = nxp_c45_get_sqi_max, + .remove = nxp_c45_remove, }, }; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 1a2f074685fa..30c166b33468 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1586,6 +1586,25 @@ void phylink_destroy(struct phylink *pl) } EXPORT_SYMBOL_GPL(phylink_destroy); +/** + * phylink_expects_phy() - Determine if phylink expects a phy to be attached + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * When using fixed-link mode, or in-band mode with 1000base-X or 2500base-X, + * no PHY is needed. + * + * Returns true if phylink will be expecting a PHY. + */ +bool phylink_expects_phy(struct phylink *pl) +{ + if (pl->cfg_link_an_mode == MLO_AN_FIXED || + (pl->cfg_link_an_mode == MLO_AN_INBAND && + phy_interface_mode_is_8023z(pl->link_config.interface))) + return false; + return true; +} +EXPORT_SYMBOL_GPL(phylink_expects_phy); + static void phylink_phy_change(struct phy_device *phydev, bool up) { struct phylink *pl = phydev->phylink; diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index fb98db61e06c..bf345032d450 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -210,6 +210,12 @@ static const enum gpiod_flags gpio_flags[] = { #define SFP_PHY_ADDR 22 #define SFP_PHY_ADDR_ROLLBALL 17 +/* SFP_EEPROM_BLOCK_SIZE is the size of data chunk to read the EEPROM + * at a time. Some SFP modules and also some Linux I2C drivers do not like + * reads longer than 16 bytes. + */ +#define SFP_EEPROM_BLOCK_SIZE 16 + struct sff_data { unsigned int gpios; bool (*module_supported)(const struct sfp_eeprom_id *id); @@ -387,6 +393,10 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_F("HALNy", "HL-GSFP", sfp_fixup_halny_gsfp), + // HG MXPD-483II-F 2.5G supports 2500Base-X, but incorrectly reports + // 2600MBd in their EERPOM + SFP_QUIRK_M("HG GENUINE", "MXPD-483II", sfp_quirk_2500basex), + // Huawei MA5671A can operate at 2500base-X, but report 1.2GBd NRZ in // their EEPROM SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex, @@ -1925,11 +1935,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) u8 check; int ret; - /* Some SFP modules and also some Linux I2C drivers do not like reads - * longer than 16 bytes, so read the EEPROM in chunks of 16 bytes at - * a time. - */ - sfp->i2c_block_size = 16; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; ret = sfp_read(sfp, false, 0, &id.base, sizeof(id.base)); if (ret < 0) { @@ -2481,6 +2487,9 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee, unsigned int first, last, len; int ret; + if (!(sfp->state & SFP_F_PRESENT)) + return -ENODEV; + if (ee->len == 0) return -EINVAL; @@ -2513,6 +2522,9 @@ static int sfp_module_eeprom_by_page(struct sfp *sfp, const struct ethtool_module_eeprom *page, struct netlink_ext_ack *extack) { + if (!(sfp->state & SFP_F_PRESENT)) + return -ENODEV; + if (page->bank) { NL_SET_ERR_MSG(extack, "Banks not supported"); return -EOPNOTSUPP; @@ -2617,6 +2629,7 @@ static struct sfp *sfp_alloc(struct device *dev) return ERR_PTR(-ENOMEM); sfp->dev = dev; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; mutex_init(&sfp->sm_mutex); mutex_init(&sfp->st_mutex); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index decb5ba56a25..0fc4b959edc1 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1943,7 +1943,7 @@ static struct rx_agg *alloc_rx_agg(struct r8152 *tp, gfp_t mflags) if (!rx_agg) return NULL; - rx_agg->page = alloc_pages(mflags | __GFP_COMP, order); + rx_agg->page = alloc_pages(mflags | __GFP_COMP | __GFP_NOWARN, order); if (!rx_agg->page) goto free_rx; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index c1178915496d..4b3c6647edc6 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1262,11 +1262,12 @@ static void veth_set_xdp_features(struct net_device *dev) peer = rtnl_dereference(priv->peer); if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) { + struct veth_priv *priv_peer = netdev_priv(peer); xdp_features_t val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_RX_SG; - if (priv->_xdp_prog || veth_gro_requested(dev)) + if (priv_peer->_xdp_prog || veth_gro_requested(peer)) val |= NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag(dev, val); @@ -1504,19 +1505,23 @@ static int veth_set_features(struct net_device *dev, { netdev_features_t changed = features ^ dev->features; struct veth_priv *priv = netdev_priv(dev); + struct net_device *peer; int err; if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog) return 0; + peer = rtnl_dereference(priv->peer); if (features & NETIF_F_GRO) { err = veth_napi_enable(dev); if (err) return err; - xdp_features_set_redirect_target(dev, true); + if (peer) + xdp_features_set_redirect_target(peer, true); } else { - xdp_features_clear_redirect_target(dev); + if (peer) + xdp_features_clear_redirect_target(peer); veth_napi_del(dev); } return 0; @@ -1598,13 +1603,13 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, peer->max_mtu = max_mtu; } - xdp_features_set_redirect_target(dev, true); + xdp_features_set_redirect_target(peer, true); } if (old_prog) { if (!prog) { - if (!veth_gro_requested(dev)) - xdp_features_clear_redirect_target(dev); + if (peer && !veth_gro_requested(dev)) + xdp_features_clear_redirect_target(peer); if (dev->flags & IFF_UP) veth_disable_xdp(dev); @@ -1648,14 +1653,18 @@ static int veth_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { struct veth_xdp_buff *_ctx = (void *)ctx; + struct sk_buff *skb = _ctx->skb; - if (!_ctx->skb) + if (!skb) return -ENODATA; - *hash = skb_get_hash(_ctx->skb); + *hash = skb_get_hash(skb); + *rss_type = skb->l4_hash ? XDP_RSS_TYPE_L4_ANY : XDP_RSS_TYPE_NONE; + return 0; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2396c28c0122..ea1bd4bb326d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -814,8 +814,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, int page_off, unsigned int *len) { - struct page *page = alloc_page(GFP_ATOMIC); + int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + struct page *page; + + if (page_off + *len + tailroom > PAGE_SIZE) + return NULL; + page = alloc_page(GFP_ATOMIC); if (!page) return NULL; @@ -823,7 +828,6 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, page_off += *len; while (--*num_buf) { - int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); unsigned int buflen; void *buf; int off; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index da488cbb0542..f2b76ee866a4 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1504,7 +1504,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, goto rcd_done; } - if (rxDataRingUsed) { + if (rxDataRingUsed && adapter->rxdataring_enabled) { size_t sz; BUG_ON(rcd->len > rq->data_ring.desc_size); diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index 86995e8dc913..a62ee05c5409 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -16,7 +16,7 @@ #include "pci.h" #include "pcic.h" -#define MHI_TIMEOUT_DEFAULT_MS 90000 +#define MHI_TIMEOUT_DEFAULT_MS 20000 #define RDDM_DUMP_SIZE 0x420000 static struct mhi_channel_config ath11k_mhi_channels_qca6390[] = { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index b7c918f241c9..65d4799a5658 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -994,15 +994,34 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = { MODULE_DEVICE_TABLE(sdio, brcmf_sdmmc_ids); -static void brcmf_sdiod_acpi_set_power_manageable(struct device *dev, - int val) +static void brcmf_sdiod_acpi_save_power_manageable(struct brcmf_sdio_dev *sdiodev) { #if IS_ENABLED(CONFIG_ACPI) struct acpi_device *adev; - adev = ACPI_COMPANION(dev); + adev = ACPI_COMPANION(&sdiodev->func1->dev); if (adev) - adev->flags.power_manageable = 0; + sdiodev->func1_power_manageable = adev->flags.power_manageable; + + adev = ACPI_COMPANION(&sdiodev->func2->dev); + if (adev) + sdiodev->func2_power_manageable = adev->flags.power_manageable; +#endif +} + +static void brcmf_sdiod_acpi_set_power_manageable(struct brcmf_sdio_dev *sdiodev, + int enable) +{ +#if IS_ENABLED(CONFIG_ACPI) + struct acpi_device *adev; + + adev = ACPI_COMPANION(&sdiodev->func1->dev); + if (adev) + adev->flags.power_manageable = enable ? sdiodev->func1_power_manageable : 0; + + adev = ACPI_COMPANION(&sdiodev->func2->dev); + if (adev) + adev->flags.power_manageable = enable ? sdiodev->func2_power_manageable : 0; #endif } @@ -1012,7 +1031,6 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, int err; struct brcmf_sdio_dev *sdiodev; struct brcmf_bus *bus_if; - struct device *dev; brcmf_dbg(SDIO, "Enter\n"); brcmf_dbg(SDIO, "Class=%x\n", func->class); @@ -1020,14 +1038,9 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, brcmf_dbg(SDIO, "sdio device ID: 0x%04x\n", func->device); brcmf_dbg(SDIO, "Function#: %d\n", func->num); - dev = &func->dev; - /* Set MMC_QUIRK_LENIENT_FN0 for this card */ func->card->quirks |= MMC_QUIRK_LENIENT_FN0; - /* prohibit ACPI power management for this device */ - brcmf_sdiod_acpi_set_power_manageable(dev, 0); - /* Consume func num 1 but dont do anything with it. */ if (func->num == 1) return 0; @@ -1059,6 +1072,7 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, dev_set_drvdata(&sdiodev->func1->dev, bus_if); sdiodev->dev = &sdiodev->func1->dev; + brcmf_sdiod_acpi_save_power_manageable(sdiodev); brcmf_sdiod_change_state(sdiodev, BRCMF_SDIOD_DOWN); brcmf_dbg(SDIO, "F2 found, calling brcmf_sdiod_probe...\n"); @@ -1124,6 +1138,8 @@ void brcmf_sdio_wowl_config(struct device *dev, bool enabled) if (sdiodev->settings->bus.sdio.oob_irq_supported || pm_caps & MMC_PM_WAKE_SDIO_IRQ) { + /* Stop ACPI from turning off the device when wowl is enabled */ + brcmf_sdiod_acpi_set_power_manageable(sdiodev, !enabled); sdiodev->wowl_enabled = enabled; brcmf_dbg(SDIO, "Configuring WOWL, enabled=%d\n", enabled); return; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h index b76d34d36bde..0d18ed15b403 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h @@ -188,6 +188,8 @@ struct brcmf_sdio_dev { char nvram_name[BRCMF_FW_NAME_LEN]; char clm_name[BRCMF_FW_NAME_LEN]; bool wowl_enabled; + bool func1_power_manageable; + bool func2_power_manageable; enum brcmf_sdiod_state state; struct brcmf_sdiod_freezer *freezer; const struct firmware *clm_fw; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c index ca50feb0b3a9..1b1358c6bb46 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c @@ -512,15 +512,15 @@ mt7603_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) return -EOPNOTSUPP; - if (cmd == SET_KEY) { - key->hw_key_idx = wcid->idx; - wcid->hw_key_idx = idx; - } else { + if (cmd != SET_KEY) { if (idx == wcid->hw_key_idx) wcid->hw_key_idx = -1; - key = NULL; + return 0; } + + key->hw_key_idx = wcid->idx; + wcid->hw_key_idx = idx; mt76_wcid_key_setup(&dev->mt76, wcid, key); return mt7603_wtbl_set_key(dev, wcid->idx, key); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index a95602473359..51a968a6afdc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -1193,8 +1193,7 @@ EXPORT_SYMBOL_GPL(mt7615_mac_enable_rtscts); static int mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, struct ieee80211_key_conf *key, - enum mt76_cipher_type cipher, u16 cipher_mask, - enum set_key_cmd cmd) + enum mt76_cipher_type cipher, u16 cipher_mask) { u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx) + 30 * 4; u8 data[32] = {}; @@ -1203,27 +1202,18 @@ mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, return -EINVAL; mt76_rr_copy(dev, addr, data, sizeof(data)); - if (cmd == SET_KEY) { - if (cipher == MT_CIPHER_TKIP) { - /* Rx/Tx MIC keys are swapped */ - memcpy(data, key->key, 16); - memcpy(data + 16, key->key + 24, 8); - memcpy(data + 24, key->key + 16, 8); - } else { - if (cipher_mask == BIT(cipher)) - memcpy(data, key->key, key->keylen); - else if (cipher != MT_CIPHER_BIP_CMAC_128) - memcpy(data, key->key, 16); - if (cipher == MT_CIPHER_BIP_CMAC_128) - memcpy(data + 16, key->key, 16); - } + if (cipher == MT_CIPHER_TKIP) { + /* Rx/Tx MIC keys are swapped */ + memcpy(data, key->key, 16); + memcpy(data + 16, key->key + 24, 8); + memcpy(data + 24, key->key + 16, 8); } else { + if (cipher_mask == BIT(cipher)) + memcpy(data, key->key, key->keylen); + else if (cipher != MT_CIPHER_BIP_CMAC_128) + memcpy(data, key->key, 16); if (cipher == MT_CIPHER_BIP_CMAC_128) - memset(data + 16, 0, 16); - else if (cipher_mask) - memset(data, 0, 16); - if (!cipher_mask) - memset(data, 0, sizeof(data)); + memcpy(data + 16, key->key, 16); } mt76_wr_copy(dev, addr, data, sizeof(data)); @@ -1234,7 +1224,7 @@ mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, static int mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid, enum mt76_cipher_type cipher, u16 cipher_mask, - int keyidx, enum set_key_cmd cmd) + int keyidx) { u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx), w0, w1; @@ -1253,9 +1243,7 @@ mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid, else w0 &= ~MT_WTBL_W0_RX_IK_VALID; - if (cmd == SET_KEY && - (cipher != MT_CIPHER_BIP_CMAC_128 || - cipher_mask == BIT(cipher))) { + if (cipher != MT_CIPHER_BIP_CMAC_128 || cipher_mask == BIT(cipher)) { w0 &= ~MT_WTBL_W0_KEY_IDX; w0 |= FIELD_PREP(MT_WTBL_W0_KEY_IDX, keyidx); } @@ -1272,19 +1260,10 @@ mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid, static void mt7615_mac_wtbl_update_cipher(struct mt7615_dev *dev, struct mt76_wcid *wcid, - enum mt76_cipher_type cipher, u16 cipher_mask, - enum set_key_cmd cmd) + enum mt76_cipher_type cipher, u16 cipher_mask) { u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx); - if (!cipher_mask) { - mt76_clear(dev, addr + 2 * 4, MT_WTBL_W2_KEY_TYPE); - return; - } - - if (cmd != SET_KEY) - return; - if (cipher == MT_CIPHER_BIP_CMAC_128 && cipher_mask & ~BIT(MT_CIPHER_BIP_CMAC_128)) return; @@ -1295,8 +1274,7 @@ mt7615_mac_wtbl_update_cipher(struct mt7615_dev *dev, struct mt76_wcid *wcid, int __mt7615_mac_wtbl_set_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, - struct ieee80211_key_conf *key, - enum set_key_cmd cmd) + struct ieee80211_key_conf *key) { enum mt76_cipher_type cipher; u16 cipher_mask = wcid->cipher; @@ -1306,19 +1284,14 @@ int __mt7615_mac_wtbl_set_key(struct mt7615_dev *dev, if (cipher == MT_CIPHER_NONE) return -EOPNOTSUPP; - if (cmd == SET_KEY) - cipher_mask |= BIT(cipher); - else - cipher_mask &= ~BIT(cipher); - - mt7615_mac_wtbl_update_cipher(dev, wcid, cipher, cipher_mask, cmd); - err = mt7615_mac_wtbl_update_key(dev, wcid, key, cipher, cipher_mask, - cmd); + cipher_mask |= BIT(cipher); + mt7615_mac_wtbl_update_cipher(dev, wcid, cipher, cipher_mask); + err = mt7615_mac_wtbl_update_key(dev, wcid, key, cipher, cipher_mask); if (err < 0) return err; err = mt7615_mac_wtbl_update_pk(dev, wcid, cipher, cipher_mask, - key->keyidx, cmd); + key->keyidx); if (err < 0) return err; @@ -1329,13 +1302,12 @@ int __mt7615_mac_wtbl_set_key(struct mt7615_dev *dev, int mt7615_mac_wtbl_set_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, - struct ieee80211_key_conf *key, - enum set_key_cmd cmd) + struct ieee80211_key_conf *key) { int err; spin_lock_bh(&dev->mt76.lock); - err = __mt7615_mac_wtbl_set_key(dev, wcid, key, cmd); + err = __mt7615_mac_wtbl_set_key(dev, wcid, key); spin_unlock_bh(&dev->mt76.lock); return err; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index ab4c1b4478aa..dadb13f2ca09 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -391,18 +391,17 @@ static int mt7615_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, if (cmd == SET_KEY) *wcid_keyidx = idx; - else if (idx == *wcid_keyidx) - *wcid_keyidx = -1; - else + else { + if (idx == *wcid_keyidx) + *wcid_keyidx = -1; goto out; + } - mt76_wcid_key_setup(&dev->mt76, wcid, - cmd == SET_KEY ? key : NULL); - + mt76_wcid_key_setup(&dev->mt76, wcid, key); if (mt76_is_mmio(&dev->mt76)) - err = mt7615_mac_wtbl_set_key(dev, wcid, key, cmd); + err = mt7615_mac_wtbl_set_key(dev, wcid, key); else - err = __mt7615_mac_wtbl_set_key(dev, wcid, key, cmd); + err = __mt7615_mac_wtbl_set_key(dev, wcid, key); out: mt7615_mutex_release(dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h index 43591b4c1d9a..9e58f6924493 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h @@ -490,11 +490,9 @@ int mt7615_mac_write_txwi(struct mt7615_dev *dev, __le32 *txwi, void mt7615_mac_set_timing(struct mt7615_phy *phy); int __mt7615_mac_wtbl_set_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, - struct ieee80211_key_conf *key, - enum set_key_cmd cmd); + struct ieee80211_key_conf *key); int mt7615_mac_wtbl_set_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, - struct ieee80211_key_conf *key, - enum set_key_cmd cmd); + struct ieee80211_key_conf *key); void mt7615_mac_reset_work(struct work_struct *work); u32 mt7615_mac_get_sta_tid_sn(struct mt7615_dev *dev, int wcid, u8 tid); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c index 7451a63206a5..dcbb5c605dfe 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c @@ -454,20 +454,20 @@ int mt76x02_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, msta = sta ? (struct mt76x02_sta *)sta->drv_priv : NULL; wcid = msta ? &msta->wcid : &mvif->group_wcid; - if (cmd == SET_KEY) { - key->hw_key_idx = wcid->idx; - wcid->hw_key_idx = idx; - if (key->flags & IEEE80211_KEY_FLAG_RX_MGMT) { - key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX; - wcid->sw_iv = true; - } - } else { + if (cmd != SET_KEY) { if (idx == wcid->hw_key_idx) { wcid->hw_key_idx = -1; wcid->sw_iv = false; } - key = NULL; + return 0; + } + + key->hw_key_idx = wcid->idx; + wcid->hw_key_idx = idx; + if (key->flags & IEEE80211_KEY_FLAG_RX_MGMT) { + key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX; + wcid->sw_iv = true; } mt76_wcid_key_setup(&dev->mt76, wcid, key); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index 3bbccbdfc5eb..784191ec4802 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -410,16 +410,15 @@ static int mt7915_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, mt7915_mcu_add_bss_info(phy, vif, true); } - if (cmd == SET_KEY) + if (cmd == SET_KEY) { *wcid_keyidx = idx; - else if (idx == *wcid_keyidx) - *wcid_keyidx = -1; - else + } else { + if (idx == *wcid_keyidx) + *wcid_keyidx = -1; goto out; + } - mt76_wcid_key_setup(&dev->mt76, wcid, - cmd == SET_KEY ? key : NULL); - + mt76_wcid_key_setup(&dev->mt76, wcid, key); err = mt76_connac_mcu_add_key(&dev->mt76, vif, &msta->bip, key, MCU_EXT_CMD(STA_REC_UPDATE), &msta->wcid, cmd); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c index 80c71acfe159..cc94531185da 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c @@ -171,12 +171,12 @@ mt7921_mac_init_band(struct mt7921_dev *dev, u8 band) u8 mt7921_check_offload_capability(struct device *dev, const char *fw_wm) { - struct mt7921_fw_features *features = NULL; const struct mt76_connac2_fw_trailer *hdr; struct mt7921_realease_info *rel_info; const struct firmware *fw; int ret, i, offset = 0; const u8 *data, *end; + u8 offload_caps = 0; ret = request_firmware(&fw, fw_wm, dev); if (ret) @@ -208,7 +208,10 @@ u8 mt7921_check_offload_capability(struct device *dev, const char *fw_wm) data += sizeof(*rel_info); if (rel_info->tag == MT7921_FW_TAG_FEATURE) { + struct mt7921_fw_features *features; + features = (struct mt7921_fw_features *)data; + offload_caps = features->data; break; } @@ -218,7 +221,7 @@ u8 mt7921_check_offload_capability(struct device *dev, const char *fw_wm) out: release_firmware(fw); - return features ? features->data : 0; + return offload_caps; } EXPORT_SYMBOL_GPL(mt7921_check_offload_capability); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 75eaf86c6a78..42933a6b7334 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -569,16 +569,15 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, mt7921_mutex_acquire(dev); - if (cmd == SET_KEY) + if (cmd == SET_KEY) { *wcid_keyidx = idx; - else if (idx == *wcid_keyidx) - *wcid_keyidx = -1; - else + } else { + if (idx == *wcid_keyidx) + *wcid_keyidx = -1; goto out; + } - mt76_wcid_key_setup(&dev->mt76, wcid, - cmd == SET_KEY ? key : NULL); - + mt76_wcid_key_setup(&dev->mt76, wcid, key); err = mt76_connac_mcu_add_key(&dev->mt76, vif, &msta->bip, key, MCU_UNI_CMD(STA_REC_UPDATE), &msta->wcid, cmd); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index cb72ded37256..5c23c827abe4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -20,7 +20,7 @@ static const struct pci_device_id mt7921_pci_device_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x0608), .driver_data = (kernel_ulong_t)MT7921_FIRMWARE_WM }, { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x0616), - .driver_data = (kernel_ulong_t)MT7921_FIRMWARE_WM }, + .driver_data = (kernel_ulong_t)MT7922_FIRMWARE_WM }, { }, }; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 3e4da0350d96..1ba22d147949 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -351,16 +351,15 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, mt7996_mcu_add_bss_info(phy, vif, true); } - if (cmd == SET_KEY) + if (cmd == SET_KEY) { *wcid_keyidx = idx; - else if (idx == *wcid_keyidx) - *wcid_keyidx = -1; - else + } else { + if (idx == *wcid_keyidx) + *wcid_keyidx = -1; goto out; + } - mt76_wcid_key_setup(&dev->mt76, wcid, - cmd == SET_KEY ? key : NULL); - + mt76_wcid_key_setup(&dev->mt76, wcid, key); err = mt7996_mcu_add_key(&dev->mt76, vif, &msta->bip, key, MCU_WMWA_UNI_CMD(STA_REC_UPDATE), &msta->wcid, cmd); diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 5bf5a93937c9..04517bd3325a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -295,7 +295,7 @@ static int ipc_pcie_probe(struct pci_dev *pci, ret = dma_set_mask(ipc_pcie->dev, DMA_BIT_MASK(64)); if (ret) { dev_err(ipc_pcie->dev, "Could not set PCI DMA mask: %d", ret); - return ret; + goto set_mask_fail; } ipc_pcie_config_aspm(ipc_pcie); @@ -323,6 +323,7 @@ static int ipc_pcie_probe(struct pci_dev *pci, imem_init_fail: ipc_pcie_resources_release(ipc_pcie); resources_req_fail: +set_mask_fail: pci_disable_device(pci); pci_enable_fail: kfree(ipc_pcie); diff --git a/drivers/net/wwan/t7xx/Makefile b/drivers/net/wwan/t7xx/Makefile index 268ff9e87e5b..2652cd00504e 100644 --- a/drivers/net/wwan/t7xx/Makefile +++ b/drivers/net/wwan/t7xx/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -ccflags-y += -Werror - obj-${CONFIG_MTK_T7XX} := mtk_t7xx.o mtk_t7xx-y:= t7xx_pci.o \ t7xx_pcie_mac.o \ diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 53ef028596c6..d6a9bac91a4c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1674,6 +1674,9 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) struct request_queue *queue = disk->queue; u32 size = queue_logical_block_size(queue); + if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX)) + ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl); + if (ctrl->max_discard_sectors == 0) { blk_queue_max_discard_sectors(queue, 0); return; @@ -1688,9 +1691,6 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) if (queue->limits.max_discard_sectors) return; - if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX)) - ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl); - blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors); blk_queue_max_discard_segments(queue, ctrl->max_discard_segments); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 282d808400c5..cd7873de3121 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3443,6 +3443,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1d97, 0x2269), /* Lexar NM760 */ .driver_data = NVME_QUIRK_BOGUS_NID | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x10ec, 0x5763), /* TEAMGROUP T-FORCE CARDEA ZERO Z330 SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 07d93753b12f..e311d406b170 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -226,6 +226,7 @@ static void __of_attach_node(struct device_node *np) np->sibling = np->parent->child; np->parent->child = np; of_node_clear_flag(np, OF_DETACHED); + np->fwnode.flags |= FWNODE_FLAG_NOT_DEVICE; } /** diff --git a/drivers/of/platform.c b/drivers/of/platform.c index b2bd2e783445..78ae84187449 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -737,6 +737,11 @@ static int of_platform_notify(struct notifier_block *nb, if (of_node_check_flag(rd->dn, OF_POPULATED)) return NOTIFY_OK; + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; /* pdev_parent may be NULL when no bus platform device */ pdev_parent = of_find_device_by_node(rd->dn->parent); pdev = of_platform_device_create(rd->dn, NULL, diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index 66d9ab288646..e5e9b287b976 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -128,7 +128,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, return -EIO; /* Length is 2 DW of header + length of payload in DW */ - length = 2 + task->request_pl_sz / sizeof(u32); + length = 2 + task->request_pl_sz / sizeof(__le32); if (length > PCI_DOE_MAX_LENGTH) return -EIO; if (length == PCI_DOE_MAX_LENGTH) @@ -141,9 +141,9 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH, length)); - for (i = 0; i < task->request_pl_sz / sizeof(u32); i++) + for (i = 0; i < task->request_pl_sz / sizeof(__le32); i++) pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, - task->request_pl[i]); + le32_to_cpu(task->request_pl[i])); pci_doe_write_ctrl(doe_mb, PCI_DOE_CTRL_GO); @@ -195,11 +195,11 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas /* First 2 dwords have already been read */ length -= 2; - payload_length = min(length, task->response_pl_sz / sizeof(u32)); + payload_length = min(length, task->response_pl_sz / sizeof(__le32)); /* Read the rest of the response payload */ for (i = 0; i < payload_length; i++) { - pci_read_config_dword(pdev, offset + PCI_DOE_READ, - &task->response_pl[i]); + pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); + task->response_pl[i] = cpu_to_le32(val); /* Prior to the last ack, ensure Data Object Ready */ if (i == (payload_length - 1) && !pci_doe_data_obj_ready(doe_mb)) return -EIO; @@ -217,13 +217,14 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) return -EIO; - return min(length, task->response_pl_sz / sizeof(u32)) * sizeof(u32); + return min(length, task->response_pl_sz / sizeof(__le32)) * sizeof(__le32); } static void signal_task_complete(struct pci_doe_task *task, int rv) { task->rv = rv; task->complete(task); + destroy_work_on_stack(&task->work); } static void signal_task_abort(struct pci_doe_task *task, int rv) @@ -317,14 +318,16 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, { u32 request_pl = FIELD_PREP(PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX, *index); + __le32 request_pl_le = cpu_to_le32(request_pl); + __le32 response_pl_le; u32 response_pl; DECLARE_COMPLETION_ONSTACK(c); struct pci_doe_task task = { .prot.vid = PCI_VENDOR_ID_PCI_SIG, .prot.type = PCI_DOE_PROTOCOL_DISCOVERY, - .request_pl = &request_pl, + .request_pl = &request_pl_le, .request_pl_sz = sizeof(request_pl), - .response_pl = &response_pl, + .response_pl = &response_pl_le, .response_pl_sz = sizeof(response_pl), .complete = pci_doe_task_complete, .private = &c, @@ -340,6 +343,7 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, if (task.rv != sizeof(response_pl)) return -EIO; + response_pl = le32_to_cpu(response_pl_le); *vid = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID, response_pl); *protocol = FIELD_GET(PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL, response_pl); @@ -520,6 +524,8 @@ EXPORT_SYMBOL_GPL(pci_doe_supports_prot); * task->complete will be called when the state machine is done processing this * task. * + * @task must be allocated on the stack. + * * Excess data will be discarded. * * RETURNS: 0 when task has been successfully queued, -ERRNO on error @@ -533,15 +539,15 @@ int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) * DOE requests must be a whole number of DW and the response needs to * be big enough for at least 1 DW */ - if (task->request_pl_sz % sizeof(u32) || - task->response_pl_sz < sizeof(u32)) + if (task->request_pl_sz % sizeof(__le32) || + task->response_pl_sz < sizeof(__le32)) return -EINVAL; if (test_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags)) return -EIO; task->doe_mb = doe_mb; - INIT_WORK(&task->work, doe_statemachine_work); + INIT_WORK_ONSTACK(&task->work, doe_statemachine_work); queue_work(doe_mb->work_queue, &task->work); return 0; } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 0145aef1b930..22d39e12b236 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -157,8 +157,6 @@ void pci_remove_root_bus(struct pci_bus *bus) list_for_each_entry_safe(child, tmp, &bus->devices, bus_list) pci_remove_bus_device(child); - pci_remove_bus(bus); - host_bridge->bus = NULL; #ifdef CONFIG_PCI_DOMAINS_GENERIC /* Release domain_nr if it was dynamically allocated */ @@ -166,6 +164,9 @@ void pci_remove_root_bus(struct pci_bus *bus) pci_bus_release_domain_nr(bus, host_bridge->dev.parent); #endif + pci_remove_bus(bus); + host_bridge->bus = NULL; + /* remove the host bridge */ device_del(&host_bridge->dev); } diff --git a/drivers/perf/amlogic/meson_g12_ddr_pmu.c b/drivers/perf/amlogic/meson_g12_ddr_pmu.c index a78fdb15e26c..8b643888d503 100644 --- a/drivers/perf/amlogic/meson_g12_ddr_pmu.c +++ b/drivers/perf/amlogic/meson_g12_ddr_pmu.c @@ -21,23 +21,23 @@ #define DMC_QOS_IRQ BIT(30) /* DMC bandwidth monitor register address offset */ -#define DMC_MON_G12_CTRL0 (0x20 << 2) -#define DMC_MON_G12_CTRL1 (0x21 << 2) -#define DMC_MON_G12_CTRL2 (0x22 << 2) -#define DMC_MON_G12_CTRL3 (0x23 << 2) -#define DMC_MON_G12_CTRL4 (0x24 << 2) -#define DMC_MON_G12_CTRL5 (0x25 << 2) -#define DMC_MON_G12_CTRL6 (0x26 << 2) -#define DMC_MON_G12_CTRL7 (0x27 << 2) -#define DMC_MON_G12_CTRL8 (0x28 << 2) - -#define DMC_MON_G12_ALL_REQ_CNT (0x29 << 2) -#define DMC_MON_G12_ALL_GRANT_CNT (0x2a << 2) -#define DMC_MON_G12_ONE_GRANT_CNT (0x2b << 2) -#define DMC_MON_G12_SEC_GRANT_CNT (0x2c << 2) -#define DMC_MON_G12_THD_GRANT_CNT (0x2d << 2) -#define DMC_MON_G12_FOR_GRANT_CNT (0x2e << 2) -#define DMC_MON_G12_TIMER (0x2f << 2) +#define DMC_MON_G12_CTRL0 (0x0 << 2) +#define DMC_MON_G12_CTRL1 (0x1 << 2) +#define DMC_MON_G12_CTRL2 (0x2 << 2) +#define DMC_MON_G12_CTRL3 (0x3 << 2) +#define DMC_MON_G12_CTRL4 (0x4 << 2) +#define DMC_MON_G12_CTRL5 (0x5 << 2) +#define DMC_MON_G12_CTRL6 (0x6 << 2) +#define DMC_MON_G12_CTRL7 (0x7 << 2) +#define DMC_MON_G12_CTRL8 (0x8 << 2) + +#define DMC_MON_G12_ALL_REQ_CNT (0x9 << 2) +#define DMC_MON_G12_ALL_GRANT_CNT (0xa << 2) +#define DMC_MON_G12_ONE_GRANT_CNT (0xb << 2) +#define DMC_MON_G12_SEC_GRANT_CNT (0xc << 2) +#define DMC_MON_G12_THD_GRANT_CNT (0xd << 2) +#define DMC_MON_G12_FOR_GRANT_CNT (0xe << 2) +#define DMC_MON_G12_TIMER (0xf << 2) /* Each bit represent a axi line */ PMU_FORMAT_ATTR(event, "config:0-7"); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 609821b756c2..9236a132c7ba 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -872,34 +872,32 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, }; -static void amd_gpio_irq_init_pin(struct amd_gpio *gpio_dev, int pin) +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) { - const struct pin_desc *pd; + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; unsigned long flags; u32 pin_reg, mask; + int i; mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) | BIT(WAKE_CNTRL_OFF_S4); - pd = pin_desc_get(gpio_dev->pctrl, pin); - if (!pd) - return; + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); - raw_spin_lock_irqsave(&gpio_dev->lock, flags); - pin_reg = readl(gpio_dev->base + pin * 4); - pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + pin * 4); - raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); -} + if (!pd) + continue; -static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) -{ - struct pinctrl_desc *desc = gpio_dev->pctrl->desc; - int i; + raw_spin_lock_irqsave(&gpio_dev->lock, flags); - for (i = 0; i < desc->npins; i++) - amd_gpio_irq_init_pin(gpio_dev, i); + pin_reg = readl(gpio_dev->base + i * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + i * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } } #ifdef CONFIG_PM_SLEEP @@ -952,10 +950,8 @@ static int amd_gpio_resume(struct device *dev) for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number; - if (!amd_gpio_should_save(gpio_dev, pin)) { - amd_gpio_irq_init_pin(gpio_dev, pin); + if (!amd_gpio_should_save(gpio_dev, pin)) continue; - } raw_spin_lock_irqsave(&gpio_dev->lock, flags); gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING; diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index c816646eb661..78dc82bda4dd 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -920,7 +920,7 @@ static ssize_t display_name_show(struct kobject *kobj, struct kobj_attribute *at static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct tlmi_attr_setting *setting = to_tlmi_attr_setting(kobj); - char *item, *value; + char *item, *value, *p; int ret; ret = tlmi_setting(setting->index, &item, LENOVO_BIOS_SETTING_GUID); @@ -930,10 +930,15 @@ static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *a /* validate and split from `item,value` -> `value` */ value = strpbrk(item, ","); if (!value || value == item || !strlen(value + 1)) - return -EINVAL; - - ret = sysfs_emit(buf, "%s\n", value + 1); + ret = -EINVAL; + else { + /* On Workstations remove the Options part after the value */ + p = strchrnul(value, ';'); + *p = '\0'; + ret = sysfs_emit(buf, "%s\n", value + 1); + } kfree(item); + return ret; } @@ -1457,10 +1462,10 @@ static int tlmi_analyze(void) * name string. * Try and pull that out if it's available. */ - char *item, *optstart, *optend; + char *optitem, *optstart, *optend; - if (!tlmi_setting(setting->index, &item, LENOVO_BIOS_SETTING_GUID)) { - optstart = strstr(item, "[Optional:"); + if (!tlmi_setting(setting->index, &optitem, LENOVO_BIOS_SETTING_GUID)) { + optstart = strstr(optitem, "[Optional:"); if (optstart) { optstart += strlen("[Optional:"); optend = strstr(optstart, "]"); @@ -1469,6 +1474,7 @@ static int tlmi_analyze(void) kstrndup(optstart, optend - optstart, GFP_KERNEL); } + kfree(optitem); } } /* diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 32c10457399e..7191ff2625b1 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4479,6 +4479,14 @@ static const struct dmi_system_id fwbug_list[] __initconst = { } }, { + .ident = "T14s Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20UJ"), + } + }, + { .ident = "P14s Gen1 AMD", .driver_data = &quirk_s2idle_bug, .matches = { diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index e01147f66e15..474725714a05 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -115,7 +115,14 @@ static int pwm_device_request(struct pwm_device *pwm, const char *label) } if (pwm->chip->ops->get_state) { - struct pwm_state state; + /* + * Zero-initialize state because most drivers are unaware of + * .usage_power. The other members of state are supposed to be + * set by lowlevel drivers. We still initialize the whole + * structure for simplicity even though this might paper over + * faulty implementations of .get_state(). + */ + struct pwm_state state = { 0, }; err = pwm->chip->ops->get_state(pwm->chip, pwm, &state); trace_pwm_get(pwm, &state, err); @@ -448,7 +455,7 @@ static void pwm_apply_state_debug(struct pwm_device *pwm, { struct pwm_state *last = &pwm->last; struct pwm_chip *chip = pwm->chip; - struct pwm_state s1, s2; + struct pwm_state s1 = { 0 }, s2 = { 0 }; int err; if (!IS_ENABLED(CONFIG_PWM_DEBUG)) @@ -530,6 +537,7 @@ static void pwm_apply_state_debug(struct pwm_device *pwm, return; } + *last = (struct pwm_state){ 0 }; err = chip->ops->get_state(chip, pwm, last); trace_pwm_get(pwm, last, err); if (err) diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c index 86df6702cb83..ad18b0ebe3f1 100644 --- a/drivers/pwm/pwm-cros-ec.c +++ b/drivers/pwm/pwm-cros-ec.c @@ -198,6 +198,7 @@ static int cros_ec_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, state->enabled = (ret > 0); state->period = EC_PWM_MAX_DUTY; + state->polarity = PWM_POLARITY_NORMAL; /* * Note that "disabled" and "duty cycle == 0" are treated the same. If diff --git a/drivers/pwm/pwm-hibvt.c b/drivers/pwm/pwm-hibvt.c index 12c05c155cab..1b9274c5ad87 100644 --- a/drivers/pwm/pwm-hibvt.c +++ b/drivers/pwm/pwm-hibvt.c @@ -146,6 +146,7 @@ static int hibvt_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, value = readl(base + PWM_CTRL_ADDR(pwm->hwpwm)); state->enabled = (PWM_ENABLE_MASK & value); + state->polarity = (PWM_POLARITY_MASK & value) ? PWM_POLARITY_INVERSED : PWM_POLARITY_NORMAL; return 0; } diff --git a/drivers/pwm/pwm-iqs620a.c b/drivers/pwm/pwm-iqs620a.c index 8362b4870c66..47b3141135f3 100644 --- a/drivers/pwm/pwm-iqs620a.c +++ b/drivers/pwm/pwm-iqs620a.c @@ -126,6 +126,7 @@ static int iqs620_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, mutex_unlock(&iqs620_pwm->lock); state->period = IQS620_PWM_PERIOD_NS; + state->polarity = PWM_POLARITY_NORMAL; return 0; } diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 16d79ca5d8f5..5cd7b90872c6 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -162,6 +162,12 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, duty = state->duty_cycle; period = state->period; + /* + * Note this is wrong. The result is an output wave that isn't really + * inverted and so is wrongly identified by .get_state as normal. + * Fixing this needs some care however as some machines might rely on + * this. + */ if (state->polarity == PWM_POLARITY_INVERSED) duty = period - duty; @@ -358,6 +364,8 @@ static int meson_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, state->duty_cycle = 0; } + state->polarity = PWM_POLARITY_NORMAL; + return 0; } diff --git a/drivers/pwm/pwm-sprd.c b/drivers/pwm/pwm-sprd.c index d866ce345f97..bde579a338c2 100644 --- a/drivers/pwm/pwm-sprd.c +++ b/drivers/pwm/pwm-sprd.c @@ -109,6 +109,7 @@ static int sprd_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, duty = val & SPRD_PWM_DUTY_MSK; tmp = (prescale + 1) * NSEC_PER_SEC * duty; state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, chn->clk_rate); + state->polarity = PWM_POLARITY_NORMAL; /* Disable PWM clocks if the PWM channel is not in enable state. */ if (!state->enabled) diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c index 529963a7e4f5..41537c45f036 100644 --- a/drivers/regulator/fan53555.c +++ b/drivers/regulator/fan53555.c @@ -8,18 +8,19 @@ // Copyright (c) 2012 Marvell Technology Ltd. // Yunfan Zhang <yfzhang@marvell.com> +#include <linux/bits.h> +#include <linux/err.h> +#include <linux/i2c.h> #include <linux/module.h> +#include <linux/of_device.h> #include <linux/param.h> -#include <linux/err.h> #include <linux/platform_device.h> +#include <linux/regmap.h> #include <linux/regulator/driver.h> +#include <linux/regulator/fan53555.h> #include <linux/regulator/machine.h> #include <linux/regulator/of_regulator.h> -#include <linux/of_device.h> -#include <linux/i2c.h> #include <linux/slab.h> -#include <linux/regmap.h> -#include <linux/regulator/fan53555.h> /* Voltage setting */ #define FAN53555_VSEL0 0x00 @@ -60,7 +61,7 @@ #define TCS_VSEL1_MODE (1 << 6) #define TCS_SLEW_SHIFT 3 -#define TCS_SLEW_MASK (0x3 < 3) +#define TCS_SLEW_MASK GENMASK(4, 3) enum fan53555_vendor { FAN53526_VENDOR_FAIRCHILD = 0, diff --git a/drivers/regulator/sm5703-regulator.c b/drivers/regulator/sm5703-regulator.c index 05ad28fc4da8..229df7170792 100644 --- a/drivers/regulator/sm5703-regulator.c +++ b/drivers/regulator/sm5703-regulator.c @@ -42,6 +42,7 @@ static const int sm5703_buck_voltagemap[] = { .type = REGULATOR_VOLTAGE, \ .id = SM5703_USBLDO ## _id, \ .ops = &sm5703_regulator_ops_fixed, \ + .n_voltages = 1, \ .fixed_uV = SM5703_USBLDO_MICROVOLT, \ .enable_reg = SM5703_REG_USBLDO12, \ .enable_mask = SM5703_REG_EN_USBLDO ##_id, \ @@ -56,6 +57,7 @@ static const int sm5703_buck_voltagemap[] = { .type = REGULATOR_VOLTAGE, \ .id = SM5703_VBUS, \ .ops = &sm5703_regulator_ops_fixed, \ + .n_voltages = 1, \ .fixed_uV = SM5703_VBUS_MICROVOLT, \ .enable_reg = SM5703_REG_CNTL, \ .enable_mask = SM5703_OPERATION_MODE_MASK, \ diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index c76f82fb8b63..15f452908926 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -771,13 +771,12 @@ static int iscsi_sw_tcp_conn_set_param(struct iscsi_cls_conn *cls_conn, iscsi_set_param(cls_conn, param, buf, buflen); break; case ISCSI_PARAM_DATADGST_EN: - iscsi_set_param(cls_conn, param, buf, buflen); - mutex_lock(&tcp_sw_conn->sock_lock); if (!tcp_sw_conn->sock) { mutex_unlock(&tcp_sw_conn->sock_lock); return -ENOTCONN; } + iscsi_set_param(cls_conn, param, buf, buflen); tcp_sw_conn->sendpage = conn->datadgst_en ? sock_no_sendpage : tcp_sw_conn->sock->ops->sendpage; mutex_unlock(&tcp_sw_conn->sock_lock); diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index a565817aa56d..d109a4ceb72b 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -2526,7 +2526,7 @@ static void mpi3mr_watchdog_work(struct work_struct *work) mrioc->unrecoverable = 1; goto schedule_work; case MPI3_SYSIF_FAULT_CODE_SOFT_RESET_IN_PROGRESS: - return; + goto schedule_work; case MPI3_SYSIF_FAULT_CODE_CI_ACTIVATION_RESET: reset_reason = MPI3MR_RESET_FROM_CIACTIV_FAULT; break; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bee1b8a82020..d0cdbfe771a9 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3617,6 +3617,7 @@ skip_dpc: probe_failed: qla_enode_stop(base_vha); qla_edb_stop(base_vha); + vfree(base_vha->scan.l); if (base_vha->gnl.l) { dma_free_coherent(&ha->pdev->dev, base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index b11a9162e73a..b54f2c6c08c3 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -509,9 +509,6 @@ static int ses_enclosure_find_by_addr(struct enclosure_device *edev, int i; struct ses_component *scomp; - if (!edev->component[0].scratch) - return 0; - for (i = 0; i < edev->components; i++) { scomp = edev->component[i].scratch; if (scomp->addr != efd->addr) @@ -602,8 +599,10 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, components++, type_ptr[0], name); - else + else if (components < edev->components) ecomp = &edev->component[components++]; + else + ecomp = ERR_PTR(-EINVAL); if (!IS_ERR(ecomp)) { if (addl_desc_ptr) { @@ -734,11 +733,6 @@ static int ses_intf_add(struct device *cdev, components += type_ptr[1]; } - if (components == 0) { - sdev_printk(KERN_WARNING, sdev, "enclosure has no enumerated components\n"); - goto err_free; - } - ses_dev->page1 = buf; ses_dev->page1_len = len; buf = NULL; @@ -780,9 +774,11 @@ static int ses_intf_add(struct device *cdev, buf = NULL; } page2_not_supported: - scomp = kcalloc(components, sizeof(struct ses_component), GFP_KERNEL); - if (!scomp) - goto err_free; + if (components > 0) { + scomp = kcalloc(components, sizeof(struct ses_component), GFP_KERNEL); + if (!scomp) + goto err_free; + } edev = enclosure_register(cdev->parent, dev_name(&sdev->sdev_gendev), components, &ses_enclosure_callbacks); diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c index bd87d3c92dd3..69347b6bf60c 100644 --- a/drivers/spi/spi-rockchip-sfc.c +++ b/drivers/spi/spi-rockchip-sfc.c @@ -632,7 +632,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) if (ret) { dev_err(dev, "Failed to request irq\n"); - return ret; + goto err_irq; } ret = rockchip_sfc_init(sfc); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 44b85a8d47f1..7bc14fb309a6 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -4456,6 +4456,11 @@ static int of_spi_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_OK; } + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; spi = of_register_spi_device(ctlr, rd->dn); put_device(&ctlr->dev); diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 290b1bb0e9cd..df5fb5410b72 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -488,7 +488,7 @@ static bool is_normal_memory(pgprot_t p) #elif defined(CONFIG_ARM64) return (pgprot_val(p) & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL); #else -#error "Unuspported architecture" +#error "Unsupported architecture" #endif } diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index b1c6231defad..673cf0359494 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -32,7 +32,7 @@ static int shm_get_kernel_pages(unsigned long start, size_t page_count, is_kmap_addr((void *)start))) return -EINVAL; - page = virt_to_page(start); + page = virt_to_page((void *)start); for (n = 0; n < page_count; n++) { pages[n] = page + n; get_page(pages[n]); diff --git a/drivers/thermal/intel/therm_throt.c b/drivers/thermal/intel/therm_throt.c index 2e22bb82b738..e69868e868eb 100644 --- a/drivers/thermal/intel/therm_throt.c +++ b/drivers/thermal/intel/therm_throt.c @@ -193,8 +193,67 @@ static const struct attribute_group thermal_attr_group = { #define THERM_THROT_POLL_INTERVAL HZ #define THERM_STATUS_PROCHOT_LOG BIT(1) -#define THERM_STATUS_CLEAR_CORE_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11) | BIT(13) | BIT(15)) -#define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11)) +static u64 therm_intr_core_clear_mask; +static u64 therm_intr_pkg_clear_mask; + +static void thermal_intr_init_core_clear_mask(void) +{ + if (therm_intr_core_clear_mask) + return; + + /* + * Reference: Intel SDM Volume 4 + * "Table 2-2. IA-32 Architectural MSRs", MSR 0x19C + * IA32_THERM_STATUS. + */ + + /* + * Bit 1, 3, 5: CPUID.01H:EDX[22] = 1. This driver will not + * enable interrupts, when 0 as it checks for X86_FEATURE_ACPI. + */ + therm_intr_core_clear_mask = (BIT(1) | BIT(3) | BIT(5)); + + /* + * Bit 7 and 9: Thermal Threshold #1 and #2 log + * If CPUID.01H:ECX[8] = 1 + */ + if (boot_cpu_has(X86_FEATURE_TM2)) + therm_intr_core_clear_mask |= (BIT(7) | BIT(9)); + + /* Bit 11: Power Limitation log (R/WC0) If CPUID.06H:EAX[4] = 1 */ + if (boot_cpu_has(X86_FEATURE_PLN)) + therm_intr_core_clear_mask |= BIT(11); + + /* + * Bit 13: Current Limit log (R/WC0) If CPUID.06H:EAX[7] = 1 + * Bit 15: Cross Domain Limit log (R/WC0) If CPUID.06H:EAX[7] = 1 + */ + if (boot_cpu_has(X86_FEATURE_HWP)) + therm_intr_core_clear_mask |= (BIT(13) | BIT(15)); +} + +static void thermal_intr_init_pkg_clear_mask(void) +{ + if (therm_intr_pkg_clear_mask) + return; + + /* + * Reference: Intel SDM Volume 4 + * "Table 2-2. IA-32 Architectural MSRs", MSR 0x1B1 + * IA32_PACKAGE_THERM_STATUS. + */ + + /* All bits except BIT 26 depend on CPUID.06H: EAX[6] = 1 */ + if (boot_cpu_has(X86_FEATURE_PTS)) + therm_intr_pkg_clear_mask = (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11)); + + /* + * Intel SDM Volume 2A: Thermal and Power Management Leaf + * Bit 26: CPUID.06H: EAX[19] = 1 + */ + if (boot_cpu_has(X86_FEATURE_HFI)) + therm_intr_pkg_clear_mask |= BIT(26); +} /* * Clear the bits in package thermal status register for bit = 1 @@ -207,13 +266,10 @@ void thermal_clear_package_intr_status(int level, u64 bit_mask) if (level == CORE_LEVEL) { msr = MSR_IA32_THERM_STATUS; - msr_val = THERM_STATUS_CLEAR_CORE_MASK; + msr_val = therm_intr_core_clear_mask; } else { msr = MSR_IA32_PACKAGE_THERM_STATUS; - msr_val = THERM_STATUS_CLEAR_PKG_MASK; - if (boot_cpu_has(X86_FEATURE_HFI)) - msr_val |= BIT(26); - + msr_val = therm_intr_pkg_clear_mask; } msr_val &= ~bit_mask; @@ -708,6 +764,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c) h = THERMAL_APIC_VECTOR | APIC_DM_FIXED | APIC_LVT_MASKED; apic_write(APIC_LVTTHMR, h); + thermal_intr_init_core_clear_mask(); + thermal_intr_init_pkg_clear_mask(); + rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) wrmsr(MSR_IA32_THERM_INTERRUPT, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fa43df05342b..3ba9c8b93ae6 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1903,6 +1903,17 @@ EXPORT_SYMBOL_GPL(serial8250_modem_status); static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) { switch (iir & 0x3f) { + case UART_IIR_THRI: + /* + * Postpone DMA or not decision to IIR_RDI or IIR_RX_TIMEOUT + * because it's impossible to do an informed decision about + * that with IIR_THRI. + * + * This also fixes one known DMA Rx corruption issue where + * DR is asserted but DMA Rx only gets a corrupted zero byte + * (too early DR?). + */ + return false; case UART_IIR_RDI: if (!up->dma->rx_running) break; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 56e6ba3250cd..074bfed57fc9 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -858,11 +858,17 @@ static unsigned int lpuart32_tx_empty(struct uart_port *port) struct lpuart_port, port); unsigned long stat = lpuart32_read(port, UARTSTAT); unsigned long sfifo = lpuart32_read(port, UARTFIFO); + unsigned long ctrl = lpuart32_read(port, UARTCTRL); if (sport->dma_tx_in_progress) return 0; - if (stat & UARTSTAT_TC && sfifo & UARTFIFO_TXEMPT) + /* + * LPUART Transmission Complete Flag may never be set while queuing a break + * character, so avoid checking for transmission complete when UARTCTRL_SBK + * is asserted. + */ + if ((stat & UARTSTAT_TC && sfifo & UARTFIFO_TXEMPT) || ctrl & UARTCTRL_SBK) return TIOCSER_TEMT; return 0; @@ -2942,7 +2948,7 @@ static bool lpuart_uport_is_active(struct lpuart_port *sport) tty = tty_port_tty_get(port); if (tty) { tty_dev = tty->dev; - may_wake = device_may_wakeup(tty_dev); + may_wake = tty_dev && device_may_wakeup(tty_dev); tty_kref_put(tty); } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 7bd080720929..caa09a0c48f4 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -31,6 +31,7 @@ #include <linux/ioport.h> #include <linux/ktime.h> #include <linux/major.h> +#include <linux/minmax.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/of.h> @@ -2864,6 +2865,13 @@ static int sci_init_single(struct platform_device *dev, sci_port->irqs[i] = platform_get_irq(dev, i); } + /* + * The fourth interrupt on SCI port is transmit end interrupt, so + * shuffle the interrupts. + */ + if (p->type == PORT_SCI) + swap(sci_port->irqs[SCIx_BRI_IRQ], sci_port->irqs[SCIx_TEI_IRQ]); + /* The SCI generates several interrupts. They can be muxed together or * connected to different interrupt lines. In the muxed case only one * interrupt resource is specified as there is only one interrupt ID. @@ -2929,7 +2937,7 @@ static int sci_init_single(struct platform_device *dev, port->flags = UPF_FIXED_PORT | UPF_BOOT_AUTOCONF | p->flags; port->fifosize = sci_port->params->fifosize; - if (port->type == PORT_SCI) { + if (port->type == PORT_SCI && !dev->dev.of_node) { if (sci_port->reg_size >= 0x20) port->regshift = 2; else diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 37e178a9ac47..70b112038792 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1409,13 +1409,6 @@ static int ufshcd_devfreq_target(struct device *dev, struct ufs_clk_info *clki; unsigned long irq_flags; - /* - * Skip devfreq if UFS initialization is not finished. - * Otherwise ufs could be in a inconsistent state. - */ - if (!smp_load_acquire(&hba->logical_unit_scan_finished)) - return 0; - if (!ufshcd_is_clkscaling_supported(hba)) return -EINVAL; @@ -8399,6 +8392,22 @@ static int ufshcd_add_lus(struct ufs_hba *hba) if (ret) goto out; + /* Initialize devfreq after UFS device is detected */ + if (ufshcd_is_clkscaling_supported(hba)) { + memcpy(&hba->clk_scaling.saved_pwr_info.info, + &hba->pwr_info, + sizeof(struct ufs_pa_layer_attr)); + hba->clk_scaling.saved_pwr_info.is_valid = true; + hba->clk_scaling.is_allowed = true; + + ret = ufshcd_devfreq_init(hba); + if (ret) + goto out; + + hba->clk_scaling.is_enabled = true; + ufshcd_init_clk_scaling_sysfs(hba); + } + ufs_bsg_probe(hba); ufshpb_init(hba); scsi_scan_host(hba->host); @@ -8670,12 +8679,6 @@ out: if (ret) { pm_runtime_put_sync(hba->dev); ufshcd_hba_exit(hba); - } else { - /* - * Make sure that when reader code sees UFS initialization has finished, - * all initialization steps have really been executed. - */ - smp_store_release(&hba->logical_unit_scan_finished, true); } } @@ -10316,30 +10319,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) */ ufshcd_set_ufs_dev_active(hba); - /* Initialize devfreq */ - if (ufshcd_is_clkscaling_supported(hba)) { - memcpy(&hba->clk_scaling.saved_pwr_info.info, - &hba->pwr_info, - sizeof(struct ufs_pa_layer_attr)); - hba->clk_scaling.saved_pwr_info.is_valid = true; - hba->clk_scaling.is_allowed = true; - - err = ufshcd_devfreq_init(hba); - if (err) - goto rpm_put_sync; - - hba->clk_scaling.is_enabled = true; - ufshcd_init_clk_scaling_sysfs(hba); - } - async_schedule(ufshcd_async_scan, hba); ufs_sysfs_add_nodes(hba->dev); device_enable_async_suspend(dev); return 0; -rpm_put_sync: - pm_runtime_put_sync(dev); free_tmf_queue: blk_mq_destroy_queue(hba->tmf_queue); blk_put_queue(hba->tmf_queue); diff --git a/drivers/usb/cdns3/cdnsp-ep0.c b/drivers/usb/cdns3/cdnsp-ep0.c index d63d5d92f255..f317d3c84781 100644 --- a/drivers/usb/cdns3/cdnsp-ep0.c +++ b/drivers/usb/cdns3/cdnsp-ep0.c @@ -414,7 +414,7 @@ static int cdnsp_ep0_std_request(struct cdnsp_device *pdev, void cdnsp_setup_analyze(struct cdnsp_device *pdev) { struct usb_ctrlrequest *ctrl = &pdev->setup; - int ret = 0; + int ret = -EINVAL; u16 len; trace_cdnsp_ctrl_req(ctrl); @@ -424,7 +424,6 @@ void cdnsp_setup_analyze(struct cdnsp_device *pdev) if (pdev->gadget.state == USB_STATE_NOTATTACHED) { dev_err(pdev->dev, "ERR: Setup detected in unattached state\n"); - ret = -EINVAL; goto out; } diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index a23ddbb81979..560793545362 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -49,6 +49,7 @@ #define PCI_DEVICE_ID_INTEL_RPLS 0x7a61 #define PCI_DEVICE_ID_INTEL_MTLM 0x7eb1 #define PCI_DEVICE_ID_INTEL_MTLP 0x7ec1 +#define PCI_DEVICE_ID_INTEL_MTLS 0x7f6f #define PCI_DEVICE_ID_INTEL_MTL 0x7e7e #define PCI_DEVICE_ID_INTEL_TGL 0x9a15 #define PCI_DEVICE_ID_AMD_MR 0x163a @@ -474,6 +475,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLP), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLS), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ddfc537c7526..56cdfb2e4211 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1251,7 +1251,7 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) p->kiocb = kiocb; if (p->aio) { p->to_free = dup_iter(&p->data, to, GFP_KERNEL); - if (!p->to_free) { + if (!iter_is_ubuf(&p->data) && !p->to_free) { kfree(p); return -ENOMEM; } diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index d605bc2e7e8f..28249d0bf062 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -614,7 +614,7 @@ ep_read_iter(struct kiocb *iocb, struct iov_iter *to) if (!priv) goto fail; priv->to_free = dup_iter(&priv->to, to, GFP_KERNEL); - if (!priv->to_free) { + if (!iter_is_ubuf(&priv->to) && !priv->to_free) { kfree(priv); goto fail; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index fb988e4ea924..6db07ca419c3 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -771,12 +771,11 @@ static struct pci_driver xhci_pci_driver = { /* suspend and resume implemented later */ .shutdown = usb_hcd_pci_shutdown, - .driver = { #ifdef CONFIG_PM - .pm = &usb_hcd_pci_pm_ops, -#endif - .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .driver = { + .pm = &usb_hcd_pci_pm_ops }, +#endif }; static int __init xhci_pci_init(void) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 1ff22f675930..a88c39e525c2 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1360,6 +1360,9 @@ static void tegra_xhci_id_work(struct work_struct *work) mutex_unlock(&tegra->lock); + tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl, + tegra->otg_usb2_port); + if (tegra->host_mode) { /* switch to host mode */ if (tegra->otg_usb3_port >= 0) { @@ -1474,9 +1477,6 @@ static int tegra_xhci_id_notify(struct notifier_block *nb, } tegra->otg_usb2_port = tegra_xusb_get_usb2_port(tegra, usbphy); - tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion( - tegra->padctl, - tegra->otg_usb2_port); tegra->host_mode = (usbphy->last_event == USB_EVENT_ID) ? true : false; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6183ce8574b1..6307bae9cddf 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -9,6 +9,7 @@ */ #include <linux/pci.h> +#include <linux/iommu.h> #include <linux/iopoll.h> #include <linux/irq.h> #include <linux/log2.h> @@ -228,6 +229,7 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us) static void xhci_zero_64b_regs(struct xhci_hcd *xhci) { struct device *dev = xhci_to_hcd(xhci)->self.sysdev; + struct iommu_domain *domain; int err, i; u64 val; u32 intrs; @@ -246,7 +248,9 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci) * an iommu. Doing anything when there is no iommu is definitely * unsafe... */ - if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !device_iommu_mapped(dev)) + domain = iommu_get_domain_for_dev(dev); + if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !domain || + domain->type == IOMMU_DOMAIN_IDENTITY) return; xhci_info(xhci, "Zeroing 64bit base registers, expecting fault\n"); @@ -4438,6 +4442,7 @@ static int __maybe_unused xhci_change_max_exit_latency(struct xhci_hcd *xhci, if (!virt_dev || max_exit_latency == virt_dev->current_mel) { spin_unlock_irqrestore(&xhci->lock, flags); + xhci_free_command(xhci, command); return 0; } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 832ad592b7ef..cdea1bff3b70 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -120,6 +120,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */ { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */ { USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */ + { USB_DEVICE(0x10C4, 0x82AA) }, /* Silicon Labs IFS-USB-DATACABLE used with Quint UPS */ { USB_DEVICE(0x10C4, 0x82EF) }, /* CESINEL FALCO 6105 AC Power Supply */ { USB_DEVICE(0x10C4, 0x82F1) }, /* CESINEL MEDCAL EFD Earth Fault Detector */ { USB_DEVICE(0x10C4, 0x82F2) }, /* CESINEL MEDCAL ST Network Analyzer */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e6d8d9b35ad0..f31cc3c76329 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1198,6 +1198,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, 0x0900, 0xff, 0, 0), /* RM500U-CN */ + .driver_info = ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, @@ -1300,6 +1302,14 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ .driver_info = RSVD(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990 (rmnet) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff), /* Telit FE990 (MBIM) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1082, 0xff), /* Telit FE990 (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 662cd043b50e..8f3e884222ad 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -112,8 +112,12 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con) if (dp->data.status & DP_STATUS_PREFER_MULTI_FUNC && pin_assign & DP_PIN_ASSIGN_MULTI_FUNC_MASK) pin_assign &= DP_PIN_ASSIGN_MULTI_FUNC_MASK; - else if (pin_assign & DP_PIN_ASSIGN_DP_ONLY_MASK) + else if (pin_assign & DP_PIN_ASSIGN_DP_ONLY_MASK) { pin_assign &= DP_PIN_ASSIGN_DP_ONLY_MASK; + /* Default to pin assign C if available */ + if (pin_assign & BIT(DP_PIN_ASSIGN_C)) + pin_assign = BIT(DP_PIN_ASSIGN_C); + } if (!pin_assign) return -EINVAL; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 520646ae7fa0..195963b82b63 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2467,10 +2467,11 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) err = 0; goto out; } + mlx5_vdpa_add_debugfs(ndev); err = setup_virtqueues(mvdev); if (err) { mlx5_vdpa_warn(mvdev, "setup_virtqueues\n"); - goto out; + goto err_setup; } err = create_rqt(ndev); @@ -2500,6 +2501,8 @@ err_tir: destroy_rqt(ndev); err_rqt: teardown_virtqueues(ndev); +err_setup: + mlx5_vdpa_remove_debugfs(ndev->debugfs); out: return err; } @@ -2513,6 +2516,8 @@ static void teardown_driver(struct mlx5_vdpa_net *ndev) if (!ndev->setup) return; + mlx5_vdpa_remove_debugfs(ndev->debugfs); + ndev->debugfs = NULL; teardown_steering(ndev); destroy_tir(ndev); destroy_rqt(ndev); @@ -3261,7 +3266,6 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_reg; - mlx5_vdpa_add_debugfs(ndev); mgtdev->ndev = ndev; return 0; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index 862f405362de..dfe2ce341803 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -466,16 +466,21 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, vdpasim_net_setup_config(simdev, config); - ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM); - if (ret) - goto reg_err; - net = sim_to_net(simdev); u64_stats_init(&net->tx_stats.syncp); u64_stats_init(&net->rx_stats.syncp); u64_stats_init(&net->cq_stats.syncp); + /* + * Initialization must be completed before this call, since it can + * connect the device to the vDPA bus, so requests can arrive after + * this call. + */ + ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM); + if (ret) + goto reg_err; + return 0; reg_err: diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index b244e7c0f514..32d0be968103 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -125,7 +125,6 @@ struct vhost_scsi_tpg { struct se_portal_group se_tpg; /* Pointer back to vhost_scsi, protected by tv_tpg_mutex */ struct vhost_scsi *vhost_scsi; - struct list_head tmf_queue; }; struct vhost_scsi_tport { @@ -206,10 +205,8 @@ struct vhost_scsi { struct vhost_scsi_tmf { struct vhost_work vwork; - struct vhost_scsi_tpg *tpg; struct vhost_scsi *vhost; struct vhost_scsi_virtqueue *svq; - struct list_head queue_entry; struct se_cmd se_cmd; u8 scsi_resp; @@ -352,12 +349,9 @@ static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd) static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf) { - struct vhost_scsi_tpg *tpg = tmf->tpg; struct vhost_scsi_inflight *inflight = tmf->inflight; - mutex_lock(&tpg->tv_tpg_mutex); - list_add_tail(&tpg->tmf_queue, &tmf->queue_entry); - mutex_unlock(&tpg->tv_tpg_mutex); + kfree(tmf); vhost_scsi_put_inflight(inflight); } @@ -1194,19 +1188,11 @@ vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg, goto send_reject; } - mutex_lock(&tpg->tv_tpg_mutex); - if (list_empty(&tpg->tmf_queue)) { - pr_err("Missing reserve TMF. Could not handle LUN RESET.\n"); - mutex_unlock(&tpg->tv_tpg_mutex); + tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); + if (!tmf) goto send_reject; - } - - tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, - queue_entry); - list_del_init(&tmf->queue_entry); - mutex_unlock(&tpg->tv_tpg_mutex); - tmf->tpg = tpg; + vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); tmf->vhost = vs; tmf->svq = svq; tmf->resp_iov = vq->iov[vc->out]; @@ -1658,7 +1644,10 @@ undepend: for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { tpg = vs_tpg[i]; if (tpg) { + mutex_lock(&tpg->tv_tpg_mutex); + tpg->vhost_scsi = NULL; tpg->tv_tpg_vhost_count--; + mutex_unlock(&tpg->tv_tpg_mutex); target_undepend_item(&tpg->se_tpg.tpg_group.cg_item); } } @@ -2032,19 +2021,11 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tmf *tmf; - - tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); - if (!tmf) - return -ENOMEM; - INIT_LIST_HEAD(&tmf->queue_entry); - vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; - list_add_tail(&tmf->queue_entry, &tpg->tmf_queue); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotplug(tpg, lun); @@ -2059,16 +2040,11 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tmf *tmf; mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; - tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, - queue_entry); - list_del(&tmf->queue_entry); - kfree(tmf); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotunplug(tpg, lun); @@ -2329,7 +2305,6 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name) } mutex_init(&tpg->tv_tpg_mutex); INIT_LIST_HEAD(&tpg->tv_tpg_list); - INIT_LIST_HEAD(&tpg->tmf_queue); tpg->tport = tport; tpg->tport_tpgt = tpgt; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 0a2c47df01f4..eb565a10e5cd 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -823,7 +823,7 @@ static int set_con2fb_map(int unit, int newidx, int user) int oldidx = con2fb_map[unit]; struct fb_info *info = fbcon_registered_fb[newidx]; struct fb_info *oldinfo = NULL; - int found, err = 0, show_logo; + int err = 0, show_logo; WARN_CONSOLE_UNLOCKED(); @@ -841,26 +841,26 @@ static int set_con2fb_map(int unit, int newidx, int user) if (oldidx != -1) oldinfo = fbcon_registered_fb[oldidx]; - found = search_fb_in_map(newidx); - - if (!err && !found) { + if (!search_fb_in_map(newidx)) { err = con2fb_acquire_newinfo(vc, info, unit); - if (!err) - con2fb_map[unit] = newidx; + if (err) + return err; + + fbcon_add_cursor_work(info); } + con2fb_map[unit] = newidx; + /* * If old fb is not mapped to any of the consoles, * fbcon should release it. */ - if (!err && oldinfo && !search_fb_in_map(oldidx)) + if (oldinfo && !search_fb_in_map(oldidx)) con2fb_release_oldinfo(vc, oldinfo, info); show_logo = (fg_console == 0 && !user && logo_shown != FBCON_LOGO_DONTSHOW); - if (!found) - fbcon_add_cursor_work(info); con2fb_map_boot[unit] = newidx; con2fb_init_display(vc, info, unit, show_logo); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 875541ff185b..3fd95a79e4c3 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1116,6 +1116,8 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd, case FBIOPUT_VSCREENINFO: if (copy_from_user(&var, argp, sizeof(var))) return -EFAULT; + /* only for kernel-internal use */ + var.activate &= ~FB_ACTIVATE_KD_TEXT; console_lock(); lock_fb_info(info); ret = fbcon_modechange_possible(info, &var); diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 50f7f3f6b55e..1974a38bce20 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -35,10 +35,12 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, return retval; } if (attr_size > buffer_size) { - if (!buffer_size) /* request to get the attr_size */ - retval = attr_size; - else + if (buffer_size) retval = -ERANGE; + else if (attr_size > SSIZE_MAX) + retval = -EOVERFLOW; + else /* request to get the attr_size */ + retval = attr_size; } else { iov_iter_truncate(&to, attr_size); retval = p9_client_read(attr_fid, 0, &to, &err); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b53f0e30ce2b..9e1596bb208d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2250,6 +2250,20 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) fs_info->csum_shash = csum_shash; + /* + * Check if the checksum implementation is a fast accelerated one. + * As-is this is a bit of a hack and should be replaced once the csum + * implementations provide that information themselves. + */ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + default: + break; + } + btrfs_info(fs_info, "using %s (%s) checksum algorithm", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(csum_shash)); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 581845bc206a..366fb4cde145 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1516,8 +1516,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); btrfs_sb(s)->bdev_holder = fs_type; - if (!strstr(crc32c_impl(), "generic")) - set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); error = btrfs_fill_super(s, fs_devices, data); } if (!error) @@ -1631,6 +1629,8 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, btrfs_workqueue_set_max(fs_info->hipri_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_meta_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size); btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 0d30b17494e4..9d963caec35c 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -120,7 +120,7 @@ again: spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect) { spin_unlock(&server->srv_lock); - mutex_lock(&ses->session_mutex); + mutex_unlock(&ses->session_mutex); if (tcon->retry) goto again; diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 6d13f8207e96..ace11a1a7c8a 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -441,13 +441,14 @@ out: * but there are some bugs that prevent rename from working if there are * multiple delimiters. * - * Returns a sanitized duplicate of @path. The caller is responsible for - * cleaning up the original. + * Returns a sanitized duplicate of @path. @gfp indicates the GFP_* flags + * for kstrdup. + * The caller is responsible for freeing the original. */ #define IS_DELIM(c) ((c) == '/' || (c) == '\\') -static char *sanitize_path(char *path) +char *cifs_sanitize_prepath(char *prepath, gfp_t gfp) { - char *cursor1 = path, *cursor2 = path; + char *cursor1 = prepath, *cursor2 = prepath; /* skip all prepended delimiters */ while (IS_DELIM(*cursor1)) @@ -469,7 +470,7 @@ static char *sanitize_path(char *path) cursor2--; *(cursor2) = '\0'; - return kstrdup(path, GFP_KERNEL); + return kstrdup(prepath, gfp); } /* @@ -531,7 +532,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) if (!*pos) return 0; - ctx->prepath = sanitize_path(pos); + ctx->prepath = cifs_sanitize_prepath(pos, GFP_KERNEL); if (!ctx->prepath) return -ENOMEM; diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index 3de00e7127ec..f4eaf8558902 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -287,4 +287,7 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); */ #define SMB3_MAX_DCLOSETIMEO (1 << 30) #define SMB3_DEF_DCLOSETIMEO (1 * HZ) /* even 1 sec enough to help eg open/write/close/open/read */ + +extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); + #endif diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index b44fb51968bf..7f085ed2d866 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1195,7 +1195,7 @@ int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix) kfree(cifs_sb->prepath); if (prefix && *prefix) { - cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC); + cifs_sb->prepath = cifs_sanitize_prepath(prefix, GFP_ATOMIC); if (!cifs_sb->prepath) return -ENOMEM; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2b92132097dc..4245249dbba8 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -587,11 +587,15 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, } +/* If invalid preauth context warn but use what we requested, SHA-512 */ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) { unsigned int len = le16_to_cpu(ctxt->DataLength); - /* If invalid preauth context warn but use what we requested, SHA-512 */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one HashAlgorithms member is accounted for. + */ if (len < MIN_PREAUTH_CTXT_DATA_LEN) { pr_warn_once("server sent bad preauth context\n"); return; @@ -610,7 +614,11 @@ static void decode_compress_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(ctxt->DataLength); - /* sizeof compress context is a one element compression capbility struct */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one CompressionAlgorithms member is accounted + * for. + */ if (len < 10) { pr_warn_once("server sent bad compression cntxt\n"); return; @@ -632,6 +640,11 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server, unsigned int len = le16_to_cpu(ctxt->DataLength); cifs_dbg(FYI, "decode SMB3.11 encryption neg context of len %d\n", len); + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one Cipher flexible array member is accounted + * for. + */ if (len < MIN_ENCRYPT_CTXT_DATA_LEN) { pr_warn_once("server sent bad crypto ctxt len\n"); return -EINVAL; @@ -678,6 +691,11 @@ static void decode_signing_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(pctxt->DataLength); + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one SigningAlgorithms flexible array member is + * accounted for. + */ if ((len < 4) || (len > 16)) { pr_warn_once("server sent bad signing negcontext\n"); return; @@ -719,14 +737,19 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, for (i = 0; i < ctxt_cnt; i++) { int clen; /* check that offset is not beyond end of SMB */ - if (len_of_ctxts == 0) - break; - if (len_of_ctxts < sizeof(struct smb2_neg_context)) break; pctx = (struct smb2_neg_context *)(offset + (char *)rsp); - clen = le16_to_cpu(pctx->DataLength); + clen = sizeof(struct smb2_neg_context) + + le16_to_cpu(pctx->DataLength); + /* + * 2.2.4 SMB2 NEGOTIATE Response + * Subsequent negotiate contexts MUST appear at the first 8-byte + * aligned offset following the previous negotiate context. + */ + if (i + 1 != ctxt_cnt) + clen = ALIGN(clen, 8); if (clen > len_of_ctxts) break; @@ -747,12 +770,10 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, else cifs_server_dbg(VFS, "unknown negcontext of type %d ignored\n", le16_to_cpu(pctx->ContextType)); - if (rc) break; - /* offsets must be 8 byte aligned */ - clen = ALIGN(clen, 8); - offset += clen + sizeof(struct smb2_neg_context); + + offset += clen; len_of_ctxts -= clen; } return rc; @@ -781,6 +781,33 @@ out: return ret; } +static int __dax_clear_dirty_range(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + XA_STATE(xas, &mapping->i_pages, start); + unsigned int scanned = 0; + void *entry; + + xas_lock_irq(&xas); + xas_for_each(&xas, entry, end) { + entry = get_unlocked_entry(&xas, 0); + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + put_unlocked_entry(&xas, entry, WAKE_NEXT); + + if (++scanned % XA_CHECK_SCHED) + continue; + + xas_pause(&xas); + xas_unlock_irq(&xas); + cond_resched(); + xas_lock_irq(&xas); + } + xas_unlock_irq(&xas); + + return 0; +} + /* * Delete DAX entry at @index from @mapping. Wait for it * to be unlocked before deleting it. @@ -1258,15 +1285,20 @@ static s64 dax_unshare_iter(struct iomap_iter *iter) /* don't bother with blocks that are not shared to start with */ if (!(iomap->flags & IOMAP_F_SHARED)) return length; - /* don't bother with holes or unwritten extents */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) - return length; id = dax_read_lock(); ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL); if (ret < 0) goto out_unlock; + /* zero the distance if srcmap is HOLE or UNWRITTEN */ + if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) { + memset(daddr, 0, length); + dax_flush(iomap->dax_dev, daddr, length); + ret = length; + goto out_unlock; + } + ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL); if (ret < 0) goto out_unlock; @@ -1435,6 +1467,16 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, * written by write(2) is visible in mmap. */ if (iomap->flags & IOMAP_F_NEW || cow) { + /* + * Filesystem allows CoW on non-shared extents. The src extents + * may have been mmapped with dirty mark before. To be able to + * invalidate its dax entries, we need to clear the dirty mark + * in advance. + */ + if (cow) + __dax_clear_dirty_range(iomi->inode->i_mapping, + pos >> PAGE_SHIFT, + (end - 1) >> PAGE_SHIFT); invalidate_inode_pages2_range(iomi->inode->i_mapping, pos >> PAGE_SHIFT, (end - 1) >> PAGE_SHIFT); @@ -2022,8 +2064,8 @@ int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, while ((ret = iomap_iter(&src_iter, ops)) > 0 && (ret = iomap_iter(&dst_iter, ops)) > 0) { - compared = dax_range_compare_iter(&src_iter, &dst_iter, len, - same); + compared = dax_range_compare_iter(&src_iter, &dst_iter, + min(src_iter.len, dst_iter.len), same); if (compared < 0) return ret; src_iter.processed = dst_iter.processed = compared; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 195dc23e0d83..1db3e3c24b43 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -978,6 +978,16 @@ restart: continue; } + /* + * If wb_tryget fails, the wb has been shutdown, skip it. + * + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + if (!wb_tryget(wb)) + continue; + /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; @@ -986,13 +996,6 @@ restart: work->done = &fallback_work_done; wb_queue_work(wb, work); - - /* - * Pin @wb so that it stays on @bdi->wb_list. This allows - * continuing iteration from @wb after dropping and - * regrabbing rcu read lock. - */ - wb_get(wb); last_wb = wb; rcu_read_unlock(); diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 115a67d2cf78..365ac32af505 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -112,10 +112,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct list_head *requests_queue = NULL; - if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) { + if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; - work->synchronous = true; - } if (requests_queue) { atomic_inc(&conn->req_running); @@ -136,14 +134,14 @@ int ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) if (!work->multiRsp) atomic_dec(&conn->req_running); - spin_lock(&conn->request_lock); if (!work->multiRsp) { + spin_lock(&conn->request_lock); list_del_init(&work->request_entry); - if (!work->synchronous) - list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + if (work->asynchronous) + release_async_work(work); ret = 0; } - spin_unlock(&conn->request_lock); wake_up_all(&conn->req_running_q); return ret; @@ -326,10 +324,7 @@ int ksmbd_conn_handler_loop(void *p) /* 4 for rfc1002 length field */ size = pdu_size + 4; - conn->request_buf = kvmalloc(size, - GFP_KERNEL | - __GFP_NOWARN | - __GFP_NORETRY); + conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; diff --git a/fs/ksmbd/ksmbd_work.h b/fs/ksmbd/ksmbd_work.h index 3234f2cf6327..f8ae6144c0ae 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/ksmbd/ksmbd_work.h @@ -68,7 +68,7 @@ struct ksmbd_work { /* Request is encrypted */ bool encrypted:1; /* Is this SYNC or ASYNC ksmbd_work */ - bool synchronous:1; + bool asynchronous:1; bool need_invalidate_rkey:1; unsigned int remote_key; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 394b6ceac431..0d8242789dc8 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -289,10 +289,7 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) work->request_buf = conn->request_buf; conn->request_buf = NULL; - if (ksmbd_init_smb_server(work)) { - ksmbd_free_work_struct(work); - return -EINVAL; - } + ksmbd_init_smb_server(work); ksmbd_conn_enqueue_request(work); atomic_inc(&conn->r_count); diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 97c9d1b5bcc0..67b7e766a06b 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -229,9 +229,6 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) struct smb2_negotiate_rsp *rsp; struct ksmbd_conn *conn = work->conn; - if (conn->need_neg == false) - return -EINVAL; - *(__be32 *)work->response_buf = cpu_to_be32(conn->vals->header_size); @@ -498,12 +495,6 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) rsp_hdr->SessionId = rcv_hdr->SessionId; memcpy(rsp_hdr->Signature, rcv_hdr->Signature, 16); - work->synchronous = true; - if (work->async_id) { - ksmbd_release_id(&conn->async_ida, work->async_id); - work->async_id = 0; - } - return 0; } @@ -644,7 +635,7 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) pr_err("Failed to alloc async message id\n"); return id; } - work->synchronous = false; + work->asynchronous = true; work->async_id = id; rsp_hdr->Id.AsyncId = cpu_to_le64(id); @@ -664,6 +655,24 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) return 0; } +void release_async_work(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + + spin_lock(&conn->request_lock); + list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + + work->asynchronous = 0; + work->cancel_fn = NULL; + kfree(work->cancel_argv); + work->cancel_argv = NULL; + if (work->async_id) { + ksmbd_release_id(&conn->async_ida, work->async_id); + work->async_id = 0; + } +} + void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) { struct smb2_hdr *rsp_hdr; @@ -867,17 +876,21 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, } static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, - struct smb2_preauth_neg_context *pneg_ctxt) + struct smb2_preauth_neg_context *pneg_ctxt, + int len_of_ctxts) { - __le32 err = STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP; + /* + * sizeof(smb2_preauth_neg_context) assumes SMB311_SALT_SIZE Salt, + * which may not be present. Only check for used HashAlgorithms[1]. + */ + if (len_of_ctxts < MIN_PREAUTH_CTXT_DATA_LEN) + return STATUS_INVALID_PARAMETER; - if (pneg_ctxt->HashAlgorithms == SMB2_PREAUTH_INTEGRITY_SHA512) { - conn->preauth_info->Preauth_HashId = - SMB2_PREAUTH_INTEGRITY_SHA512; - err = STATUS_SUCCESS; - } + if (pneg_ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) + return STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP; - return err; + conn->preauth_info->Preauth_HashId = SMB2_PREAUTH_INTEGRITY_SHA512; + return STATUS_SUCCESS; } static void decode_encrypt_ctxt(struct ksmbd_conn *conn, @@ -1005,7 +1018,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, break; status = decode_preauth_ctxt(conn, - (struct smb2_preauth_neg_context *)pctx); + (struct smb2_preauth_neg_context *)pctx, + len_of_ctxts); if (status != STATUS_SUCCESS) break; } else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) { @@ -7045,13 +7059,9 @@ skip: ksmbd_vfs_posix_lock_wait(flock); - spin_lock(&work->conn->request_lock); spin_lock(&fp->f_lock); list_del(&work->fp_entry); - work->cancel_fn = NULL; - kfree(argv); spin_unlock(&fp->f_lock); - spin_unlock(&work->conn->request_lock); if (work->state != KSMBD_WORK_ACTIVE) { list_del(&smb_lock->llist); @@ -7069,6 +7079,7 @@ skip: work->send_no_response = 1; goto out; } + init_smb2_rsp_hdr(work); smb2_set_err_rsp(work); rsp->hdr.Status = @@ -7081,7 +7092,7 @@ skip: spin_lock(&work->conn->llist_lock); list_del(&smb_lock->clist); spin_unlock(&work->conn->llist_lock); - + release_async_work(work); goto retry; } else if (!rc) { spin_lock(&work->conn->llist_lock); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index 0c8a770fe318..9420dd2813fb 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -486,6 +486,7 @@ int find_matching_smb2_dialect(int start_index, __le16 *cli_dialects, struct file_lock *smb_flock_init(struct file *f); int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg); +void release_async_work(struct ksmbd_work *work); void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status); struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn *conn); diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 9c1ce6d199ce..af0c2a9b8529 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -283,20 +283,121 @@ err_out: return BAD_PROT_ID; } -int ksmbd_init_smb_server(struct ksmbd_work *work) +#define SMB_COM_NEGOTIATE_EX 0x0 + +/** + * get_smb1_cmd_val() - get smb command value from smb header + * @work: smb work containing smb header + * + * Return: smb command value + */ +static u16 get_smb1_cmd_val(struct ksmbd_work *work) { - struct ksmbd_conn *conn = work->conn; + return SMB_COM_NEGOTIATE_EX; +} - if (conn->need_neg == false) +/** + * init_smb1_rsp_hdr() - initialize smb negotiate response header + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -EINVAL + */ +static int init_smb1_rsp_hdr(struct ksmbd_work *work) +{ + struct smb_hdr *rsp_hdr = (struct smb_hdr *)work->response_buf; + struct smb_hdr *rcv_hdr = (struct smb_hdr *)work->request_buf; + + /* + * Remove 4 byte direct TCP header. + */ + *(__be32 *)work->response_buf = + cpu_to_be32(sizeof(struct smb_hdr) - 4); + + rsp_hdr->Command = SMB_COM_NEGOTIATE; + *(__le32 *)rsp_hdr->Protocol = SMB1_PROTO_NUMBER; + rsp_hdr->Flags = SMBFLG_RESPONSE; + rsp_hdr->Flags2 = SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS | + SMBFLG2_EXT_SEC | SMBFLG2_IS_LONG_NAME; + rsp_hdr->Pid = rcv_hdr->Pid; + rsp_hdr->Mid = rcv_hdr->Mid; + return 0; +} + +/** + * smb1_check_user_session() - check for valid session for a user + * @work: smb work containing smb request buffer + * + * Return: 0 on success, otherwise error + */ +static int smb1_check_user_session(struct ksmbd_work *work) +{ + unsigned int cmd = work->conn->ops->get_cmd_val(work); + + if (cmd == SMB_COM_NEGOTIATE_EX) return 0; - init_smb3_11_server(conn); + return -EINVAL; +} + +/** + * smb1_allocate_rsp_buf() - allocate response buffer for a command + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -ENOMEM + */ +static int smb1_allocate_rsp_buf(struct ksmbd_work *work) +{ + work->response_buf = kmalloc(MAX_CIFS_SMALL_BUFFER_SIZE, + GFP_KERNEL | __GFP_ZERO); + work->response_sz = MAX_CIFS_SMALL_BUFFER_SIZE; + + if (!work->response_buf) { + pr_err("Failed to allocate %u bytes buffer\n", + MAX_CIFS_SMALL_BUFFER_SIZE); + return -ENOMEM; + } - if (conn->ops->get_cmd_val(work) != SMB_COM_NEGOTIATE) - conn->need_neg = false; return 0; } +static struct smb_version_ops smb1_server_ops = { + .get_cmd_val = get_smb1_cmd_val, + .init_rsp_hdr = init_smb1_rsp_hdr, + .allocate_rsp_buf = smb1_allocate_rsp_buf, + .check_user_session = smb1_check_user_session, +}; + +static int smb1_negotiate(struct ksmbd_work *work) +{ + return ksmbd_smb_negotiate_common(work, SMB_COM_NEGOTIATE); +} + +static struct smb_version_cmds smb1_server_cmds[1] = { + [SMB_COM_NEGOTIATE_EX] = { .proc = smb1_negotiate, }, +}; + +static void init_smb1_server(struct ksmbd_conn *conn) +{ + conn->ops = &smb1_server_ops; + conn->cmds = smb1_server_cmds; + conn->max_cmds = ARRAY_SIZE(smb1_server_cmds); +} + +void ksmbd_init_smb_server(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + __le32 proto; + + if (conn->need_neg == false) + return; + + proto = *(__le32 *)((struct smb_hdr *)work->request_buf)->Protocol; + if (proto == SMB1_PROTO_NUMBER) + init_smb1_server(conn); + else + init_smb3_11_server(conn); +} + int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, struct ksmbd_file *dir, struct ksmbd_dir_info *d_info, @@ -444,20 +545,10 @@ static int smb_handle_negotiate(struct ksmbd_work *work) ksmbd_debug(SMB, "Unsupported SMB1 protocol\n"); - /* - * Remove 4 byte direct TCP header, add 2 byte bcc and - * 2 byte DialectIndex. - */ - *(__be32 *)work->response_buf = - cpu_to_be32(sizeof(struct smb_hdr) - 4 + 2 + 2); + /* Add 2 byte bcc and 2 byte DialectIndex. */ + inc_rfc1001_len(work->response_buf, 4); neg_rsp->hdr.Status.CifsError = STATUS_SUCCESS; - neg_rsp->hdr.Command = SMB_COM_NEGOTIATE; - *(__le32 *)neg_rsp->hdr.Protocol = SMB1_PROTO_NUMBER; - neg_rsp->hdr.Flags = SMBFLG_RESPONSE; - neg_rsp->hdr.Flags2 = SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS | - SMBFLG2_EXT_SEC | SMBFLG2_IS_LONG_NAME; - neg_rsp->hdr.WordCount = 1; neg_rsp->DialectIndex = cpu_to_le16(work->conn->dialect); neg_rsp->ByteCount = 0; @@ -474,23 +565,12 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); if (command == SMB2_NEGOTIATE_HE) { - struct smb2_hdr *smb2_hdr = smb2_get_msg(work->request_buf); - - if (smb2_hdr->ProtocolId != SMB2_PROTO_NUMBER) { - ksmbd_debug(SMB, "Downgrade to SMB1 negotiation\n"); - command = SMB_COM_NEGOTIATE; - } - } - - if (command == SMB2_NEGOTIATE_HE) { ret = smb2_handle_negotiate(work); - init_smb2_neg_rsp(work); return ret; } if (command == SMB_COM_NEGOTIATE) { if (__smb2_negotiate(conn)) { - conn->need_neg = true; init_smb3_11_server(conn); init_smb2_neg_rsp(work); ksmbd_debug(SMB, "Upgrade to SMB2 negotiation\n"); diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index d30ce4c1a151..9130d2e3cd78 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -427,7 +427,7 @@ bool ksmbd_smb_request(struct ksmbd_conn *conn); int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count); -int ksmbd_init_smb_server(struct ksmbd_work *work); +void ksmbd_init_smb_server(struct ksmbd_work *work); struct ksmbd_kstat; int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, diff --git a/fs/ksmbd/unicode.c b/fs/ksmbd/unicode.c index a0db699ddafd..9ae676906ed3 100644 --- a/fs/ksmbd/unicode.c +++ b/fs/ksmbd/unicode.c @@ -114,24 +114,6 @@ cp_convert: } /* - * is_char_allowed() - check for valid character - * @ch: input character to be checked - * - * Return: 1 if char is allowed, otherwise 0 - */ -static inline int is_char_allowed(char *ch) -{ - /* check for control chars, wildcards etc. */ - if (!(*ch & 0x80) && - (*ch <= 0x1f || - *ch == '?' || *ch == '"' || *ch == '<' || - *ch == '>' || *ch == '|')) - return 0; - - return 1; -} - -/* * smb_from_utf16() - convert utf16le string to local charset * @to: destination buffer * @from: source buffer diff --git a/fs/namespace.c b/fs/namespace.c index bc0f15257b49..6836e937ee61 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4183,9 +4183,9 @@ out: unlock_mount_hash(); if (kattr->propagation) { - namespace_unlock(); if (err) cleanup_group_ids(mnt, NULL); + namespace_unlock(); } return err; diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index e9a45dea748a..8a4c86687429 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -139,7 +139,7 @@ static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter, size_t seg = min_t(size_t, PAGE_SIZE - off, len); *pages++ = NULL; - sg_set_page(sg, page, len, off); + sg_set_page(sg, page, seg, off); sgtable->nents++; sg++; len -= seg; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 450d6c3bc05e..c1c7ed2fd860 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -75,7 +75,6 @@ config NFS_V3_ACL config NFS_V4 tristate "NFS client support for NFS version 4" depends on NFS_FS - select RPCSEC_GSS_KRB5 select KEYS help This option enables support for version 4 of the NFS protocol diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 04697f8dc37d..01d7fd108cf3 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -297,6 +297,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb, out_free_dev: kfree(dev); + gdp->gd_device = NULL; return ret; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 2a815f5a52c4..4039ffcf90ba 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -946,8 +946,8 @@ static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct r if (!kcred) return NULL; - kcred->uid = ses->se_cb_sec.uid; - kcred->gid = ses->se_cb_sec.gid; + kcred->fsuid = ses->se_cb_sec.uid; + kcred->fsgid = ses->se_cb_sec.gid; return kcred; } } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index e12e5a4ad502..e2e485167ac4 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2476,10 +2476,12 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) for (i = 0; i < argp->opcnt; i++) { op = &argp->ops[i]; op->replay = NULL; + op->opdesc = NULL; if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0) return false; if (nfsd4_opnum_in_range(argp, op)) { + op->opdesc = OPDESC(op); op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); if (op->status != nfs_ok) trace_nfsd_compound_decode_err(argp->rqstp, @@ -2490,7 +2492,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; } - op->opdesc = OPDESC(op); + /* * We'll try to cache the result in the DRC if any one * op in the compound wants to be cached: @@ -5400,10 +5402,8 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) __be32 *p; p = xdr_reserve_space(xdr, 8); - if (!p) { - WARN_ON_ONCE(1); - return; - } + if (!p) + goto release; *p++ = cpu_to_be32(op->opnum); post_err_offset = xdr->buf->len; @@ -5418,8 +5418,6 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) op->status = encoder(resp, op->status, &op->u); if (op->status) trace_nfsd_compound_encode_err(rqstp, op->opnum, op->status); - if (opdesc && opdesc->op_release) - opdesc->op_release(&op->u); xdr_commit_encode(xdr); /* nfsd4_check_resp_size guarantees enough room for error status */ @@ -5460,6 +5458,9 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) } status: *p = op->status; +release: + if (opdesc && opdesc->op_release) + opdesc->op_release(&op->u); } /* diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 2681a449edc1..13592e82eaf6 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -2219,6 +2219,7 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, /* on-disk format */ binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = level; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index a35f2795b242..4c85914f2abc 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -314,6 +314,7 @@ static int nilfs_direct_assign_p(struct nilfs_bmap *direct, binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = 0; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 19446a8243d7..228659612c0d 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -430,6 +430,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) return 0; } +/** + * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area + * @sci: segment constructor object + * + * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of + * the current segment summary block. + */ +static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci) +{ + struct nilfs_segsum_pointer *ssp; + + ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr; + if (ssp->offset < ssp->bh->b_size) + memset(ssp->bh->b_data + ssp->offset, 0, + ssp->bh->b_size - ssp->offset); +} + static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; @@ -438,6 +455,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) * The current segment is filled up * (internal code) */ + nilfs_segctor_zeropad_segsum(sci); sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -542,6 +560,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, goto retry; } if (unlikely(required)) { + nilfs_segctor_zeropad_segsum(sci); err = nilfs_segbuf_extend_segsum(segbuf); if (unlikely(err)) goto failed; @@ -1533,6 +1552,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } + nilfs_segctor_zeropad_segsum(sci); nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile); return 0; @@ -2609,11 +2629,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1422b8ba24ed..77f1e5778d1c 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -482,6 +482,7 @@ static void nilfs_put_super(struct super_block *sb) up_write(&nilfs->ns_sem); } + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1105,6 +1106,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); failed_unload: + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 3a4c9c150cbf..2894152a6b25 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -87,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { - nilfs_sysfs_delete_device_group(nilfs); brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } @@ -305,6 +304,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; } + err = nilfs_sysfs_create_device_group(sb); + if (unlikely(err)) + goto sysfs_error; + if (valid_fs) goto skip_recovery; @@ -366,6 +369,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; failed_unload: + nilfs_sysfs_delete_device_group(nilfs); + + sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); @@ -697,10 +703,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - err = nilfs_sysfs_create_device_group(sb); - if (err) - goto failed_sbh; - set_nilfs_init(nilfs); err = 0; out: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 44d1ee429eb0..40f9e1a2ebdd 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1955,8 +1955,10 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - /* Ignore unsupported features (userspace built against newer kernel) */ - features = uffdio_api.features & UFFD_API_FEATURES; + features = uffdio_api.features; + ret = -EINVAL; + if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) + goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; diff --git a/include/acpi/video.h b/include/acpi/video.h index 8ed9bec03e53..ff5a8da5d883 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -59,8 +59,6 @@ extern void acpi_video_unregister(void); extern void acpi_video_register_backlight(void); extern int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, void **edid); -extern enum acpi_backlight_type acpi_video_get_backlight_type(void); -extern bool acpi_video_backlight_use_native(void); /* * Note: The value returned by acpi_video_handles_brightness_key_presses() * may change over time and should not be cached. @@ -69,6 +67,19 @@ extern bool acpi_video_handles_brightness_key_presses(void); extern int acpi_video_get_levels(struct acpi_device *device, struct acpi_video_device_brightness **dev_br, int *pmax_level); + +extern enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, + bool *auto_detect); + +static inline enum acpi_backlight_type acpi_video_get_backlight_type(void) +{ + return __acpi_video_get_backlight_type(false, NULL); +} + +static inline bool acpi_video_backlight_use_native(void) +{ + return __acpi_video_get_backlight_type(true, NULL) == acpi_backlight_native; +} #else static inline void acpi_video_report_nolcd(void) { return; }; static inline int acpi_video_register(void) { return -ENODEV; } diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 04b8be9f1a77..e271d6708c87 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -130,7 +130,7 @@ ATOMIC_OP(xor, ^) #define arch_atomic_read(v) READ_ONCE((v)->counter) #define arch_atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#define arch_atomic_xchg(ptr, v) (arch_xchg(&(ptr)->counter, (v))) -#define arch_atomic_cmpxchg(v, old, new) (arch_cmpxchg(&((v)->counter), (old), (new))) +#define arch_atomic_xchg(ptr, v) (arch_xchg(&(ptr)->counter, (u32)(v))) +#define arch_atomic_cmpxchg(v, old, new) (arch_cmpxchg(&((v)->counter), (u32)(old), (u32)(new))) #endif /* __ASM_GENERIC_ATOMIC_H */ diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h index c3e7315b7c1d..3df9f59a544e 100644 --- a/include/asm-generic/cmpxchg-local.h +++ b/include/asm-generic/cmpxchg-local.h @@ -26,16 +26,16 @@ static inline unsigned long __generic_cmpxchg_local(volatile void *ptr, raw_local_irq_save(flags); switch (size) { case 1: prev = *(u8 *)ptr; - if (prev == (u8)old) - *(u8 *)ptr = (u8)new; + if (prev == (old & 0xffu)) + *(u8 *)ptr = (new & 0xffu); break; case 2: prev = *(u16 *)ptr; - if (prev == (u16)old) - *(u16 *)ptr = (u16)new; + if (prev == (old & 0xffffu)) + *(u16 *)ptr = (new & 0xffffu); break; case 4: prev = *(u32 *)ptr; - if (prev == (u32)old) - *(u32 *)ptr = (u32)new; + if (prev == (old & 0xffffffffffu)) + *(u32 *)ptr = (new & 0xffffffffu); break; case 8: prev = *(u64 *)ptr; if (prev == old) diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h index dca4419922a9..848de25fc4bf 100644 --- a/include/asm-generic/cmpxchg.h +++ b/include/asm-generic/cmpxchg.h @@ -32,7 +32,7 @@ unsigned long __generic_xchg(unsigned long x, volatile void *ptr, int size) #else local_irq_save(flags); ret = *(volatile u8 *)ptr; - *(volatile u8 *)ptr = x; + *(volatile u8 *)ptr = (x & 0xffu); local_irq_restore(flags); return ret; #endif /* __xchg_u8 */ @@ -43,7 +43,7 @@ unsigned long __generic_xchg(unsigned long x, volatile void *ptr, int size) #else local_irq_save(flags); ret = *(volatile u16 *)ptr; - *(volatile u16 *)ptr = x; + *(volatile u16 *)ptr = (x & 0xffffu); local_irq_restore(flags); return ret; #endif /* __xchg_u16 */ @@ -54,7 +54,7 @@ unsigned long __generic_xchg(unsigned long x, volatile void *ptr, int size) #else local_irq_save(flags); ret = *(volatile u32 *)ptr; - *(volatile u32 *)ptr = x; + *(volatile u32 *)ptr = (x & 0xffffffffu); local_irq_restore(flags); return ret; #endif /* __xchg_u32 */ diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 4c44a29b5e8e..587e7e9b9a37 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -236,7 +236,7 @@ static inline u64 readq(const volatile void __iomem *addr) log_read_mmio(64, addr, _THIS_IP_, _RET_IP_); __io_br(); - val = __le64_to_cpu(__raw_readq(addr)); + val = __le64_to_cpu((__le64 __force)__raw_readq(addr)); __io_ar(val); log_post_read_mmio(val, 64, addr, _THIS_IP_, _RET_IP_); return val; @@ -287,7 +287,7 @@ static inline void writeq(u64 value, volatile void __iomem *addr) { log_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); __io_bw(); - __raw_writeq(__cpu_to_le64(value), addr); + __raw_writeq((u64 __force)__cpu_to_le64(value), addr); __io_aw(); log_post_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); } @@ -319,7 +319,7 @@ static inline u16 readw_relaxed(const volatile void __iomem *addr) u16 val; log_read_mmio(16, addr, _THIS_IP_, _RET_IP_); - val = __le16_to_cpu(__raw_readw(addr)); + val = __le16_to_cpu((__le16 __force)__raw_readw(addr)); log_post_read_mmio(val, 16, addr, _THIS_IP_, _RET_IP_); return val; } @@ -332,7 +332,7 @@ static inline u32 readl_relaxed(const volatile void __iomem *addr) u32 val; log_read_mmio(32, addr, _THIS_IP_, _RET_IP_); - val = __le32_to_cpu(__raw_readl(addr)); + val = __le32_to_cpu((__le32 __force)__raw_readl(addr)); log_post_read_mmio(val, 32, addr, _THIS_IP_, _RET_IP_); return val; } @@ -345,7 +345,7 @@ static inline u64 readq_relaxed(const volatile void __iomem *addr) u64 val; log_read_mmio(64, addr, _THIS_IP_, _RET_IP_); - val = __le64_to_cpu(__raw_readq(addr)); + val = __le64_to_cpu((__le64 __force)__raw_readq(addr)); log_post_read_mmio(val, 64, addr, _THIS_IP_, _RET_IP_); return val; } @@ -366,7 +366,7 @@ static inline void writeb_relaxed(u8 value, volatile void __iomem *addr) static inline void writew_relaxed(u16 value, volatile void __iomem *addr) { log_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_); - __raw_writew(cpu_to_le16(value), addr); + __raw_writew((u16 __force)cpu_to_le16(value), addr); log_post_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_); } #endif @@ -376,7 +376,7 @@ static inline void writew_relaxed(u16 value, volatile void __iomem *addr) static inline void writel_relaxed(u32 value, volatile void __iomem *addr) { log_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_); - __raw_writel(__cpu_to_le32(value), addr); + __raw_writel((u32 __force)__cpu_to_le32(value), addr); log_post_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_); } #endif @@ -386,7 +386,7 @@ static inline void writel_relaxed(u32 value, volatile void __iomem *addr) static inline void writeq_relaxed(u64 value, volatile void __iomem *addr) { log_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); - __raw_writeq(__cpu_to_le64(value), addr); + __raw_writeq((u64 __force)__cpu_to_le64(value), addr); log_post_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); } #endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 366c730beaa3..402fc061de75 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -980,7 +980,7 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) -static inline unsigned long get_lock_parent_ip(void) +static __always_inline unsigned long get_lock_parent_ip(void) { unsigned long addr = CALLER_ADDR0; diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e38ae3c34618..30b17647ce3c 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -134,11 +134,12 @@ void kmsan_kfree_large(const void *ptr); * @page_shift: page_shift passed to vmap_range_noflush(). * * KMSAN maps shadow and origin pages of @pages into contiguous ranges in - * vmalloc metadata address range. + * vmalloc metadata address range. Returns 0 on success, callers must check + * for non-zero return value. */ -void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -159,11 +160,12 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * @page_shift: page_shift argument passed to vmap_range_noflush(). * * KMSAN creates new metadata pages for the physical pages mapped into the - * virtual memory. + * virtual memory. Returns 0 on success, callers must check for non-zero return + * value. */ -void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -281,12 +283,13 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline void kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift) { + return 0; } static inline void kmsan_vunmap_range_noflush(unsigned long start, @@ -294,12 +297,12 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline void kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, - pgprot_t prot, - unsigned int page_shift) +static inline int kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift) { + return 0; } static inline void kmsan_iounmap_page_range(unsigned long start, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8ada23756b0e..a9adf75344be 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -755,6 +755,7 @@ struct kvm { struct { spinlock_t lock; struct list_head items; + /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; @@ -1986,6 +1987,9 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQFD int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) @@ -1994,6 +1998,13 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) } static inline void kvm_irqfd_release(struct kvm *kvm) {} + +static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + return false; +} #endif #else diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index dac047abdba7..8ad43692e3bb 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -31,7 +31,7 @@ struct kvm_kernel_irqfd_resampler { /* * Entry in list of kvm->irqfd.resampler_list. Use for sharing * resamplers among irqfds on the same gsi. - * Accessed and modified under kvm->irqfds.resampler_lock + * RCU list modified under kvm->irqfds.resampler_lock */ struct list_head link; }; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 71b06ebad402..1db19a9d26e3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -36,6 +36,7 @@ #include <linux/types.h> #include <rdma/ib_verbs.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/bitfield.h> #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -980,14 +981,23 @@ enum { }; enum { - CQE_RSS_HTYPE_IP = 0x3 << 2, + CQE_RSS_HTYPE_IP = GENMASK(3, 2), /* cqe->rss_hash_type[3:2] - IP destination selected for hash * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved) */ - CQE_RSS_HTYPE_L4 = 0x3 << 6, + CQE_RSS_IP_NONE = 0x0, + CQE_RSS_IPV4 = 0x1, + CQE_RSS_IPV6 = 0x2, + CQE_RSS_RESERVED = 0x3, + + CQE_RSS_HTYPE_L4 = GENMASK(7, 6), /* cqe->rss_hash_type[7:6] - L4 destination selected for hash * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI */ + CQE_RSS_L4_NONE = 0x0, + CQE_RSS_L4_TCP = 0x1, + CQE_RSS_L4_UDP = 0x2, + CQE_RSS_L4_IPSEC = 0x3, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..7e225e41d55b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1211,11 +1211,6 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } -static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num); -} - static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..a57e6ae78e65 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -774,7 +774,8 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; -#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ + MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 470085b121d3..c35f04f636f1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1624,7 +1624,8 @@ struct net_device_ops { struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash); + int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); }; /** diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index ed9b4df792b8..43765eaf2342 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -34,6 +34,10 @@ struct pci_doe_mb; * @work: Used internally by the mailbox * @doe_mb: Used internally by the mailbox * + * Payloads are treated as opaque byte streams which are transmitted verbatim, + * without byte-swapping. If payloads contain little-endian register values, + * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). + * * The payload sizes and rv are specified in bytes with the following * restrictions concerning the protocol. * @@ -45,9 +49,9 @@ struct pci_doe_mb; */ struct pci_doe_task { struct pci_doe_protocol prot; - u32 *request_pl; + __le32 *request_pl; size_t request_pl_sz; - u32 *response_pl; + __le32 *response_pl; size_t response_pl_sz; int rv; void (*complete)(struct pci_doe_task *task); diff --git a/include/linux/pci.h b/include/linux/pci.h index b50e5c79f7e3..a5dda515fcd1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1624,6 +1624,8 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ return false; } static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, const struct irq_affinity_desc *affdesc) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c492c26202b5..637698ed5cb6 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -574,6 +574,7 @@ struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); void phylink_destroy(struct phylink *); +bool phylink_expects_phy(struct phylink *pl); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 92ad75549e9c..b6e6378dcbbd 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -25,7 +25,8 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq); + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff7ad331fb82..dbcaac8b6966 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -294,6 +294,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; @@ -4712,7 +4713,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -4732,7 +4733,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6ed9b4d546a7..d5311ceb21c6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -954,6 +954,7 @@ enum { HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, HCI_CONN_DROP, + HCI_CONN_CANCEL, HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, diff --git a/include/net/bonding.h b/include/net/bonding.h index ea36ab7f9e72..c3843239517d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -761,13 +761,17 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { + struct in6_addr mcaddr; int i; - for (i = 0; i < BOND_MAX_NS_TARGETS; i++) - if (ipv6_addr_equal(&targets[i], ip)) + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { + addrconf_addr_solict_mult(&targets[i], &mcaddr); + if ((ipv6_addr_equal(&targets[i], ip)) || + (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; + } return -1; } diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 9430128aae99..1b8e305bb54a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1085,6 +1085,10 @@ struct nft_chain { }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); +int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem); +int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, diff --git a/include/net/raw.h b/include/net/raw.h index 2c004c20ed99..3af5289fdead 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -37,7 +37,7 @@ int raw_rcv(struct sock *, struct sk_buff *); struct raw_hashinfo { spinlock_t lock; - struct hlist_nulls_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; + struct hlist_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; }; static inline u32 raw_hashfunc(const struct net *net, u32 proto) @@ -51,7 +51,7 @@ static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) spin_lock_init(&hashinfo->lock); for (i = 0; i < RAW_HTABLE_SIZE; i++) - INIT_HLIST_NULLS_HEAD(&hashinfo->ht[i], i); + INIT_HLIST_HEAD(&hashinfo->ht[i]); } #ifdef CONFIG_PROC_FS diff --git a/include/net/xdp.h b/include/net/xdp.h index 41c57b8b1671..76aa748e7923 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -8,6 +8,7 @@ #include <linux/skbuff.h> /* skb_shared_info */ #include <uapi/linux/netdev.h> +#include <linux/bitfield.h> /** * DOC: XDP RX-queue information @@ -425,6 +426,52 @@ XDP_METADATA_KFUNC_xxx MAX_XDP_METADATA_KFUNC, }; +enum xdp_rss_hash_type { + /* First part: Individual bits for L3/L4 types */ + XDP_RSS_L3_IPV4 = BIT(0), + XDP_RSS_L3_IPV6 = BIT(1), + + /* The fixed (L3) IPv4 and IPv6 headers can both be followed by + * variable/dynamic headers, IPv4 called Options and IPv6 called + * Extension Headers. HW RSS type can contain this info. + */ + XDP_RSS_L3_DYNHDR = BIT(2), + + /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in + * addition to the protocol specific bit. This ease interaction with + * SKBs and avoids reserving a fixed mask for future L4 protocol bits. + */ + XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */ + XDP_RSS_L4_TCP = BIT(4), + XDP_RSS_L4_UDP = BIT(5), + XDP_RSS_L4_SCTP = BIT(6), + XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ + + /* Second part: RSS hash type combinations used for driver HW mapping */ + XDP_RSS_TYPE_NONE = 0, + XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE, + + XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4, + XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6, + XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR, + + XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4, + XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_TCP, + XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, + XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, + XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + + XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, + XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, + XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, + XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + + XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, +}; + #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); diff --git a/include/trace/stages/stage5_get_offsets.h b/include/trace/stages/stage5_get_offsets.h index ac5c24d3beeb..e30a13be46ba 100644 --- a/include/trace/stages/stage5_get_offsets.h +++ b/include/trace/stages/stage5_get_offsets.h @@ -9,17 +9,30 @@ #undef __entry #define __entry entry +/* + * Fields should never declare an array: i.e. __field(int, arr[5]) + * If they do, it will cause issues in parsing and possibly corrupt the + * events. To prevent that from happening, test the sizeof() a fictitious + * type called "struct _test_no_array_##item" which will fail if "item" + * contains array elements (like "arr[5]"). + * + * If you hit this, use __array(int, arr, 5) instead. + */ #undef __field -#define __field(type, item) +#define __field(type, item) \ + { (void)sizeof(struct _test_no_array_##item *); } #undef __field_ext -#define __field_ext(type, item, filter_type) +#define __field_ext(type, item, filter_type) \ + { (void)sizeof(struct _test_no_array_##item *); } #undef __field_struct -#define __field_struct(type, item) +#define __field_struct(type, item) \ + { (void)sizeof(struct _test_no_array_##item *); } #undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) +#define __field_struct_ext(type, item, filter_type) \ + { (void)sizeof(struct _test_no_array_##item *); } #undef __array #define __array(type, item, len) diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 5af2a0300bb9..3744e4da1b2a 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -140,11 +140,11 @@ struct virtio_blk_config { /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */ struct virtio_blk_zoned_characteristics { - __le32 zone_sectors; - __le32 max_open_zones; - __le32 max_active_zones; - __le32 max_append_sectors; - __le32 write_granularity; + __virtio32 zone_sectors; + __virtio32 max_open_zones; + __virtio32 max_active_zones; + __virtio32 max_append_sectors; + __virtio32 write_granularity; __u8 model; __u8 unused2[3]; } zoned; @@ -241,11 +241,11 @@ struct virtio_blk_outhdr { */ struct virtio_blk_zone_descriptor { /* Zone capacity */ - __le64 z_cap; + __virtio64 z_cap; /* The starting sector of the zone */ - __le64 z_start; + __virtio64 z_start; /* Zone write pointer position in sectors */ - __le64 z_wp; + __virtio64 z_wp; /* Zone type */ __u8 z_type; /* Zone state */ @@ -254,7 +254,7 @@ struct virtio_blk_zone_descriptor { }; struct virtio_blk_zone_report { - __le64 nr_zones; + __virtio64 nr_zones; __u8 reserved[56]; struct virtio_blk_zone_descriptor zones[]; }; diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 25aab8ec4f86..431c3afb2ce0 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -979,7 +979,6 @@ struct ufs_hba { struct completion *uic_async_done; enum ufshcd_state ufshcd_state; - bool logical_unit_scan_finished; u32 eh_flags; u32 intr_mask; u16 ee_ctrl_mask; diff --git a/init/initramfs.c b/init/initramfs.c index f6c112e30bd4..e7a01c2ccd1b 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -60,15 +60,8 @@ static void __init error(char *x) message = x; } -static void panic_show_mem(const char *fmt, ...) -{ - va_list args; - - show_mem(0, NULL); - va_start(args, fmt); - panic(fmt, args); - va_end(args); -} +#define panic_show_mem(fmt, ...) \ + ({ show_mem(0, NULL); panic(fmt, ##__VA_ARGS__); }) /* link hash */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 722624b6d0dc..4a865f0e85d0 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -998,7 +998,7 @@ static void __io_req_complete_post(struct io_kiocb *req) void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags) { - if (req->ctx->task_complete && (issue_flags & IO_URING_F_IOWQ)) { + if (req->ctx->task_complete && req->ctx->submitter_task != current) { req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); } else if (!(issue_flags & IO_URING_F_UNLOCKED) || @@ -2789,8 +2789,8 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_eventfd_unregister(ctx); io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free); io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); - mutex_unlock(&ctx->uring_lock); io_destroy_buffers(ctx); + mutex_unlock(&ctx->uring_lock); if (ctx->sq_creds) put_cred(ctx->sq_creds); if (ctx->submitter_task) diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 3002dc827195..a90c820ce99e 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -228,17 +228,18 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, return i; } - /* the head kbuf is the list itself */ + /* protects io_buffers_cache */ + lockdep_assert_held(&ctx->uring_lock); + while (!list_empty(&bl->buf_list)) { struct io_buffer *nxt; nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); - list_del(&nxt->list); + list_move(&nxt->list, &ctx->io_buffers_cache); if (++i == nbufs) return i; cond_resched(); } - i++; return i; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d517d13878cf..767e8930b0bd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2967,6 +2967,21 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; + } else if (BPF_SRC(insn->code) == BPF_X) { + if (!(*reg_mask & (dreg | sreg))) + return 0; + /* dreg <cond> sreg + * Both dreg and sreg need precision before + * this insn. If only sreg was marked precise + * before it would be equally necessary to + * propagate it to dreg. + */ + *reg_mask |= (sreg | dreg); + /* else dreg <cond> K + * Only dreg still needs precision before + * this insn, so for the K-based conditional + * there is nothing new to be marked. + */ } } else if (class == BPF_LD) { if (!(*reg_mask & dreg)) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 636f1c682ac0..505d86b16642 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1513,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, spin_unlock_irq(&callback_lock); if (adding || deleting) - update_tasks_cpumask(parent, tmp->new_cpus); + update_tasks_cpumask(parent, tmp->addmask); /* * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary. @@ -1770,10 +1770,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, /* * Use the cpumasks in trialcs for tmpmasks when they are pointers * to allocated cpumasks. + * + * Note that update_parent_subparts_cpumask() uses only addmask & + * delmask, but not new_cpus. */ tmp.addmask = trialcs->subparts_cpus; tmp.delmask = trialcs->effective_cpus; - tmp.new_cpus = trialcs->cpus_allowed; + tmp.new_cpus = NULL; #endif retval = validate_change(cs, trialcs); @@ -1838,6 +1841,11 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, } spin_unlock_irq(&callback_lock); +#ifdef CONFIG_CPUMASK_OFFSTACK + /* Now trialcs->cpus_allowed is available */ + tmp.new_cpus = trialcs->cpus_allowed; +#endif + /* effective_cpus will be updated here */ update_cpumasks_hier(cs, &tmp, false); @@ -2445,6 +2453,20 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; +/* + * Check to see if a cpuset can accept a new task + * For v1, cpus_allowed and mems_allowed can't be empty. + * For v2, effective_cpus can't be empty. + * Note that in v1, effective_cpus = cpus_allowed. + */ +static int cpuset_can_attach_check(struct cpuset *cs) +{ + if (cpumask_empty(cs->effective_cpus) || + (!is_in_v2_mode() && nodes_empty(cs->mems_allowed))) + return -ENOSPC; + return 0; +} + /* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { @@ -2459,16 +2481,9 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) percpu_down_write(&cpuset_rwsem); - /* allow moving tasks into an empty cpuset if on default hierarchy */ - ret = -ENOSPC; - if (!is_in_v2_mode() && - (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) - goto out_unlock; - - /* - * Task cannot be moved to a cpuset with empty effective cpus. - */ - if (cpumask_empty(cs->effective_cpus)) + /* Check to see if task is allowed in the cpuset */ + ret = cpuset_can_attach_check(cs); + if (ret) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { @@ -2485,7 +2500,6 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; - ret = 0; out_unlock: percpu_up_write(&cpuset_rwsem); return ret; @@ -2494,25 +2508,47 @@ out_unlock: static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; + struct cpuset *cs; cgroup_taskset_first(tset, &css); + cs = css_cs(css); percpu_down_write(&cpuset_rwsem); - css_cs(css)->attach_in_progress--; + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); } /* - * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach() + * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; +static nodemask_t cpuset_attach_nodemask_to; + +static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) +{ + percpu_rwsem_assert_held(&cpuset_rwsem); + + if (cs != &top_cpuset) + guarantee_online_cpus(task, cpus_attach); + else + cpumask_andnot(cpus_attach, task_cpu_possible_mask(task), + cs->subparts_cpus); + /* + * can_attach beforehand should guarantee that this doesn't + * fail. TODO: have a better way to handle failure here + */ + WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); + + cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); + cpuset_update_task_spread_flags(cs, task); +} static void cpuset_attach(struct cgroup_taskset *tset) { - /* static buf protected by cpuset_rwsem */ - static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; struct cgroup_subsys_state *css; @@ -2543,20 +2579,8 @@ static void cpuset_attach(struct cgroup_taskset *tset) guarantee_online_mems(cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, css, tset) { - if (cs != &top_cpuset) - guarantee_online_cpus(task, cpus_attach); - else - cpumask_copy(cpus_attach, task_cpu_possible_mask(task)); - /* - * can_attach beforehand should guarantee that this doesn't - * fail. TODO: have a better way to handle failure here - */ - WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); - - cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); - cpuset_update_task_spread_flags(cs, task); - } + cgroup_taskset_for_each(task, css, tset) + cpuset_attach_task(cs, task); /* * Change mm for all threadgroup leaders. This is expensive and may @@ -3248,17 +3272,101 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) } /* + * In case the child is cloned into a cpuset different from its parent, + * additional checks are done to see if the move is allowed. + */ +static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) +{ + struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); + bool same_cs; + int ret; + + rcu_read_lock(); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) + return 0; + + lockdep_assert_held(&cgroup_mutex); + percpu_down_write(&cpuset_rwsem); + + /* Check to see if task is allowed in the cpuset */ + ret = cpuset_can_attach_check(cs); + if (ret) + goto out_unlock; + + ret = task_can_attach(task, cs->effective_cpus); + if (ret) + goto out_unlock; + + ret = security_task_setscheduler(task); + if (ret) + goto out_unlock; + + /* + * Mark attach is in progress. This makes validate_change() fail + * changes which zero cpus/mems_allowed. + */ + cs->attach_in_progress++; +out_unlock: + percpu_up_write(&cpuset_rwsem); + return ret; +} + +static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) +{ + struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); + bool same_cs; + + rcu_read_lock(); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) + return; + + percpu_down_write(&cpuset_rwsem); + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + percpu_up_write(&cpuset_rwsem); +} + +/* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { - if (task_css_is_root(task, cpuset_cgrp_id)) + struct cpuset *cs; + bool same_cs; + + rcu_read_lock(); + cs = task_cs(task); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) { + if (cs == &top_cpuset) + return; + + set_cpus_allowed_ptr(task, current->cpus_ptr); + task->mems_allowed = current->mems_allowed; return; + } + + /* CLONE_INTO_CGROUP */ + percpu_down_write(&cpuset_rwsem); + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + cpuset_attach_task(cs, task); + + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); - set_cpus_allowed_ptr(task, current->cpus_ptr); - task->mems_allowed = current->mems_allowed; + percpu_up_write(&cpuset_rwsem); } struct cgroup_subsys cpuset_cgrp_subsys = { @@ -3271,6 +3379,8 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, + .can_fork = cpuset_can_fork, + .cancel_fork = cpuset_cancel_fork, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files, diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 1b6b21851e9d..936473203a6b 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -22,6 +22,7 @@ #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/mutex.h> +#include <linux/cpu.h> /* * A cgroup is freezing if any FREEZING flags are set. FREEZING_SELF is @@ -350,7 +351,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze, if (freeze) { if (!(freezer->state & CGROUP_FREEZING)) - static_branch_inc(&freezer_active); + static_branch_inc_cpuslocked(&freezer_active); freezer->state |= state; freeze_cgroup(freezer); } else { @@ -361,7 +362,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze, if (!(freezer->state & CGROUP_FREEZING)) { freezer->state &= ~CGROUP_FROZEN; if (was_freezing) - static_branch_dec(&freezer_active); + static_branch_dec_cpuslocked(&freezer_active); unfreeze_cgroup(freezer); } } @@ -379,6 +380,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) { struct cgroup_subsys_state *pos; + cpus_read_lock(); /* * Update all its descendants in pre-order traversal. Each * descendant will try to inherit its parent's FREEZING state as @@ -407,6 +409,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) } rcu_read_unlock(); mutex_unlock(&freezer_mutex); + cpus_read_unlock(); } static ssize_t freezer_write(struct kernfs_open_file *of, diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 831f1f472bb8..0a2b4967e333 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -457,9 +457,7 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) struct task_cputime *cputime = &bstat->cputime; int i; - cputime->stime = 0; - cputime->utime = 0; - cputime->sum_exec_runtime = 0; + memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 5b919ef832b6..dac42a2ad588 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -623,7 +623,7 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index, phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = - dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); + dma_get_min_align_mask(dev) | alloc_align_mask; unsigned int nslots = nr_slots(alloc_size), stride; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int index, slots_checked, count = 0, i; @@ -639,8 +639,8 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index, * allocations. */ if (alloc_size >= PAGE_SIZE) - iotlb_align_mask &= PAGE_MASK; - iotlb_align_mask &= alloc_align_mask; + iotlb_align_mask |= ~PAGE_MASK; + iotlb_align_mask &= ~(IO_TLB_SIZE - 1); /* * For mappings with an alignment requirement don't bother looping to diff --git a/kernel/events/core.c b/kernel/events/core.c index fb3e436bcd4a..435815d3be3f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -12173,7 +12173,7 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) /* * If its not a per-cpu rb, it must be the same task. */ - if (output_event->cpu == -1 && output_event->ctx != event->ctx) + if (output_event->cpu == -1 && output_event->hw.target != event->hw.target) goto out; /* @@ -12893,12 +12893,14 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) __perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->pinned_groups, &events); __perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->flexible_groups, &events); - /* - * Wait for the events to quiesce before re-instating them. - */ - synchronize_rcu(); + if (!list_empty(&events)) { + /* + * Wait for the events to quiesce before re-instating them. + */ + synchronize_rcu(); - __perf_pmu_install(dst_ctx, dst_cpu, pmu, &events); + __perf_pmu_install(dst_ctx, dst_cpu, pmu, &events); + } mutex_unlock(&dst_ctx->mutex); mutex_unlock(&src_ctx->mutex); diff --git a/kernel/fork.c b/kernel/fork.c index c0257cbee093..ea332319dffe 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -617,6 +617,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (retval) goto out; + mt_clear_in_rcu(vmi.mas.tree); for_each_vma(old_vmi, mpnt) { struct file *file; @@ -700,6 +701,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); + if (!retval) + mt_set_in_rcu(vmi.mas.tree); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); @@ -1171,6 +1174,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, fail_pcpu: while (i > 0) percpu_counter_destroy(&mm->rss_stat[--i]); + destroy_context(mm); fail_nocontext: mm_free_pgd(mm); fail_nopgd: diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8e880c09ab59..7b95ee98a1a5 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3024,6 +3024,18 @@ need_offload_krc(struct kfree_rcu_cpu *krcp) return !!READ_ONCE(krcp->head); } +static bool +need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp) +{ + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + if (!list_empty(&krwp->bulk_head_free[i])) + return true; + + return !!krwp->head_free; +} + static int krc_count(struct kfree_rcu_cpu *krcp) { int sum = atomic_read(&krcp->head_count); @@ -3107,15 +3119,14 @@ static void kfree_rcu_monitor(struct work_struct *work) for (i = 0; i < KFREE_N_BATCHES; i++) { struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]); - // Try to detach bulk_head or head and attach it over any - // available corresponding free channel. It can be that - // a previous RCU batch is in progress, it means that - // immediately to queue another one is not possible so - // in that case the monitor work is rearmed. - if ((!list_empty(&krcp->bulk_head[0]) && list_empty(&krwp->bulk_head_free[0])) || - (!list_empty(&krcp->bulk_head[1]) && list_empty(&krwp->bulk_head_free[1])) || - (READ_ONCE(krcp->head) && !krwp->head_free)) { + // Try to detach bulk_head or head and attach it, only when + // all channels are free. Any channel is not free means at krwp + // there is on-going rcu work to handle krwp's free business. + if (need_wait_for_krwp_work(krwp)) + continue; + // kvfree_rcu_drain_ready() might handle this krcp, if so give up. + if (need_offload_krc(krcp)) { // Channel 1 corresponds to the SLAB-pointer bulk path. // Channel 2 corresponds to vmalloc-pointer bulk path. for (j = 0; j < FREE_N_CHANNELS; j++) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6986ea31c984..5f6587d94c1d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10238,6 +10238,16 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / sds->total_capacity; + + /* + * If the local group is more loaded than the average system + * load, don't try to pull any tasks. + */ + if (local->avg_load >= sds->avg_load) { + env->imbalance = 0; + return; + } + } /* diff --git a/kernel/sys.c b/kernel/sys.c index 495cd87d9bf4..351de7916302 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -664,6 +664,7 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) struct cred *new; int retval; kuid_t kruid, keuid, ksuid; + bool ruid_new, euid_new, suid_new; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); @@ -678,25 +679,29 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; + old = current_cred(); + + /* check for no-op */ + if ((ruid == (uid_t) -1 || uid_eq(kruid, old->uid)) && + (euid == (uid_t) -1 || (uid_eq(keuid, old->euid) && + uid_eq(keuid, old->fsuid))) && + (suid == (uid_t) -1 || uid_eq(ksuid, old->suid))) + return 0; + + ruid_new = ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && + !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid); + euid_new = euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && + !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid); + suid_new = suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && + !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid); + if ((ruid_new || euid_new || suid_new) && + !ns_capable_setid(old->user_ns, CAP_SETUID)) + return -EPERM; + new = prepare_creds(); if (!new) return -ENOMEM; - old = current_cred(); - - retval = -EPERM; - if (!ns_capable_setid(old->user_ns, CAP_SETUID)) { - if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && - !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) - goto error; - if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && - !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) - goto error; - if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && - !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) - goto error; - } - if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(kruid, old->uid)) { @@ -761,6 +766,7 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) struct cred *new; int retval; kgid_t krgid, kegid, ksgid; + bool rgid_new, egid_new, sgid_new; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); @@ -773,23 +779,28 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; + old = current_cred(); + + /* check for no-op */ + if ((rgid == (gid_t) -1 || gid_eq(krgid, old->gid)) && + (egid == (gid_t) -1 || (gid_eq(kegid, old->egid) && + gid_eq(kegid, old->fsgid))) && + (sgid == (gid_t) -1 || gid_eq(ksgid, old->sgid))) + return 0; + + rgid_new = rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && + !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid); + egid_new = egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && + !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid); + sgid_new = sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && + !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid); + if ((rgid_new || egid_new || sgid_new) && + !ns_capable_setid(old->user_ns, CAP_SETGID)) + return -EPERM; + new = prepare_creds(); if (!new) return -ENOMEM; - old = current_cred(); - - retval = -EPERM; - if (!ns_capable_setid(old->user_ns, CAP_SETGID)) { - if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && - !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) - goto error; - if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && - !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) - goto error; - if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && - !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) - goto error; - } if (rgid != (gid_t) -1) new->gid = krgid; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0feea145bb29..c67bcc89a771 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5667,12 +5667,15 @@ int modify_ftrace_direct(unsigned long ip, ret = 0; } - if (unlikely(ret && new_direct)) { - direct->count++; - list_del_rcu(&new_direct->next); - synchronize_rcu_tasks(); - kfree(new_direct); - ftrace_direct_func_count--; + if (ret) { + direct->addr = old_addr; + if (unlikely(new_direct)) { + direct->count++; + list_del_rcu(&new_direct->next); + synchronize_rcu_tasks(); + kfree(new_direct); + ftrace_direct_func_count--; + } } out_unlock: diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c6f47b6cfd5f..76a2d91eecad 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3098,6 +3098,10 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) if (RB_WARN_ON(cpu_buffer, rb_is_reader_page(cpu_buffer->tail_page))) return; + /* + * No need for a memory barrier here, as the update + * of the tail_page did it for this page. + */ local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); rb_inc_page(&cpu_buffer->commit_page); @@ -3107,6 +3111,8 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) while (rb_commit_index(cpu_buffer) != rb_page_write(cpu_buffer->commit_page)) { + /* Make sure the readers see the content of what is committed. */ + smp_wmb(); local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); RB_WARN_ON(cpu_buffer, @@ -4684,7 +4690,12 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) /* * Make sure we see any padding after the write update - * (see rb_reset_tail()) + * (see rb_reset_tail()). + * + * In addition, a writer may be writing on the reader page + * if the page has not been fully filled, so the read barrier + * is also needed to make sure we see the content of what is + * committed by the writer (see rb_set_commit_to_write()). */ smp_rmb(); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 937e9676dfd4..36a6037823cd 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1149,22 +1149,22 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr, unsigned long flags; if (in_nmi()) { - internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); - internal_trace_puts("*** snapshot is being ignored ***\n"); + trace_array_puts(tr, "*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); + trace_array_puts(tr, "*** snapshot is being ignored ***\n"); return; } if (!tr->allocated_snapshot) { - internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n"); - internal_trace_puts("*** stopping trace here! ***\n"); - tracing_off(); + trace_array_puts(tr, "*** SNAPSHOT NOT ALLOCATED ***\n"); + trace_array_puts(tr, "*** stopping trace here! ***\n"); + tracer_tracing_off(tr); return; } /* Note, snapshot can not be used when the tracer uses it */ if (tracer->use_max_tr) { - internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n"); - internal_trace_puts("*** Can not use snapshot (sorry) ***\n"); + trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } @@ -9516,6 +9516,7 @@ static int __remove_instance(struct trace_array *tr) tracefs_remove(tr->dir); free_percpu(tr->last_func_repeats); free_trace_buffers(tr); + clear_tracing_err_log(tr); for (i = 0; i < tr->nr_topts; i++) { kfree(tr->topts[i].topts); @@ -10393,19 +10394,20 @@ out: void __init ftrace_boot_snapshot(void) { +#ifdef CONFIG_TRACER_MAX_TRACE struct trace_array *tr; - if (snapshot_at_boot) { - tracing_snapshot(); - internal_trace_puts("** Boot snapshot taken **\n"); - } + if (!snapshot_at_boot) + return; list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr == &global_trace) + if (!tr->allocated_snapshot) continue; - trace_array_puts(tr, "** Boot snapshot taken **\n"); + tracing_snapshot_instance(tr); + trace_array_puts(tr, "** Boot snapshot taken **\n"); } +#endif } void __init early_trace_init(void) diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 46d0abb32d0f..d6a70aff2410 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -44,14 +44,21 @@ enum { ERRORS }; static const char *err_text[] = { ERRORS }; +static DEFINE_MUTEX(lastcmd_mutex); static char *last_cmd; static int errpos(const char *str) { + int ret = 0; + + mutex_lock(&lastcmd_mutex); if (!str || !last_cmd) - return 0; + goto out; - return err_pos(last_cmd, str); + ret = err_pos(last_cmd, str); + out: + mutex_unlock(&lastcmd_mutex); + return ret; } static void last_cmd_set(const char *str) @@ -59,18 +66,22 @@ static void last_cmd_set(const char *str) if (!str) return; + mutex_lock(&lastcmd_mutex); kfree(last_cmd); - last_cmd = kstrdup(str, GFP_KERNEL); + mutex_unlock(&lastcmd_mutex); } static void synth_err(u8 err_type, u16 err_pos) { + mutex_lock(&lastcmd_mutex); if (!last_cmd) - return; + goto out; tracing_log_err(NULL, "synthetic_events", last_cmd, err_text, err_type, err_pos); + out: + mutex_unlock(&lastcmd_mutex); } static int create_synth_event(const char *raw_command); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 9176bb7a9bb4..4496975f2029 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1296,7 +1296,7 @@ static void notify_new_max_latency(u64 latency) rcu_read_lock(); list_for_each_entry_rcu(inst, &osnoise_instances, list) { tr = inst->tr; - if (tr->max_latency < latency) { + if (tracer_tracing_is_on(tr) && tr->max_latency < latency) { tr->max_latency = latency; latency_fsnotify(tr); } @@ -1738,6 +1738,8 @@ static int timerlat_main(void *data) trace_timerlat_sample(&s); + notify_new_max_latency(diff); + timerlat_dump_stack(time_to_us(diff)); tlat->tracing_thread = false; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c8b379e2e9ad..39d1d93164bd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1143,7 +1143,7 @@ menu "Scheduler Debugging" config SCHED_DEBUG bool "Collect scheduler debugging info" - depends on DEBUG_KERNEL && PROC_FS + depends on DEBUG_KERNEL && DEBUG_FS default y help If you say Y here, the /sys/kernel/debug/sched file will be provided @@ -1392,7 +1392,7 @@ config LOCKDEP_STACK_TRACE_HASH_BITS range 10 30 default 14 help - Try increasing this value if you need large MAX_STACK_TRACE_ENTRIES. + Try increasing this value if you need large STACK_TRACE_HASH_SIZE. config LOCKDEP_CIRCULAR_QUEUE_BITS int "Bitsize for elements in circular_queue struct" diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 9e2735cbc2b4..1281a40d5735 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -185,7 +185,7 @@ static void mt_free_rcu(struct rcu_head *head) */ static void ma_free_rcu(struct maple_node *node) { - node->parent = ma_parent_ptr(node); + WARN_ON(node->parent != ma_parent_ptr(node)); call_rcu(&node->rcu, mt_free_rcu); } @@ -539,11 +539,14 @@ static inline struct maple_node *mte_parent(const struct maple_enode *enode) */ static inline bool ma_dead_node(const struct maple_node *node) { - struct maple_node *parent = (void *)((unsigned long) - node->parent & ~MAPLE_NODE_MASK); + struct maple_node *parent; + /* Do not reorder reads from the node prior to the parent check */ + smp_rmb(); + parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } + /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node @@ -555,6 +558,8 @@ static inline bool mte_dead_node(const struct maple_enode *enode) struct maple_node *parent, *node; node = mte_to_node(enode); + /* Do not reorder reads from the node prior to the parent check */ + smp_rmb(); parent = mte_parent(enode); return (parent == node); } @@ -625,6 +630,8 @@ static inline unsigned int mas_alloc_req(const struct ma_state *mas) * @node - the maple node * @type - the node type * + * In the event of a dead node, this array may be %NULL + * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, @@ -817,6 +824,11 @@ static inline void *mt_slot(const struct maple_tree *mt, return rcu_dereference_check(slots[offset], mt_locked(mt)); } +static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, + unsigned char offset) +{ + return rcu_dereference_protected(slots[offset], mt_locked(mt)); +} /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state @@ -828,7 +840,7 @@ static inline void *mt_slot(const struct maple_tree *mt, static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { - return rcu_dereference_protected(slots[offset], mt_locked(mas->tree)); + return mt_slot_locked(mas->tree, slots, offset); } /* @@ -900,6 +912,45 @@ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, } /* + * mt_clear_meta() - clear the metadata information of a node, if it exists + * @mt: The maple tree + * @mn: The maple node + * @type: The maple node type + * @offset: The offset of the highest sub-gap in this node. + * @end: The end of the data in this node. + */ +static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, + enum maple_type type) +{ + struct maple_metadata *meta; + unsigned long *pivots; + void __rcu **slots; + void *next; + + switch (type) { + case maple_range_64: + pivots = mn->mr64.pivot; + if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { + slots = mn->mr64.slot; + next = mt_slot_locked(mt, slots, + MAPLE_RANGE64_SLOTS - 1); + if (unlikely((mte_to_node(next) && + mte_node_type(next)))) + return; /* no metadata, could be node */ + } + fallthrough; + case maple_arange_64: + meta = ma_meta(mn, type); + break; + default: + return; + } + + meta->gap = 0; + meta->end = 0; +} + +/* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type @@ -1096,8 +1147,11 @@ static int mas_ascend(struct ma_state *mas) a_type = mas_parent_enum(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); - pivots = ma_pivots(a_node, a_type); a_enode = mt_mk_node(a_node, a_type); + pivots = ma_pivots(a_node, a_type); + + if (unlikely(ma_dead_node(a_node))) + return 1; if (!set_min && a_slot) { set_min = true; @@ -1249,26 +1303,21 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) node = mas->alloc; node->request_count = 0; while (requested) { - max_req = MAPLE_ALLOC_SLOTS; - if (node->node_count) { - unsigned int offset = node->node_count; - - slots = (void **)&node->slot[offset]; - max_req -= offset; - } else { - slots = (void **)&node->slot; - } - + max_req = MAPLE_ALLOC_SLOTS - node->node_count; + slots = (void **)&node->slot[node->node_count]; max_req = min(requested, max_req); count = mt_alloc_bulk(gfp, max_req, slots); if (!count) goto nomem_bulk; + if (node->node_count == 0) { + node->slot[0]->node_count = 0; + node->slot[0]->request_count = 0; + } + node->node_count += count; allocated += count; node = node->slot[0]; - node->node_count = 0; - node->request_count = 0; requested -= count; } mas->alloc->total = allocated; @@ -1354,12 +1403,16 @@ static inline struct maple_enode *mas_start(struct ma_state *mas) mas->max = ULONG_MAX; mas->depth = 0; +retry: root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; mas->node = mte_safe_root(root); mas->offset = 0; + if (mte_dead_node(mas->node)) + goto retry; + return NULL; } @@ -1401,6 +1454,9 @@ static inline unsigned char ma_data_end(struct maple_node *node, { unsigned char offset; + if (!pivots) + return 0; + if (type == maple_arange_64) return ma_meta_end(node, type); @@ -1436,6 +1492,9 @@ static inline unsigned char mas_data_end(struct ma_state *mas) return ma_meta_end(node, type); pivots = ma_pivots(node, type); + if (unlikely(ma_dead_node(node))) + return 0; + offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); @@ -1724,8 +1783,10 @@ static inline void mas_replace(struct ma_state *mas, bool advanced) rcu_assign_pointer(slots[offset], mas->node); } - if (!advanced) + if (!advanced) { + mte_set_node_dead(old_enode); mas_free(mas, old_enode); + } } /* @@ -3659,10 +3720,9 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) slot++; mas->depth = 1; mas_set_height(mas); - + ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); - ma_set_meta(node, maple_leaf_64, 0, slot); return slot; } @@ -3875,18 +3935,13 @@ static inline void *mtree_lookup_walk(struct ma_state *mas) end = ma_data_end(node, type, pivots, max); if (unlikely(ma_dead_node(node))) goto dead_node; - - if (pivots[offset] >= mas->index) - goto next; - do { - offset++; - } while ((offset < end) && (pivots[offset] < mas->index)); - - if (likely(offset > end)) - max = pivots[offset]; + if (pivots[offset] >= mas->index) { + max = pivots[offset]; + break; + } + } while (++offset < end); -next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) @@ -4164,6 +4219,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas) done: mas_leaf_set_meta(mas, newnode, dst_pivots, maple_leaf_64, new_end); if (in_rcu) { + mte_set_node_dead(mas->node); mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace(mas, false); } else { @@ -4505,6 +4561,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); + if (unlikely(ma_dead_node(node))) + return 1; + mas->max = pivots[offset]; if (offset) mas->min = pivots[offset - 1] + 1; @@ -4526,6 +4585,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, mas->max); + if (unlikely(ma_dead_node(node))) + return 1; + if (offset) mas->min = pivots[offset - 1] + 1; @@ -4574,6 +4636,7 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, struct maple_enode *enode; int level = 0; unsigned char offset; + unsigned char node_end; enum maple_type mt; void __rcu **slots; @@ -4597,7 +4660,11 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); - } while (unlikely(offset == ma_data_end(node, mt, pivots, mas->max))); + node_end = ma_data_end(node, mt, pivots, mas->max); + if (unlikely(ma_dead_node(node))) + return 1; + + } while (unlikely(offset == node_end)); slots = ma_slots(node, mt); pivot = mas_safe_pivot(mas, pivots, ++offset, mt); @@ -4613,6 +4680,9 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, mt = mte_node_type(mas->node); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); + if (unlikely(ma_dead_node(node))) + return 1; + offset = 0; pivot = pivots[0]; } @@ -4659,11 +4729,14 @@ static inline void *mas_next_nentry(struct ma_state *mas, return NULL; } - pivots = ma_pivots(node, type); slots = ma_slots(node, type); - mas->index = mas_safe_min(mas, pivots, mas->offset); + pivots = ma_pivots(node, type); count = ma_data_end(node, type, pivots, mas->max); - if (ma_dead_node(node)) + if (unlikely(ma_dead_node(node))) + return NULL; + + mas->index = mas_safe_min(mas, pivots, mas->offset); + if (unlikely(ma_dead_node(node))) return NULL; if (mas->index > max) @@ -4817,6 +4890,11 @@ retry: slots = ma_slots(mn, mt); pivots = ma_pivots(mn, mt); + if (unlikely(ma_dead_node(mn))) { + mas_rewalk(mas, index); + goto retry; + } + if (offset == mt_pivots[mt]) pivot = mas->max; else @@ -4887,7 +4965,8 @@ not_found: * Return: True if found in a leaf, false otherwise. * */ -static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) +static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, + unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); @@ -4952,8 +5031,8 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) if (unlikely(ma_is_leaf(type))) { mas->offset = offset; - mas->min = min; - mas->max = min + gap - 1; + *gap_min = min; + *gap_max = min + gap - 1; return true; } @@ -4977,10 +5056,10 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; - unsigned char offset; - unsigned long *gaps; - unsigned long *pivots = ma_pivots(mas_mn(mas), type); - void __rcu **slots = ma_slots(mas_mn(mas), type); + unsigned char offset, data_end; + unsigned long *gaps, *pivots; + void __rcu **slots; + struct maple_node *node; bool found = false; if (ma_is_dense(type)) { @@ -4988,13 +5067,15 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) return true; } - gaps = ma_gaps(mte_to_node(mas->node), type); + node = mas_mn(mas); + pivots = ma_pivots(node, type); + slots = ma_slots(node, type); + gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); - for (; offset < mt_slots[type]; offset++) { - pivot = mas_safe_pivot(mas, pivots, offset, type); - if (offset && !pivot) - break; + data_end = ma_data_end(node, type, pivots, mas->max); + for (; offset <= data_end; offset++) { + pivot = mas_logical_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) @@ -5229,6 +5310,9 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long *pivots; enum maple_type mt; + if (min >= max) + return -EINVAL; + if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) @@ -5283,6 +5367,9 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, { struct maple_enode *last = mas->node; + if (min >= max) + return -EINVAL; + if (mas_is_start(mas)) { mas_start(mas); mas->offset = mas_data_end(mas); @@ -5302,7 +5389,7 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, mas->index = min; mas->last = max; - while (!mas_rev_awalk(mas, size)) { + while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; @@ -5317,17 +5404,9 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; - /* - * mas_rev_awalk() has set mas->min and mas->max to the gap values. If - * the maximum is outside the window we are searching, then use the last - * location in the search. - * mas->max and mas->min is the range of the gap. - * mas->index and mas->last are currently set to the search range. - */ - /* Trim the upper limit to the max. */ - if (mas->max <= mas->last) - mas->last = mas->max; + if (max <= mas->last) + mas->last = max; mas->index = mas->last - size + 1; return 0; @@ -5400,24 +5479,26 @@ no_gap: } /* - * mas_dead_leaves() - Mark all leaves of a node as dead. + * mte_dead_leaves() - Mark all leaves of a node as dead. * @mas: The maple state * @slots: Pointer to the slot array + * @type: The maple node type * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline -unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) +unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, + void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; - for (offset = 0; offset < mt_slot_count(mas->node); offset++) { - entry = mas_slot_locked(mas, slots, offset); + for (offset = 0; offset < mt_slot_count(enode); offset++) { + entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ @@ -5425,7 +5506,6 @@ unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) break; mte_set_node_dead(entry); - smp_wmb(); /* Needed for RCU */ node->type = type; rcu_assign_pointer(slots[offset], node); } @@ -5433,151 +5513,160 @@ unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) return offset; } -static void __rcu **mas_dead_walk(struct ma_state *mas, unsigned char offset) +/** + * mte_dead_walk() - Walk down a dead tree to just before the leaves + * @enode: The maple encoded node + * @offset: The starting offset + * + * Note: This can only be used from the RCU callback context. + */ +static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; - next = mas_mn(mas); + next = mte_to_node(*enode); do { - mas->node = ma_enode_ptr(next); - node = mas_mn(mas); + *enode = ma_enode_ptr(next); + node = mte_to_node(*enode); slots = ma_slots(node, node->type); - next = mas_slot_locked(mas, slots, offset); + next = rcu_dereference_protected(slots[offset], + lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } +/** + * mt_free_walk() - Walk & free a tree in the RCU callback context + * @head: The RCU head that's within the node. + * + * Note: This can only be used from the RCU callback context. + */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; - struct maple_tree mt; + struct maple_enode *enode; unsigned char offset; enum maple_type type; - MA_STATE(mas, &mt, 0, 0); node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; - mt_init_flags(&mt, node->ma_flags); - mas_lock(&mas); start = node; - mas.node = mt_mk_node(node, node->type); - slots = mas_dead_walk(&mas, 0); - node = mas_mn(&mas); + enode = mt_mk_node(node, node->type); + slots = mte_dead_walk(&enode, 0); + node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; - mas.node = node->piv_parent; - if (mas_mn(&mas) == node) - goto start_slots_free; - - type = mte_node_type(mas.node); - slots = ma_slots(mte_to_node(mas.node), type); - if ((offset < mt_slots[type]) && (slots[offset])) - slots = mas_dead_walk(&mas, offset); - - node = mas_mn(&mas); + enode = node->piv_parent; + if (mte_to_node(enode) == node) + goto free_leaf; + + type = mte_node_type(enode); + slots = ma_slots(mte_to_node(enode), type); + if ((offset < mt_slots[type]) && + rcu_dereference_protected(slots[offset], + lock_is_held(&rcu_callback_map))) + slots = mte_dead_walk(&enode, offset); + node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); -start_slots_free: - mas_unlock(&mas); free_leaf: mt_free_rcu(&node->rcu); } -static inline void __rcu **mas_destroy_descend(struct ma_state *mas, - struct maple_enode *prev, unsigned char offset) +static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, + struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; - struct maple_enode *next = mas->node; + struct maple_enode *next = *enode; void __rcu **slots = NULL; + enum maple_type type; + unsigned char next_offset = 0; do { - mas->node = next; - node = mas_mn(mas); - slots = ma_slots(node, mte_node_type(mas->node)); - next = mas_slot_locked(mas, slots, 0); + *enode = next; + node = mte_to_node(*enode); + type = mte_node_type(*enode); + slots = ma_slots(node, type); + next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) - next = mas_slot_locked(mas, slots, 1); + next = mt_slot_locked(mt, slots, ++next_offset); - mte_set_node_dead(mas->node); - node->type = mte_node_type(mas->node); + mte_set_node_dead(*enode); + node->type = type; node->piv_parent = prev; node->parent_slot = offset; - offset = 0; - prev = mas->node; + offset = next_offset; + next_offset = 0; + prev = *enode; } while (!mte_is_leaf(next)); return slots; } -static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags, +static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; - struct maple_tree mt; - MA_STATE(mas, &mt, 0, 0); - - if (mte_is_leaf(enode)) + if (mte_is_leaf(enode)) { + node->type = mte_node_type(enode); goto free_leaf; + } - mt_init_flags(&mt, ma_flags); - mas_lock(&mas); - - mas.node = start = enode; - slots = mas_destroy_descend(&mas, start, 0); - node = mas_mn(&mas); + start = enode; + slots = mte_destroy_descend(&enode, mt, start, 0); + node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; - node->slot_len = mas_dead_leaves(&mas, slots); + node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; - mas.node = node->piv_parent; - if (mas_mn(&mas) == node) - goto start_slots_free; + enode = node->piv_parent; + if (mte_to_node(enode) == node) + goto free_leaf; - type = mte_node_type(mas.node); - slots = ma_slots(mte_to_node(mas.node), type); + type = mte_node_type(enode); + slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; - tmp = mas_slot_locked(&mas, slots, offset); + tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { - parent = mas.node; - mas.node = tmp; - slots = mas_destroy_descend(&mas, parent, offset); + parent = enode; + enode = tmp; + slots = mte_destroy_descend(&enode, mt, parent, offset); } next: - node = mas_mn(&mas); - } while (start != mas.node); + node = mte_to_node(enode); + } while (start != enode); - node = mas_mn(&mas); - node->slot_len = mas_dead_leaves(&mas, slots); + node = mte_to_node(enode); + node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); -start_slots_free: - mas_unlock(&mas); - free_leaf: if (free) mt_free_rcu(&node->rcu); + else + mt_clear_meta(mt, node, node->type); } /* @@ -5593,10 +5682,10 @@ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { - mt_destroy_walk(enode, mt->ma_flags, false); + mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { - mt_destroy_walk(enode, mt->ma_flags, true); + mt_destroy_walk(enode, mt, true); } } @@ -6617,11 +6706,11 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn, while (likely(!ma_is_leaf(mt))) { MT_BUG_ON(mas->tree, mte_dead_node(mas->node)); slots = ma_slots(mn, mt); - pivots = ma_pivots(mn, mt); - max = pivots[0]; entry = mas_slot(mas, slots, 0); + pivots = ma_pivots(mn, mt); if (unlikely(ma_dead_node(mn))) return NULL; + max = pivots[0]; mas->node = entry; mn = mas_mn(mas); mt = mte_node_type(mas->node); @@ -6641,13 +6730,13 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn, if (likely(entry)) return entry; - pivots = ma_pivots(mn, mt); - mas->index = pivots[0] + 1; mas->offset = 1; entry = mas_slot(mas, slots, 1); + pivots = ma_pivots(mn, mt); if (unlikely(ma_dead_node(mn))) return NULL; + mas->index = pivots[0] + 1; if (mas->index > limit) goto none; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index a53b9360b72e..30d2d0386fdb 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -507,6 +507,15 @@ static LIST_HEAD(offline_cgwbs); static void cleanup_offline_cgwbs_workfn(struct work_struct *work); static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); +static void cgwb_free_rcu(struct rcu_head *rcu_head) +{ + struct bdi_writeback *wb = container_of(rcu_head, + struct bdi_writeback, rcu); + + percpu_ref_exit(&wb->refcnt); + kfree(wb); +} + static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, @@ -529,11 +538,10 @@ static void cgwb_release_workfn(struct work_struct *work) list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); - percpu_ref_exit(&wb->refcnt); wb_exit(wb); bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); - kfree_rcu(wb, rcu); + call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 032fb0ef9cd1..3fae2d2496ab 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1838,10 +1838,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (is_swap_pmd(*pmd)) { swp_entry_t entry = pmd_to_swp_entry(*pmd); struct page *page = pfn_swap_entry_to_page(entry); + pmd_t newpmd; VM_BUG_ON(!is_pmd_migration_entry(*pmd)); if (is_writable_migration_entry(entry)) { - pmd_t newpmd; /* * A protection check is difficult so * just be safe and disable write @@ -1855,8 +1855,16 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, newpmd = pmd_swp_mksoft_dirty(newpmd); if (pmd_swp_uffd_wp(*pmd)) newpmd = pmd_swp_mkuffd_wp(newpmd); - set_pmd_at(mm, addr, pmd, newpmd); + } else { + newpmd = *pmd; } + + if (uffd_wp) + newpmd = pmd_swp_mkuffd_wp(newpmd); + else if (uffd_wp_resolve) + newpmd = pmd_swp_clear_uffd_wp(newpmd); + if (!pmd_same(*pmd, newpmd)) + set_pmd_at(mm, addr, pmd, newpmd); goto unlock; } #endif @@ -2657,9 +2665,10 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); is_hzp = is_huge_zero_page(&folio->page); - VM_WARN_ON_ONCE_FOLIO(is_hzp, folio); - if (is_hzp) + if (is_hzp) { + pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); return -EBUSY; + } if (folio_test_writeback(folio)) return -EBUSY; @@ -3251,6 +3260,8 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); + if (pmd_uffd_wp(pmdval)) + pmdswp = pmd_swp_mkuffd_wp(pmdswp); set_pmd_at(mm, address, pvmw->pmd, pmdswp); page_remove_rmap(page, vma, true); put_page(page); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 07abcb6eb203..245038a9fe4e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5478,7 +5478,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, struct folio *pagecache_folio, spinlock_t *ptl) { const bool unshare = flags & FAULT_FLAG_UNSHARE; - pte_t pte; + pte_t pte = huge_ptep_get(ptep); struct hstate *h = hstate_vma(vma); struct page *old_page; struct folio *new_folio; @@ -5488,6 +5488,17 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, struct mmu_notifier_range range; /* + * Never handle CoW for uffd-wp protected pages. It should be only + * handled when the uffd-wp protection is removed. + * + * Note that only the CoW optimization path (in hugetlb_no_page()) + * can trigger this, because hugetlb_fault() will always resolve + * uffd-wp bit first. + */ + if (!unshare && huge_pte_uffd_wp(pte)) + return 0; + + /* * hugetlb does not support FOLL_FORCE-style write faults that keep the * PTE mapped R/O such as maybe_mkwrite() would do. */ @@ -5500,7 +5511,6 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } - pte = huge_ptep_get(ptep); old_page = pte_page(pte); delayacct_wpcopy_start(); diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 79c94ee55f97..1065e0568d05 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -556,15 +556,11 @@ static unsigned long kfence_init_pool(void) * enters __slab_free() slow-path. */ for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { - struct slab *slab = page_slab(&pages[i]); + struct slab *slab = page_slab(nth_page(pages, i)); if (!i || (i % 2)) continue; - /* Verify we do not have a compound head page. */ - if (WARN_ON(compound_head(&pages[i]) != &pages[i])) - return addr; - __folio_set_slab(slab_folio(slab)); #ifdef CONFIG_MEMCG slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg | @@ -597,12 +593,26 @@ static unsigned long kfence_init_pool(void) /* Protect the right redzone. */ if (unlikely(!kfence_protect(addr + PAGE_SIZE))) - return addr; + goto reset_slab; addr += 2 * PAGE_SIZE; } return 0; + +reset_slab: + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { + struct slab *slab = page_slab(nth_page(pages, i)); + + if (!i || (i % 2)) + continue; +#ifdef CONFIG_MEMCG + slab->memcg_data = 0; +#endif + __folio_clear_slab(slab_folio(slab)); + } + + return addr; } static bool __init kfence_init_pool_early(void) @@ -632,16 +642,6 @@ static bool __init kfence_init_pool_early(void) * fails for the first page, and therefore expect addr==__kfence_pool in * most failure cases. */ - for (char *p = (char *)addr; p < __kfence_pool + KFENCE_POOL_SIZE; p += PAGE_SIZE) { - struct slab *slab = virt_to_slab(p); - - if (!slab) - continue; -#ifdef CONFIG_MEMCG - slab->memcg_data = 0; -#endif - __folio_clear_slab(slab_folio(slab)); - } memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); __kfence_pool = NULL; return false; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 92e6f56a932d..0ec69b96b497 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -572,6 +572,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, result = SCAN_PTE_NON_PRESENT; goto out; } + if (pte_uffd_wp(pteval)) { + result = SCAN_PTE_UFFD_WP; + goto out; + } page = vm_normal_page(vma, address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c index 3807502766a3..ec0da72e65aa 100644 --- a/mm/kmsan/hooks.c +++ b/mm/kmsan/hooks.c @@ -148,35 +148,74 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end) * into the virtual memory. If those physical pages already had shadow/origin, * those are ignored. */ -void kmsan_ioremap_page_range(unsigned long start, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift) +int kmsan_ioremap_page_range(unsigned long start, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift) { gfp_t gfp_mask = GFP_KERNEL | __GFP_ZERO; struct page *shadow, *origin; unsigned long off = 0; - int nr; + int nr, err = 0, clean = 0, mapped; if (!kmsan_enabled || kmsan_in_runtime()) - return; + return 0; nr = (end - start) / PAGE_SIZE; kmsan_enter_runtime(); - for (int i = 0; i < nr; i++, off += PAGE_SIZE) { + for (int i = 0; i < nr; i++, off += PAGE_SIZE, clean = i) { shadow = alloc_pages(gfp_mask, 1); origin = alloc_pages(gfp_mask, 1); - __vmap_pages_range_noflush( + if (!shadow || !origin) { + err = -ENOMEM; + goto ret; + } + mapped = __vmap_pages_range_noflush( vmalloc_shadow(start + off), vmalloc_shadow(start + off + PAGE_SIZE), prot, &shadow, PAGE_SHIFT); - __vmap_pages_range_noflush( + if (mapped) { + err = mapped; + goto ret; + } + shadow = NULL; + mapped = __vmap_pages_range_noflush( vmalloc_origin(start + off), vmalloc_origin(start + off + PAGE_SIZE), prot, &origin, PAGE_SHIFT); + if (mapped) { + __vunmap_range_noflush( + vmalloc_shadow(start + off), + vmalloc_shadow(start + off + PAGE_SIZE)); + err = mapped; + goto ret; + } + origin = NULL; + } + /* Page mapping loop finished normally, nothing to clean up. */ + clean = 0; + +ret: + if (clean > 0) { + /* + * Something went wrong. Clean up shadow/origin pages allocated + * on the last loop iteration, then delete mappings created + * during the previous iterations. + */ + if (shadow) + __free_pages(shadow, 1); + if (origin) + __free_pages(origin, 1); + __vunmap_range_noflush( + vmalloc_shadow(start), + vmalloc_shadow(start + clean * PAGE_SIZE)); + __vunmap_range_noflush( + vmalloc_origin(start), + vmalloc_origin(start + clean * PAGE_SIZE)); } flush_cache_vmap(vmalloc_shadow(start), vmalloc_shadow(end)); flush_cache_vmap(vmalloc_origin(start), vmalloc_origin(end)); kmsan_leave_runtime(); + return err; } void kmsan_iounmap_page_range(unsigned long start, unsigned long end) diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index a787c04e9583..b8bb95eea5e3 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -216,27 +216,29 @@ void kmsan_free_page(struct page *page, unsigned int order) kmsan_leave_runtime(); } -void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift) +int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift) { unsigned long shadow_start, origin_start, shadow_end, origin_end; struct page **s_pages, **o_pages; - int nr, mapped; + int nr, mapped, err = 0; if (!kmsan_enabled) - return; + return 0; shadow_start = vmalloc_meta((void *)start, KMSAN_META_SHADOW); shadow_end = vmalloc_meta((void *)end, KMSAN_META_SHADOW); if (!shadow_start) - return; + return 0; nr = (end - start) / PAGE_SIZE; s_pages = kcalloc(nr, sizeof(*s_pages), GFP_KERNEL); o_pages = kcalloc(nr, sizeof(*o_pages), GFP_KERNEL); - if (!s_pages || !o_pages) + if (!s_pages || !o_pages) { + err = -ENOMEM; goto ret; + } for (int i = 0; i < nr; i++) { s_pages[i] = shadow_page_for(pages[i]); o_pages[i] = origin_page_for(pages[i]); @@ -249,10 +251,16 @@ void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, kmsan_enter_runtime(); mapped = __vmap_pages_range_noflush(shadow_start, shadow_end, prot, s_pages, page_shift); - KMSAN_WARN_ON(mapped); + if (mapped) { + err = mapped; + goto ret; + } mapped = __vmap_pages_range_noflush(origin_start, origin_end, prot, o_pages, page_shift); - KMSAN_WARN_ON(mapped); + if (mapped) { + err = mapped; + goto ret; + } kmsan_leave_runtime(); flush_tlb_kernel_range(shadow_start, shadow_end); flush_tlb_kernel_range(origin_start, origin_end); @@ -262,6 +270,7 @@ void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, ret: kfree(s_pages); kfree(o_pages); + return err; } /* Allocate metadata for pages allocated at boot time. */ diff --git a/mm/memory.c b/mm/memory.c index f456f3b5049c..01a23ad48a04 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3563,8 +3563,21 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct mmu_notifier_range range; - if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) + /* + * We need a reference to lock the folio because we don't hold + * the PTL so a racing thread can remove the device-exclusive + * entry and unmap it. If the folio is free the entry must + * have been removed already. If it happens to have already + * been re-allocated after being freed all we do is lock and + * unlock it. + */ + if (!folio_try_get(folio)) + return 0; + + if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) { + folio_put(folio); return VM_FAULT_RETRY; + } mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); @@ -3577,6 +3590,7 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) pte_unmap_unlock(vmf->pte, vmf->ptl); folio_unlock(folio); + folio_put(folio); mmu_notifier_invalidate_range_end(&range); return 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a256a241fd1d..2068b594dc88 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -790,61 +790,50 @@ static int vma_replace_policy(struct vm_area_struct *vma, return err; } -/* Step 2: apply policy to a range and do splits. */ -static int mbind_range(struct mm_struct *mm, unsigned long start, - unsigned long end, struct mempolicy *new_pol) +/* Split or merge the VMA (if required) and apply the new policy */ +static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, + unsigned long end, struct mempolicy *new_pol) { - VMA_ITERATOR(vmi, mm, start); - struct vm_area_struct *prev; - struct vm_area_struct *vma; - int err = 0; + struct vm_area_struct *merged; + unsigned long vmstart, vmend; pgoff_t pgoff; + int err; - prev = vma_prev(&vmi); - vma = vma_find(&vmi, end); - if (WARN_ON(!vma)) + vmend = min(end, vma->vm_end); + if (start > vma->vm_start) { + *prev = vma; + vmstart = start; + } else { + vmstart = vma->vm_start; + } + + if (mpol_equal(vma_policy(vma), new_pol)) return 0; - if (start > vma->vm_start) - prev = vma; - - do { - unsigned long vmstart = max(start, vma->vm_start); - unsigned long vmend = min(end, vma->vm_end); - - if (mpol_equal(vma_policy(vma), new_pol)) - goto next; - - pgoff = vma->vm_pgoff + - ((vmstart - vma->vm_start) >> PAGE_SHIFT); - prev = vma_merge(&vmi, mm, prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, - new_pol, vma->vm_userfaultfd_ctx, - anon_vma_name(vma)); - if (prev) { - vma = prev; - goto replace; - } - if (vma->vm_start != vmstart) { - err = split_vma(&vmi, vma, vmstart, 1); - if (err) - goto out; - } - if (vma->vm_end != vmend) { - err = split_vma(&vmi, vma, vmend, 0); - if (err) - goto out; - } -replace: - err = vma_replace_policy(vma, new_pol); + pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); + merged = vma_merge(vmi, vma->vm_mm, *prev, vmstart, vmend, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, new_pol, + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + if (merged) { + *prev = merged; + return vma_replace_policy(merged, new_pol); + } + + if (vma->vm_start != vmstart) { + err = split_vma(vmi, vma, vmstart, 1); if (err) - goto out; -next: - prev = vma; - } for_each_vma_range(vmi, vma, end); + return err; + } -out: - return err; + if (vma->vm_end != vmend) { + err = split_vma(vmi, vma, vmend, 0); + if (err) + return err; + } + + *prev = vma; + return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ @@ -1259,6 +1248,8 @@ static long do_mbind(unsigned long start, unsigned long len, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; + struct vm_area_struct *vma, *prev; + struct vma_iterator vmi; struct mempolicy *new; unsigned long end; int err; @@ -1328,7 +1319,13 @@ static long do_mbind(unsigned long start, unsigned long len, goto up_out; } - err = mbind_range(mm, start, end, new); + vma_iter_init(&vmi, mm, start); + prev = vma_prev(&vmi); + for_each_vma_range(vmi, vma, end) { + err = mbind_range(&vmi, vma, &prev, start, end, new); + if (err) + break; + } if (!err) { int nr_failed = 0; @@ -1489,10 +1486,8 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; - unsigned long vmstart; - unsigned long vmend; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); @@ -1521,6 +1516,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le if (end == start) return 0; mmap_write_lock(mm); + prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND @@ -1541,9 +1537,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le } new->home_node = home_node; - vmstart = max(start, vma->vm_start); - vmend = min(end, vma->vm_end); - err = mbind_range(mm, vmstart, vmend, new); + err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; diff --git a/mm/mmap.c b/mm/mmap.c index ad499f7b767f..d5475fbf5729 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1518,7 +1518,8 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) */ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { - unsigned long length, gap; + unsigned long length, gap, low_limit; + struct vm_area_struct *tmp; MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); @@ -1527,12 +1528,29 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) if (length < info->length) return -ENOMEM; - if (mas_empty_area(&mas, info->low_limit, info->high_limit - 1, - length)) + low_limit = info->low_limit; +retry: + if (mas_empty_area(&mas, low_limit, info->high_limit - 1, length)) return -ENOMEM; gap = mas.index; gap += (info->align_offset - gap) & info->align_mask; + tmp = mas_next(&mas, ULONG_MAX); + if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */ + if (vm_start_gap(tmp) < gap + length - 1) { + low_limit = tmp->vm_end; + mas_reset(&mas); + goto retry; + } + } else { + tmp = mas_prev(&mas, 0); + if (tmp && vm_end_gap(tmp) > gap) { + low_limit = vm_end_gap(tmp); + mas_reset(&mas); + goto retry; + } + } + return gap; } @@ -1548,7 +1566,8 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) */ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { - unsigned long length, gap; + unsigned long length, gap, high_limit, gap_end; + struct vm_area_struct *tmp; MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); /* Adjust search length to account for worst case alignment overhead */ @@ -1556,12 +1575,31 @@ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) if (length < info->length) return -ENOMEM; - if (mas_empty_area_rev(&mas, info->low_limit, info->high_limit - 1, + high_limit = info->high_limit; +retry: + if (mas_empty_area_rev(&mas, info->low_limit, high_limit - 1, length)) return -ENOMEM; gap = mas.last + 1 - info->length; gap -= (gap - info->align_offset) & info->align_mask; + gap_end = mas.last; + tmp = mas_next(&mas, ULONG_MAX); + if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */ + if (vm_start_gap(tmp) <= gap_end) { + high_limit = vm_start_gap(tmp); + mas_reset(&mas); + goto retry; + } + } else { + tmp = mas_prev(&mas, 0); + if (tmp && vm_end_gap(tmp) > gap) { + high_limit = tmp->vm_start; + mas_reset(&mas); + goto retry; + } + } + return gap; } @@ -2277,7 +2315,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, int count = 0; int error = -ENOMEM; MA_STATE(mas_detach, &mt_detach, 0, 0); - mt_init_flags(&mt_detach, MT_FLAGS_LOCK_EXTERN); + mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); /* @@ -3037,6 +3075,7 @@ void exit_mmap(struct mm_struct *mm) */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); + mt_clear_in_rcu(&mm->mm_mt); free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb); diff --git a/mm/mprotect.c b/mm/mprotect.c index 13e84d8c0797..36351a00c0e8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -838,7 +838,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, } tlb_finish_mmu(&tlb); - if (vma_iter_end(&vmi) < end) + if (!error && vma_iter_end(&vmi) < end) error = -ENOMEM; out: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7136c36c5d01..8e39705c7bdc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6632,7 +6632,21 @@ static void __build_all_zonelists(void *data) int nid; int __maybe_unused cpu; pg_data_t *self = data; + unsigned long flags; + /* + * Explicitly disable this CPU's interrupts before taking seqlock + * to prevent any IRQ handler from calling into the page allocator + * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock. + */ + local_irq_save(flags); + /* + * Explicitly disable this CPU's synchronous printk() before taking + * seqlock to prevent any printk() from trying to hold port->lock, for + * tty_insert_flip_string_and_push_buffer() on other CPU might be + * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held. + */ + printk_deferred_enter(); write_seqlock(&zonelist_update_seq); #ifdef CONFIG_NUMA @@ -6671,6 +6685,8 @@ static void __build_all_zonelists(void *data) } write_sequnlock(&zonelist_update_seq); + printk_deferred_exit(); + local_irq_restore(flags); } static noinline void __init @@ -9450,6 +9466,9 @@ static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, if (PageReserved(page)) return false; + + if (PageHuge(page)) + return false; } return true; } diff --git a/mm/swap.c b/mm/swap.c index 57cb01b042f6..423199ee8478 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -222,7 +222,7 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); folios_put(fbatch->folios, folio_batch_count(fbatch)); - folio_batch_init(fbatch); + folio_batch_reinit(fbatch); } static void folio_batch_add_and_move(struct folio_batch *fbatch, diff --git a/mm/swapfile.c b/mm/swapfile.c index 62ba2bf577d7..2c718f45745f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -679,6 +679,7 @@ static void __del_from_avail_list(struct swap_info_struct *p) { int nid; + assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } @@ -2434,8 +2435,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - del_from_avail_list(p); spin_lock(&p->lock); + del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bef6cf2b4d46..31ff782d368b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -313,8 +313,8 @@ int ioremap_page_range(unsigned long addr, unsigned long end, ioremap_max_page_shift); flush_cache_vmap(addr, end); if (!err) - kmsan_ioremap_page_range(addr, end, phys_addr, prot, - ioremap_max_page_shift); + err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, + ioremap_max_page_shift); return err; } @@ -605,7 +605,11 @@ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { - kmsan_vmap_pages_range_noflush(addr, end, prot, pages, page_shift); + int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, + page_shift); + + if (ret) + return ret; return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); } @@ -3042,9 +3046,11 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { - warn_alloc(gfp_mask, NULL, - "vmalloc error: size %lu, page order %u, failed to allocate pages", - area->nr_pages * PAGE_SIZE, page_order); + /* vm_area_alloc_pages() can also fail due to a fatal signal */ + if (!fatal_signal_pending(current)) + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, page order %u, failed to allocate pages", + area->nr_pages * PAGE_SIZE, page_order); goto fail; } diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index c64050e839ac..1fffe2bed5b0 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -280,6 +280,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 17b946f9ba31..8455ba141ee6 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -68,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn) +static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -88,9 +88,28 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) params = hci_pend_le_action_lookup(&hdev->pend_le_conns, bdaddr, bdaddr_type); - if (!params || !params->explicit_connect) + if (!params) return; + if (params->conn) { + hci_conn_drop(params->conn); + hci_conn_put(params->conn); + params->conn = NULL; + } + + if (!params->explicit_connect) + return; + + /* If the status indicates successful cancellation of + * the attempt (i.e. Unknown Connection Id) there's no point of + * notifying failure since we'll go back to keep trying to + * connect. The only exception is explicit connect requests + * where a timeout + cancel does indicate an actual failure. + */ + if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other * autoconnect action, remove them completely. If they are, just unmark @@ -178,7 +197,7 @@ static void le_scan_cleanup(struct work_struct *work) rcu_read_unlock(); if (c == conn) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); hci_conn_cleanup(conn); } @@ -1049,6 +1068,17 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, return conn; } +static bool hci_conn_unlink(struct hci_conn *conn) +{ + if (!conn->link) + return false; + + conn->link->link = NULL; + conn->link = NULL; + + return true; +} + int hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1060,15 +1090,16 @@ int hci_conn_del(struct hci_conn *conn) cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - struct hci_conn *sco = conn->link; - if (sco) { - sco->link = NULL; + struct hci_conn *link = conn->link; + + if (link) { + hci_conn_unlink(conn); /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. */ - if (sco->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(sco); + if (link->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(link); } /* Unacked frames */ @@ -1084,7 +1115,7 @@ int hci_conn_del(struct hci_conn *conn) struct hci_conn *acl = conn->link; if (acl) { - acl->link = NULL; + hci_conn_unlink(conn); hci_conn_drop(acl); } @@ -1179,31 +1210,8 @@ EXPORT_SYMBOL(hci_get_route); static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; - struct hci_conn_params *params; - params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, - conn->dst_type); - if (params && params->conn) { - hci_conn_drop(params->conn); - hci_conn_put(params->conn); - params->conn = NULL; - } - - /* If the status indicates successful cancellation of - * the attempt (i.e. Unknown Connection Id) there's no point of - * notifying failure since we'll go back to keep trying to - * connect. The only exception is explicit connect requests - * where a timeout + cancel does indicate an actual failure. - */ - if (status != HCI_ERROR_UNKNOWN_CONN_ID || - (params && params->explicit_connect)) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, status); - - /* Since we may have temporarily stopped the background scanning in - * favor of connection establishment, we should restart it. - */ - hci_update_passive_scan(hdev); + hci_connect_le_scan_cleanup(conn, status); /* Enable advertising in case this was a failed connection * attempt as a peripheral. @@ -1237,15 +1245,15 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; + bt_dev_dbg(hdev, "err %d", err); + hci_dev_lock(hdev); if (!err) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); goto done; } - bt_dev_err(hdev, "request failed to create LE connection: err %d", err); - /* Check if connection is still pending */ if (conn != hci_lookup_le_connect(hdev)) goto done; @@ -2438,6 +2446,12 @@ void hci_conn_hash_flush(struct hci_dev *hdev) c->state = BT_CLOSED; hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + + /* Unlink before deleting otherwise it is possible that + * hci_conn_del removes the link which may cause the list to + * contain items already freed. + */ + hci_conn_unlink(c); hci_conn_del(c); } } @@ -2775,6 +2789,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) { int r = 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ad92a4be5851..e87c928c9e17 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2881,16 +2881,6 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, conn->resp_addr_type = peer_addr_type; bacpy(&conn->resp_addr, peer_addr); - - /* We don't want the connection attempt to stick around - * indefinitely since LE doesn't have a page timeout concept - * like BR/EDR. Set a timer for any connection that doesn't use - * the accept list for connecting. - */ - if (filter_policy == HCI_LE_USE_PEER_ADDR) - queue_delayed_work(conn->hdev->workqueue, - &conn->le_conn_timeout, - conn->conn_timeout); } static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) @@ -5902,6 +5892,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock; + /* Drop the connection if it has been aborted */ + if (test_bit(HCI_CONN_CANCEL, &conn->flags)) { + hci_conn_drop(conn); + goto unlock; + } + if (conn->dst_type == ADDR_LE_DEV_PUBLIC) addr_type = BDADDR_LE_PUBLIC; else @@ -6995,7 +6991,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.in.sdu = le16_to_cpu(ev->max_pdu); - hci_connect_cfm(bis, ev->status); + hci_iso_setup_path(bis); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5a6aa1627791..632be1267288 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -246,8 +246,9 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); if (IS_ERR(skb)) { - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, - PTR_ERR(skb)); + if (!event) + bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + PTR_ERR(skb)); return PTR_ERR(skb); } @@ -5126,8 +5127,11 @@ static int hci_le_connect_cancel_sync(struct hci_dev *hdev, if (test_bit(HCI_CONN_SCANNING, &conn->flags)) return 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, - 6, &conn->dst, HCI_CMD_TIMEOUT); + 0, NULL, HCI_CMD_TIMEOUT); } static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -6102,6 +6106,9 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) conn->conn_timeout, NULL); done: + if (err == -ETIMEDOUT) + hci_le_connect_cancel_sync(hdev, conn); + /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); return err; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index bed1a7b9205c..707f229f896a 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -433,7 +433,7 @@ static void hidp_set_timer(struct hidp_session *session) static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) - del_timer(&session->timer); + del_timer_sync(&session->timer); } static void hidp_process_report(struct hidp_session *session, int type, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 49926f59cc12..55a7226233f9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4652,33 +4652,27 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp); chan->ops->set_shutdown(chan); + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -4698,33 +4692,27 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; } + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1111da4e2f2b..cd1a27ac555d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -235,27 +235,41 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, return err; } -static int sco_connect(struct hci_dev *hdev, struct sock *sk) +static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; + struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); + hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); + if (!hdev) + return -EHOSTUNREACH; + + hci_dev_lock(hdev); + if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) - return -EOPNOTSUPP; + (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { + err = -EOPNOTSUPP; + goto unlock; + } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec); - if (IS_ERR(hcon)) - return PTR_ERR(hcon); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } + + hci_dev_unlock(hdev); + hci_dev_put(hdev); conn = sco_conn_add(hcon); if (!conn) { @@ -263,13 +277,15 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) return -ENOMEM; } - /* Update source addr of the socket */ - bacpy(&sco_pi(sk)->src, &hcon->src); - err = sco_chan_add(conn, sk, NULL); if (err) return err; + lock_sock(sk); + + /* Update source addr of the socket */ + bacpy(&sco_pi(sk)->src, &hcon->src); + if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; @@ -278,6 +294,13 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) sco_sock_set_timer(sk, sk->sk_sndtimeo); } + release_sock(sk); + + return err; + +unlock: + hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } @@ -565,7 +588,6 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; - struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); @@ -574,37 +596,26 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen addr->sa_family != AF_BLUETOOTH) return -EINVAL; - lock_sock(sk); - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { - err = -EBADFD; - goto done; - } + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) + return -EBADFD; - if (sk->sk_type != SOCK_SEQPACKET) { + if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; - goto done; - } - - hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); - if (!hdev) { - err = -EHOSTUNREACH; - goto done; - } - hci_dev_lock(hdev); + lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); + release_sock(sk); - err = sco_connect(hdev, sk); - hci_dev_unlock(hdev); - hci_dev_put(hdev); + err = sco_connect(sk); if (err) - goto done; + return err; + + lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); -done: release_sock(sk); return err; } @@ -1129,6 +1140,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, break; } + release_sock(sk); + /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { @@ -1146,15 +1159,13 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); - err = -ENOBUFS; - break; + return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); - err = -EFAULT; - break; + return -EFAULT; } ptr += sizeof(num_codecs); @@ -1194,12 +1205,14 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, ptr += len; } - if (!err && put_user(buf_len, optlen)) - err = -EFAULT; - hci_dev_unlock(hdev); hci_dev_put(hdev); + lock_sock(sk); + + if (!err && put_user(buf_len, optlen)) + err = -EFAULT; + break; default: diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 638a4d5359db..4bc6761517bb 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -868,12 +868,17 @@ static unsigned int ip_sabotage_in(void *priv, { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge && !nf_bridge->in_prerouting && - !netif_is_l3_master(skb->dev) && - !netif_is_l3_slave(skb->dev)) { - nf_bridge_info_free(skb); - state->okfn(state->net, state->sk, skb); - return NF_STOLEN; + if (nf_bridge) { + if (nf_bridge->sabotage_in_done) + return NF_ACCEPT; + + if (!nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev) && + !netif_is_l3_slave(skb->dev)) { + nf_bridge->sabotage_in_done = 1; + state->okfn(state->net, state->sk, skb); + return NF_STOLEN; + } } return NF_ACCEPT; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index de18e9c1d7a7..ba95c4d74a60 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -148,6 +148,17 @@ br_switchdev_fdb_notify(struct net_bridge *br, if (test_bit(BR_FDB_LOCKED, &fdb->flags)) return; + /* Entries with these flags were created using ndm_state == NUD_REACHABLE, + * ndm_flags == NTF_MASTER( | NTF_STICKY), ext_flags == 0 by something + * equivalent to 'bridge fdb add ... master dynamic (sticky)'. + * Drivers don't know how to deal with these, so don't notify them to + * avoid confusing them. + */ + if (test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags) && + !test_bit(BR_FDB_STATIC, &fdb->flags) && + !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) + return; + br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { diff --git a/net/can/isotp.c b/net/can/isotp.c index 9bc344851704..5761d4ab839d 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -119,7 +119,8 @@ enum { ISOTP_WAIT_FIRST_FC, ISOTP_WAIT_FC, ISOTP_WAIT_DATA, - ISOTP_SENDING + ISOTP_SENDING, + ISOTP_SHUTDOWN, }; struct tpcon { @@ -880,8 +881,8 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) txtimer); struct sock *sk = &so->sk; - /* don't handle timeouts in IDLE state */ - if (so->tx.state == ISOTP_IDLE) + /* don't handle timeouts in IDLE or SHUTDOWN state */ + if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) return HRTIMER_NORESTART; /* we did not get any flow control or echo frame in time */ @@ -918,7 +919,6 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); - u32 old_state = so->tx.state; struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; @@ -928,23 +928,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) int off; int err; - if (!so->bound) + if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; +wait_free_buffer: /* we do not support multiple buffers - for now */ - if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE || - wq_has_sleeper(&so->wait)) { - if (msg->msg_flags & MSG_DONTWAIT) { - err = -EAGAIN; - goto err_out; - } + if (wq_has_sleeper(&so->wait) && (msg->msg_flags & MSG_DONTWAIT)) + return -EAGAIN; - /* wait for complete transmission of current pdu */ - err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - if (err) - goto err_out; + /* wait for complete transmission of current pdu */ + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_event_drop; - so->tx.state = ISOTP_SENDING; + if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { + if (so->tx.state == ISOTP_SHUTDOWN) + return -EADDRNOTAVAIL; + + goto wait_free_buffer; } if (!size || size > MAX_MSG_LENGTH) { @@ -1074,7 +1075,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (wait_tx_done) { /* wait for complete transmission of current pdu */ - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_event_drop; if (sk->sk_err) return -sk->sk_err; @@ -1082,13 +1085,15 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return size; +err_event_drop: + /* got signal: force tx state machine to be idle */ + so->tx.state = ISOTP_IDLE; + hrtimer_cancel(&so->txfrtimer); + hrtimer_cancel(&so->txtimer); err_out_drop: /* drop this PDU and unlock a potential wait queue */ - old_state = ISOTP_IDLE; -err_out: - so->tx.state = old_state; - if (so->tx.state == ISOTP_IDLE) - wake_up_interruptible(&so->wait); + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); return err; } @@ -1120,7 +1125,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (ret < 0) goto out_err; - sock_recv_timestamp(msg, sk, skb); + sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(ISOTP_MIN_NAMELEN); @@ -1150,10 +1155,12 @@ static int isotp_release(struct socket *sock) net = sock_net(sk); /* wait for complete transmission of current pdu */ - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && + cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) + ; /* force state machines to be idle also when a signal occurred */ - so->tx.state = ISOTP_IDLE; + so->tx.state = ISOTP_SHUTDOWN; so->rx.state = ISOTP_IDLE; spin_lock(&isotp_notifier_lock); @@ -1608,6 +1615,21 @@ static int isotp_init(struct sock *sk) return 0; } +static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wait) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + + __poll_t mask = datagram_poll(file, sock, wait); + poll_wait(file, &so->wait, wait); + + /* Check for false positives due to TX state */ + if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) + mask &= ~(EPOLLOUT | EPOLLWRNORM); + + return mask; +} + static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { @@ -1623,7 +1645,7 @@ static const struct proto_ops isotp_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = isotp_getname, - .poll = datagram_poll, + .poll = isotp_poll, .ioctl = isotp_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fb92c3609e17..fe3df23a2595 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -604,7 +604,10 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); - memcpy(skb->cb, re_skcb, sizeof(skb->cb)); + /* skb->cb must be large enough to hold a j1939_sk_buff_cb structure */ + BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*re_skcb)); + + memcpy(skb->cb, re_skcb, sizeof(*re_skcb)); skcb = j1939_skb_to_cb(skb); if (swap_src_dst) j1939_skbcb_swap(skcb); diff --git a/net/core/dev.c b/net/core/dev.c index 253584777101..1488f700bf81 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3199,6 +3199,7 @@ static u16 skb_tx_hash(const struct net_device *dev, } if (skb_rx_queue_recorded(skb)) { + DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; @@ -10846,7 +10847,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, - portid, nlmsg_seq(nlh)); + portid, nlh); /* * Flush the unicast and multicast chains diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a089b704b986..e6a739b1afa9 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -137,6 +137,20 @@ static void queue_process(struct work_struct *work) } } +static int netif_local_xmit_active(struct net_device *dev) +{ + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + return 1; + } + + return 0; +} + static void poll_one_napi(struct napi_struct *napi) { int work; @@ -183,7 +197,10 @@ void netpoll_poll_dev(struct net_device *dev) if (!ni || down_trylock(&ni->dev_lock)) return; - if (!netif_running(dev)) { + /* Some drivers will take the same locks in poll and xmit, + * we can't poll if local CPU is already in xmit. + */ + if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5d8eb57867a9..6e44e92ebdf5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3972,16 +3972,23 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq) + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + u32 seq = 0; skb = nlmsg_new(if_nlmsg_size(dev, 0), flags); if (skb == NULL) goto errout; + if (nlmsg_report(nlh)) + seq = nlmsg_seq(nlh); + else + portid = 0; + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); @@ -4017,7 +4024,7 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex, portid, nlmsg_seq(nlh)); + new_ifindex, portid, nlh); if (skb) rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1a31815104d6..4c0879798eb8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5599,18 +5599,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* In general, avoid mixing slab allocated and page_pool allocated - * pages within the same SKB. However when @to is not pp_recycle and - * @from is cloned, we can transition frag pages from page_pool to - * reference counted. - * - * On the other hand, don't allow coalescing two pp_recycle SKBs if - * @from is cloned, in case the SKB is using page_pool fragment + /* In general, avoid mixing page_pool and non-page_pool allocated + * pages within the same SKB. Additionally avoid dealing with clones + * with page_pool pages, in case the SKB is using page_pool fragment * references (PP_FLAG_PAGE_FRAG). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. + * In theory we could take full references if @from is cloned and + * !@to->pp_recycle but its tricky (due to potential race with + * the clone disappearing) and rare, so not worth dealing with. */ - if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle || + (from->pp_recycle && skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 528d4b37983d..fb85aca81961 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -734,13 +734,21 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *tim * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. + * @rss_type: Return value pointer for RSS type. + * + * The RSS hash type (@rss_type) specifies what portion of packet headers NIC + * hardware used when calculating RSS hash value. The RSS type can be decoded + * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits + * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* + * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ -__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) +__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index fab66c169b9f..20165e07ef90 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -270,11 +270,12 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, "lanes configuration not supported by device"); return -EOPNOTSUPP; } - } else if (!lsettings->autoneg) { - /* If autoneg is off and lanes parameter is not passed from user, - * set the lanes parameter to 0. + } else if (!lsettings->autoneg && ksettings->lanes) { + /* If autoneg is off and lanes parameter is not passed from user but + * it was defined previously then set the lanes parameter to 0. */ ksettings->lanes = 0; + *mod = true; } ret = ethnl_update_bitset(ksettings->link_modes.advertising, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 8cebb476b3ab..b8607763d113 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -749,6 +749,11 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); + /* Guard against tiny mtu. We need to include at least one + * IP network header for this message to make any sense. + */ + if (room <= (int)sizeof(struct iphdr)) + goto ende; icmp_param.data_len = skb_in->len - icmp_param.offset; if (icmp_param.data_len > room) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 409ec2a1f95b..5178a3f3cb53 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1089,13 +1089,13 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) } void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) - __acquires(RCU) + __acquires(ping_table.lock) { struct ping_iter_state *state = seq->private; state->bucket = 0; state->family = family; - rcu_read_lock(); + spin_lock(&ping_table.lock); return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1121,9 +1121,9 @@ void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(ping_seq_next); void ping_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) + __releases(ping_table.lock) { - rcu_read_unlock(); + spin_unlock(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_seq_stop); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 94df935ee0c5..8088a5011e7d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -91,12 +91,12 @@ EXPORT_SYMBOL_GPL(raw_v4_hashinfo); int raw_hash_sk(struct sock *sk) { struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; - struct hlist_nulls_head *hlist; + struct hlist_head *hlist; hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); - __sk_nulls_add_node_rcu(sk, hlist); + sk_add_node_rcu(sk, hlist); sock_set_flag(sk, SOCK_RCU_FREE); spin_unlock(&h->lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -110,7 +110,7 @@ void raw_unhash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; spin_lock(&h->lock); - if (__sk_nulls_del_node_init_rcu(sk)) + if (sk_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(&h->lock); } @@ -163,16 +163,15 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) static int raw_v4_input(struct net *net, struct sk_buff *skb, const struct iphdr *iph, int hash) { - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int sdif = inet_sdif(skb); + struct hlist_head *hlist; int dif = inet_iif(skb); int delivered = 0; struct sock *sk; hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; @@ -264,10 +263,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); + struct hlist_head *hlist; const struct iphdr *iph; struct sock *sk; int hash; @@ -276,7 +274,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { iph = (const struct iphdr *)skb->data; if (!raw_v4_match(net, sk, iph->protocol, iph->daddr, iph->saddr, dif, sdif)) @@ -950,14 +948,13 @@ static struct sock *raw_get_first(struct seq_file *seq, int bucket) { struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; for (state->bucket = bucket; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { hlist = &h->ht[state->bucket]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each(sk, hlist) { if (sock_net(sk) == seq_file_net(seq)) return sk; } @@ -970,7 +967,7 @@ static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) struct raw_iter_state *state = raw_seq_private(seq); do { - sk = sk_nulls_next(sk); + sk = sk_next(sk); } while (sk && sock_net(sk) != seq_file_net(seq)); if (!sk) @@ -989,9 +986,12 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) } void *raw_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) + __acquires(&h->lock) { - rcu_read_lock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_lock(&h->lock); + return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(raw_seq_start); @@ -1010,9 +1010,11 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) + __releases(&h->lock) { - rcu_read_unlock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_unlock(&h->lock); } EXPORT_SYMBOL_GPL(raw_seq_stop); diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 999321834b94..da3591a66a16 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -57,8 +57,7 @@ static bool raw_lookup(struct net *net, struct sock *sk, static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r) { struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int slot; @@ -68,7 +67,7 @@ static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 rcu_read_lock(); for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) { hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (raw_lookup(net, sk, r)) { /* * Grab it and keep until we fill @@ -142,9 +141,8 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); struct net *net = sock_net(skb->sk); struct inet_diag_dump_data *cb_data; - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int num, s_num, slot, s_slot; + struct hlist_head *hlist; struct sock *sk = NULL; struct nlattr *bc; @@ -161,7 +159,7 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num = 0; hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d0cc4ef2b85..40fe70fc2015 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -25,6 +25,7 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1198,6 +1199,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ea370afa70ed..b9d55277cb85 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2780,7 +2780,7 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { while (iter->cur_sk < iter->end_sk) - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, @@ -2941,7 +2941,7 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) * st->bucket. See tcp_seek_last_pos(). */ st->offset++; - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } if (iter->cur_sk < iter->end_sk) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c314fdde0097..95a55c6630ad 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1965,8 +1965,13 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + u8 icmp6_type; - ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + icmp6_type = fl6->fl6_icmp_type; + else + icmp6_type = icmp6_hdr(skb)->icmp6_type; + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bac9ba747bde..a327aa481df4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -141,10 +141,9 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister); static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; const struct in6_addr *saddr; const struct in6_addr *daddr; + struct hlist_head *hlist; struct sock *sk; bool delivered = false; __u8 hash; @@ -155,7 +154,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { int filtered; if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, @@ -333,15 +332,14 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int hash; hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index 488aec9e1a74..d1876f192225 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -32,7 +32,8 @@ static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i) size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre) { - return (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); + return sizeof(struct ipv6_rpl_sr_hdr) + (n * IPV6_PFXTAIL_LEN(cmpri)) + + IPV6_PFXTAIL_LEN(cmpre); } void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fb2f33ee3a7..a675acfb901d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1395,9 +1395,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 4db5a554bdbd..41a74fc84ca1 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -677,8 +677,8 @@ MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like - * enums +/* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, + * because __stringify doesn't like enums */ -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); -MODULE_ALIAS_NET_PF_PROTO(PF_INET, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 115, 2); +MODULE_ALIAS_NET_PF_PROTO(PF_INET, 115); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 2478aa60145f..5137ea1861ce 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -806,8 +806,8 @@ MODULE_AUTHOR("Chris Elston <celston@katalix.com>"); MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like - * enums +/* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, + * because __stringify doesn't like enums */ -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP); -MODULE_ALIAS_NET_PF_PROTO(PF_INET6, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 115, 2); +MODULE_ALIAS_NET_PF_PROTO(PF_INET6, 115); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index e8de500eb9f3..af57616d2f1d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2769,14 +2769,6 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta if (sdata->crypto_tx_tailroom_needed_cnt) tailroom = IEEE80211_ENCRYPT_TAILROOM; - if (!--mesh_hdr->ttl) { - if (multicast) - goto rx_accept; - - IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); - return RX_DROP_MONITOR; - } - if (mesh_hdr->flags & MESH_FLAGS_AE) { struct mesh_path *mppath; char *proxied_addr; @@ -2807,6 +2799,14 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta if (ether_addr_equal(sdata->vif.addr, eth->h_dest)) goto rx_accept; + if (!--mesh_hdr->ttl) { + if (multicast) + goto rx_accept; + + IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); + return RX_DROP_MONITOR; + } + if (!ifmsh->mshcfg.dot11MeshForwarding) { if (is_multicast_ether_addr(eth->h_dest)) goto rx_accept; @@ -2833,6 +2833,9 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta if (skb_cow_head(fwd_skb, hdrlen - sizeof(struct ethhdr))) return RX_DROP_UNUSABLE; + + if (skb_linearize(fwd_skb)) + return RX_DROP_UNUSABLE; } fwd_hdr = skb_push(fwd_skb, hdrlen - sizeof(struct ethhdr)); @@ -2847,7 +2850,7 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta hdrlen += ETH_ALEN; else fwd_skb->protocol = htons(fwd_skb->len - hdrlen); - skb_set_network_header(fwd_skb, hdrlen); + skb_set_network_header(fwd_skb, hdrlen + 2); info = IEEE80211_SKB_CB(fwd_skb); memset(info, 0, sizeof(*info)); @@ -2896,7 +2899,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; __le16 fc = hdr->frame_control; struct sk_buff_head frame_list; - static ieee80211_rx_result res; + ieee80211_rx_result res; struct ethhdr ethhdr; const u8 *check_da = ethhdr.h_dest, *check_sa = ethhdr.h_source; @@ -2930,7 +2933,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) data_offset, true)) return RX_DROP_UNUSABLE; - if (rx->sta && rx->sta->amsdu_mesh_control < 0) { + if (rx->sta->amsdu_mesh_control < 0) { bool valid_std = ieee80211_is_valid_amsdu(skb, true); bool valid_nonstd = ieee80211_is_valid_amsdu(skb, false); @@ -3006,7 +3009,7 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) } } - if (is_multicast_ether_addr(hdr->addr1)) + if (is_multicast_ether_addr(hdr->addr1) || !rx->sta) return RX_DROP_UNUSABLE; if (rx->key) { @@ -3037,7 +3040,7 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) struct net_device *dev = sdata->dev; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; __le16 fc = hdr->frame_control; - static ieee80211_rx_result res; + ieee80211_rx_result res; bool port_control; int err; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 7d68dbc872d7..941bda9141fa 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1264,7 +1264,8 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta) list_del_rcu(&sta->list); sta->removed = true; - drv_sta_pre_rcu_remove(local, sta->sdata, sta); + if (sta->uploaded) + drv_sta_pre_rcu_remove(local, sta->sdata, sta); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && rcu_access_pointer(sdata->u.vlan.sta) == sta) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3aceb3b731bf..8c397650b96f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -4906,7 +4906,7 @@ u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) &eht_cap->eht_cap_elem, is_ap); return 2 + 1 + - sizeof(he_cap->he_cap_elem) + n + + sizeof(eht_cap->eht_cap_elem) + n + ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], eht_cap->eht_cap_elem.phy_cap_info); return 0; diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index d237d142171c..bceaab8dd8e4 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -9,11 +9,18 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req) { - struct sock *ssk = subflow->tcp_sock; - struct sock *sk = subflow->conn; + struct sock *sk, *ssk; struct sk_buff *skb; struct tcp_sock *tp; + /* on early fallback the subflow context is deleted by + * subflow_syn_recv_sock() + */ + if (!subflow) + return; + + ssk = subflow->tcp_sock; + sk = subflow->conn; tp = tcp_sk(ssk); subflow->is_mptfo = 1; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b30cea2fbf3f..355f798d575a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1192,9 +1192,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && - mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) && - schedule_work(&msk->work)) - sock_hold(subflow->conn); + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64)) + mptcp_schedule_work((struct sock *)msk); return true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 60b23b2716c4..b998e9df53ce 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2315,7 +2315,26 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, unsigned int flags) { struct mptcp_sock *msk = mptcp_sk(sk); - bool need_push, dispose_it; + bool dispose_it, need_push = false; + + /* If the first subflow moved to a close state before accept, e.g. due + * to an incoming reset, mptcp either: + * - if either the subflow or the msk are dead, destroy the context + * (the subflow socket is deleted by inet_child_forget) and the msk + * - otherwise do nothing at the moment and take action at accept and/or + * listener shutdown - user-space must be able to accept() the closed + * socket. + */ + if (msk->in_accept_queue && msk->first == ssk) { + if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) + return; + + /* ensure later check in mptcp_worker() will dispose the msk */ + sock_set_flag(sk, SOCK_DEAD); + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + mptcp_subflow_drop_ctx(ssk); + goto out_release; + } dispose_it = !msk->subflow || ssk != msk->subflow->sk; if (dispose_it) @@ -2351,28 +2370,22 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (!inet_csk(ssk)->icsk_ulp_ops) { WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); - } else if (msk->in_accept_queue && msk->first == ssk) { - /* if the first subflow moved to a close state, e.g. due to - * incoming reset and we reach here before inet_child_forget() - * the TCP stack could later try to close it via - * inet_csk_listen_stop(), or deliver it to the user space via - * accept(). - * We can't delete the subflow - or risk a double free - nor let - * the msk survive - or will be leaked in the non accept scenario: - * fallback and let TCP cope with the subflow cleanup. - */ - WARN_ON_ONCE(sock_flag(ssk, SOCK_DEAD)); - mptcp_subflow_drop_ctx(ssk); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ - if (ssk->sk_state == TCP_LISTEN) + if (ssk->sk_state == TCP_LISTEN) { + tcp_set_state(ssk, TCP_CLOSE); + mptcp_subflow_queue_clean(sk, ssk); + inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); + } __tcp_close(ssk, 0); /* close acquired an extra ref */ __sock_put(ssk); } + +out_release: release_sock(ssk); sock_put(ssk); @@ -2427,21 +2440,14 @@ static void __mptcp_close_subflow(struct sock *sk) mptcp_close_ssk(sk, ssk, subflow); } - /* if the MPC subflow has been closed before the msk is accepted, - * msk will never be accept-ed, close it now - */ - if (!msk->first && msk->in_accept_queue) { - sock_set_flag(sk, SOCK_DEAD); - inet_sk_state_store(sk, TCP_CLOSE); - } } -static bool mptcp_check_close_timeout(const struct sock *sk) +static bool mptcp_should_close(const struct sock *sk) { s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp; struct mptcp_subflow_context *subflow; - if (delta >= TCP_TIMEWAIT_LEN) + if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue) return true; /* if all subflows are in closed status don't bother with additional @@ -2626,7 +2632,7 @@ static void mptcp_worker(struct work_struct *work) lock_sock(sk); state = sk->sk_state; - if (unlikely(state == TCP_CLOSE)) + if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_data_fin_ack(sk); @@ -2649,7 +2655,7 @@ static void mptcp_worker(struct work_struct *work) * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_check_close_timeout(sk)) { + if (mptcp_should_close(sk)) { inet_sk_state_store(sk, TCP_CLOSE); mptcp_do_fastclose(sk); } @@ -2895,6 +2901,14 @@ static void __mptcp_destroy_sock(struct sock *sk) sock_put(sk); } +void __mptcp_unaccepted_force_close(struct sock *sk) +{ + sock_set_flag(sk, SOCK_DEAD); + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_do_fastclose(sk); + __mptcp_destroy_sock(sk); +} + static __poll_t mptcp_check_readable(struct mptcp_sock *msk) { /* Concurrent splices from sk_receive_queue into receive_queue will @@ -3733,6 +3747,18 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk->sk_socket) mptcp_sock_graft(ssk, newsock); } + + /* Do late cleanup for the first subflow as necessary. Also + * deal with bad peers not doing a complete shutdown. + */ + if (msk->first && + unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { + __mptcp_close_ssk(newsk, msk->first, + mptcp_subflow_ctx(msk->first), 0); + if (unlikely(list_empty(&msk->conn_list))) + inet_sk_state_store(newsk, TCP_CLOSE); + } + release_sock(newsk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 339a6f072989..d6469b6ab38e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -629,10 +629,12 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); void __mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); +void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); void mptcp_cancel_work(struct sock *sk); +void __mptcp_unaccepted_force_close(struct sock *sk); void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a0041360ee9d..281c1cc8dc8d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -408,9 +408,8 @@ void mptcp_subflow_reset(struct sock *ssk) tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); - if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && - schedule_work(&mptcp_sk(sk)->work)) - return; /* worker will put sk for us */ + if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } @@ -724,9 +723,12 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) if (!ctx) return; - subflow_ulp_fallback(ssk, ctx); - if (ctx->conn) - sock_put(ctx->conn); + list_del(&mptcp_subflow_ctx(ssk)->node); + if (inet_csk(ssk)->icsk_ulp_ops) { + subflow_ulp_fallback(ssk, ctx); + if (ctx->conn) + sock_put(ctx->conn); + } kfree_rcu(ctx, rcu); } @@ -1118,8 +1120,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } else { - if (updated && schedule_work(&msk->work)) - sock_hold((struct sock *)msk); + if (updated) + mptcp_schedule_work((struct sock *)msk); return MAPPING_DATA_FIN; } @@ -1222,17 +1224,12 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { - struct sock *sk = (struct sock *)msk; - if (likely(ssk->sk_state != TCP_CLOSE)) return; if (skb_queue_empty(&ssk->sk_receive_queue) && - !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) { - sock_hold(sk); - if (!schedule_work(&msk->work)) - sock_put(sk); - } + !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + mptcp_schedule_work((struct sock *)msk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) @@ -1825,6 +1822,77 @@ static void subflow_state_change(struct sock *sk) } } +void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) +{ + struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; + struct mptcp_sock *msk, *next, *head = NULL; + struct request_sock *req; + struct sock *sk; + + /* build a list of all unaccepted mptcp sockets */ + spin_lock_bh(&queue->rskq_lock); + for (req = queue->rskq_accept_head; req; req = req->dl_next) { + struct mptcp_subflow_context *subflow; + struct sock *ssk = req->sk; + + if (!sk_is_mptcp(ssk)) + continue; + + subflow = mptcp_subflow_ctx(ssk); + if (!subflow || !subflow->conn) + continue; + + /* skip if already in list */ + sk = subflow->conn; + msk = mptcp_sk(sk); + if (msk->dl_next || msk == head) + continue; + + sock_hold(sk); + msk->dl_next = head; + head = msk; + } + spin_unlock_bh(&queue->rskq_lock); + if (!head) + return; + + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (msk = head; msk; msk = next) { + sk = (struct sock *)msk; + + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + next = msk->dl_next; + msk->dl_next = NULL; + + __mptcp_unaccepted_force_close(sk); + release_sock(sk); + + /* lockdep will report a false positive ABBA deadlock + * between cancel_work_sync and the listener socket. + * The involved locks belong to different sockets WRT + * the existing AB chain. + * Using a per socket key is problematic as key + * deregistration requires process context and must be + * performed at socket disposal time, in atomic + * context. + * Just tell lockdep to consider the listener socket + * released here. + */ + mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); + mptcp_cancel_work(sk); + mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + sock_put(sk); + } + + /* we are still under the listener msk socket lock */ + lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); +} + static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6004d4b24451..e48ab8dfb541 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3447,6 +3447,64 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) return 0; } +int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; + const struct nft_data *data; + int err; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) + return 0; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; + default: + break; + } + + return 0; +} + +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + ret = nft_setelem_validate(ctx, set, NULL, &elem); + if (ret < 0) + return ret; + } + + return ret; +} + static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla); @@ -4759,12 +4817,6 @@ err_set_name: return err; } -struct nft_set_elem_catchall { - struct list_head list; - struct rcu_head rcu; - void *elem; -}; - static void nft_set_catchall_destroy(const struct nft_ctx *ctx, struct nft_set *set) { @@ -6056,7 +6108,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + if (((flags & NFT_SET_ELEM_CATCHALL) && nla[NFTA_SET_ELEM_KEY]) || + (!(flags & NFT_SET_ELEM_CATCHALL) && !nla[NFTA_SET_ELEM_KEY])) return -EINVAL; if (flags != 0) { @@ -7052,7 +7105,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, } if (nla[NFTA_OBJ_USERDATA]) { - obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL); + obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL_ACCOUNT); if (obj->udata == NULL) goto err_userdata; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index cae5a6724163..cecf8ab90e58 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -199,37 +199,6 @@ nla_put_failure: return -1; } -static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - struct nft_ctx *pctx = (struct nft_ctx *)ctx; - const struct nft_data *data; - int err; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - pctx->level++; - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - pctx->level--; - break; - default: - break; - } - - return 0; -} - static int nft_lookup_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **d) @@ -245,9 +214,12 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, iter.skip = 0; iter.count = 0; iter.err = 0; - iter.fn = nft_lookup_validate_setelem; + iter.fn = nft_setelem_validate; priv->set->ops->walk(ctx, priv->set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_validate(ctx, priv->set); + if (iter.err < 0) return iter.err; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c64277659753..f365dfdd672d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1952,7 +1952,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - size_t copied; + size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; @@ -1985,9 +1985,10 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, #endif /* Record the max length of recvmsg() calls for future allocations */ - nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); - nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, - SKB_WITH_OVERHEAD(32768)); + max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); + max_recvmsg_len = min_t(size_t, max_recvmsg_len, + SKB_WITH_OVERHEAD(32768)); + WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { @@ -2236,6 +2237,7 @@ static int netlink_dump(struct sock *sk) struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; + size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; @@ -2258,8 +2260,9 @@ static int netlink_dump(struct sock *sk) cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); - if (alloc_min_size < nlk->max_recvmsg_len) { - alloc_size = nlk->max_recvmsg_len; + max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); + if (alloc_min_size < max_recvmsg_len) { + alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ca3ebfdb3023..a8cf9a88758e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -913,7 +913,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport)) { + if (likely(vport && netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 5c2fb992803b..76f0434d3d06 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -393,10 +393,12 @@ static struct qrtr_node *qrtr_node_lookup(unsigned int nid) struct qrtr_node *node; unsigned long flags; + mutex_lock(&qrtr_node_lock); spin_lock_irqsave(&qrtr_nodes_lock, flags); node = radix_tree_lookup(&qrtr_nodes, nid); node = qrtr_node_acquire(node); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); + mutex_unlock(&qrtr_node_lock); return node; } @@ -496,6 +498,11 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!size || len != ALIGN(size, 4) + hdrlen) goto err; + if ((cb->type == QRTR_TYPE_NEW_SERVER || + cb->type == QRTR_TYPE_RESUME_TX) && + size < sizeof(struct qrtr_ctrl_pkt)) + goto err; + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && cb->type != QRTR_TYPE_RESUME_TX) goto err; @@ -508,9 +515,6 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) /* Remote node endpoint can bridge other distant nodes */ const struct qrtr_ctrl_pkt *pkt; - if (size < sizeof(*pkt)) - goto err; - pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); } diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 722936f7dd98..0f25a386138c 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -274,7 +274,7 @@ err: return NULL; } -static int server_del(struct qrtr_node *node, unsigned int port) +static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) { struct qrtr_lookup *lookup; struct qrtr_server *srv; @@ -287,7 +287,7 @@ static int server_del(struct qrtr_node *node, unsigned int port) radix_tree_delete(&node->servers, port); /* Broadcast the removal of local servers */ - if (srv->node == qrtr_ns.local_node) + if (srv->node == qrtr_ns.local_node && bcast) service_announce_del(&qrtr_ns.bcast_sq, srv); /* Announce the service's disappearance to observers */ @@ -373,7 +373,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) } slot = radix_tree_iter_resume(slot, &iter); rcu_read_unlock(); - server_del(node, srv->port); + server_del(node, srv->port, true); rcu_read_lock(); } rcu_read_unlock(); @@ -459,10 +459,13 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, kfree(lookup); } - /* Remove the server belonging to this port */ + /* Remove the server belonging to this port but don't broadcast + * DEL_SERVER. Neighbours would've already removed the server belonging + * to this port due to the DEL_CLIENT broadcast from qrtr_port_remove(). + */ node = node_get(node_id); if (node) - server_del(node, port); + server_del(node, port, false); /* Advertise the removal of this client to all local servers */ local_node = node_get(qrtr_ns.local_node); @@ -567,7 +570,7 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, if (!node) return -ENOENT; - return server_del(node, port); + return server_del(node, port, true); } static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2a6b6be0811b..35785a36c802 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3235,6 +3235,9 @@ int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, err_miss_alloc: tcf_exts_destroy(exts); +#ifdef CONFIG_NET_CLS_ACT + exts->actions = NULL; +#endif return err; } EXPORT_SYMBOL(tcf_exts_init_ex); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cf5ebe43b3b4..02098a02943e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -421,15 +421,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } else weight = 1; - if (tb[TCA_QFQ_LMAX]) { + if (tb[TCA_QFQ_LMAX]) lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - } else + else lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { + pr_notice("qfq: invalid max length %u\n", lmax); + return -EINVAL; + } + inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b91616f819de..218e0982c370 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1830,6 +1830,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) goto err; + if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { + err = -EINVAL; + goto err; + } } if (sctp_state(asoc, CLOSED)) { diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 94727feb07b3..b046b11200c9 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1154,7 +1154,8 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + (void *)pos <= (void *)chunk->subh.ifwdtsn_hdr->skip + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c6b4a62276f6..50c38b624f77 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3270,6 +3270,17 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, sk_common_release(sk); goto out; } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); } else { smc->clcsock = clcsock; } diff --git a/net/sunrpc/auth_gss/gss_krb5_test.c b/net/sunrpc/auth_gss/gss_krb5_test.c index ce0541e32fc9..95ca783795c5 100644 --- a/net/sunrpc/auth_gss/gss_krb5_test.c +++ b/net/sunrpc/auth_gss/gss_krb5_test.c @@ -73,7 +73,6 @@ static void checksum_case(struct kunit *test) { const struct gss_krb5_test_param *param = test->param_value; struct xdr_buf buf = { - .head[0].iov_base = param->plaintext->data, .head[0].iov_len = param->plaintext->len, .len = param->plaintext->len, }; @@ -99,6 +98,10 @@ static void checksum_case(struct kunit *test) err = crypto_ahash_setkey(tfm, Kc.data, Kc.len); KUNIT_ASSERT_EQ(test, err, 0); + buf.head[0].iov_base = kunit_kzalloc(test, buf.head[0].iov_len, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf.head[0].iov_base); + memcpy(buf.head[0].iov_base, param->plaintext->data, buf.head[0].iov_len); + checksum.len = gk5e->cksumlength; checksum.data = kunit_kzalloc(test, checksum.len, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, checksum.data); @@ -1327,6 +1330,7 @@ static void rfc6803_encrypt_case(struct kunit *test) if (!gk5e) kunit_skip(test, "Encryption type is not available"); + memset(usage_data, 0, sizeof(usage_data)); usage.data[3] = param->constant; Ke.len = gk5e->Ke_length; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 983c5891cb56..4246363cb095 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -416,14 +416,23 @@ static int unix_gid_hash(kuid_t uid) return hash_long(from_kuid(&init_user_ns, uid), GID_HASHBITS); } -static void unix_gid_put(struct kref *kref) +static void unix_gid_free(struct rcu_head *rcu) { - struct cache_head *item = container_of(kref, struct cache_head, ref); - struct unix_gid *ug = container_of(item, struct unix_gid, h); + struct unix_gid *ug = container_of(rcu, struct unix_gid, rcu); + struct cache_head *item = &ug->h; + if (test_bit(CACHE_VALID, &item->flags) && !test_bit(CACHE_NEGATIVE, &item->flags)) put_group_info(ug->gi); - kfree_rcu(ug, rcu); + kfree(ug); +} + +static void unix_gid_put(struct kref *kref) +{ + struct cache_head *item = container_of(kref, struct cache_head, ref); + struct unix_gid *ug = container_of(item, struct unix_gid, h); + + call_rcu(&ug->rcu, unix_gid_free); } static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 37934dfe72f4..ee78b4082ef9 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -94,6 +94,11 @@ virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, info->op, info->flags); + if (info->vsk && !skb_set_owner_sk_safe(skb, sk_vsock(info->vsk))) { + WARN_ONCE(1, "failed to allocate skb on vsock socket with sk_refcnt == 0\n"); + goto out; + } + return skb; out: @@ -1303,6 +1308,11 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, goto free_pkt; } + if (!skb_set_owner_sk_safe(skb, sk)) { + WARN_ONCE(1, "receiving vsock socket has sk_refcnt == 0\n"); + goto free_pkt; + } + vsk = vsock_sk(sk); lock_sock(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 36eb16a40745..95cc4d79ba29 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1842,7 +1842,13 @@ static ssize_t vmci_transport_stream_enqueue( struct msghdr *msg, size_t len) { - return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0); + ssize_t err; + + err = vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0); + if (err < 0) + err = -ENOMEM; + + return err; } static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk) diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 61f72eb8d9be..4d90691505b1 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -27,21 +27,6 @@ fi ; \ tar -I $(KGZIP) -c $(RCS_TAR_IGNORE) -f $(2).tar.gz \ --transform 's:^:$(2)/:S' $(TAR_CONTENT) $(3) -# tarball compression -# --------------------------------------------------------------------------- - -%.tar.gz: %.tar - $(call cmd,gzip) - -%.tar.bz2: %.tar - $(call cmd,bzip2) - -%.tar.xz: %.tar - $(call cmd,xzmisc) - -%.tar.zst: %.tar - $(call cmd,zstd) - # Git # --------------------------------------------------------------------------- @@ -57,16 +42,24 @@ check-git: false; \ fi +git-config-tar.gz = -c tar.tar.gz.command="$(KGZIP)" +git-config-tar.bz2 = -c tar.tar.bz2.command="$(KBZIP2)" +git-config-tar.xz = -c tar.tar.xz.command="$(XZ)" +git-config-tar.zst = -c tar.tar.zst.command="$(ZSTD)" + +quiet_cmd_archive = ARCHIVE $@ + cmd_archive = git -C $(srctree) $(git-config-tar$(suffix $@)) archive \ + --output=$$(realpath $@) --prefix=$(basename $@)/ $(archive-args) + # Linux source tarball # --------------------------------------------------------------------------- -quiet_cmd_archive_linux = ARCHIVE $@ - cmd_archive_linux = \ - git -C $(srctree) archive --output=$$(realpath $@) --prefix=$(basename $@)/ $$(cat $<) +linux-tarballs := $(addprefix linux, .tar.gz) -targets += linux.tar -linux.tar: .tmp_HEAD FORCE - $(call if_changed,archive_linux) +targets += $(linux-tarballs) +$(linux-tarballs): archive-args = $$(cat $<) +$(linux-tarballs): .tmp_HEAD FORCE + $(call if_changed,archive) # rpm-pkg # --------------------------------------------------------------------------- @@ -94,7 +87,7 @@ binrpm-pkg: $(UTS_MACHINE)-linux -bb $(objtree)/binkernel.spec quiet_cmd_debianize = GEN $@ - cmd_debianize = $(srctree)/scripts/package/mkdebian + cmd_debianize = $(srctree)/scripts/package/mkdebian $(mkdebian-opts) debian: FORCE $(call cmd,debianize) @@ -103,6 +96,7 @@ PHONY += debian-orig debian-orig: private source = $(shell dpkg-parsechangelog -S Source) debian-orig: private version = $(shell dpkg-parsechangelog -S Version | sed 's/-[^-]*$$//') debian-orig: private orig-name = $(source)_$(version).orig.tar.gz +debian-orig: mkdebian-opts = --need-source debian-orig: linux.tar.gz debian $(Q)if [ "$(df --output=target .. 2>/dev/null)" = "$(df --output=target $< 2>/dev/null)" ]; then \ ln -f $< ../$(orig-name); \ @@ -145,10 +139,17 @@ tar-install: FORCE $(Q)$(MAKE) -f $(srctree)/Makefile +$(Q)$(srctree)/scripts/package/buildtar $@ +compress-tar.gz = -I "$(KGZIP)" +compress-tar.bz2 = -I "$(KBZIP2)" +compress-tar.xz = -I "$(XZ)" +compress-tar.zst = -I "$(ZSTD)" + quiet_cmd_tar = TAR $@ - cmd_tar = cd $<; tar cf ../$@ --owner=root --group=root --sort=name * + cmd_tar = cd $<; tar cf ../$@ $(compress-tar$(suffix $@)) --owner=root --group=root --sort=name * -linux-$(KERNELRELEASE)-$(ARCH).tar: tar-install +dir-tarballs := $(addprefix linux-$(KERNELRELEASE)-$(ARCH), .tar .tar.gz .tar.bz2 .tar.xz .tar.zst) + +$(dir-tarballs): tar-install $(call cmd,tar) PHONY += dir-pkg @@ -180,16 +181,17 @@ quiet_cmd_perf_version_file = GEN $@ .tmp_perf/PERF-VERSION-FILE: .tmp_HEAD $(srctree)/tools/perf/util/PERF-VERSION-GEN | .tmp_perf $(call cmd,perf_version_file) -quiet_cmd_archive_perf = ARCHIVE $@ - cmd_archive_perf = \ - git -C $(srctree) archive --output=$$(realpath $@) --prefix=$(basename $@)/ \ - --add-file=$$(realpath $(word 2, $^)) \ +perf-archive-args = --add-file=$$(realpath $(word 2, $^)) \ --add-file=$$(realpath $(word 3, $^)) \ $$(cat $(word 2, $^))^{tree} $$(cat $<) -targets += perf-$(KERNELVERSION).tar -perf-$(KERNELVERSION).tar: tools/perf/MANIFEST .tmp_perf/HEAD .tmp_perf/PERF-VERSION-FILE FORCE - $(call if_changed,archive_perf) + +perf-tarballs := $(addprefix perf-$(KERNELVERSION), .tar .tar.gz .tar.bz2 .tar.xz .tar.zst) + +targets += $(perf-tarballs) +$(perf-tarballs): archive-args = $(perf-archive-args) +$(perf-tarballs): tools/perf/MANIFEST .tmp_perf/HEAD .tmp_perf/PERF-VERSION-FILE FORCE + $(call if_changed,archive) PHONY += perf-tar-src-pkg perf-tar-src-pkg: perf-$(KERNELVERSION).tar diff --git a/scripts/package/gen-diff-patch b/scripts/package/gen-diff-patch index f842ab50a780..8a98b7bb78a0 100755 --- a/scripts/package/gen-diff-patch +++ b/scripts/package/gen-diff-patch @@ -1,44 +1,36 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0-only -diff_patch="${1}" -untracked_patch="${2}" -srctree=$(dirname $0)/../.. +diff_patch=$1 -rm -f ${diff_patch} ${untracked_patch} +mkdir -p "$(dirname "${diff_patch}")" -if ! ${srctree}/scripts/check-git; then - exit -fi - -mkdir -p "$(dirname ${diff_patch})" "$(dirname ${untracked_patch})" +git -C "${srctree:-.}" diff HEAD > "${diff_patch}" -git -C "${srctree}" diff HEAD > "${diff_patch}" - -if [ ! -s "${diff_patch}" ]; then - rm -f "${diff_patch}" +if [ ! -s "${diff_patch}" ] || + [ -z "$(git -C "${srctree:-.}" ls-files --other --exclude-standard | head -n1)" ]; then exit fi -git -C ${srctree} status --porcelain --untracked-files=all | -while read stat path -do - if [ "${stat}" = '??' ]; then - - if ! diff -u /dev/null "${srctree}/${path}" > .tmp_diff && - ! head -n1 .tmp_diff | grep -q "Binary files"; then - { - echo "--- /dev/null" - echo "+++ linux/$path" - cat .tmp_diff | tail -n +3 - } >> ${untracked_patch} - fi - fi -done - -rm -f .tmp_diff - -if [ ! -s "${diff_patch}" ]; then - rm -f "${diff_patch}" - exit -fi +# The source tarball, which is generated by 'git archive', contains everything +# you committed in the repository. If you have local diff ('git diff HEAD'), +# it will go into ${diff_patch}. If untracked files are remaining, the resulting +# source package may not be correct. +# +# Examples: +# - You modified a source file to add #include "new-header.h" +# but forgot to add new-header.h +# - You modified a Makefile to add 'obj-$(CONFIG_FOO) += new-dirver.o' +# but you forgot to add new-driver.c +# +# You need to commit them, or at least stage them by 'git add'. +# +# This script does not take care of untracked files because doing so would +# introduce additional complexity. Instead, print a warning message here if +# untracked files are found. +# If all untracked files are just garbage, you can ignore this warning. +echo >&2 "============================ WARNING ============================" +echo >&2 "Your working tree has diff from HEAD, and also untracked file(s)." +echo >&2 "Please make sure you did 'git add' for all new files you need in" +echo >&2 "the source package." +echo >&2 "=================================================================" diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index e20a2b5be9eb..a4c2c2276223 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -84,7 +84,66 @@ set_debarch() { fi } +# Create debian/source/ if it is a source package build +gen_source () +{ + mkdir -p debian/source + + echo "3.0 (quilt)" > debian/source/format + + { + echo "diff-ignore" + echo "extend-diff-ignore = .*" + } > debian/source/local-options + + # Add .config as a patch + mkdir -p debian/patches + { + echo "Subject: Add .config" + echo "Author: ${maintainer}" + echo + echo "--- /dev/null" + echo "+++ linux/.config" + diff -u /dev/null "${KCONFIG_CONFIG}" | tail -n +3 + } > debian/patches/config.patch + echo config.patch > debian/patches/series + + "${srctree}/scripts/package/gen-diff-patch" debian/patches/diff.patch + if [ -s debian/patches/diff.patch ]; then + sed -i " + 1iSubject: Add local diff + 1iAuthor: ${maintainer} + 1i + " debian/patches/diff.patch + + echo diff.patch >> debian/patches/series + else + rm -f debian/patches/diff.patch + fi +} + rm -rf debian +mkdir debian + +email=${DEBEMAIL-$EMAIL} + +# use email string directly if it contains <email> +if echo "${email}" | grep -q '<.*>'; then + maintainer=${email} +else + # or construct the maintainer string + user=${KBUILD_BUILD_USER-$(id -nu)} + name=${DEBFULLNAME-${user}} + if [ -z "${email}" ]; then + buildhost=${KBUILD_BUILD_HOST-$(hostname -f 2>/dev/null || hostname)} + email="${user}@${buildhost}" + fi + maintainer="${name} <${email}>" +fi + +if [ "$1" = --need-source ]; then + gen_source +fi # Some variables and settings used throughout the script version=$KERNELRELEASE @@ -104,22 +163,6 @@ fi debarch= set_debarch -email=${DEBEMAIL-$EMAIL} - -# use email string directly if it contains <email> -if echo $email | grep -q '<.*>'; then - maintainer=$email -else - # or construct the maintainer string - user=${KBUILD_BUILD_USER-$(id -nu)} - name=${DEBFULLNAME-$user} - if [ -z "$email" ]; then - buildhost=${KBUILD_BUILD_HOST-$(hostname -f 2>/dev/null || hostname)} - email="$user@$buildhost" - fi - maintainer="$name <$email>" -fi - # Try to determine distribution if [ -n "$KDEB_CHANGELOG_DIST" ]; then distribution=$KDEB_CHANGELOG_DIST @@ -132,34 +175,6 @@ else echo >&2 "Install lsb-release or set \$KDEB_CHANGELOG_DIST explicitly" fi -mkdir -p debian/source/ -echo "3.0 (quilt)" > debian/source/format - -{ - echo "diff-ignore" - echo "extend-diff-ignore = .*" -} > debian/source/local-options - -# Add .config as a patch -mkdir -p debian/patches -{ - echo "Subject: Add .config" - echo "Author: ${maintainer}" - echo - echo "--- /dev/null" - echo "+++ linux/.config" - diff -u /dev/null "${KCONFIG_CONFIG}" | tail -n +3 -} > debian/patches/config -echo config > debian/patches/series - -$(dirname $0)/gen-diff-patch debian/patches/diff.patch debian/patches/untracked.patch -if [ -f debian/patches/diff.patch ]; then - echo diff.patch >> debian/patches/series -fi -if [ -f debian/patches/untracked.patch ]; then - echo untracked.patch >> debian/patches/series -fi - echo $debarch > debian/arch extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)" extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)" diff --git a/scripts/package/mkspec b/scripts/package/mkspec index b7d1dc28a5d6..fc8ad3fbc0a9 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -19,8 +19,7 @@ else mkdir -p rpmbuild/SOURCES cp linux.tar.gz rpmbuild/SOURCES cp "${KCONFIG_CONFIG}" rpmbuild/SOURCES/config - $(dirname $0)/gen-diff-patch rpmbuild/SOURCES/diff.patch rpmbuild/SOURCES/untracked.patch - touch rpmbuild/SOURCES/diff.patch rpmbuild/SOURCES/untracked.patch + "${srctree}/scripts/package/gen-diff-patch" rpmbuild/SOURCES/diff.patch fi if grep -q CONFIG_MODULES=y include/config/auto.conf; then @@ -56,7 +55,6 @@ sed -e '/^DEL/d' -e 's/^\t*//' <<EOF $S Source0: linux.tar.gz $S Source1: config $S Source2: diff.patch -$S Source3: untracked.patch Provides: $PROVIDES $S BuildRequires: bc binutils bison dwarves $S BuildRequires: (elfutils-libelf-devel or libelf-devel) flex @@ -94,12 +92,7 @@ $S$M $S %prep $S %setup -q -n linux $S cp %{SOURCE1} .config -$S if [ -s %{SOURCE2} ]; then -$S patch -p1 < %{SOURCE2} -$S fi -$S if [ -s %{SOURCE3} ]; then -$S patch -p1 < %{SOURCE3} -$S fi +$S patch -p1 < %{SOURCE2} $S $S %build $S $MAKE %{?_smp_mflags} KERNELRELEASE=$KERNELRELEASE KBUILD_BUILD_VERSION=%{release} diff --git a/sound/firewire/tascam/tascam-stream.c b/sound/firewire/tascam/tascam-stream.c index 53e094cc411f..dfe783d01d7d 100644 --- a/sound/firewire/tascam/tascam-stream.c +++ b/sound/firewire/tascam/tascam-stream.c @@ -490,7 +490,7 @@ int snd_tscm_stream_start_duplex(struct snd_tscm *tscm, unsigned int rate) // packet is important for media clock recovery. err = amdtp_domain_start(&tscm->domain, tx_init_skip_cycles, true, true); if (err < 0) - return err; + goto error; if (!amdtp_domain_wait_ready(&tscm->domain, READY_TIMEOUT_MS)) { err = -ETIMEDOUT; diff --git a/sound/i2c/cs8427.c b/sound/i2c/cs8427.c index 65012af6a36e..f58b14b49045 100644 --- a/sound/i2c/cs8427.c +++ b/sound/i2c/cs8427.c @@ -561,10 +561,13 @@ int snd_cs8427_iec958_active(struct snd_i2c_device *cs8427, int active) if (snd_BUG_ON(!cs8427)) return -ENXIO; chip = cs8427->private_data; - if (active) + if (active) { memcpy(chip->playback.pcm_status, chip->playback.def_status, 24); - chip->playback.pcm_ctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_INACTIVE; + chip->playback.pcm_ctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_INACTIVE; + } else { + chip->playback.pcm_ctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_INACTIVE; + } snd_ctl_notify(cs8427->bus->card, SNDRV_CTL_EVENT_MASK_VALUE | SNDRV_CTL_EVENT_MASK_INFO, &chip->playback.pcm_ctl->id); diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 48af77ae8020..6ec394fb1846 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -1236,7 +1236,7 @@ static int snd_emu10k1_capture_mic_close(struct snd_pcm_substream *substream) { struct snd_emu10k1 *emu = snd_pcm_substream_chip(substream); - emu->capture_interrupt = NULL; + emu->capture_mic_interrupt = NULL; emu->pcm_capture_mic_substream = NULL; return 0; } @@ -1344,7 +1344,7 @@ static int snd_emu10k1_capture_efx_close(struct snd_pcm_substream *substream) { struct snd_emu10k1 *emu = snd_pcm_substream_chip(substream); - emu->capture_interrupt = NULL; + emu->capture_efx_interrupt = NULL; emu->pcm_capture_efx_substream = NULL; return 0; } @@ -1781,17 +1781,21 @@ int snd_emu10k1_pcm_efx(struct snd_emu10k1 *emu, int device) struct snd_kcontrol *kctl; int err; - err = snd_pcm_new(emu->card, "emu10k1 efx", device, 8, 1, &pcm); + err = snd_pcm_new(emu->card, "emu10k1 efx", device, emu->audigy ? 0 : 8, 1, &pcm); if (err < 0) return err; pcm->private_data = emu; - snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &snd_emu10k1_fx8010_playback_ops); + if (!emu->audigy) + snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &snd_emu10k1_fx8010_playback_ops); snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_emu10k1_capture_efx_ops); pcm->info_flags = 0; - strcpy(pcm->name, "Multichannel Capture/PT Playback"); + if (emu->audigy) + strcpy(pcm->name, "Multichannel Capture"); + else + strcpy(pcm->name, "Multichannel Capture/PT Playback"); emu->pcm_efx = pcm; /* EFX capture - record the "FXBUS2" channels, by default we connect the EXTINs diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 9ea633fe9339..5c6980394dce 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -81,6 +81,7 @@ struct hdmi_spec_per_pin { struct delayed_work work; struct hdmi_pcm *pcm; /* pointer to spec->pcm_rec[n] dynamically*/ int pcm_idx; /* which pcm is attached. -1 means no pcm is attached */ + int prev_pcm_idx; /* previously assigned pcm index */ int repoll_count; bool setup; /* the stream has been set up by prepare callback */ bool silent_stream; @@ -1380,9 +1381,17 @@ static void hdmi_attach_hda_pcm(struct hdmi_spec *spec, /* pcm already be attached to the pin */ if (per_pin->pcm) return; + /* try the previously used slot at first */ + idx = per_pin->prev_pcm_idx; + if (idx >= 0) { + if (!test_bit(idx, &spec->pcm_bitmap)) + goto found; + per_pin->prev_pcm_idx = -1; /* no longer valid, clear it */ + } idx = hdmi_find_pcm_slot(spec, per_pin); if (idx == -EBUSY) return; + found: per_pin->pcm_idx = idx; per_pin->pcm = get_hdmi_pcm(spec, idx); set_bit(idx, &spec->pcm_bitmap); @@ -1398,6 +1407,7 @@ static void hdmi_detach_hda_pcm(struct hdmi_spec *spec, return; idx = per_pin->pcm_idx; per_pin->pcm_idx = -1; + per_pin->prev_pcm_idx = idx; /* remember the previous index */ per_pin->pcm = NULL; if (idx >= 0 && idx < spec->pcm_used) clear_bit(idx, &spec->pcm_bitmap); @@ -1924,6 +1934,7 @@ static int hdmi_add_pin(struct hda_codec *codec, hda_nid_t pin_nid) per_pin->pcm = NULL; per_pin->pcm_idx = -1; + per_pin->prev_pcm_idx = -1; per_pin->pin_nid = pin_nid; per_pin->pin_nid_idx = spec->num_nids; per_pin->dev_id = i; @@ -4593,7 +4604,7 @@ HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862818, "Raptorlake HDMI", patch_i915_tgl_hdmi), -HDA_CODEC_ENTRY(0x80862819, "DG2 HDMI", patch_i915_adlp_hdmi), +HDA_CODEC_ENTRY(0x80862819, "DG2 HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_adlp_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a2706fd87b14..3b9f077a227f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2624,6 +2624,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), + SND_PCI_QUIRK(0x1558, 0x3702, "Clevo X370SN[VW]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -6959,6 +6960,8 @@ enum { ALC269_FIXUP_DELL_M101Z, ALC269_FIXUP_SKU_IGNORE, ALC269_FIXUP_ASUS_G73JW, + ALC269_FIXUP_ASUS_N7601ZM_PINS, + ALC269_FIXUP_ASUS_N7601ZM, ALC269_FIXUP_LENOVO_EAPD, ALC275_FIXUP_SONY_HWEQ, ALC275_FIXUP_SONY_DISABLE_AAMIX, @@ -7255,6 +7258,29 @@ static const struct hda_fixup alc269_fixups[] = { { } } }, + [ALC269_FIXUP_ASUS_N7601ZM_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03A11050 }, + { 0x1a, 0x03A11C30 }, + { 0x21, 0x03211420 }, + { } + } + }, + [ALC269_FIXUP_ASUS_N7601ZM] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + {0x20, AC_VERB_SET_COEF_INDEX, 0x62}, + {0x20, AC_VERB_SET_PROC_COEF, 0xa007}, + {0x20, AC_VERB_SET_COEF_INDEX, 0x10}, + {0x20, AC_VERB_SET_PROC_COEF, 0x8420}, + {0x20, AC_VERB_SET_COEF_INDEX, 0x0f}, + {0x20, AC_VERB_SET_PROC_COEF, 0x7774}, + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_ASUS_N7601ZM_PINS, + }, [ALC269_FIXUP_LENOVO_EAPD] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -9443,6 +9469,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b66, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED), @@ -9464,6 +9491,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1271, "ASUS X430UN", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM), SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC), @@ -9661,6 +9689,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x22f1, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x22f2, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x22f3, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x2318, "Thinkpad Z13 Gen2", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x2319, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x231a, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index a794a01a68ca..61258b0aac8d 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1707,6 +1707,7 @@ static const struct snd_pci_quirk stac925x_fixup_tbl[] = { }; static const struct hda_pintbl ref92hd73xx_pin_configs[] = { + // Port A-H { 0x0a, 0x02214030 }, { 0x0b, 0x02a19040 }, { 0x0c, 0x01a19020 }, @@ -1715,9 +1716,12 @@ static const struct hda_pintbl ref92hd73xx_pin_configs[] = { { 0x0f, 0x01014010 }, { 0x10, 0x01014020 }, { 0x11, 0x01014030 }, + // CD in { 0x12, 0x02319040 }, + // Digial Mic ins { 0x13, 0x90a000f0 }, { 0x14, 0x90a000f0 }, + // Digital outs { 0x22, 0x01452050 }, { 0x23, 0x01452050 }, {} @@ -1758,6 +1762,7 @@ static const struct hda_pintbl alienware_m17x_pin_configs[] = { }; static const struct hda_pintbl intel_dg45id_pin_configs[] = { + // Analog outputs { 0x0a, 0x02214230 }, { 0x0b, 0x02A19240 }, { 0x0c, 0x01013214 }, @@ -1765,6 +1770,9 @@ static const struct hda_pintbl intel_dg45id_pin_configs[] = { { 0x0e, 0x01A19250 }, { 0x0f, 0x01011212 }, { 0x10, 0x01016211 }, + // Digital output + { 0x22, 0x01451380 }, + { 0x23, 0x40f000f0 }, {} }; @@ -1955,6 +1963,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = { "DFI LanParty", STAC_92HD73XX_REF), SND_PCI_QUIRK(PCI_VENDOR_ID_DFI, 0x3101, "DFI LanParty", STAC_92HD73XX_REF), + SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5001, + "Intel DP45SG", STAC_92HD73XX_INTEL), SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5002, "Intel DG45ID", STAC_92HD73XX_INTEL), SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5003, diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 4a69ce702360..0acdf0156f07 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -269,6 +269,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "8A43"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8A22"), + } + }, {} }; diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index 0068780fe0a7..1c1f211a8e2e 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -2022,6 +2022,11 @@ static int da7213_i2c_probe(struct i2c_client *i2c) return ret; } +static void da7213_i2c_remove(struct i2c_client *i2c) +{ + pm_runtime_disable(&i2c->dev); +} + static int __maybe_unused da7213_runtime_suspend(struct device *dev) { struct da7213_priv *da7213 = dev_get_drvdata(dev); @@ -2065,6 +2070,7 @@ static struct i2c_driver da7213_i2c_driver = { .pm = &da7213_pm, }, .probe_new = da7213_i2c_probe, + .remove = da7213_i2c_remove, .id_table = da7213_i2c_id, }; diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index ed4f7cdda04f..8b6b76029694 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -436,23 +436,28 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_device *hdev, return 0; } -static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai, - unsigned int tx_mask, unsigned int rx_mask, - int slots, int slot_width) +static int hdac_hdmi_set_stream(struct snd_soc_dai *dai, + void *stream, int direction) { struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai); struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_pcm *pcm; + struct hdac_stream *hstream; - dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, tx_mask); + if (!stream) + return -EINVAL; + + hstream = (struct hdac_stream *)stream; + + dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, hstream->stream_tag); dai_map = &hdmi->dai_map[dai->id]; pcm = hdac_hdmi_get_pcm_from_cvt(hdmi, dai_map->cvt); if (pcm) - pcm->stream_tag = (tx_mask << 4); + pcm->stream_tag = (hstream->stream_tag << 4); return 0; } @@ -1544,7 +1549,7 @@ static const struct snd_soc_dai_ops hdmi_dai_ops = { .startup = hdac_hdmi_pcm_open, .shutdown = hdac_hdmi_pcm_close, .hw_params = hdac_hdmi_set_hw_params, - .set_tdm_slot = hdac_hdmi_set_tdm_slot, + .set_stream = hdac_hdmi_set_stream, }; /* diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index a73a7d7a1c0a..faba4237bd3d 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -3670,9 +3670,9 @@ static int __maybe_unused rx_macro_runtime_suspend(struct device *dev) regcache_cache_only(rx->regmap, true); regcache_mark_dirty(rx->regmap); - clk_disable_unprepare(rx->mclk); - clk_disable_unprepare(rx->npl); clk_disable_unprepare(rx->fsgen); + clk_disable_unprepare(rx->npl); + clk_disable_unprepare(rx->mclk); return 0; } diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 473d3cd39554..589c490a8c48 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -2098,9 +2098,9 @@ static int __maybe_unused tx_macro_runtime_suspend(struct device *dev) regcache_cache_only(tx->regmap, true); regcache_mark_dirty(tx->regmap); - clk_disable_unprepare(tx->mclk); - clk_disable_unprepare(tx->npl); clk_disable_unprepare(tx->fsgen); + clk_disable_unprepare(tx->npl); + clk_disable_unprepare(tx->mclk); return 0; } diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c index ba7480f3831e..3f6f1bdd4e03 100644 --- a/sound/soc/codecs/lpass-wsa-macro.c +++ b/sound/soc/codecs/lpass-wsa-macro.c @@ -2506,9 +2506,9 @@ static int __maybe_unused wsa_macro_runtime_suspend(struct device *dev) regcache_cache_only(wsa->regmap, true); regcache_mark_dirty(wsa->regmap); - clk_disable_unprepare(wsa->mclk); - clk_disable_unprepare(wsa->npl); clk_disable_unprepare(wsa->fsgen); + clk_disable_unprepare(wsa->npl); + clk_disable_unprepare(wsa->mclk); return 0; } diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 79e0039c79a3..5a12940ef907 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -533,6 +533,18 @@ static int byt_rt5640_aif1_hw_params(struct snd_pcm_substream *substream, /* Please keep this list alphabetically sorted */ static const struct dmi_system_id byt_rt5640_quirk_table[] = { + { /* Acer Iconia One 7 B1-750 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "VESPA2"), + }, + .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | + BYT_RT5640_JD_SRC_JD1_IN4P | + BYT_RT5640_OVCD_TH_1500UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Acer Iconia Tab 8 W1-810 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index d2ed807abde9..767fa89d0870 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -213,6 +213,17 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { SOF_SDW_PCH_DMIC | RT711_JD1), }, + { + /* NUC15 'Rooks County' LAPRC510 and LAPRC710 skews */ + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel(R) Client Systems"), + DMI_MATCH(DMI_PRODUCT_NAME, "LAPRC"), + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + SOF_SDW_PCH_DMIC | + RT711_JD2_100K), + }, /* TigerLake-SDCA devices */ { .callback = sof_sdw_quirk_cb, diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c index 28dd2046e4ac..d8c80041388a 100644 --- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c @@ -354,6 +354,20 @@ static const struct snd_soc_acpi_link_adr adl_sdw_rt711_link0_rt1316_link3[] = { {} }; +static const struct snd_soc_acpi_link_adr adl_sdw_rt711_link0_rt1316_link2[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt711_sdca_0_adr), + .adr_d = rt711_sdca_0_adr, + }, + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt1316_2_single_adr), + .adr_d = rt1316_2_single_adr, + }, + {} +}; + static const struct snd_soc_acpi_adr_device mx8373_2_adr[] = { { .adr = 0x000223019F837300ull, @@ -625,6 +639,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_sdw_machines[] = { .sof_tplg_filename = "sof-adl-rt711-l0-rt1316-l3.tplg", }, { + .link_mask = 0x5, /* 2 active links required */ + .links = adl_sdw_rt711_link0_rt1316_link2, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-adl-rt711-l0-rt1316-l2.tplg", + }, + { .link_mask = 0x1, /* link0 required */ .links = adl_rvp, .drv_name = "sof_sdw", diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 5eb056b942ce..7958c9defd49 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1661,10 +1661,14 @@ static void dpcm_runtime_setup_fe(struct snd_pcm_substream *substream) struct snd_pcm_hardware *hw = &runtime->hw; struct snd_soc_dai *dai; int stream = substream->stream; + u64 formats = hw->formats; int i; soc_pcm_hw_init(hw); + if (formats) + hw->formats &= formats; + for_each_rtd_cpu_dais(fe, i, dai) { struct snd_soc_pcm_stream *cpu_stream; diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index a623707c8ffc..669b99a4f76e 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -1805,6 +1805,14 @@ static int sof_ipc4_route_setup(struct snd_sof_dev *sdev, struct snd_sof_route * u32 header, extension; int ret; + if (!src_fw_module || !sink_fw_module) { + /* The NULL module will print as "(efault)" */ + dev_err(sdev->dev, "source %s or sink %s widget weren't set up properly\n", + src_fw_module->man4_module_entry.name, + sink_fw_module->man4_module_entry.name); + return -ENODEV; + } + sroute->src_queue_id = sof_ipc4_get_queue_id(src_widget, sink_widget, SOF_PIN_TYPE_SOURCE); if (sroute->src_queue_id < 0) { diff --git a/sound/soc/sof/ipc4.c b/sound/soc/sof/ipc4.c index 8ede4b952997..246b56d24a6f 100644 --- a/sound/soc/sof/ipc4.c +++ b/sound/soc/sof/ipc4.c @@ -405,6 +405,9 @@ static int sof_ipc4_tx_msg(struct snd_sof_dev *sdev, void *msg_data, size_t msg_ static int sof_ipc4_set_get_data(struct snd_sof_dev *sdev, void *data, size_t payload_bytes, bool set) { + const struct sof_dsp_power_state target_state = { + .state = SOF_DSP_PM_D0, + }; size_t payload_limit = sdev->ipc->max_payload_size; struct sof_ipc4_msg *ipc4_msg = data; struct sof_ipc4_msg tx = {{ 0 }}; @@ -435,6 +438,11 @@ static int sof_ipc4_set_get_data(struct snd_sof_dev *sdev, void *data, tx.extension |= SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK(1); + /* ensure the DSP is in D0i0 before sending IPC */ + ret = snd_sof_dsp_set_power_state(sdev, &target_state); + if (ret < 0) + return ret; + /* Serialise IPC TX */ mutex_lock(&sdev->ipc->tx_mutex); diff --git a/tools/Makefile b/tools/Makefile index e497875fc7e3..37e9f6804832 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -39,7 +39,7 @@ help: @echo ' turbostat - Intel CPU idle stats and freq reporting tool' @echo ' usb - USB testing tools' @echo ' virtio - vhost test module' - @echo ' vm - misc vm tools' + @echo ' mm - misc mm tools' @echo ' wmi - WMI interface examples' @echo ' x86_energy_perf_policy - Intel energy policy tool' @echo '' @@ -69,7 +69,7 @@ acpi: FORCE cpupower: FORCE $(call descend,power/$@) -cgroup counter firewire hv guest bootconfig spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE +cgroup counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE $(call descend,$@) bpf/%: FORCE @@ -118,7 +118,7 @@ kvm_stat: FORCE all: acpi cgroup counter cpupower gpio hv firewire \ perf selftests bootconfig spi turbostat usb \ - virtio vm bpf x86_energy_perf_policy \ + virtio mm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ pci debugging tracing thermal thermometer thermal-engine @@ -128,7 +128,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install: +cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install: $(call descend,$(@:_install=),install) selftests_install: @@ -158,7 +158,7 @@ kvm_stat_install: install: acpi_install cgroup_install counter_install cpupower_install gpio_install \ hv_install firewire_install iio_install \ perf_install selftests_install turbostat_install usb_install \ - virtio_install vm_install bpf_install x86_energy_perf_policy_install \ + virtio_install mm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ wmi_install pci_install debugging_install intel-speed-select_install \ tracing_install thermometer_install thermal-engine_install @@ -169,7 +169,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean tracing_clean: +cgroup_clean counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean mm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean tracing_clean: $(call descend,$(@:_clean=),clean) libapi_clean: @@ -211,7 +211,7 @@ build_clean: clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \ - vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ + mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean diff --git a/tools/arch/loongarch/include/uapi/asm/bitsperlong.h b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h index d4e32b3d4843..00b4ba1e5cdf 100644 --- a/tools/arch/loongarch/include/uapi/asm/bitsperlong.h +++ b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h @@ -2,7 +2,7 @@ #ifndef __ASM_LOONGARCH_BITSPERLONG_H #define __ASM_LOONGARCH_BITSPERLONG_H -#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8) +#define __BITS_PER_LONG (__SIZEOF_LONG__ * 8) #include <asm-generic/bitsperlong.h> diff --git a/tools/mm/page_owner_sort.c b/tools/mm/page_owner_sort.c index 7c2ac124cdc8..99798894b879 100644 --- a/tools/mm/page_owner_sort.c +++ b/tools/mm/page_owner_sort.c @@ -857,7 +857,7 @@ int main(int argc, char **argv) if (cull & CULL_PID || filter & FILTER_PID) fprintf(fout, ", PID %d", list[i].pid); if (cull & CULL_TGID || filter & FILTER_TGID) - fprintf(fout, ", TGID %d", list[i].pid); + fprintf(fout, ", TGID %d", list[i].tgid); if (cull & CULL_COMM || filter & FILTER_COMM) fprintf(fout, ", task_comm_name: %s", list[i].comm); if (cull & CULL_ALLOCATOR) { diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 958ee9bdb316..4c89ff333f6f 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -108,6 +108,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mn->slot[1] != NULL); MT_BUG_ON(mt, mas_allocated(&mas) != 0); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas.node = MAS_START; mas_nomem(&mas, GFP_KERNEL); @@ -160,6 +161,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != i); MT_BUG_ON(mt, !mn); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } @@ -192,6 +194,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != i - 1); MT_BUG_ON(mt, !mn); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } @@ -210,6 +213,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); MT_BUG_ON(mt, mas_allocated(&mas) != j - 1); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -233,6 +237,7 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != i - j); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1); } @@ -269,6 +274,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -294,6 +300,7 @@ static noinline void check_new_node(struct maple_tree *mt) mn = mas_pop_node(&mas2); /* get the next node. */ MT_BUG_ON(mt, mn == NULL); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas2) != 0); @@ -334,10 +341,12 @@ static noinline void check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2); mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); for (i = 1; i <= MAPLE_ALLOC_SLOTS + 1; i++) { mn = mas_pop_node(&mas); MT_BUG_ON(mt, not_empty(mn)); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); } MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -375,6 +384,7 @@ static noinline void check_new_node(struct maple_tree *mt) mas_node_count(&mas, i); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas_destroy(&mas); @@ -382,10 +392,13 @@ static noinline void check_new_node(struct maple_tree *mt) mas_node_count(&mas, i); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mn = mas_pop_node(&mas); /* get the next node. */ + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); mas_destroy(&mas); } @@ -35369,6 +35382,7 @@ static noinline void check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, allocated != 1 + height * 3); mn = mas_pop_node(&mas); MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); mas_destroy(&mas); @@ -35386,6 +35400,7 @@ static noinline void check_prealloc(struct maple_tree *mt) mas_destroy(&mas); allocated = mas_allocated(&mas); MT_BUG_ON(mt, allocated != 0); + mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0); @@ -35756,6 +35771,7 @@ void farmer_tests(void) tree.ma_root = mt_mk_node(node, maple_leaf_64); mt_dump(&tree); + node->parent = ma_parent_ptr(node); ma_free_rcu(node); /* Check things that will make lockdep angry */ diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index 7271a18ab3e2..8251a0fc6ee9 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -167,8 +167,7 @@ void test_xdp_do_redirect(void) if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | - NETDEV_XDP_ACT_NDO_XMIT_SG, + NETDEV_XDP_ACT_RX_SG, "veth_src query_opts.feature_flags")) goto out; @@ -178,9 +177,34 @@ void test_xdp_do_redirect(void) if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "veth_dst query_opts.feature_flags")) + goto out; + + /* Enable GRO */ + SYS("ethtool -K veth_src gro on"); + SYS("ethtool -K veth_dst gro on"); + + err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_src bpf_xdp_query gro on")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT_SG, - "veth_dst query_opts.feature_flags")) + "veth_src query_opts.feature_flags gro on")) + goto out; + + err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_dst bpf_xdp_query gro on")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_dst query_opts.feature_flags gro on")) goto out; memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index aa4beae99f4f..8c5e98da9ae9 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -273,6 +273,8 @@ static int verify_xsk_metadata(struct xsk *xsk) if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash")) return -1; + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type"); + xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 4c55b4d79d3d..e1c787815e44 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -12,10 +12,14 @@ struct { __type(value, __u32); } xsk SEC(".maps"); +__u64 pkts_skip = 0; +__u64 pkts_fail = 0; +__u64 pkts_redir = 0; + extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -26,7 +30,7 @@ int rx(struct xdp_md *ctx) struct udphdr *udp = NULL; struct iphdr *iph = NULL; struct xdp_meta *meta; - int ret; + int err; data = (void *)(long)ctx->data; data_end = (void *)(long)ctx->data_end; @@ -46,17 +50,20 @@ int rx(struct xdp_md *ctx) udp = NULL; } - if (!udp) + if (!udp) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - if (udp->dest != bpf_htons(9091)) + /* Forwarding UDP:9091 to AF_XDP */ + if (udp->dest != bpf_htons(9091)) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - bpf_printk("forwarding UDP:9091 to AF_XDP"); - - ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); - if (ret != 0) { - bpf_printk("bpf_xdp_adjust_meta returned %d", ret); + err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (err) { + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } @@ -65,20 +72,19 @@ int rx(struct xdp_md *ctx) meta = data_meta; if (meta + 1 > data) { - bpf_printk("bpf_xdp_adjust_meta doesn't appear to work"); + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } - if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) - bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp); - else + err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); + if (err) meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ - if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash)) - bpf_printk("populated rx_hash with %u", meta->rx_hash); - else - meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */ + err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + if (err < 0) + meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */ + __sync_add_and_fetch(&pkts_redir, 1); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c index 77678b034389..d151d406a123 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -21,8 +21,8 @@ struct { extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -56,7 +56,7 @@ int rx(struct xdp_md *ctx) if (timestamp == 0) meta->rx_timestamp = 1; - bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash); + bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c index cf69d05451c3..85f88d9d7a78 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata2.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c @@ -5,17 +5,18 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; int called; SEC("freplace/rx") int freplace_rx(struct xdp_md *ctx) { + enum xdp_rss_hash_type type = 0; u32 hash = 0; /* Call _any_ metadata function to make sure we don't crash. */ - bpf_xdp_metadata_rx_hash(ctx, &hash); + bpf_xdp_metadata_rx_hash(ctx, &hash, &type); called++; return XDP_PASS; } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 1c8acb68b977..987cf0db5ebc 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -141,7 +141,11 @@ static void verify_xdp_metadata(void *data) meta = data - sizeof(*meta); printf("rx_timestamp: %llu\n", meta->rx_timestamp); - printf("rx_hash: %u\n", meta->rx_hash); + if (meta->rx_hash_err < 0) + printf("No rx_hash err=%d\n", meta->rx_hash_err); + else + printf("rx_hash: 0x%X with RSS type:0x%X\n", + meta->rx_hash, meta->rx_hash_type); } static void verify_skb_metadata(int fd) @@ -212,7 +216,9 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) while (true) { errno = 0; ret = poll(fds, rxq + 1, 1000); - printf("poll: %d (%d)\n", ret, errno); + printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n", + ret, errno, bpf_obj->bss->pkts_skip, + bpf_obj->bss->pkts_fail, bpf_obj->bss->pkts_redir); if (ret < 0) break; if (ret == 0) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index f6780fbb0a21..0c4624dc6f2f 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -12,4 +12,8 @@ struct xdp_meta { __u64 rx_timestamp; __u32 rx_hash; + union { + __u32 rx_hash_type; + __s32 rx_hash_err; + }; }; diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index a39bb2560d9b..03f92d7aeb19 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -8,11 +8,12 @@ TEST_PROGS := \ dev_addr_lists.sh \ mode-1-recovery-updelay.sh \ mode-2-recovery-updelay.sh \ - option_prio.sh \ + bond_options.sh \ bond-eth-type-change.sh TEST_FILES := \ lag_lib.sh \ + bond_topo_3d1c.sh \ net_forwarding_lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh new file mode 100755 index 000000000000..db29a3146a86 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -0,0 +1,264 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bonding options with mode 1,5,6 + +ALL_TESTS=" + prio + arp_validate +" + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source ${lib_dir}/net_forwarding_lib.sh +source ${lib_dir}/bond_topo_3d1c.sh + +skip_prio() +{ + local skip=1 + + # check if iproute support prio option + ip -n ${s_ns} link set eth0 type bond_slave prio 10 + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support prio option + ip -n ${s_ns} -d link show eth0 | grep -q "prio 10" + [[ $? -ne 0 ]] && skip=0 + + return $skip +} + +skip_ns() +{ + local skip=1 + + # check if iproute support ns_ip6_target option + ip -n ${s_ns} link add bond1 type bond ns_ip6_target ${g_ip6} + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support ns_ip6_target option + ip -n ${s_ns} -d link show bond1 | grep -q "ns_ip6_target ${g_ip6}" + [[ $? -ne 0 ]] && skip=0 + + ip -n ${s_ns} link del bond1 + + return $skip +} + +active_slave="" +check_active_slave() +{ + local target_active_slave=$1 + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + test "$active_slave" = "$target_active_slave" + check_err $? "Current active slave is $active_slave but not $target_active_slave" +} + + +# Test bonding prio option +prio_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + # check bonding member prio value + ip -n ${s_ns} link set eth0 type bond_slave prio 0 + ip -n ${s_ns} link set eth1 type bond_slave prio 10 + ip -n ${s_ns} link set eth2 type bond_slave prio 11 + cmd_jq "ip -n ${s_ns} -d -j link show eth0" \ + ".[].linkinfo.info_slave_data | select (.prio == 0)" "-e" &> /dev/null + check_err $? "eth0 prio is not 0" + cmd_jq "ip -n ${s_ns} -d -j link show eth1" \ + ".[].linkinfo.info_slave_data | select (.prio == 10)" "-e" &> /dev/null + check_err $? "eth1 prio is not 10" + cmd_jq "ip -n ${s_ns} -d -j link show eth2" \ + ".[].linkinfo.info_slave_data | select (.prio == 11)" "-e" &> /dev/null + check_err $? "eth2 prio is not 11" + + bond_check_connection "setup" + + # active slave should be the primary slave + check_active_slave eth1 + + # active slave should be the higher prio slave + ip -n ${s_ns} link set $active_slave down + bond_check_connection "fail over" + check_active_slave eth2 + + # when only 1 slave is up + ip -n ${s_ns} link set $active_slave down + bond_check_connection "only 1 slave up" + check_active_slave eth0 + + # when a higher prio slave change to up + ip -n ${s_ns} link set eth2 up + bond_check_connection "higher prio slave up" + case $primary_reselect in + "0") + check_active_slave "eth2" + ;; + "1") + check_active_slave "eth0" + ;; + "2") + check_active_slave "eth0" + ;; + esac + local pre_active_slave=$active_slave + + # when the primary slave change to up + ip -n ${s_ns} link set eth1 up + bond_check_connection "primary slave up" + case $primary_reselect in + "0") + check_active_slave "eth1" + ;; + "1") + check_active_slave "$pre_active_slave" + ;; + "2") + check_active_slave "$pre_active_slave" + ip -n ${s_ns} link set $active_slave down + bond_check_connection "pre_active slave down" + check_active_slave "eth1" + ;; + esac + + # Test changing bond slave prio + if [[ "$primary_reselect" == "0" ]];then + ip -n ${s_ns} link set eth0 type bond_slave prio 1000000 + ip -n ${s_ns} link set eth1 type bond_slave prio 0 + ip -n ${s_ns} link set eth2 type bond_slave prio -50 + ip -n ${s_ns} -d link show eth0 | grep -q 'prio 1000000' + check_err $? "eth0 prio is not 1000000" + ip -n ${s_ns} -d link show eth1 | grep -q 'prio 0' + check_err $? "eth1 prio is not 0" + ip -n ${s_ns} -d link show eth2 | grep -q 'prio -50' + check_err $? "eth3 prio is not -50" + check_active_slave "eth1" + + ip -n ${s_ns} link set $active_slave down + bond_check_connection "change slave prio" + check_active_slave "eth0" + fi +} + +prio_miimon() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode $mode miimon 100 primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode miimon primary_reselect $primary_reselect" + done +} + +prio_arp() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect" + done +} + +prio_ns() +{ + local primary_reselect + local mode=$1 + + if skip_ns; then + log_test_skip "prio ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect" + done +} + +prio() +{ + local mode modes="active-backup balance-tlb balance-alb" + + if skip_prio; then + log_test_skip "prio" "Current iproute or kernel doesn't support bond option 'prio'." + return 0 + fi + + for mode in $modes; do + prio_miimon $mode + prio_arp $mode + prio_ns $mode + done +} + +arp_validate_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + bond_check_connection + [ $RET -ne 0 ] && log_test "arp_validate" "$retmsg" + + # wait for a while to make sure the mii status stable + sleep 5 + for i in $(seq 0 2); do + mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status") + if [ ${mii_status} != "UP" ]; then + RET=1 + log_test "arp_validate" "interface eth$i mii_status $mii_status" + fi + done +} + +arp_validate_arp() +{ + local mode=$1 + local val + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} arp_validate $val" + log_test "arp_validate" "$mode arp_ip_target arp_validate $val" + done +} + +arp_validate_ns() +{ + local mode=$1 + local val + + if skip_ns; then + log_test_skip "arp_validate ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} arp_validate $val" + log_test "arp_validate" "$mode ns_ip6_target arp_validate $val" + done +} + +arp_validate() +{ + arp_validate_arp "active-backup" + arp_validate_ns "active-backup" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh new file mode 100644 index 000000000000..4045ca97fb22 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -0,0 +1,143 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Topology for Bond mode 1,5,6 testing +# +# +-------------------------------------+ +# | bond0 | +# | + | Server +# | eth0 | eth1 eth2 | 192.0.2.1/24 +# | +-------------------+ | 2001:db8::1/24 +# | | | | | +# +-------------------------------------+ +# | | | +# +-------------------------------------+ +# | | | | | +# | +---+---------+---------+---+ | Gateway +# | | br0 | | 192.0.2.254/24 +# | +-------------+-------------+ | 2001:db8::254/24 +# | | | +# +-------------------------------------+ +# | +# +-------------------------------------+ +# | | | Client +# | + | 192.0.2.10/24 +# | eth0 | 2001:db8::10/24 +# +-------------------------------------+ + +s_ns="s-$(mktemp -u XXXXXX)" +c_ns="c-$(mktemp -u XXXXXX)" +g_ns="g-$(mktemp -u XXXXXX)" +s_ip4="192.0.2.1" +c_ip4="192.0.2.10" +g_ip4="192.0.2.254" +s_ip6="2001:db8::1" +c_ip6="2001:db8::10" +g_ip6="2001:db8::254" + +gateway_create() +{ + ip netns add ${g_ns} + ip -n ${g_ns} link add br0 type bridge + ip -n ${g_ns} link set br0 up + ip -n ${g_ns} addr add ${g_ip4}/24 dev br0 + ip -n ${g_ns} addr add ${g_ip6}/24 dev br0 +} + +gateway_destroy() +{ + ip -n ${g_ns} link del br0 + ip netns del ${g_ns} +} + +server_create() +{ + ip netns add ${s_ns} + ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100 + + for i in $(seq 0 2); do + ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + + ip -n ${g_ns} link set s${i} up + ip -n ${g_ns} link set s${i} master br0 + ip -n ${s_ns} link set eth${i} master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +# Reset bond with new mode and options +bond_reset() +{ + local param="$1" + + ip -n ${s_ns} link set bond0 down + ip -n ${s_ns} link del bond0 + + ip -n ${s_ns} link add bond0 type bond $param + for i in $(seq 0 2); do + ip -n ${s_ns} link set eth$i master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +server_destroy() +{ + for i in $(seq 0 2); do + ip -n ${s_ns} link del eth${i} + done + ip netns del ${s_ns} +} + +client_create() +{ + ip netns add ${c_ns} + ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns} + + ip -n ${g_ns} link set c0 up + ip -n ${g_ns} link set c0 master br0 + + ip -n ${c_ns} link set eth0 up + ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0 + ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0 +} + +client_destroy() +{ + ip -n ${c_ns} link del eth0 + ip netns del ${c_ns} +} + +setup_prepare() +{ + gateway_create + server_create + client_create +} + +cleanup() +{ + pre_cleanup + + client_destroy + server_destroy + gateway_destroy +} + +bond_check_connection() +{ + local msg=${1:-"check connection"} + + sleep 2 + ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping failed" + ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping6 failed" +} diff --git a/tools/testing/selftests/drivers/net/bonding/option_prio.sh b/tools/testing/selftests/drivers/net/bonding/option_prio.sh deleted file mode 100755 index c32eebff5005..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/option_prio.sh +++ /dev/null @@ -1,245 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test bonding option prio -# - -ALL_TESTS=" - prio_arp_ip_target_test - prio_miimon_test -" - -REQUIRE_MZ=no -REQUIRE_JQ=no -NUM_NETIFS=0 -lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh - -destroy() -{ - ip link del bond0 &>/dev/null - ip link del br0 &>/dev/null - ip link del veth0 &>/dev/null - ip link del veth1 &>/dev/null - ip link del veth2 &>/dev/null - ip netns del ns1 &>/dev/null - ip link del veth3 &>/dev/null -} - -cleanup() -{ - pre_cleanup - - destroy -} - -skip() -{ - local skip=1 - ip link add name bond0 type bond mode 1 miimon 100 &>/dev/null - ip link add name veth0 type veth peer name veth0_p - ip link set veth0 master bond0 - - # check if iproute support prio option - ip link set dev veth0 type bond_slave prio 10 - [[ $? -ne 0 ]] && skip=0 - - # check if bonding support prio option - ip -d link show veth0 | grep -q "prio 10" - [[ $? -ne 0 ]] && skip=0 - - ip link del bond0 &>/dev/null - ip link del veth0 - - return $skip -} - -active_slave="" -check_active_slave() -{ - local target_active_slave=$1 - active_slave="$(cat /sys/class/net/bond0/bonding/active_slave)" - test "$active_slave" = "$target_active_slave" - check_err $? "Current active slave is $active_slave but not $target_active_slave" -} - - -# Test bonding prio option with mode=$mode monitor=$monitor -# and primary_reselect=$primary_reselect -prio_test() -{ - RET=0 - - local monitor=$1 - local mode=$2 - local primary_reselect=$3 - - local bond_ip4="192.169.1.2" - local peer_ip4="192.169.1.1" - local bond_ip6="2009:0a:0b::02" - local peer_ip6="2009:0a:0b::01" - - - # create veths - ip link add name veth0 type veth peer name veth0_p - ip link add name veth1 type veth peer name veth1_p - ip link add name veth2 type veth peer name veth2_p - - # create bond - if [[ "$monitor" == "miimon" ]];then - ip link add name bond0 type bond mode $mode miimon 100 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "arp_ip_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 arp_ip_target $peer_ip4 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "ns_ip6_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 ns_ip6_target $peer_ip6 primary veth1 primary_reselect $primary_reselect - fi - ip link set bond0 up - ip link set veth0 master bond0 - ip link set veth1 master bond0 - ip link set veth2 master bond0 - # check bonding member prio value - ip link set dev veth0 type bond_slave prio 0 - ip link set dev veth1 type bond_slave prio 10 - ip link set dev veth2 type bond_slave prio 11 - ip -d link show veth0 | grep -q 'prio 0' - check_err $? "veth0 prio is not 0" - ip -d link show veth1 | grep -q 'prio 10' - check_err $? "veth0 prio is not 10" - ip -d link show veth2 | grep -q 'prio 11' - check_err $? "veth0 prio is not 11" - - ip link set veth0 up - ip link set veth1 up - ip link set veth2 up - ip link set veth0_p up - ip link set veth1_p up - ip link set veth2_p up - - # prepare ping target - ip link add name br0 type bridge - ip link set br0 up - ip link set veth0_p master br0 - ip link set veth1_p master br0 - ip link set veth2_p master br0 - ip link add name veth3 type veth peer name veth3_p - ip netns add ns1 - ip link set veth3_p master br0 up - ip link set veth3 netns ns1 up - ip netns exec ns1 ip addr add $peer_ip4/24 dev veth3 - ip netns exec ns1 ip addr add $peer_ip6/64 dev veth3 - ip addr add $bond_ip4/24 dev bond0 - ip addr add $bond_ip6/64 dev bond0 - sleep 5 - - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 1." - ping6 $peer_ip6 -c5 -I bond0 &>/dev/null - check_err $? "ping6 failed 1." - - # active salve should be the primary slave - check_active_slave veth1 - - # active slave should be the higher prio slave - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 2." - check_active_slave veth2 - - # when only 1 slave is up - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 3." - check_active_slave veth0 - - # when a higher prio slave change to up - ip link set veth2 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 4." - case $primary_reselect in - "0") - check_active_slave "veth2" - ;; - "1") - check_active_slave "veth0" - ;; - "2") - check_active_slave "veth0" - ;; - esac - local pre_active_slave=$active_slave - - # when the primary slave change to up - ip link set veth1 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 5." - case $primary_reselect in - "0") - check_active_slave "veth1" - ;; - "1") - check_active_slave "$pre_active_slave" - ;; - "2") - check_active_slave "$pre_active_slave" - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 6." - check_active_slave "veth1" - ;; - esac - - # Test changing bond salve prio - if [[ "$primary_reselect" == "0" ]];then - ip link set dev veth0 type bond_slave prio 1000000 - ip link set dev veth1 type bond_slave prio 0 - ip link set dev veth2 type bond_slave prio -50 - ip -d link show veth0 | grep -q 'prio 1000000' - check_err $? "veth0 prio is not 1000000" - ip -d link show veth1 | grep -q 'prio 0' - check_err $? "veth1 prio is not 0" - ip -d link show veth2 | grep -q 'prio -50' - check_err $? "veth3 prio is not -50" - check_active_slave "veth1" - - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 7." - check_active_slave "veth0" - fi - - cleanup - - log_test "prio_test" "Test bonding option 'prio' with mode=$mode monitor=$monitor and primary_reselect=$primary_reselect" -} - -prio_miimon_test() -{ - local mode - local primary_reselect - - for mode in 1 5 6; do - for primary_reselect in 0 1 2; do - prio_test "miimon" $mode $primary_reselect - done - done -} - -prio_arp_ip_target_test() -{ - local primary_reselect - - for primary_reselect in 0 1 2; do - prio_test "arp_ip_target" 1 $primary_reselect - done -} - -if skip;then - log_test_skip "option_prio.sh" "Current iproute doesn't support 'prio'." - exit 0 -fi - -trap cleanup EXIT - -tests_run - -exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 582669ca38e9..c6a8c732b802 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -18,6 +18,7 @@ #include <grp.h> #include <stdbool.h> #include <stdarg.h> +#include <linux/mount.h> #include "../kselftest_harness.h" diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index cc9fd55ab869..2529226ce87c 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -48,3 +48,4 @@ CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m +CONFIG_IP_SCTP=m diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 48e52f995a98..b1eb7bce599d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -913,6 +913,7 @@ test_listener() $client4_port > /dev/null 2>&1 & local listener_pid=$! + sleep 0.5 verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -928,6 +929,7 @@ test_listener() # Delete the listener from the client ns, if one was created kill_wait $listener_pid + sleep 0.5 verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 3243c90d449e..5d467d1993cb 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -62,7 +62,7 @@ class OvsDatapath(GenericNetlinkSocket): nla_map = ( ("OVS_DP_ATTR_UNSPEC", "none"), ("OVS_DP_ATTR_NAME", "asciiz"), - ("OVS_DP_ATTR_UPCALL_PID", "uint32"), + ("OVS_DP_ATTR_UPCALL_PID", "array(uint32)"), ("OVS_DP_ATTR_STATS", "dpstats"), ("OVS_DP_ATTR_MEGAFLOW_STATS", "megaflowstats"), ("OVS_DP_ATTR_USER_FEATURES", "uint32"), diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh index 0fd0d2db3abc..a26c5624429f 100755 --- a/tools/testing/selftests/net/rps_default_mask.sh +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -60,6 +60,7 @@ ip link set dev $VETH up ip -n $NETNS link set dev $VETH up chk_rps "changing rps_default_mask affect newly created devices" "" $VETH 3 chk_rps "changing rps_default_mask don't affect newly child netns[II]" $NETNS $VETH 0 +ip link del dev $VETH ip netns del $NETNS setup diff --git a/tools/virtio/virtio-trace/README b/tools/virtio/virtio-trace/README index b64845b823ab..4fb9368bf751 100644 --- a/tools/virtio/virtio-trace/README +++ b/tools/virtio/virtio-trace/README @@ -61,7 +61,7 @@ and id=channel0,name=agent-ctl-path\ ##data path## -chardev pipe,id=charchannel1,path=/tmp/virtio-trace/trace-path-cpu0\ - -device virtserialport,bus=virtio-serial0.0,nr=2,chardev=charchannel0,\ + -device virtserialport,bus=virtio-serial0.0,nr=2,chardev=charchannel1,\ id=channel1,name=trace-path-cpu0\ ... diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c index ee01e40e8bc6..61230532fef1 100644 --- a/usr/gen_init_cpio.c +++ b/usr/gen_init_cpio.c @@ -353,6 +353,12 @@ static int cpio_mkfile(const char *name, const char *location, buf.st_mtime = 0xffffffff; } + if (buf.st_mtime < 0) { + fprintf(stderr, "%s: Timestamp negative, clipping.\n", + location); + buf.st_mtime = 0; + } + if (buf.st_size > 0xffffffff) { fprintf(stderr, "%s: Size exceeds maximum cpio file size\n", location); @@ -602,10 +608,10 @@ int main (int argc, char *argv[]) /* * Timestamps after 2106-02-07 06:28:15 UTC have an ascii hex time_t * representation that exceeds 8 chars and breaks the cpio header - * specification. + * specification. Negative timestamps similarly exceed 8 chars. */ - if (default_mtime > 0xffffffff) { - fprintf(stderr, "ERROR: Timestamp too large for cpio format\n"); + if (default_mtime > 0xffffffff || default_mtime < 0) { + fprintf(stderr, "ERROR: Timestamp out of range for cpio format\n"); exit(1); } diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 2a3ed401ce46..b0af834ffa95 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -55,6 +55,15 @@ irqfd_inject(struct work_struct *work) irqfd->gsi, 1, false); } +static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler) +{ + struct kvm_kernel_irqfd *irqfd; + + list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, + srcu_read_lock_held(&resampler->kvm->irq_srcu)) + eventfd_signal(irqfd->resamplefd, 1); +} + /* * Since resampler irqfds share an IRQ source ID, we de-assert once * then notify all of the resampler irqfds using this GSI. We can't @@ -65,7 +74,6 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) { struct kvm_kernel_irqfd_resampler *resampler; struct kvm *kvm; - struct kvm_kernel_irqfd *irqfd; int idx; resampler = container_of(kian, @@ -76,11 +84,7 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) resampler->notifier.gsi, 0, false); idx = srcu_read_lock(&kvm->irq_srcu); - - list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, - srcu_read_lock_held(&kvm->irq_srcu)) - eventfd_signal(irqfd->resamplefd, 1); - + irqfd_resampler_notify(resampler); srcu_read_unlock(&kvm->irq_srcu, idx); } @@ -96,8 +100,12 @@ irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd) synchronize_srcu(&kvm->irq_srcu); if (list_empty(&resampler->list)) { - list_del(&resampler->link); + list_del_rcu(&resampler->link); kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier); + /* + * synchronize_srcu(&kvm->irq_srcu) already called + * in kvm_unregister_irq_ack_notifier(). + */ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); kfree(resampler); @@ -369,7 +377,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) resampler->notifier.irq_acked = irqfd_resampler_ack; INIT_LIST_HEAD(&resampler->link); - list_add(&resampler->link, &kvm->irqfds.resampler_list); + list_add_rcu(&resampler->link, &kvm->irqfds.resampler_list); kvm_register_irq_ack_notifier(kvm, &resampler->notifier); irqfd->resampler = resampler; @@ -644,6 +652,31 @@ void kvm_irq_routing_update(struct kvm *kvm) spin_unlock_irq(&kvm->irqfds.lock); } +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + struct kvm_kernel_irqfd_resampler *resampler; + int gsi, idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); + if (gsi != -1) { + list_for_each_entry_srcu(resampler, + &kvm->irqfds.resampler_list, link, + srcu_read_lock_held(&kvm->irq_srcu)) { + if (resampler->notifier.gsi == gsi) { + irqfd_resampler_notify(resampler); + srcu_read_unlock(&kvm->irq_srcu, idx); + return true; + } + } + } + srcu_read_unlock(&kvm->irq_srcu, idx); + + return false; +} + /* * create a host-wide workqueue for issuing deferred shutdown requests * aggregated from all vm* instances. We need our own isolated diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d255964ec331..b1679d08a216 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4479,7 +4479,6 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) #endif #ifdef CONFIG_HAVE_KVM_IRQFD case KVM_CAP_IRQFD: - case KVM_CAP_IRQFD_RESAMPLE: #endif case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: |