diff options
386 files changed, 4757 insertions, 1810 deletions
diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io index 9b642669cb16..169fe08a649b 100644 --- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io +++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io @@ -24,7 +24,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ cpld3_version Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak <vadimpmellanox.com> Description: These files show with which CPLD versions have been burned on LED board. @@ -35,7 +35,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ jtag_enable Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak <vadimpmellanox.com> Description: These files enable and disable the access to the JTAG domain. By default access to the JTAG domain is disabled. @@ -105,7 +105,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ reset_voltmon_upgrade_fail Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak <vadimpmellanox.com> Description: These files show the system reset cause, as following: ComEx power fail, reset from ComEx, system platform reset, reset diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b799bcf67d7b..858b6c0b9a15 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1696,12 +1696,11 @@ By default, super page will be supported if Intel IOMMU has the capability. With this option, super page will not be supported. - sm_off [Default Off] - By default, scalable mode will be supported if the + sm_on [Default Off] + By default, scalable mode will be disabled even if the hardware advertises that it has support for the scalable mode translation. With this option set, scalable mode - will not be used even on hardware which claims to support - it. + will be used on hardware which claims to support it. tboot_noforce [Default Off] Do not force the Intel IOMMU enabled under tboot. By default, tboot will force Intel IOMMU on, which diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst index 2d5919b2b337..ae1e3d0394b0 100644 --- a/Documentation/driver-api/device_link.rst +++ b/Documentation/driver-api/device_link.rst @@ -28,8 +28,8 @@ suspend/resume and shutdown ordering. Device links allow representation of such dependencies in the driver core. -In its standard form, a device link combines *both* dependency types: -It guarantees correct suspend/resume and shutdown ordering between a +In its standard or *managed* form, a device link combines *both* dependency +types: It guarantees correct suspend/resume and shutdown ordering between a "supplier" device and its "consumer" devices, and it guarantees driver presence on the supplier. The consumer devices are not probed before the supplier is bound to a driver, and they're unbound before the supplier @@ -62,18 +62,24 @@ device ``->probe`` callback or a boot-time PCI quirk. Another example for an inconsistent state would be a device link that represents a driver presence dependency, yet is added from the consumer's -``->probe`` callback while the supplier hasn't probed yet: Had the driver -core known about the device link earlier, it wouldn't have probed the +``->probe`` callback while the supplier hasn't started to probe yet: Had the +driver core known about the device link earlier, it wouldn't have probed the consumer in the first place. The onus is thus on the consumer to check presence of the supplier after adding the link, and defer probing on -non-presence. - -If a device link is added in the ``->probe`` callback of the supplier or -consumer driver, it is typically deleted in its ``->remove`` callback for -symmetry. That way, if the driver is compiled as a module, the device -link is added on module load and orderly deleted on unload. The same -restrictions that apply to device link addition (e.g. exclusion of a -parallel suspend/resume transition) apply equally to deletion. +non-presence. [Note that it is valid to create a link from the consumer's +``->probe`` callback while the supplier is still probing, but the consumer must +know that the supplier is functional already at the link creation time (that is +the case, for instance, if the consumer has just acquired some resources that +would not have been available had the supplier not been functional then).] + +If a device link with ``DL_FLAG_STATELESS`` set (i.e. a stateless device link) +is added in the ``->probe`` callback of the supplier or consumer driver, it is +typically deleted in its ``->remove`` callback for symmetry. That way, if the +driver is compiled as a module, the device link is added on module load and +orderly deleted on unload. The same restrictions that apply to device link +addition (e.g. exclusion of a parallel suspend/resume transition) apply equally +to deletion. Device links with ``DL_FLAG_STATELESS`` unset (i.e. managed +device links) are deleted automatically by the driver core. Several flags may be specified on device link addition, two of which have already been mentioned above: ``DL_FLAG_STATELESS`` to express that no @@ -83,25 +89,55 @@ integration is desired. Two other flags are specifically targeted at use cases where the device link is added from the consumer's ``->probe`` callback: ``DL_FLAG_RPM_ACTIVE`` -can be specified to runtime resume the supplier upon addition of the -device link. ``DL_FLAG_AUTOREMOVE_CONSUMER`` causes the device link to be -automatically purged when the consumer fails to probe or later unbinds. -This obviates the need to explicitly delete the link in the ``->remove`` -callback or in the error path of the ``->probe`` callback. +can be specified to runtime resume the supplier and prevent it from suspending +before the consumer is runtime suspended. ``DL_FLAG_AUTOREMOVE_CONSUMER`` +causes the device link to be automatically purged when the consumer fails to +probe or later unbinds. Similarly, when the device link is added from supplier's ``->probe`` callback, ``DL_FLAG_AUTOREMOVE_SUPPLIER`` causes the device link to be automatically purged when the supplier fails to probe or later unbinds. +If neither ``DL_FLAG_AUTOREMOVE_CONSUMER`` nor ``DL_FLAG_AUTOREMOVE_SUPPLIER`` +is set, ``DL_FLAG_AUTOPROBE_CONSUMER`` can be used to request the driver core +to probe for a driver for the consumer driver on the link automatically after +a driver has been bound to the supplier device. + +Note, however, that any combinations of ``DL_FLAG_AUTOREMOVE_CONSUMER``, +``DL_FLAG_AUTOREMOVE_SUPPLIER`` or ``DL_FLAG_AUTOPROBE_CONSUMER`` with +``DL_FLAG_STATELESS`` are invalid and cannot be used. + Limitations =========== -Driver authors should be aware that a driver presence dependency (i.e. when -``DL_FLAG_STATELESS`` is not specified on link addition) may cause probing of -the consumer to be deferred indefinitely. This can become a problem if the -consumer is required to probe before a certain initcall level is reached. -Worse, if the supplier driver is blacklisted or missing, the consumer will -never be probed. +Driver authors should be aware that a driver presence dependency for managed +device links (i.e. when ``DL_FLAG_STATELESS`` is not specified on link addition) +may cause probing of the consumer to be deferred indefinitely. This can become +a problem if the consumer is required to probe before a certain initcall level +is reached. Worse, if the supplier driver is blacklisted or missing, the +consumer will never be probed. + +Moreover, managed device links cannot be deleted directly. They are deleted +by the driver core when they are not necessary any more in accordance with the +``DL_FLAG_AUTOREMOVE_CONSUMER`` and ``DL_FLAG_AUTOREMOVE_SUPPLIER`` flags. +However, stateless device links (i.e. device links with ``DL_FLAG_STATELESS`` +set) are expected to be removed by whoever called :c:func:`device_link_add()` +to add them with the help of either :c:func:`device_link_del()` or +:c:func:`device_link_remove()`. + +Passing ``DL_FLAG_RPM_ACTIVE`` along with ``DL_FLAG_STATELESS`` to +:c:func:`device_link_add()` may cause the PM-runtime usage counter of the +supplier device to remain nonzero after a subsequent invocation of either +:c:func:`device_link_del()` or :c:func:`device_link_remove()` to remove the +device link returned by it. This happens if :c:func:`device_link_add()` is +called twice in a row for the same consumer-supplier pair without removing the +link between these calls, in which case allowing the PM-runtime usage counter +of the supplier to drop on an attempt to remove the link may cause it to be +suspended while the consumer is still PM-runtime-active and that has to be +avoided. [To work around this limitation it is sufficient to let the consumer +runtime suspend at least once, or call :c:func:`pm_runtime_set_suspended()` for +it with PM-runtime disabled, between the :c:func:`device_link_add()` and +:c:func:`device_link_del()` or :c:func:`device_link_remove()` calls.] Sometimes drivers depend on optional resources. They are able to operate in a degraded mode (reduced feature set or performance) when those resources @@ -285,4 +321,4 @@ API === .. kernel-doc:: drivers/base/core.c - :functions: device_link_add device_link_del + :functions: device_link_add device_link_del device_link_remove diff --git a/MAINTAINERS b/MAINTAINERS index 8c68de3cfd80..9919840d54cd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2848,6 +2848,9 @@ F: include/uapi/linux/if_bonding.h BPF (Safe dynamic programs and tools) M: Alexei Starovoitov <ast@kernel.org> M: Daniel Borkmann <daniel@iogearbox.net> +R: Martin KaFai Lau <kafai@fb.com> +R: Song Liu <songliubraving@fb.com> +R: Yonghong Song <yhs@fb.com> L: netdev@vger.kernel.org L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git @@ -2873,6 +2876,8 @@ F: samples/bpf/ F: tools/bpf/ F: tools/lib/bpf/ F: tools/testing/selftests/bpf/ +K: bpf +N: bpf BPF JIT for ARM M: Shubham Bansal <illusionist.neo@gmail.com> @@ -5181,7 +5186,7 @@ DRM DRIVERS FOR XEN M: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> T: git git://anongit.freedesktop.org/drm/drm-misc L: dri-devel@lists.freedesktop.org -L: xen-devel@lists.xen.org +L: xen-devel@lists.xenproject.org (moderated for non-subscribers) S: Supported F: drivers/gpu/drm/xen/ F: Documentation/gpu/xen-front.rst @@ -11307,10 +11312,12 @@ F: include/dt-bindings/ OPENCORES I2C BUS DRIVER M: Peter Korsgaard <peter@korsgaard.com> +M: Andrew Lunn <andrew@lunn.ch> L: linux-i2c@vger.kernel.org S: Maintained F: Documentation/i2c/busses/i2c-ocores F: drivers/i2c/busses/i2c-ocores.c +F: include/linux/platform_data/i2c-ocores.h OPENRISC ARCHITECTURE M: Jonas Bonn <jonas@southpole.se> @@ -12868,6 +12875,13 @@ F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt F: drivers/net/dsa/realtek-smi* F: drivers/net/dsa/rtl83* +REDPINE WIRELESS DRIVER +M: Amitkumar Karwar <amitkarwar@gmail.com> +M: Siva Rebbagondla <siva8118@gmail.com> +L: linux-wireless@vger.kernel.org +S: Maintained +F: drivers/net/wireless/rsi/ + REGISTER MAP ABSTRACTION M: Mark Brown <broonie@kernel.org> L: linux-kernel@vger.kernel.org @@ -13696,6 +13710,15 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ +SFF/SFP/SFP+ MODULE SUPPORT +M: Russell King <linux@armlinux.org.uk> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/phy/phylink.c +F: drivers/net/phy/sfp* +F: include/linux/phylink.h +F: include/linux/sfp.h + SGI GRU DRIVER M: Dimitri Sivanich <sivanich@sgi.com> S: Maintained @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Shy Crocodile # *DOCUMENTATION* @@ -583,7 +583,7 @@ export KBUILD_MODULES KBUILD_BUILTIN ifeq ($(KBUILD_EXTMOD),) # Objects we will link into vmlinux / subdirs we need to visit init-y := init/ -drivers-y := drivers/ sound/ firmware/ +drivers-y := drivers/ sound/ net-y := net/ libs-y := lib/ core-y := usr/ diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts index d0fd68873689..5b250060f6dd 100644 --- a/arch/arm/boot/dts/am335x-shc.dts +++ b/arch/arm/boot/dts/am335x-shc.dts @@ -215,7 +215,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; bus-width = <0x4>; - cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; + cd-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; cd-inverted; max-frequency = <26000000>; vmmc-supply = <&vmmcsd_fixed>; diff --git a/arch/arm/boot/dts/da850.dtsi b/arch/arm/boot/dts/da850.dtsi index 47aa53ba6b92..559659b399d0 100644 --- a/arch/arm/boot/dts/da850.dtsi +++ b/arch/arm/boot/dts/da850.dtsi @@ -476,7 +476,7 @@ clocksource: timer@20000 { compatible = "ti,da830-timer"; reg = <0x20000 0x1000>; - interrupts = <12>, <13>; + interrupts = <21>, <22>; interrupt-names = "tint12", "tint34"; clocks = <&pll0_auxclk>; }; diff --git a/arch/arm/boot/dts/imx6q-pistachio.dts b/arch/arm/boot/dts/imx6q-pistachio.dts index 5edf858c8b86..a31b17eaf51c 100644 --- a/arch/arm/boot/dts/imx6q-pistachio.dts +++ b/arch/arm/boot/dts/imx6q-pistachio.dts @@ -103,7 +103,7 @@ power { label = "Power Button"; gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; - gpio-key,wakeup; + wakeup-source; linux,code = <KEY_POWER>; }; }; diff --git a/arch/arm/boot/dts/imx6sll-evk.dts b/arch/arm/boot/dts/imx6sll-evk.dts index d8163705363e..4a31a415f88e 100644 --- a/arch/arm/boot/dts/imx6sll-evk.dts +++ b/arch/arm/boot/dts/imx6sll-evk.dts @@ -309,7 +309,7 @@ pinctrl-2 = <&pinctrl_usdhc3_200mhz>; cd-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>; keep-power-in-suspend; - enable-sdio-wakeup; + wakeup-source; vmmc-supply = <®_sd3_vmmc>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 272ff6133ec1..d1375d3650fd 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -467,7 +467,7 @@ }; gpt: gpt@2098000 { - compatible = "fsl,imx6sx-gpt", "fsl,imx31-gpt"; + compatible = "fsl,imx6sx-gpt", "fsl,imx6dl-gpt"; reg = <0x02098000 0x4000>; interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SX_CLK_GPT_BUS>, diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index e4645f612712..2ab74860d962 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -274,7 +274,7 @@ compatible = "amlogic,meson6-dwmac", "snps,dwmac"; reg = <0xc9410000 0x10000 0xc1108108 0x4>; - interrupts = <GIC_SPI 8 IRQ_TYPE_EDGE_RISING>; + interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/meson8b-ec100.dts b/arch/arm/boot/dts/meson8b-ec100.dts index 0872f6e3abf5..d50fc2f60fa3 100644 --- a/arch/arm/boot/dts/meson8b-ec100.dts +++ b/arch/arm/boot/dts/meson8b-ec100.dts @@ -205,8 +205,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm/boot/dts/meson8b-odroidc1.dts b/arch/arm/boot/dts/meson8b-odroidc1.dts index 58669abda259..0f0a46ddf3ff 100644 --- a/arch/arm/boot/dts/meson8b-odroidc1.dts +++ b/arch/arm/boot/dts/meson8b-odroidc1.dts @@ -221,7 +221,6 @@ /* Realtek RTL8211F (0x001cc916) */ eth_phy: ethernet-phy@0 { reg = <0>; - eee-broken-1000t; interrupt-parent = <&gpio_intc>; /* GPIOH_3 */ interrupts = <17 IRQ_TYPE_LEVEL_LOW>; @@ -273,8 +272,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&tflash_vdd>; vqmmc-supply = <&tf_io>; diff --git a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts index f5853610b20b..6ac02beb5fa7 100644 --- a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts +++ b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts @@ -206,8 +206,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index ddc7a7bb33c0..f57acf8f66b9 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -105,7 +105,7 @@ interrupts-extended = < &cpcap 15 0 &cpcap 14 0 &cpcap 28 0 &cpcap 19 0 &cpcap 18 0 &cpcap 17 0 &cpcap 16 0 &cpcap 49 0 - &cpcap 48 1 + &cpcap 48 0 >; interrupt-names = "id_ground", "id_float", "se0conn", "vbusvld", diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index e53d32691308..93b420934e8e 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -714,11 +714,7 @@ vdda-supply = <&vdac>; - #address-cells = <1>; - #size-cells = <0>; - port { - reg = <0>; venc_out: endpoint { remote-endpoint = <&opa_in>; ti,channels = <1>; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 182a53991c90..826920e6b878 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -814,7 +814,7 @@ /* For debugging, it is often good idea to remove this GPIO. It means you can remove back cover (to reboot by removing battery) and still use the MMC card. */ - cd-gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>; /* 160 */ + cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */ }; /* most boards use vaux3, only some old versions use vmmc2 instead */ diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index 0d9b85317529..e142e6c70a59 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -370,6 +370,19 @@ compatible = "ti,omap2-onenand"; reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */ + /* + * These timings are based on CONFIG_OMAP_GPMC_DEBUG=y reported + * bootloader set values when booted with v4.19 using both N950 + * and N9 devices (OneNAND Manufacturer: Samsung): + * + * gpmc cs0 before gpmc_cs_program_settings: + * cs0 GPMC_CS_CONFIG1: 0xfd001202 + * cs0 GPMC_CS_CONFIG2: 0x00181800 + * cs0 GPMC_CS_CONFIG3: 0x00030300 + * cs0 GPMC_CS_CONFIG4: 0x18001804 + * cs0 GPMC_CS_CONFIG5: 0x03171d1d + * cs0 GPMC_CS_CONFIG6: 0x97080000 + */ gpmc,sync-read; gpmc,sync-write; gpmc,burst-length = <16>; @@ -379,26 +392,27 @@ gpmc,device-width = <2>; gpmc,mux-add-data = <2>; gpmc,cs-on-ns = <0>; - gpmc,cs-rd-off-ns = <87>; - gpmc,cs-wr-off-ns = <87>; + gpmc,cs-rd-off-ns = <122>; + gpmc,cs-wr-off-ns = <122>; gpmc,adv-on-ns = <0>; - gpmc,adv-rd-off-ns = <10>; - gpmc,adv-wr-off-ns = <10>; - gpmc,oe-on-ns = <15>; - gpmc,oe-off-ns = <87>; + gpmc,adv-rd-off-ns = <15>; + gpmc,adv-wr-off-ns = <15>; + gpmc,oe-on-ns = <20>; + gpmc,oe-off-ns = <122>; gpmc,we-on-ns = <0>; - gpmc,we-off-ns = <87>; - gpmc,rd-cycle-ns = <112>; - gpmc,wr-cycle-ns = <112>; - gpmc,access-ns = <81>; + gpmc,we-off-ns = <122>; + gpmc,rd-cycle-ns = <148>; + gpmc,wr-cycle-ns = <148>; + gpmc,access-ns = <117>; gpmc,page-burst-access-ns = <15>; gpmc,bus-turnaround-ns = <0>; gpmc,cycle2cycle-delay-ns = <0>; gpmc,wait-monitoring-ns = <0>; - gpmc,clk-activation-ns = <5>; - gpmc,wr-data-mux-bus-ns = <30>; - gpmc,wr-access-ns = <81>; - gpmc,sync-clk-ps = <15000>; + gpmc,clk-activation-ns = <10>; + gpmc,wr-data-mux-bus-ns = <40>; + gpmc,wr-access-ns = <117>; + + gpmc,sync-clk-ps = <15000>; /* TBC; Where this value came? */ /* * MTD partition table corresponding to Nokia's MeeGo 1.2 diff --git a/arch/arm/boot/dts/omap5-l4.dtsi b/arch/arm/boot/dts/omap5-l4.dtsi index 9c7e309d9c2c..0960348002ad 100644 --- a/arch/arm/boot/dts/omap5-l4.dtsi +++ b/arch/arm/boot/dts/omap5-l4.dtsi @@ -1046,8 +1046,6 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; ti,syss-mask = <1>; - ti,no-reset-on-init; - ti,no-idle-on-init; /* Domains (V, P, C): core, core_pwrdm, l4per_clkdm */ clocks = <&l4per_clkctrl OMAP5_UART3_CLKCTRL 0>; clock-names = "fck"; diff --git a/arch/arm/boot/dts/r8a7743.dtsi b/arch/arm/boot/dts/r8a7743.dtsi index 3cc33f7ff7fe..3adc158a40bb 100644 --- a/arch/arm/boot/dts/r8a7743.dtsi +++ b/arch/arm/boot/dts/r8a7743.dtsi @@ -1681,15 +1681,12 @@ du: display@feb00000 { compatible = "renesas,du-r8a7743"; - reg = <0 0xfeb00000 0 0x40000>, - <0 0xfeb90000 0 0x1c>; - reg-names = "du", "lvds.0"; + reg = <0 0xfeb00000 0 0x40000>; interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cpg CPG_MOD 724>, - <&cpg CPG_MOD 723>, - <&cpg CPG_MOD 726>; - clock-names = "du.0", "du.1", "lvds.0"; + <&cpg CPG_MOD 723>; + clock-names = "du.0", "du.1"; status = "disabled"; ports { @@ -1704,6 +1701,33 @@ port@1 { reg = <1>; du_out_lvds0: endpoint { + remote-endpoint = <&lvds0_in>; + }; + }; + }; + }; + + lvds0: lvds@feb90000 { + compatible = "renesas,r8a7743-lvds"; + reg = <0 0xfeb90000 0 0x1c>; + clocks = <&cpg CPG_MOD 726>; + power-domains = <&sysc R8A7743_PD_ALWAYS_ON>; + resets = <&cpg 726>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + lvds0_in: endpoint { + remote-endpoint = <&du_out_lvds0>; + }; + }; + port@1 { + reg = <1>; + lvds0_out: endpoint { }; }; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index 353d90f99b40..13304b8c5139 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -216,6 +216,7 @@ #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <24000000>; + clock-output-names = "osc24M"; }; osc32k: clk-32k { diff --git a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts index 5d23667dc2d2..25540b7694d5 100644 --- a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts +++ b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts @@ -53,7 +53,7 @@ aliases { serial0 = &uart0; - /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */ + ethernet0 = &emac; ethernet1 = &sdiowifi; }; diff --git a/arch/arm/boot/dts/vf610-bk4.dts b/arch/arm/boot/dts/vf610-bk4.dts index 689c8930dce3..b08d561d6748 100644 --- a/arch/arm/boot/dts/vf610-bk4.dts +++ b/arch/arm/boot/dts/vf610-bk4.dts @@ -110,11 +110,11 @@ bus-num = <3>; status = "okay"; spi-slave; + #address-cells = <0>; - slave@0 { + slave { compatible = "lwn,bk4"; spi-max-frequency = <30000000>; - reg = <0>; }; }; diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c index 3b73813c6b04..23e8c93515d4 100644 --- a/arch/arm/mach-iop32x/n2100.c +++ b/arch/arm/mach-iop32x/n2100.c @@ -75,8 +75,7 @@ void __init n2100_map_io(void) /* * N2100 PCI. */ -static int __init -n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { int irq; diff --git a/arch/arm/mach-tango/pm.c b/arch/arm/mach-tango/pm.c index 028e50c6383f..a32c3b631484 100644 --- a/arch/arm/mach-tango/pm.c +++ b/arch/arm/mach-tango/pm.c @@ -3,6 +3,7 @@ #include <linux/suspend.h> #include <asm/suspend.h> #include "smc.h" +#include "pm.h" static int tango_pm_powerdown(unsigned long arg) { @@ -24,10 +25,7 @@ static const struct platform_suspend_ops tango_pm_ops = { .valid = suspend_valid_only_mem, }; -static int __init tango_pm_init(void) +void __init tango_pm_init(void) { suspend_set_ops(&tango_pm_ops); - return 0; } - -late_initcall(tango_pm_init); diff --git a/arch/arm/mach-tango/pm.h b/arch/arm/mach-tango/pm.h new file mode 100644 index 000000000000..35ea705a0ee2 --- /dev/null +++ b/arch/arm/mach-tango/pm.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifdef CONFIG_SUSPEND +void __init tango_pm_init(void); +#else +#define tango_pm_init NULL +#endif diff --git a/arch/arm/mach-tango/setup.c b/arch/arm/mach-tango/setup.c index 677dd7b5efd9..824f90737b04 100644 --- a/arch/arm/mach-tango/setup.c +++ b/arch/arm/mach-tango/setup.c @@ -2,6 +2,7 @@ #include <asm/mach/arch.h> #include <asm/hardware/cache-l2x0.h> #include "smc.h" +#include "pm.h" static void tango_l2c_write(unsigned long val, unsigned int reg) { @@ -15,4 +16,5 @@ DT_MACHINE_START(TANGO_DT, "Sigma Tango DT") .dt_compat = tango_dt_compat, .l2c_aux_mask = ~0, .l2c_write_sec = tango_l2c_write, + .init_late = tango_pm_init, MACHINE_END diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index ed36dcab80f1..f51919974183 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -190,8 +190,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) if (ssp == NULL) return -ENODEV; - iounmap(ssp->mmio_base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); @@ -201,7 +199,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) list_del(&ssp->node); mutex_unlock(&ssp_lock); - kfree(ssp); return 0; } diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index cb44aa290e73..e1d44b903dfc 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -7,7 +7,6 @@ #include <linux/of_address.h> #include <linux/slab.h> #include <linux/types.h> -#include <linux/dma-mapping.h> #include <linux/vmalloc.h> #include <linux/swiotlb.h> diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index b0c64f75792c..8974b5a1d3b1 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -188,6 +188,7 @@ reg = <0x3a3>; interrupt-parent = <&r_intc>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + x-powers,drive-vbus-en; /* set N_VBUSEN as output pin */ }; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 837a03dee875..2abb335145a6 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -390,7 +390,7 @@ }; video-codec@1c0e000 { - compatible = "allwinner,sun50i-h5-video-engine"; + compatible = "allwinner,sun50i-a64-video-engine"; reg = <0x01c0e000 0x1000>; clocks = <&ccu CLK_BUS_VE>, <&ccu CLK_VE>, <&ccu CLK_DRAM_VE>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index e14e0ce7e89f..016641a41694 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -187,8 +187,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 8cd50b75171d..ade2ee09ae96 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -305,8 +305,7 @@ max-frequency = <200000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddio_ao3v3>; vqmmc-supply = <&vddio_tf>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index 4cf7f6e80c6a..25105ac96d55 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 2e1cd5e3a246..1cc9dc68ef00 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -258,8 +258,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&tflash_vdd>; vqmmc-supply = <&tf_io>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index ce862266b9aa..0be0f2a5d2fe 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -196,8 +196,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index 93a4acf2c46c..ad4d50bd9d77 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -154,8 +154,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi index ec09bb5792b7..2d2db783c44c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi @@ -211,8 +211,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vcc_3v3>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts index f1c410e2da2b..796baea7a0bf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts @@ -131,8 +131,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index db293440e4ca..255cede7b447 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; vqmmc-supply = <&vcc_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 6739697be1de..9cbdb85fb591 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -183,8 +183,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index a1b31013ab6e..bc811a2faf42 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -137,8 +137,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index 3c3a667a8df8..3f086ed7de05 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -356,8 +356,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index f7a1cffab4a8..8acfd40090d2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -147,8 +147,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts index 7212dc4531e4..7fa20a8ede17 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts @@ -170,8 +170,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 99b7495455a6..838e32cc14c9 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -404,7 +404,7 @@ }; intc: interrupt-controller@9bc0000 { - compatible = "arm,gic-v3"; + compatible = "qcom,msm8996-gic-v3", "arm,gic-v3"; #interrupt-cells = <3>; interrupt-controller; #redistributor-regions = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi index 20745a8528c5..719ed9d9067d 100644 --- a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi @@ -1011,6 +1011,9 @@ <&cpg CPG_CORE R8A774A1_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi index afedbf5728ec..0648d12778ed 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi @@ -1262,6 +1262,9 @@ <&cpg CPG_CORE R8A7796_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a77965.dtsi b/arch/arm64/boot/dts/renesas/r8a77965.dtsi index 6dc9b1fef830..4b3730f640ef 100644 --- a/arch/arm64/boot/dts/renesas/r8a77965.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77965.dtsi @@ -1068,6 +1068,9 @@ <&cpg CPG_CORE R8A77965_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A77965_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index f2c211a6229b..58871333737a 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -120,10 +120,12 @@ static int create_dtb(struct kimage *image, { void *buf; size_t buf_size; + size_t cmdline_len; int ret; + cmdline_len = cmdline ? strlen(cmdline) : 0; buf_size = fdt_totalsize(initial_boot_params) - + strlen(cmdline) + DTB_EXTRA_SPACE; + + cmdline_len + DTB_EXTRA_SPACE; for (;;) { buf = vmalloc(buf_size); diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index fcb1f2a6d7c6..99bb8facb5cb 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,74 +286,73 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start, + unsigned long end) { - pte_t *ptep = pte_offset_kernel(pmdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long addr = start; + pte_t *ptep = pte_offset_kernel(pmdp, start); - for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { - addr = start + i * PAGE_SIZE; + do { note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); - } + } while (ptep++, addr += PAGE_SIZE, addr != end); } -static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start, + unsigned long end) { - pmd_t *pmdp = pmd_offset(pudp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pmd_t *pmdp = pmd_offset(pudp, start); - for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + do { pmd_t pmd = READ_ONCE(*pmdp); + next = pmd_addr_end(addr, end); - addr = start + i * PMD_SIZE; if (pmd_none(pmd) || pmd_sect(pmd)) { note_page(st, addr, 3, pmd_val(pmd)); } else { BUG_ON(pmd_bad(pmd)); - walk_pte(st, pmdp, addr); + walk_pte(st, pmdp, addr, next); } - } + } while (pmdp++, addr = next, addr != end); } -static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start, + unsigned long end) { - pud_t *pudp = pud_offset(pgdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pud_t *pudp = pud_offset(pgdp, start); - for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + do { pud_t pud = READ_ONCE(*pudp); + next = pud_addr_end(addr, end); - addr = start + i * PUD_SIZE; if (pud_none(pud) || pud_sect(pud)) { note_page(st, addr, 2, pud_val(pud)); } else { BUG_ON(pud_bad(pud)); - walk_pmd(st, pudp, addr); + walk_pmd(st, pudp, addr, next); } - } + } while (pudp++, addr = next, addr != end); } static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgdp = pgd_offset(mm, 0UL); - unsigned i; - unsigned long addr; + unsigned long end = (start < TASK_SIZE_64) ? TASK_SIZE_64 : 0; + unsigned long next, addr = start; + pgd_t *pgdp = pgd_offset(mm, start); - for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + do { pgd_t pgd = READ_ONCE(*pgdp); + next = pgd_addr_end(addr, end); - addr = start + i * PGDIR_SIZE; if (pgd_none(pgd)) { note_page(st, addr, 1, pgd_val(pgd)); } else { BUG_ON(pgd_bad(pgd)); - walk_pud(st, pgdp, addr); + walk_pud(st, pgdp, addr, next); } - } + } while (pgdp++, addr = next, addr != end); } void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info) diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index 38049357d6d3..40712e49381b 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -155,18 +155,22 @@ out: static int __init nfhd_init(void) { u32 blocks, bsize; + int ret; int i; nfhd_id = nf_get_id("XHDI"); if (!nfhd_id) return -ENODEV; - major_num = register_blkdev(major_num, "nfhd"); - if (major_num <= 0) { + ret = register_blkdev(major_num, "nfhd"); + if (ret < 0) { pr_warn("nfhd: unable to get major number\n"); - return major_num; + return ret; } + if (!major_num) + major_num = ret; + for (i = NFHD_DEV_OFFSET; i < 24; i++) { if (nfhd_get_capacity(i, 0, &blocks, &bsize)) continue; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0d14f51d0002..a84c24d894aa 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1403,6 +1403,21 @@ config LOONGSON3_ENHANCEMENT please say 'N' here. If you want a high-performance kernel to run on new Loongson 3 machines only, please say 'Y' here. +config CPU_LOONGSON3_WORKAROUNDS + bool "Old Loongson 3 LLSC Workarounds" + default y if SMP + depends on CPU_LOONGSON3 + help + Loongson 3 processors have the llsc issues which require workarounds. + Without workarounds the system may hang unexpectedly. + + Newer Loongson 3 will fix these issues and no workarounds are needed. + The workarounds have no significant side effect on them but may + decrease the performance of the system so this option should be + disabled unless the kernel is intended to be run on old systems. + + If unsure, please say Y. + config CPU_LOONGSON2E bool "Loongson 2E" depends on SYS_HAS_CPU_LOONGSON2E diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 50cff3cbcc6d..4f7b1fa31cf5 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -76,7 +76,7 @@ status = "okay"; pinctrl-names = "default"; - pinctrl-0 = <&pins_uart2>; + pinctrl-0 = <&pins_uart3>; }; &uart4 { @@ -196,9 +196,9 @@ bias-disable; }; - pins_uart2: uart2 { - function = "uart2"; - groups = "uart2-data", "uart2-hwflow"; + pins_uart3: uart3 { + function = "uart3"; + groups = "uart3-data", "uart3-hwflow"; bias-disable; }; diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 6fb16fd24035..2beb78a62b7d 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -161,7 +161,7 @@ #dma-cells = <2>; interrupt-parent = <&intc>; - interrupts = <29>; + interrupts = <20>; clocks = <&cgu JZ4740_CLK_DMA>; diff --git a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts index 2152b7ba65fb..cc8dbea0911f 100644 --- a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts +++ b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts @@ -90,11 +90,11 @@ interrupts = <0>; }; - axi_i2c: i2c@10A00000 { + axi_i2c: i2c@10a00000 { compatible = "xlnx,xps-iic-2.00.a"; interrupt-parent = <&axi_intc>; interrupts = <4>; - reg = < 0x10A00000 0x10000 >; + reg = < 0x10a00000 0x10000 >; clocks = <&ext>; xlnx,clk-freq = <0x5f5e100>; xlnx,family = "Artix7"; @@ -106,9 +106,9 @@ #address-cells = <1>; #size-cells = <0>; - ad7420@4B { + ad7420@4b { compatible = "adi,adt7420"; - reg = <0x4B>; + reg = <0x4b>; }; } ; }; diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 43fcd35e2957..94096299fc56 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -58,6 +58,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -85,6 +86,7 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -118,6 +120,7 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -256,6 +259,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -283,6 +287,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -316,6 +321,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h index a5eb1bb199a7..b7f6ac5e513c 100644 --- a/arch/mips/include/asm/barrier.h +++ b/arch/mips/include/asm/barrier.h @@ -222,6 +222,42 @@ #define __smp_mb__before_atomic() __smp_mb__before_llsc() #define __smp_mb__after_atomic() smp_llsc_mb() +/* + * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load, + * store or pref) in between an ll & sc can cause the sc instruction to + * erroneously succeed, breaking atomicity. Whilst it's unusual to write code + * containing such sequences, this bug bites harder than we might otherwise + * expect due to reordering & speculation: + * + * 1) A memory access appearing prior to the ll in program order may actually + * be executed after the ll - this is the reordering case. + * + * In order to avoid this we need to place a memory barrier (ie. a sync + * instruction) prior to every ll instruction, in between it & any earlier + * memory access instructions. Many of these cases are already covered by + * smp_mb__before_llsc() but for the remaining cases, typically ones in + * which multiple CPUs may operate on a memory location but ordering is not + * usually guaranteed, we use loongson_llsc_mb() below. + * + * This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later. + * + * 2) If a conditional branch exists between an ll & sc with a target outside + * of the ll-sc loop, for example an exit upon value mismatch in cmpxchg() + * or similar, then misprediction of the branch may allow speculative + * execution of memory accesses from outside of the ll-sc loop. + * + * In order to avoid this we need a memory barrier (ie. a sync instruction) + * at each affected branch target, for which we also use loongson_llsc_mb() + * defined below. + * + * This case affects all current Loongson 3 CPUs. + */ +#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */ +#define loongson_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory") +#else +#define loongson_llsc_mb() do { } while (0) +#endif + #include <asm-generic/barrier.h> #endif /* __ASM_BARRIER_H */ diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index c4675957b21b..830c93a010c3 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -69,6 +69,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) : "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m)); #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { + loongson_llsc_mb(); do { __asm__ __volatile__( " " __LL "%0, %1 # set_bit \n" @@ -79,6 +80,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) } while (unlikely(!temp)); #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ } else if (kernel_uses_llsc) { + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" @@ -123,6 +125,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) : "ir" (~(1UL << bit))); #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { + loongson_llsc_mb(); do { __asm__ __volatile__( " " __LL "%0, %1 # clear_bit \n" @@ -133,6 +136,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) } while (unlikely(!temp)); #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ } else if (kernel_uses_llsc) { + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" @@ -193,6 +197,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr) unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); unsigned long temp; + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index c14d798f3888..b83b0397462d 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -50,6 +50,7 @@ "i" (-EFAULT) \ : "memory"); \ } else if (cpu_has_llsc) { \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ @@ -163,6 +164,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, "i" (-EFAULT) : "memory"); } else if (cpu_has_llsc) { + loongson_llsc_mb(); __asm__ __volatile__( "# futex_atomic_cmpxchg_inatomic \n" " .set push \n" @@ -192,6 +194,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory"); + loongson_llsc_mb(); } else return -ENOSYS; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 57933fc8fd98..910851c62db3 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -228,6 +228,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) : [global] "r" (page_global)); } else if (kernel_uses_llsc) { + loongson_llsc_mb(); __asm__ __volatile__ ( " .set push \n" " .set "MIPS_ISA_ARCH_LEVEL" \n" @@ -242,6 +243,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) " .set pop \n" : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) : [global] "r" (page_global)); + loongson_llsc_mb(); } #else /* !CONFIG_SMP */ if (pte_none(*buddy)) diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 8f5bd04f320a..7f3f136572de 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -457,5 +457,5 @@ void mips_cm_error_report(void) } /* reprime cause register */ - write_gcr_error_cause(0); + write_gcr_error_cause(cm_error); } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 6829a064aac8..339870ed92f7 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -371,7 +371,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip, int *frame_size) static int get_frame_info(struct mips_frame_info *info) { bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS); - union mips_instruction insn, *ip, *ip_end; + union mips_instruction insn, *ip; const unsigned int max_insns = 128; unsigned int last_insn_size = 0; unsigned int i; @@ -384,10 +384,9 @@ static int get_frame_info(struct mips_frame_info *info) if (!ip) goto err; - ip_end = (void *)ip + info->func_size; - - for (i = 0; i < max_insns && ip < ip_end; i++) { + for (i = 0; i < max_insns; i++) { ip = (void *)ip + last_insn_size; + if (is_mmips && mm_insn_16bit(ip->halfword[0])) { insn.word = ip->halfword[0] << 16; last_insn_size = 2; diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index 0fce4608aa88..c1a4d4dc4665 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -23,6 +23,29 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS endif cflags-$(CONFIG_CPU_LOONGSON3) += -Wa,--trap + +# +# Some versions of binutils, not currently mainline as of 2019/02/04, support +# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction +# to work around a CPU bug (see loongson_llsc_mb() in asm/barrier.h for a +# description). +# +# We disable this in order to prevent the assembler meddling with the +# instruction that labels refer to, ie. if we label an ll instruction: +# +# 1: ll v0, 0(a0) +# +# ...then with the assembler fix applied the label may actually point at a sync +# instruction inserted by the assembler, and if we were using the label in an +# exception table the table would no longer contain the address of the ll +# instruction. +# +# Avoid this by explicitly disabling that assembler behaviour. If upstream +# binutils does not merge support for the flag then we can revisit & remove +# this later - for now it ensures vendor toolchains don't cause problems. +# +cflags-$(CONFIG_CPU_LOONGSON3) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,) + # # binutils from v2.25 on and gcc starting from v4.9.0 treat -march=loongson3a # as MIPS64 R2; older versions as just R1. This leaves the possibility open diff --git a/arch/mips/loongson64/common/reset.c b/arch/mips/loongson64/common/reset.c index a60715e11306..b26892ce871c 100644 --- a/arch/mips/loongson64/common/reset.c +++ b/arch/mips/loongson64/common/reset.c @@ -59,7 +59,12 @@ static void loongson_poweroff(void) { #ifndef CONFIG_LEFI_FIRMWARE_INTERFACE mach_prepare_shutdown(); - unreachable(); + + /* + * It needs a wait loop here, but mips/kernel/reset.c already calls + * a generic delay loop, machine_hang(), so simply return. + */ + return; #else void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr; diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 37b1cb246332..65b6e85447b1 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -932,6 +932,8 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, * to mimic that here by taking a load/istream page * fault. */ + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(p, 0); UASM_i_LA(p, ptr, (unsigned long)tlb_do_page_fault_0); uasm_i_jr(p, ptr); @@ -1646,6 +1648,8 @@ static void iPTE_LW(u32 **p, unsigned int pte, unsigned int ptr) { #ifdef CONFIG_SMP + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(p, 0); # ifdef CONFIG_PHYS_ADDR_T_64BIT if (cpu_has_64bits) uasm_i_lld(p, pte, 0, ptr); @@ -2259,6 +2263,8 @@ static void build_r4000_tlb_load_handler(void) #endif uasm_l_nopage_tlbl(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_0 & 1) { @@ -2313,6 +2319,8 @@ static void build_r4000_tlb_store_handler(void) #endif uasm_l_nopage_tlbs(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_1 & 1) { @@ -2368,6 +2376,8 @@ static void build_r4000_tlb_modify_handler(void) #endif uasm_l_nopage_tlbm(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_1 & 1) { diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c index 5017d5843c5a..fc29b85cfa92 100644 --- a/arch/mips/pci/pci-octeon.c +++ b/arch/mips/pci/pci-octeon.c @@ -568,6 +568,11 @@ static int __init octeon_pci_setup(void) if (octeon_has_feature(OCTEON_FEATURE_PCIE)) return 0; + if (!octeon_is_pci_host()) { + pr_notice("Not in host mode, PCI Controller not initialized\n"); + return 0; + } + /* Point pcibios_map_irq() to the PCI version of it */ octeon_pcibios_map_irq = octeon_pci_pcibios_map_irq; @@ -579,11 +584,6 @@ static int __init octeon_pci_setup(void) else octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG; - if (!octeon_is_pci_host()) { - pr_notice("Not in host mode, PCI Controller not initialized\n"); - return 0; - } - /* PCI I/O and PCI MEM values */ set_io_port_base(OCTEON_PCI_IOSPACE_BASE); ioport_resource.start = 0; diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index f6fd340e39c2..0ede4deb8181 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -8,6 +8,7 @@ ccflags-vdso := \ $(filter -E%,$(KBUILD_CFLAGS)) \ $(filter -mmicromips,$(KBUILD_CFLAGS)) \ $(filter -march=%,$(KBUILD_CFLAGS)) \ + $(filter -m%-float,$(KBUILD_CFLAGS)) \ -D__VDSO__ ifdef CONFIG_CC_IS_CLANG @@ -129,7 +130,7 @@ $(obj)/%-o32.o: $(src)/%.c FORCE $(call cmd,force_checksrc) $(call if_changed_rule,cc_o_c) -$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := -mabi=32 +$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=32 $(obj)/vdso-o32.lds: $(src)/vdso.lds.S FORCE $(call if_changed_dep,cpp_lds_S) @@ -169,7 +170,7 @@ $(obj)/%-n32.o: $(src)/%.c FORCE $(call cmd,force_checksrc) $(call if_changed_rule,cc_o_c) -$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := -mabi=n32 +$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=n32 $(obj)/vdso-n32.lds: $(src)/vdso.lds.S FORCE $(call if_changed_dep,cpp_lds_S) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2e6ada28da64..c9bfe526ca9d 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1258,21 +1258,13 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; -static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, - struct spinlock *old_pmd_ptl, - struct vm_area_struct *vma) -{ - if (radix_enabled()) - return false; - /* - * Archs like ppc64 use pgtable to store per pmd - * specific information. So when we switch the pmd, - * we should also withdraw and deposit the pgtable - */ - return true; -} - - +extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma); +/* + * Hash translation mode use the deposited table to store hash pte + * slot information. + */ #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit static inline bool arch_needs_pgtable_deposit(void) { diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index f3c31f5e1026..ecd31569a120 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -400,3 +400,25 @@ void arch_report_meminfo(struct seq_file *m) atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20); } #endif /* CONFIG_PROC_FS */ + +/* + * For hash translation mode, we use the deposited table to store hash slot + * information and they are stored at PTRS_PER_PMD offset from related pmd + * location. Hence a pmd move requires deposit and withdraw. + * + * For radix translation with split pmd ptl, we store the deposited table in the + * pmd page. Hence if we have different pmd page we need to withdraw during pmd + * move. + * + * With hash we use deposited table always irrespective of anon or not. + * With radix we use deposited table only for anonymous mapping. + */ +int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma) +{ + if (radix_enabled()) + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); + + return true; +} diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 5b4a56131904..84e8ec4011ba 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -261,8 +261,7 @@ static char *ibmebus_chomp(const char *in, size_t count) return out; } -static ssize_t ibmebus_store_probe(struct bus_type *bus, - const char *buf, size_t count) +static ssize_t probe_store(struct bus_type *bus, const char *buf, size_t count) { struct device_node *dn = NULL; struct device *dev; @@ -298,10 +297,9 @@ out: return rc; return count; } -static BUS_ATTR(probe, 0200, NULL, ibmebus_store_probe); +static BUS_ATTR_WO(probe); -static ssize_t ibmebus_store_remove(struct bus_type *bus, - const char *buf, size_t count) +static ssize_t remove_store(struct bus_type *bus, const char *buf, size_t count) { struct device *dev; char *path; @@ -325,7 +323,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus, return -ENODEV; } } -static BUS_ATTR(remove, 0200, NULL, ibmebus_store_remove); +static BUS_ATTR_WO(remove); static struct attribute *ibmbus_bus_attrs[] = { &bus_attr_probe.attr, diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 7d6457ab5d34..bba281b1fe1b 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -43,6 +43,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; uint64_t rc, token; + uint64_t saved = 0; /* * When the hypervisor cannot map all the requested memory in a single @@ -56,6 +57,8 @@ static int drc_pmem_bind(struct papr_scm_priv *p) rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0, p->blocks, BIND_ANY_ADDR, token); token = ret[0]; + if (!saved) + saved = ret[1]; cond_resched(); } while (rc == H_BUSY); @@ -64,7 +67,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) return -ENXIO; } - p->bound_addr = ret[1]; + p->bound_addr = saved; dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res); diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index f105ae8651c9..f62e347862cc 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -602,10 +602,12 @@ ENTRY(trampoline_32bit_src) 3: /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ pushl %ecx + pushl %edx movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax wrmsr + popl %edx popl %ecx /* Enable PAE and LA57 (if required) paging modes */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 40e12cfc87f6..daafb893449b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3559,6 +3559,14 @@ static void free_excl_cntrs(int cpu) static void intel_pmu_cpu_dying(int cpu) { + fini_debug_store_on_cpu(cpu); + + if (x86_pmu.counter_freezing) + disable_counter_freeze(); +} + +static void intel_pmu_cpu_dead(int cpu) +{ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_shared_regs *pc; @@ -3570,11 +3578,6 @@ static void intel_pmu_cpu_dying(int cpu) } free_excl_cntrs(cpu); - - fini_debug_store_on_cpu(cpu); - - if (x86_pmu.counter_freezing) - disable_counter_freeze(); } static void intel_pmu_sched_task(struct perf_event_context *ctx, @@ -3663,6 +3666,7 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, }; static struct attribute *intel_pmu_attrs[]; @@ -3703,6 +3707,8 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, + .guest_get_msrs = intel_guest_get_msrs, .sched_task = intel_pmu_sched_task, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index c07bee31abe8..b10e04387f38 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1222,6 +1222,8 @@ static struct pci_driver snbep_uncore_pci_driver = { .id_table = snbep_uncore_pci_ids, }; +#define NODE_ID_MASK 0x7 + /* * build pci bus to socket mapping */ @@ -1243,7 +1245,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); if (err) break; - nodeid = config; + nodeid = config & NODE_ID_MASK; /* get the Node ID mapping */ err = pci_read_config_dword(ubox_dev, idmap_loc, &config); if (err) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 40616e805292..2779ace16d23 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1065,7 +1065,7 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - native_set_pmd(pmdp, pmd); + set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 672c7225cb1b..6ce290c506d9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -784,6 +784,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 8ff20523661b..d8ea4ebd79e7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -211,6 +211,7 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; + hrtimer_cancel(&vmx->nested.preemption_timer); vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3d27206f6c01..e67ecf25e690 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5116,6 +5116,13 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, { u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + /* + * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 4f8972311a77..14e6119838a6 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -230,6 +230,29 @@ static bool __cpa_pfn_in_highmap(unsigned long pfn) #endif +/* + * See set_mce_nospec(). + * + * Machine check recovery code needs to change cache mode of poisoned pages to + * UC to avoid speculative access logging another error. But passing the + * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a + * speculative access. So we cheat and flip the top bit of the address. This + * works fine for the code that updates the page tables. But at the end of the + * process we need to flush the TLB and cache and the non-canonical address + * causes a #GP fault when used by the INVLPG and CLFLUSH instructions. + * + * But in the common case we already have a canonical address. This code + * will fix the top bit if needed and is a no-op otherwise. + */ +static inline unsigned long fix_addr(unsigned long addr) +{ +#ifdef CONFIG_X86_64 + return (long)(addr << 1) >> 1; +#else + return addr; +#endif +} + static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx) { if (cpa->flags & CPA_PAGES_ARRAY) { @@ -313,7 +336,7 @@ void __cpa_flush_tlb(void *data) unsigned int i; for (i = 0; i < cpa->numpages; i++) - __flush_tlb_one_kernel(__cpa_addr(cpa, i)); + __flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i))); } static void cpa_flush(struct cpa_data *data, int cache) @@ -347,7 +370,7 @@ static void cpa_flush(struct cpa_data *data, int cache) * Only flush present addresses: */ if (pte && (pte_val(*pte) & _PAGE_PRESENT)) - clflush_cache_range_opt((void *)addr, PAGE_SIZE); + clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE); } mb(); } @@ -1627,29 +1650,6 @@ out: return ret; } -/* - * Machine check recovery code needs to change cache mode of poisoned - * pages to UC to avoid speculative access logging another error. But - * passing the address of the 1:1 mapping to set_memory_uc() is a fine - * way to encourage a speculative access. So we cheat and flip the top - * bit of the address. This works fine for the code that updates the - * page tables. But at the end of the process we need to flush the cache - * and the non-canonical address causes a #GP fault when used by the - * CLFLUSH instruction. - * - * But in the common case we already have a canonical address. This code - * will fix the top bit if needed and is a no-op otherwise. - */ -static inline unsigned long make_addr_canonical_again(unsigned long addr) -{ -#ifdef CONFIG_X86_64 - return (long)(addr << 1) >> 1; -#else - return addr; -#endif -} - - static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, int force_split, int in_flag, diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index fc714ef402a6..2620baa1f699 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -72,6 +72,7 @@ #include <linux/sched/loadavg.h> #include <linux/sched/signal.h> #include <trace/events/block.h> +#include <linux/blk-mq.h> #include "blk-rq-qos.h" #include "blk-stat.h" @@ -591,6 +592,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) u64 now = ktime_to_ns(ktime_get()); bool issue_as_root = bio_issue_as_root_blkg(bio); bool enabled = false; + int inflight = 0; blkg = bio->bi_blkg; if (!blkg || !bio_flagged(bio, BIO_TRACKED)) @@ -601,6 +603,9 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) return; enabled = blk_iolatency_enabled(iolat->blkiolat); + if (!enabled) + return; + while (blkg && blkg->parent) { iolat = blkg_to_lat(blkg); if (!iolat) { @@ -609,8 +614,9 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) } rqw = &iolat->rq_wait; - atomic_dec(&rqw->inflight); - if (!enabled || iolat->min_lat_nsec == 0) + inflight = atomic_dec_return(&rqw->inflight); + WARN_ON_ONCE(inflight < 0); + if (iolat->min_lat_nsec == 0) goto next; iolatency_record_time(iolat, &bio->bi_issue, now, issue_as_root); @@ -754,10 +760,13 @@ int blk_iolatency_init(struct request_queue *q) return 0; } -static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) +/* + * return 1 for enabling iolatency, return -1 for disabling iolatency, otherwise + * return 0. + */ +static int iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) { struct iolatency_grp *iolat = blkg_to_lat(blkg); - struct blk_iolatency *blkiolat = iolat->blkiolat; u64 oldval = iolat->min_lat_nsec; iolat->min_lat_nsec = val; @@ -766,9 +775,10 @@ static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) BLKIOLATENCY_MAX_WIN_SIZE); if (!oldval && val) - atomic_inc(&blkiolat->enabled); + return 1; if (oldval && !val) - atomic_dec(&blkiolat->enabled); + return -1; + return 0; } static void iolatency_clear_scaling(struct blkcg_gq *blkg) @@ -800,6 +810,7 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, u64 lat_val = 0; u64 oldval; int ret; + int enable = 0; ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx); if (ret) @@ -834,7 +845,12 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, blkg = ctx.blkg; oldval = iolat->min_lat_nsec; - iolatency_set_min_lat_nsec(blkg, lat_val); + enable = iolatency_set_min_lat_nsec(blkg, lat_val); + if (enable) { + WARN_ON_ONCE(!blk_get_queue(blkg->q)); + blkg_get(blkg); + } + if (oldval != iolat->min_lat_nsec) { iolatency_clear_scaling(blkg); } @@ -842,6 +858,24 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, ret = 0; out: blkg_conf_finish(&ctx); + if (ret == 0 && enable) { + struct iolatency_grp *tmp = blkg_to_lat(blkg); + struct blk_iolatency *blkiolat = tmp->blkiolat; + + blk_mq_freeze_queue(blkg->q); + + if (enable == 1) + atomic_inc(&blkiolat->enabled); + else if (enable == -1) + atomic_dec(&blkiolat->enabled); + else + WARN_ON_ONCE(1); + + blk_mq_unfreeze_queue(blkg->q); + + blkg_put(blkg); + blk_put_queue(blkg->q); + } return ret ?: nbytes; } @@ -977,8 +1011,14 @@ static void iolatency_pd_offline(struct blkg_policy_data *pd) { struct iolatency_grp *iolat = pd_to_lat(pd); struct blkcg_gq *blkg = lat_to_blkg(iolat); + struct blk_iolatency *blkiolat = iolat->blkiolat; + int ret; - iolatency_set_min_lat_nsec(blkg, 0); + ret = iolatency_set_min_lat_nsec(blkg, 0); + if (ret == 1) + atomic_inc(&blkiolat->enabled); + if (ret == -1) + atomic_dec(&blkiolat->enabled); iolatency_clear_scaling(blkg); } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index f8120832ca7b..7921573aebbc 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -839,6 +839,9 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { static bool debugfs_create_files(struct dentry *parent, void *data, const struct blk_mq_debugfs_attr *attr) { + if (IS_ERR_OR_NULL(parent)) + return false; + d_inode(parent)->i_private = data; for (; attr->name; attr++) { diff --git a/block/blk-mq.h b/block/blk-mq.h index d943d46b0785..d0b3dd54ef8d 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -36,7 +36,6 @@ struct blk_mq_ctx { struct kobject kobj; } ____cacheline_aligned_in_smp; -void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 5c093ce01bcd..147f6c7ea59c 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1029,6 +1029,9 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; + /* Initialize debug output. Linux does not use ACPICA defaults */ + acpi_dbg_level = ACPI_LV_INFO | ACPI_LV_REPAIR; + #ifdef CONFIG_X86 /* * If the machine falls into the DMI check table, diff --git a/drivers/android/binder.c b/drivers/android/binder.c index cdfc87629efb..4d2b2ad1ee0e 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5854,9 +5854,10 @@ static int __init init_binder_device(const char *name) static int __init binder_init(void) { int ret; - char *device_name, *device_names, *device_tmp; + char *device_name, *device_tmp; struct binder_device *device; struct hlist_node *tmp; + char *device_names = NULL; ret = binder_alloc_shrinker_init(); if (ret) @@ -5898,23 +5899,29 @@ static int __init binder_init(void) &transaction_log_fops); } - /* - * Copy the module_parameter string, because we don't want to - * tokenize it in-place. - */ - device_names = kstrdup(binder_devices_param, GFP_KERNEL); - if (!device_names) { - ret = -ENOMEM; - goto err_alloc_device_names_failed; - } + if (strcmp(binder_devices_param, "") != 0) { + /* + * Copy the module_parameter string, because we don't want to + * tokenize it in-place. + */ + device_names = kstrdup(binder_devices_param, GFP_KERNEL); + if (!device_names) { + ret = -ENOMEM; + goto err_alloc_device_names_failed; + } - device_tmp = device_names; - while ((device_name = strsep(&device_tmp, ","))) { - ret = init_binder_device(device_name); - if (ret) - goto err_init_binder_device_failed; + device_tmp = device_names; + while ((device_name = strsep(&device_tmp, ","))) { + ret = init_binder_device(device_name); + if (ret) + goto err_init_binder_device_failed; + } } + ret = init_binderfs(); + if (ret) + goto err_init_binder_device_failed; + return ret; err_init_binder_device_failed: diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 7fb97f503ef2..045b3e42d98b 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -46,4 +46,13 @@ static inline bool is_binderfs_device(const struct inode *inode) } #endif +#ifdef CONFIG_ANDROID_BINDERFS +extern int __init init_binderfs(void); +#else +static inline int __init init_binderfs(void) +{ + return 0; +} +#endif + #endif /* _LINUX_BINDER_INTERNAL_H */ diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 6a2185eb66c5..e773f45d19d9 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -395,6 +395,11 @@ static int binderfs_binder_ctl_create(struct super_block *sb) struct inode *inode = NULL; struct dentry *root = sb->s_root; struct binderfs_info *info = sb->s_fs_info; +#if defined(CONFIG_IPC_NS) + bool use_reserve = (info->ipc_ns == &init_ipc_ns); +#else + bool use_reserve = true; +#endif device = kzalloc(sizeof(*device), GFP_KERNEL); if (!device) @@ -413,7 +418,10 @@ static int binderfs_binder_ctl_create(struct super_block *sb) /* Reserve a new minor number for the new device. */ mutex_lock(&binderfs_minors_mutex); - minor = ida_alloc_max(&binderfs_minors, BINDERFS_MAX_MINOR, GFP_KERNEL); + minor = ida_alloc_max(&binderfs_minors, + use_reserve ? BINDERFS_MAX_MINOR : + BINDERFS_MAX_MINOR_CAPPED, + GFP_KERNEL); mutex_unlock(&binderfs_minors_mutex); if (minor < 0) { ret = minor; @@ -542,7 +550,7 @@ static struct file_system_type binder_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -static int __init init_binderfs(void) +int __init init_binderfs(void) { int ret; @@ -560,5 +568,3 @@ static int __init init_binderfs(void) return ret; } - -device_initcall(init_binderfs); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b8c3f9e6af89..adf28788cab5 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4554,6 +4554,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, + { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM, }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/base/base.h b/drivers/base/base.h index 7a419a7a6235..b405436ee28e 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -60,12 +60,17 @@ struct driver_private { * @knode_parent - node in sibling list * @knode_driver - node in driver list * @knode_bus - node in bus list + * @knode_class - node in class list * @deferred_probe - entry in deferred_probe_list which is used to retry the * binding of drivers which were unable to get all the resources needed by * the device; typically because it depends on another driver getting * probed first. + * @async_driver - pointer to device driver awaiting probe via async_probe * @device - pointer back to the struct device that this structure is * associated with. + * @dead - This device is currently either in the process of or has been + * removed from the system. Any asynchronous events scheduled for this + * device should exit without taking any action. * * Nothing outside of the driver core should ever touch these fields. */ @@ -74,8 +79,11 @@ struct device_private { struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; + struct klist_node knode_class; struct list_head deferred_probe; + struct device_driver *async_driver; struct device *device; + u8 dead:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) @@ -83,6 +91,8 @@ struct device_private { container_of(obj, struct device_private, knode_driver) #define to_device_private_bus(obj) \ container_of(obj, struct device_private, knode_bus) +#define to_device_private_class(obj) \ + container_of(obj, struct device_private, knode_class) /* initialisation functions */ extern int devices_init(void); @@ -124,6 +134,8 @@ extern int driver_add_groups(struct device_driver *drv, const struct attribute_group **groups); extern void driver_remove_groups(struct device_driver *drv, const struct attribute_group **groups); +int device_driver_attach(struct device_driver *drv, struct device *dev); +void device_driver_detach(struct device *dev); extern char *make_class_name(const char *name, struct kobject *kobj); diff --git a/drivers/base/bus.c b/drivers/base/bus.c index e06a57936cc9..0a58e969f8b7 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -187,11 +187,7 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf, dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == drv) { - if (dev->parent && dev->bus->need_parent_lock) - device_lock(dev->parent); - device_release_driver(dev); - if (dev->parent && dev->bus->need_parent_lock) - device_unlock(dev->parent); + device_driver_detach(dev); err = count; } put_device(dev); @@ -214,13 +210,7 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == NULL && driver_match_device(drv, dev)) { - if (dev->parent && bus->need_parent_lock) - device_lock(dev->parent); - device_lock(dev); - err = driver_probe_device(drv, dev); - device_unlock(dev); - if (dev->parent && bus->need_parent_lock) - device_unlock(dev->parent); + err = device_driver_attach(drv, dev); if (err > 0) { /* success */ @@ -236,12 +226,12 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, } static DRIVER_ATTR_IGNORE_LOCKDEP(bind, S_IWUSR, NULL, bind_store); -static ssize_t show_drivers_autoprobe(struct bus_type *bus, char *buf) +static ssize_t drivers_autoprobe_show(struct bus_type *bus, char *buf) { return sprintf(buf, "%d\n", bus->p->drivers_autoprobe); } -static ssize_t store_drivers_autoprobe(struct bus_type *bus, +static ssize_t drivers_autoprobe_store(struct bus_type *bus, const char *buf, size_t count) { if (buf[0] == '0') @@ -251,7 +241,7 @@ static ssize_t store_drivers_autoprobe(struct bus_type *bus, return count; } -static ssize_t store_drivers_probe(struct bus_type *bus, +static ssize_t drivers_probe_store(struct bus_type *bus, const char *buf, size_t count) { struct device *dev; @@ -586,9 +576,8 @@ static void remove_bind_files(struct device_driver *drv) driver_remove_file(drv, &driver_attr_unbind); } -static BUS_ATTR(drivers_probe, S_IWUSR, NULL, store_drivers_probe); -static BUS_ATTR(drivers_autoprobe, S_IWUSR | S_IRUGO, - show_drivers_autoprobe, store_drivers_autoprobe); +static BUS_ATTR_WO(drivers_probe); +static BUS_ATTR_RW(drivers_autoprobe); static int add_probe_files(struct bus_type *bus) { @@ -621,17 +610,6 @@ static ssize_t uevent_store(struct device_driver *drv, const char *buf, } static DRIVER_ATTR_WO(uevent); -static void driver_attach_async(void *_drv, async_cookie_t cookie) -{ - struct device_driver *drv = _drv; - int ret; - - ret = driver_attach(drv); - - pr_debug("bus: '%s': driver %s async attach completed: %d\n", - drv->bus->name, drv->name, ret); -} - /** * bus_add_driver - Add a driver to the bus. * @drv: driver. @@ -664,15 +642,9 @@ int bus_add_driver(struct device_driver *drv) klist_add_tail(&priv->knode_bus, &bus->p->klist_drivers); if (drv->bus->p->drivers_autoprobe) { - if (driver_allows_async_probing(drv)) { - pr_debug("bus: '%s': probing driver %s asynchronously\n", - drv->bus->name, drv->name); - async_schedule(driver_attach_async, drv); - } else { - error = driver_attach(drv); - if (error) - goto out_unregister; - } + error = driver_attach(drv); + if (error) + goto out_unregister; } module_add_driver(drv->owner, drv); @@ -774,13 +746,8 @@ EXPORT_SYMBOL_GPL(bus_rescan_devices); */ int device_reprobe(struct device *dev) { - if (dev->driver) { - if (dev->parent && dev->bus->need_parent_lock) - device_lock(dev->parent); - device_release_driver(dev); - if (dev->parent && dev->bus->need_parent_lock) - device_unlock(dev->parent); - } + if (dev->driver) + device_driver_detach(dev); return bus_rescan_devices_helper(dev, NULL); } EXPORT_SYMBOL_GPL(device_reprobe); @@ -838,7 +805,14 @@ static ssize_t bus_uevent_store(struct bus_type *bus, rc = kobject_synth_uevent(&bus->p->subsys.kobj, buf, count); return rc ? rc : count; } -static BUS_ATTR(uevent, S_IWUSR, NULL, bus_uevent_store); +/* + * "open code" the old BUS_ATTR() macro here. We want to use BUS_ATTR_WO() + * here, but can not use it as earlier in the file we have + * DEVICE_ATTR_WO(uevent), which would cause a clash with the with the store + * function name. + */ +static struct bus_attribute bus_attr_uevent = __ATTR(uevent, S_IWUSR, NULL, + bus_uevent_store); /** * bus_register - register a driver-core subsystem diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index cf78fa6d470d..a7359535caf5 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -79,8 +79,7 @@ static void cache_size(struct cacheinfo *this_leaf, struct device_node *np) ct_idx = get_cacheinfo_idx(this_leaf->type); propname = cache_type_info[ct_idx].size_prop; - if (of_property_read_u32(np, propname, &this_leaf->size)) - this_leaf->size = 0; + of_property_read_u32(np, propname, &this_leaf->size); } /* not cache_line_size() because that's a macro in include/linux/cache.h */ @@ -114,8 +113,7 @@ static void cache_nr_sets(struct cacheinfo *this_leaf, struct device_node *np) ct_idx = get_cacheinfo_idx(this_leaf->type); propname = cache_type_info[ct_idx].nr_sets_prop; - if (of_property_read_u32(np, propname, &this_leaf->number_of_sets)) - this_leaf->number_of_sets = 0; + of_property_read_u32(np, propname, &this_leaf->number_of_sets); } static void cache_associativity(struct cacheinfo *this_leaf) diff --git a/drivers/base/class.c b/drivers/base/class.c index 54def4e02f00..d8a6a5864c2e 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -117,16 +117,22 @@ static void class_put(struct class *cls) kset_put(&cls->p->subsys); } +static struct device *klist_class_to_dev(struct klist_node *n) +{ + struct device_private *p = to_device_private_class(n); + return p->device; +} + static void klist_class_dev_get(struct klist_node *n) { - struct device *dev = container_of(n, struct device, knode_class); + struct device *dev = klist_class_to_dev(n); get_device(dev); } static void klist_class_dev_put(struct klist_node *n) { - struct device *dev = container_of(n, struct device, knode_class); + struct device *dev = klist_class_to_dev(n); put_device(dev); } @@ -277,7 +283,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, struct klist_node *start_knode = NULL; if (start) - start_knode = &start->knode_class; + start_knode = &start->p->knode_class; klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode); iter->type = type; } @@ -304,7 +310,7 @@ struct device *class_dev_iter_next(struct class_dev_iter *iter) knode = klist_next(&iter->ki); if (!knode) return NULL; - dev = container_of(knode, struct device, knode_class); + dev = klist_class_to_dev(knode); if (!iter->type || iter->type == dev->type) return dev; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 0073b09bb99f..abfce4f613f8 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -165,6 +165,19 @@ void device_pm_move_to_tail(struct device *dev) device_links_read_unlock(idx); } +static void device_link_rpm_prepare(struct device *consumer, + struct device *supplier) +{ + pm_runtime_new_link(consumer); + /* + * If the link is being added by the consumer driver at probe time, + * balance the decrementation of the supplier's runtime PM usage counter + * after consumer probe in driver_probe_device(). + */ + if (consumer->links.status == DL_DEV_PROBING) + pm_runtime_get_noresume(supplier); +} + /** * device_link_add - Create a link between two devices. * @consumer: Consumer end of the link. @@ -179,10 +192,31 @@ void device_pm_move_to_tail(struct device *dev) * of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be * ignored. * - * If the DL_FLAG_AUTOREMOVE_CONSUMER is set, the link will be removed - * automatically when the consumer device driver unbinds from it. - * The combination of both DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_STATELESS - * set is invalid and will cause NULL to be returned. + * If DL_FLAG_STATELESS is set in @flags, the link is not going to be managed by + * the driver core and, in particular, the caller of this function is expected + * to drop the reference to the link acquired by it directly. + * + * If that flag is not set, however, the caller of this function is handing the + * management of the link over to the driver core entirely and its return value + * can only be used to check whether or not the link is present. In that case, + * the DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_AUTOREMOVE_SUPPLIER device link + * flags can be used to indicate to the driver core when the link can be safely + * deleted. Namely, setting one of them in @flags indicates to the driver core + * that the link is not going to be used (by the given caller of this function) + * after unbinding the consumer or supplier driver, respectively, from its + * device, so the link can be deleted at that point. If none of them is set, + * the link will be maintained until one of the devices pointed to by it (either + * the consumer or the supplier) is unregistered. + * + * Also, if DL_FLAG_STATELESS, DL_FLAG_AUTOREMOVE_CONSUMER and + * DL_FLAG_AUTOREMOVE_SUPPLIER are not set in @flags (that is, a persistent + * managed device link is being added), the DL_FLAG_AUTOPROBE_CONSUMER flag can + * be used to request the driver core to automaticall probe for a consmer + * driver after successfully binding a driver to the supplier device. + * + * The combination of DL_FLAG_STATELESS and either DL_FLAG_AUTOREMOVE_CONSUMER + * or DL_FLAG_AUTOREMOVE_SUPPLIER set in @flags at the same time is invalid and + * will cause NULL to be returned upfront. * * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending @@ -199,10 +233,22 @@ struct device_link *device_link_add(struct device *consumer, struct device_link *link; if (!consumer || !supplier || - ((flags & DL_FLAG_STATELESS) && - (flags & DL_FLAG_AUTOREMOVE_CONSUMER))) + (flags & DL_FLAG_STATELESS && + flags & (DL_FLAG_AUTOREMOVE_CONSUMER | + DL_FLAG_AUTOREMOVE_SUPPLIER | + DL_FLAG_AUTOPROBE_CONSUMER)) || + (flags & DL_FLAG_AUTOPROBE_CONSUMER && + flags & (DL_FLAG_AUTOREMOVE_CONSUMER | + DL_FLAG_AUTOREMOVE_SUPPLIER))) return NULL; + if (flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) { + if (pm_runtime_get_sync(supplier) < 0) { + pm_runtime_put_noidle(supplier); + return NULL; + } + } + device_links_write_lock(); device_pm_lock(); @@ -217,35 +263,71 @@ struct device_link *device_link_add(struct device *consumer, goto out; } - list_for_each_entry(link, &supplier->links.consumers, s_node) - if (link->consumer == consumer) { + /* + * DL_FLAG_AUTOREMOVE_SUPPLIER indicates that the link will be needed + * longer than for DL_FLAG_AUTOREMOVE_CONSUMER and setting them both + * together doesn't make sense, so prefer DL_FLAG_AUTOREMOVE_SUPPLIER. + */ + if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) + flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; + + list_for_each_entry(link, &supplier->links.consumers, s_node) { + if (link->consumer != consumer) + continue; + + /* + * Don't return a stateless link if the caller wants a stateful + * one and vice versa. + */ + if (WARN_ON((flags & DL_FLAG_STATELESS) != (link->flags & DL_FLAG_STATELESS))) { + link = NULL; + goto out; + } + + if (flags & DL_FLAG_PM_RUNTIME) { + if (!(link->flags & DL_FLAG_PM_RUNTIME)) { + device_link_rpm_prepare(consumer, supplier); + link->flags |= DL_FLAG_PM_RUNTIME; + } + if (flags & DL_FLAG_RPM_ACTIVE) + refcount_inc(&link->rpm_active); + } + + if (flags & DL_FLAG_STATELESS) { kref_get(&link->kref); goto out; } + /* + * If the life time of the link following from the new flags is + * longer than indicated by the flags of the existing link, + * update the existing link to stay around longer. + */ + if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) { + if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) { + link->flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; + link->flags |= DL_FLAG_AUTOREMOVE_SUPPLIER; + } + } else if (!(flags & DL_FLAG_AUTOREMOVE_CONSUMER)) { + link->flags &= ~(DL_FLAG_AUTOREMOVE_CONSUMER | + DL_FLAG_AUTOREMOVE_SUPPLIER); + } + goto out; + } + link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) goto out; + refcount_set(&link->rpm_active, 1); + if (flags & DL_FLAG_PM_RUNTIME) { - if (flags & DL_FLAG_RPM_ACTIVE) { - if (pm_runtime_get_sync(supplier) < 0) { - pm_runtime_put_noidle(supplier); - kfree(link); - link = NULL; - goto out; - } - link->rpm_active = true; - } - pm_runtime_new_link(consumer); - /* - * If the link is being added by the consumer driver at probe - * time, balance the decrementation of the supplier's runtime PM - * usage counter after consumer probe in driver_probe_device(). - */ - if (consumer->links.status == DL_DEV_PROBING) - pm_runtime_get_noresume(supplier); + if (flags & DL_FLAG_RPM_ACTIVE) + refcount_inc(&link->rpm_active); + + device_link_rpm_prepare(consumer, supplier); } + get_device(supplier); link->supplier = supplier; INIT_LIST_HEAD(&link->s_node); @@ -260,17 +342,26 @@ struct device_link *device_link_add(struct device *consumer, link->status = DL_STATE_NONE; } else { switch (supplier->links.status) { - case DL_DEV_DRIVER_BOUND: + case DL_DEV_PROBING: switch (consumer->links.status) { case DL_DEV_PROBING: /* - * Some callers expect the link creation during - * consumer driver probe to resume the supplier - * even without DL_FLAG_RPM_ACTIVE. + * A consumer driver can create a link to a + * supplier that has not completed its probing + * yet as long as it knows that the supplier is + * already functional (for example, it has just + * acquired some resources from the supplier). */ - if (flags & DL_FLAG_PM_RUNTIME) - pm_runtime_resume(supplier); - + link->status = DL_STATE_CONSUMER_PROBE; + break; + default: + link->status = DL_STATE_DORMANT; + break; + } + break; + case DL_DEV_DRIVER_BOUND: + switch (consumer->links.status) { + case DL_DEV_PROBING: link->status = DL_STATE_CONSUMER_PROBE; break; case DL_DEV_DRIVER_BOUND: @@ -291,6 +382,14 @@ struct device_link *device_link_add(struct device *consumer, } /* + * Some callers expect the link creation during consumer driver probe to + * resume the supplier even without DL_FLAG_RPM_ACTIVE. + */ + if (link->status == DL_STATE_CONSUMER_PROBE && + flags & DL_FLAG_PM_RUNTIME) + pm_runtime_resume(supplier); + + /* * Move the consumer and all of the devices depending on it to the end * of dpm_list and the devices_kset list. * @@ -302,17 +401,24 @@ struct device_link *device_link_add(struct device *consumer, list_add_tail_rcu(&link->s_node, &supplier->links.consumers); list_add_tail_rcu(&link->c_node, &consumer->links.suppliers); - dev_info(consumer, "Linked as a consumer to %s\n", dev_name(supplier)); + dev_dbg(consumer, "Linked as a consumer to %s\n", dev_name(supplier)); out: device_pm_unlock(); device_links_write_unlock(); + + if ((flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) && !link) + pm_runtime_put(supplier); + return link; } EXPORT_SYMBOL_GPL(device_link_add); static void device_link_free(struct device_link *link) { + while (refcount_dec_not_one(&link->rpm_active)) + pm_runtime_put(link->supplier); + put_device(link->consumer); put_device(link->supplier); kfree(link); @@ -328,8 +434,8 @@ static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); - dev_info(link->consumer, "Dropping the link to %s\n", - dev_name(link->supplier)); + dev_dbg(link->consumer, "Dropping the link to %s\n", + dev_name(link->supplier)); if (link->flags & DL_FLAG_PM_RUNTIME) pm_runtime_drop_link(link->consumer); @@ -355,8 +461,16 @@ static void __device_link_del(struct kref *kref) } #endif /* !CONFIG_SRCU */ +static void device_link_put_kref(struct device_link *link) +{ + if (link->flags & DL_FLAG_STATELESS) + kref_put(&link->kref, __device_link_del); + else + WARN(1, "Unable to drop a managed device link reference\n"); +} + /** - * device_link_del - Delete a link between two devices. + * device_link_del - Delete a stateless link between two devices. * @link: Device link to delete. * * The caller must ensure proper synchronization of this function with runtime @@ -368,14 +482,14 @@ void device_link_del(struct device_link *link) { device_links_write_lock(); device_pm_lock(); - kref_put(&link->kref, __device_link_del); + device_link_put_kref(link); device_pm_unlock(); device_links_write_unlock(); } EXPORT_SYMBOL_GPL(device_link_del); /** - * device_link_remove - remove a link between two devices. + * device_link_remove - Delete a stateless link between two devices. * @consumer: Consumer end of the link. * @supplier: Supplier end of the link. * @@ -394,7 +508,7 @@ void device_link_remove(void *consumer, struct device *supplier) list_for_each_entry(link, &supplier->links.consumers, s_node) { if (link->consumer == consumer) { - kref_put(&link->kref, __device_link_del); + device_link_put_kref(link); break; } } @@ -474,8 +588,21 @@ void device_links_driver_bound(struct device *dev) if (link->flags & DL_FLAG_STATELESS) continue; + /* + * Links created during consumer probe may be in the "consumer + * probe" state to start with if the supplier is still probing + * when they are created and they may become "active" if the + * consumer probe returns first. Skip them here. + */ + if (link->status == DL_STATE_CONSUMER_PROBE || + link->status == DL_STATE_ACTIVE) + continue; + WARN_ON(link->status != DL_STATE_DORMANT); WRITE_ONCE(link->status, DL_STATE_AVAILABLE); + + if (link->flags & DL_FLAG_AUTOPROBE_CONSUMER) + driver_deferred_probe_add(link->consumer); } list_for_each_entry(link, &dev->links.suppliers, c_node) { @@ -512,18 +639,49 @@ static void __device_links_no_driver(struct device *dev) continue; if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) - kref_put(&link->kref, __device_link_del); - else if (link->status != DL_STATE_SUPPLIER_UNBIND) + __device_link_del(&link->kref); + else if (link->status == DL_STATE_CONSUMER_PROBE || + link->status == DL_STATE_ACTIVE) WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } dev->links.status = DL_DEV_NO_DRIVER; } +/** + * device_links_no_driver - Update links after failing driver probe. + * @dev: Device whose driver has just failed to probe. + * + * Clean up leftover links to consumers for @dev and invoke + * %__device_links_no_driver() to update links to suppliers for it as + * appropriate. + * + * Links with the DL_FLAG_STATELESS flag set are ignored. + */ void device_links_no_driver(struct device *dev) { + struct device_link *link; + device_links_write_lock(); + + list_for_each_entry(link, &dev->links.consumers, s_node) { + if (link->flags & DL_FLAG_STATELESS) + continue; + + /* + * The probe has failed, so if the status of the link is + * "consumer probe" or "active", it must have been added by + * a probing consumer while this device was still probing. + * Change its state to "dormant", as it represents a valid + * relationship, but it is not functionally meaningful. + */ + if (link->status == DL_STATE_CONSUMER_PROBE || + link->status == DL_STATE_ACTIVE) + WRITE_ONCE(link->status, DL_STATE_DORMANT); + } + __device_links_no_driver(dev); + device_links_write_unlock(); } @@ -539,11 +697,11 @@ void device_links_no_driver(struct device *dev) */ void device_links_driver_cleanup(struct device *dev) { - struct device_link *link; + struct device_link *link, *ln; device_links_write_lock(); - list_for_each_entry(link, &dev->links.consumers, s_node) { + list_for_each_entry_safe(link, ln, &dev->links.consumers, s_node) { if (link->flags & DL_FLAG_STATELESS) continue; @@ -557,7 +715,7 @@ void device_links_driver_cleanup(struct device *dev) */ if (link->status == DL_STATE_SUPPLIER_UNBIND && link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) - kref_put(&link->kref, __device_link_del); + __device_link_del(&link->kref); WRITE_ONCE(link->status, DL_STATE_DORMANT); } @@ -1966,7 +2124,7 @@ int device_add(struct device *dev) if (dev->class) { mutex_lock(&dev->class->p->mutex); /* tie the class to the device */ - klist_add_tail(&dev->knode_class, + klist_add_tail(&dev->p->knode_class, &dev->class->p->klist_devices); /* notify any interfaces that the device is here */ @@ -2080,6 +2238,17 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf; + /* + * Hold the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + device_lock(dev); + dev->p->dead = true; + device_unlock(dev); + /* Notify clients of device removal. This call must come * before dpm_sysfs_remove(). */ @@ -2105,7 +2274,7 @@ void device_del(struct device *dev) if (class_intf->remove_dev) class_intf->remove_dev(dev, class_intf); /* remove the device from the class list */ - klist_del(&dev->knode_class); + klist_del(&dev->p->knode_class); mutex_unlock(&dev->class->p->mutex); } device_remove_file(dev, &dev_attr_uevent); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index eb9443d5bae1..de74d7d93558 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -409,6 +409,7 @@ static void device_create_release(struct device *dev) kfree(dev); } +__printf(4, 0) static struct device * __cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 8ac10af17c00..348fc4695d4d 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -116,7 +116,7 @@ static void deferred_probe_work_func(struct work_struct *work) } static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func); -static void driver_deferred_probe_add(struct device *dev) +void driver_deferred_probe_add(struct device *dev) { mutex_lock(&deferred_probe_mutex); if (list_empty(&dev->p->deferred_probe)) { @@ -731,15 +731,6 @@ static int __device_attach_driver(struct device_driver *drv, void *_data) bool async_allowed; int ret; - /* - * Check if device has already been claimed. This may - * happen with driver loading, device discovery/registration, - * and deferred probe processing happens all at once with - * multiple threads. - */ - if (dev->driver) - return -EBUSY; - ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ @@ -774,6 +765,15 @@ static void __device_attach_async_helper(void *_dev, async_cookie_t cookie) device_lock(dev); + /* + * Check if device has already been removed or claimed. This may + * happen with driver loading, device discovery/registration, + * and deferred probe processing happens all at once with + * multiple threads. + */ + if (dev->p->dead || dev->driver) + goto out_unlock; + if (dev->parent) pm_runtime_get_sync(dev->parent); @@ -784,7 +784,7 @@ static void __device_attach_async_helper(void *_dev, async_cookie_t cookie) if (dev->parent) pm_runtime_put(dev->parent); - +out_unlock: device_unlock(dev); put_device(dev); @@ -829,7 +829,7 @@ static int __device_attach(struct device *dev, bool allow_async) */ dev_dbg(dev, "scheduling asynchronous probe\n"); get_device(dev); - async_schedule(__device_attach_async_helper, dev); + async_schedule_dev(__device_attach_async_helper, dev); } else { pm_request_idle(dev); } @@ -867,6 +867,88 @@ void device_initial_probe(struct device *dev) __device_attach(dev, true); } +/* + * __device_driver_lock - acquire locks needed to manipulate dev->drv + * @dev: Device we will update driver info for + * @parent: Parent device. Needed if the bus requires parent lock + * + * This function will take the required locks for manipulating dev->drv. + * Normally this will just be the @dev lock, but when called for a USB + * interface, @parent lock will be held as well. + */ +static void __device_driver_lock(struct device *dev, struct device *parent) +{ + if (parent && dev->bus->need_parent_lock) + device_lock(parent); + device_lock(dev); +} + +/* + * __device_driver_unlock - release locks needed to manipulate dev->drv + * @dev: Device we will update driver info for + * @parent: Parent device. Needed if the bus requires parent lock + * + * This function will release the required locks for manipulating dev->drv. + * Normally this will just be the the @dev lock, but when called for a + * USB interface, @parent lock will be released as well. + */ +static void __device_driver_unlock(struct device *dev, struct device *parent) +{ + device_unlock(dev); + if (parent && dev->bus->need_parent_lock) + device_unlock(parent); +} + +/** + * device_driver_attach - attach a specific driver to a specific device + * @drv: Driver to attach + * @dev: Device to attach it to + * + * Manually attach driver to a device. Will acquire both @dev lock and + * @dev->parent lock if needed. + */ +int device_driver_attach(struct device_driver *drv, struct device *dev) +{ + int ret = 0; + + __device_driver_lock(dev, dev->parent); + + /* + * If device has been removed or someone has already successfully + * bound a driver before us just skip the driver probe call. + */ + if (!dev->p->dead && !dev->driver) + ret = driver_probe_device(drv, dev); + + __device_driver_unlock(dev, dev->parent); + + return ret; +} + +static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie) +{ + struct device *dev = _dev; + struct device_driver *drv; + int ret = 0; + + __device_driver_lock(dev, dev->parent); + + drv = dev->p->async_driver; + + /* + * If device has been removed or someone has already successfully + * bound a driver before us just skip the driver probe call. + */ + if (!dev->p->dead && !dev->driver) + ret = driver_probe_device(drv, dev); + + __device_driver_unlock(dev, dev->parent); + + dev_dbg(dev, "driver %s async attach completed: %d\n", drv->name, ret); + + put_device(dev); +} + static int __driver_attach(struct device *dev, void *data) { struct device_driver *drv = data; @@ -894,14 +976,26 @@ static int __driver_attach(struct device *dev, void *data) return ret; } /* ret > 0 means positive match */ - if (dev->parent && dev->bus->need_parent_lock) - device_lock(dev->parent); - device_lock(dev); - if (!dev->driver) - driver_probe_device(drv, dev); - device_unlock(dev); - if (dev->parent && dev->bus->need_parent_lock) - device_unlock(dev->parent); + if (driver_allows_async_probing(drv)) { + /* + * Instead of probing the device synchronously we will + * probe it asynchronously to allow for more parallelism. + * + * We only take the device lock here in order to guarantee + * that the dev->driver and async_driver fields are protected + */ + dev_dbg(dev, "probing driver %s asynchronously\n", drv->name); + device_lock(dev); + if (!dev->driver) { + get_device(dev); + dev->p->async_driver = drv; + async_schedule_dev(__driver_attach_async_helper, dev); + } + device_unlock(dev); + return 0; + } + + device_driver_attach(drv, dev); return 0; } @@ -932,15 +1026,11 @@ static void __device_release_driver(struct device *dev, struct device *parent) drv = dev->driver; if (drv) { while (device_links_busy(dev)) { - device_unlock(dev); - if (parent && dev->bus->need_parent_lock) - device_unlock(parent); + __device_driver_unlock(dev, parent); device_links_unbind_consumers(dev); - if (parent && dev->bus->need_parent_lock) - device_lock(parent); - device_lock(dev); + __device_driver_lock(dev, parent); /* * A concurrent invocation of the same function might * have released the driver successfully while this one @@ -968,9 +1058,9 @@ static void __device_release_driver(struct device *dev, struct device *parent) drv->remove(dev); device_links_driver_cleanup(dev); - arch_teardown_dma_ops(dev); devres_release_all(dev); + arch_teardown_dma_ops(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) @@ -993,16 +1083,12 @@ void device_release_driver_internal(struct device *dev, struct device_driver *drv, struct device *parent) { - if (parent && dev->bus->need_parent_lock) - device_lock(parent); + __device_driver_lock(dev, parent); - device_lock(dev); if (!drv || drv == dev->driver) __device_release_driver(dev, parent); - device_unlock(dev); - if (parent && dev->bus->need_parent_lock) - device_unlock(parent); + __device_driver_unlock(dev, parent); } /** @@ -1028,6 +1114,18 @@ void device_release_driver(struct device *dev) EXPORT_SYMBOL_GPL(device_release_driver); /** + * device_driver_detach - detach driver from a specific device + * @dev: device to detach driver from + * + * Detach driver from device. Will acquire both @dev lock and @dev->parent + * lock if needed. + */ +void device_driver_detach(struct device *dev) +{ + device_release_driver_internal(dev, NULL, dev->parent); +} + +/** * driver_detach - detach driver from all devices it controls. * @drv: driver. */ diff --git a/drivers/base/firmware_loader/Makefile b/drivers/base/firmware_loader/Makefile index a97eeb0be1d8..0b2dfa6259c9 100644 --- a/drivers/base/firmware_loader/Makefile +++ b/drivers/base/firmware_loader/Makefile @@ -1,7 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for the Linux firmware loader -obj-y := fallback_table.o +obj-$(CONFIG_FW_LOADER_USER_HELPER) += fallback_table.o obj-$(CONFIG_FW_LOADER) += firmware_class.o firmware_class-objs := main.o firmware_class-$(CONFIG_FW_LOADER_USER_HELPER) += fallback.o + +obj-y += builtin/ diff --git a/firmware/.gitignore b/drivers/base/firmware_loader/builtin/.gitignore index 9c8bdb9fdcc3..9c8bdb9fdcc3 100644 --- a/firmware/.gitignore +++ b/drivers/base/firmware_loader/builtin/.gitignore diff --git a/firmware/Makefile b/drivers/base/firmware_loader/builtin/Makefile index 37e5ae387400..37e5ae387400 100644 --- a/firmware/Makefile +++ b/drivers/base/firmware_loader/builtin/Makefile diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c index 7428659d8df9..776dd69cf5be 100644 --- a/drivers/base/firmware_loader/fallback_table.c +++ b/drivers/base/firmware_loader/fallback_table.c @@ -16,9 +16,6 @@ * firmware fallback configuration table */ -/* Module or buit-in */ -#ifdef CONFIG_FW_LOADER_USER_HELPER - static unsigned int zero; static unsigned int one = 1; @@ -51,5 +48,3 @@ struct ctl_table firmware_config_table[] = { { } }; EXPORT_SYMBOL_GPL(firmware_config_table); - -#endif diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 0992e67e862b..93ddbcebcece 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -727,7 +727,7 @@ void dpm_noirq_resume_devices(pm_message_t state) reinit_completion(&dev->power.completion); if (is_async(dev)) { get_device(dev); - async_schedule(async_resume_noirq, dev); + async_schedule_dev(async_resume_noirq, dev); } } @@ -884,7 +884,7 @@ void dpm_resume_early(pm_message_t state) reinit_completion(&dev->power.completion); if (is_async(dev)) { get_device(dev); - async_schedule(async_resume_early, dev); + async_schedule_dev(async_resume_early, dev); } } @@ -1048,7 +1048,7 @@ void dpm_resume(pm_message_t state) reinit_completion(&dev->power.completion); if (is_async(dev)) { get_device(dev); - async_schedule(async_resume, dev); + async_schedule_dev(async_resume, dev); } } @@ -1368,7 +1368,7 @@ static int device_suspend_noirq(struct device *dev) if (is_async(dev)) { get_device(dev); - async_schedule(async_suspend_noirq, dev); + async_schedule_dev(async_suspend_noirq, dev); return 0; } return __device_suspend_noirq(dev, pm_transition, false); @@ -1571,7 +1571,7 @@ static int device_suspend_late(struct device *dev) if (is_async(dev)) { get_device(dev); - async_schedule(async_suspend_late, dev); + async_schedule_dev(async_suspend_late, dev); return 0; } @@ -1835,7 +1835,7 @@ static int device_suspend(struct device *dev) if (is_async(dev)) { get_device(dev); - async_schedule(async_suspend, dev); + async_schedule_dev(async_suspend, dev); return 0; } diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 0ea2139c50d8..ac54f65b6d63 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -259,11 +259,8 @@ static int rpm_get_suppliers(struct device *dev) list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { int retval; - if (!(link->flags & DL_FLAG_PM_RUNTIME)) - continue; - - if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND || - link->rpm_active) + if (!(link->flags & DL_FLAG_PM_RUNTIME) || + READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) continue; retval = pm_runtime_get_sync(link->supplier); @@ -272,7 +269,7 @@ static int rpm_get_suppliers(struct device *dev) pm_runtime_put_noidle(link->supplier); return retval; } - link->rpm_active = true; + refcount_inc(&link->rpm_active); } return 0; } @@ -281,12 +278,13 @@ static void rpm_put_suppliers(struct device *dev) { struct device_link *link; - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) - if (link->rpm_active && - READ_ONCE(link->status) != DL_STATE_SUPPLIER_UNBIND) { + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { + if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) + continue; + + while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put(link->supplier); - link->rpm_active = false; - } + } } /** @@ -1091,20 +1089,43 @@ EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use); * and the device parent's counter of unsuspended children is modified to * reflect the new status. If the new status is RPM_SUSPENDED, an idle * notification request for the parent is submitted. + * + * If @dev has any suppliers (as reflected by device links to them), and @status + * is RPM_ACTIVE, they will be activated upfront and if the activation of one + * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead + * of the @status value) and the suppliers will be deacticated on exit. The + * error returned by the failing supplier activation will be returned in that + * case. */ int __pm_runtime_set_status(struct device *dev, unsigned int status) { struct device *parent = dev->parent; - unsigned long flags; bool notify_parent = false; int error = 0; if (status != RPM_ACTIVE && status != RPM_SUSPENDED) return -EINVAL; - spin_lock_irqsave(&dev->power.lock, flags); + /* + * If the new status is RPM_ACTIVE, the suppliers can be activated + * upfront regardless of the current status, because next time + * rpm_put_suppliers() runs, the rpm_active refcounts of the links + * involved will be dropped down to one anyway. + */ + if (status == RPM_ACTIVE) { + int idx = device_links_read_lock(); + + error = rpm_get_suppliers(dev); + if (error) + status = RPM_SUSPENDED; + + device_links_read_unlock(idx); + } + + spin_lock_irq(&dev->power.lock); if (!dev->power.runtime_error && !dev->power.disable_depth) { + status = dev->power.runtime_status; error = -EAGAIN; goto out; } @@ -1136,19 +1157,31 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) spin_unlock(&parent->power.lock); - if (error) + if (error) { + status = RPM_SUSPENDED; goto out; + } } out_set: __update_runtime_status(dev, status); - dev->power.runtime_error = 0; + if (!error) + dev->power.runtime_error = 0; + out: - spin_unlock_irqrestore(&dev->power.lock, flags); + spin_unlock_irq(&dev->power.lock); if (notify_parent) pm_request_idle(parent); + if (status == RPM_SUSPENDED) { + int idx = device_links_read_lock(); + + rpm_put_suppliers(dev); + + device_links_read_unlock(idx); + } + return error; } EXPORT_SYMBOL_GPL(__pm_runtime_set_status); @@ -1539,7 +1572,7 @@ void pm_runtime_remove(struct device *dev) * * Check links from this device to any consumers and if any of them have active * runtime PM references to the device, drop the usage counter of the device - * (once per link). + * (as many times as needed). * * Links with the DL_FLAG_STATELESS flag set are ignored. * @@ -1561,10 +1594,8 @@ void pm_runtime_clean_up_links(struct device *dev) if (link->flags & DL_FLAG_STATELESS) continue; - if (link->rpm_active) { + while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put_noidle(dev); - link->rpm_active = false; - } } device_links_read_unlock(idx); @@ -1615,8 +1646,6 @@ void pm_runtime_new_link(struct device *dev) void pm_runtime_drop_link(struct device *dev) { - rpm_put_suppliers(dev); - spin_lock_irq(&dev->power.lock); WARN_ON(dev->power.links_count == 0); dev->power.links_count--; diff --git a/drivers/base/test/test_async_driver_probe.c b/drivers/base/test/test_async_driver_probe.c index e7f145d662f0..f4b1d8e54daf 100644 --- a/drivers/base/test/test_async_driver_probe.c +++ b/drivers/base/test/test_async_driver_probe.c @@ -11,16 +11,47 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/time.h> +#include <linux/numa.h> +#include <linux/nodemask.h> +#include <linux/topology.h> #define TEST_PROBE_DELAY (5 * 1000) /* 5 sec */ #define TEST_PROBE_THRESHOLD (TEST_PROBE_DELAY / 2) +static atomic_t warnings, errors, timeout, async_completed; + static int test_probe(struct platform_device *pdev) { - dev_info(&pdev->dev, "sleeping for %d msecs in probe\n", - TEST_PROBE_DELAY); - msleep(TEST_PROBE_DELAY); - dev_info(&pdev->dev, "done sleeping\n"); + struct device *dev = &pdev->dev; + + /* + * Determine if we have hit the "timeout" limit for the test if we + * have then report it as an error, otherwise we wil sleep for the + * required amount of time and then report completion. + */ + if (atomic_read(&timeout)) { + dev_err(dev, "async probe took too long\n"); + atomic_inc(&errors); + } else { + dev_dbg(&pdev->dev, "sleeping for %d msecs in probe\n", + TEST_PROBE_DELAY); + msleep(TEST_PROBE_DELAY); + dev_dbg(&pdev->dev, "done sleeping\n"); + } + + /* + * Report NUMA mismatch if device node is set and we are not + * performing an async init on that node. + */ + if (dev->driver->probe_type == PROBE_PREFER_ASYNCHRONOUS) { + if (dev_to_node(dev) != numa_node_id()) { + dev_warn(dev, "NUMA node mismatch %d != %d\n", + dev_to_node(dev), numa_node_id()); + atomic_inc(&warnings); + } + + atomic_inc(&async_completed); + } return 0; } @@ -41,31 +72,64 @@ static struct platform_driver sync_driver = { .probe = test_probe, }; -static struct platform_device *async_dev_1, *async_dev_2; -static struct platform_device *sync_dev_1; +static struct platform_device *async_dev[NR_CPUS * 2]; +static struct platform_device *sync_dev[2]; + +static struct platform_device * +test_platform_device_register_node(char *name, int id, int nid) +{ + struct platform_device *pdev; + int ret; + + pdev = platform_device_alloc(name, id); + if (!pdev) + return NULL; + + if (nid != NUMA_NO_NODE) + set_dev_node(&pdev->dev, nid); + + ret = platform_device_add(pdev); + if (ret) { + platform_device_put(pdev); + return ERR_PTR(ret); + } + + return pdev; + +} static int __init test_async_probe_init(void) { - ktime_t calltime, delta; + struct platform_device **pdev = NULL; + int async_id = 0, sync_id = 0; unsigned long long duration; - int error; + ktime_t calltime, delta; + int err, nid, cpu; + + pr_info("registering first set of asynchronous devices...\n"); - pr_info("registering first asynchronous device...\n"); + for_each_online_cpu(cpu) { + nid = cpu_to_node(cpu); + pdev = &async_dev[async_id]; + *pdev = test_platform_device_register_node("test_async_driver", + async_id, + nid); + if (IS_ERR(*pdev)) { + err = PTR_ERR(*pdev); + *pdev = NULL; + pr_err("failed to create async_dev: %d\n", err); + goto err_unregister_async_devs; + } - async_dev_1 = platform_device_register_simple("test_async_driver", 1, - NULL, 0); - if (IS_ERR(async_dev_1)) { - error = PTR_ERR(async_dev_1); - pr_err("failed to create async_dev_1: %d\n", error); - return error; + async_id++; } pr_info("registering asynchronous driver...\n"); calltime = ktime_get(); - error = platform_driver_register(&async_driver); - if (error) { - pr_err("Failed to register async_driver: %d\n", error); - goto err_unregister_async_dev_1; + err = platform_driver_register(&async_driver); + if (err) { + pr_err("Failed to register async_driver: %d\n", err); + goto err_unregister_async_devs; } delta = ktime_sub(ktime_get(), calltime); @@ -73,86 +137,163 @@ static int __init test_async_probe_init(void) pr_info("registration took %lld msecs\n", duration); if (duration > TEST_PROBE_THRESHOLD) { pr_err("test failed: probe took too long\n"); - error = -ETIMEDOUT; + err = -ETIMEDOUT; goto err_unregister_async_driver; } - pr_info("registering second asynchronous device...\n"); + pr_info("registering second set of asynchronous devices...\n"); calltime = ktime_get(); - async_dev_2 = platform_device_register_simple("test_async_driver", 2, - NULL, 0); - if (IS_ERR(async_dev_2)) { - error = PTR_ERR(async_dev_2); - pr_err("failed to create async_dev_2: %d\n", error); - goto err_unregister_async_driver; + for_each_online_cpu(cpu) { + nid = cpu_to_node(cpu); + pdev = &sync_dev[sync_id]; + + *pdev = test_platform_device_register_node("test_async_driver", + async_id, + nid); + if (IS_ERR(*pdev)) { + err = PTR_ERR(*pdev); + *pdev = NULL; + pr_err("failed to create async_dev: %d\n", err); + goto err_unregister_async_driver; + } + + async_id++; } delta = ktime_sub(ktime_get(), calltime); duration = (unsigned long long) ktime_to_ms(delta); - pr_info("registration took %lld msecs\n", duration); + dev_info(&(*pdev)->dev, + "registration took %lld msecs\n", duration); if (duration > TEST_PROBE_THRESHOLD) { - pr_err("test failed: probe took too long\n"); - error = -ETIMEDOUT; - goto err_unregister_async_dev_2; + dev_err(&(*pdev)->dev, + "test failed: probe took too long\n"); + err = -ETIMEDOUT; + goto err_unregister_async_driver; } - pr_info("registering synchronous driver...\n"); - error = platform_driver_register(&sync_driver); - if (error) { - pr_err("Failed to register async_driver: %d\n", error); - goto err_unregister_async_dev_2; + pr_info("registering first synchronous device...\n"); + nid = cpu_to_node(cpu); + pdev = &sync_dev[sync_id]; + + *pdev = test_platform_device_register_node("test_sync_driver", + sync_id, + NUMA_NO_NODE); + if (IS_ERR(*pdev)) { + err = PTR_ERR(*pdev); + *pdev = NULL; + pr_err("failed to create sync_dev: %d\n", err); + goto err_unregister_async_driver; } - pr_info("registering synchronous device...\n"); + sync_id++; + + pr_info("registering synchronous driver...\n"); calltime = ktime_get(); - sync_dev_1 = platform_device_register_simple("test_sync_driver", 1, - NULL, 0); - if (IS_ERR(sync_dev_1)) { - error = PTR_ERR(sync_dev_1); - pr_err("failed to create sync_dev_1: %d\n", error); - goto err_unregister_sync_driver; + err = platform_driver_register(&sync_driver); + if (err) { + pr_err("Failed to register async_driver: %d\n", err); + goto err_unregister_sync_devs; } delta = ktime_sub(ktime_get(), calltime); duration = (unsigned long long) ktime_to_ms(delta); pr_info("registration took %lld msecs\n", duration); if (duration < TEST_PROBE_THRESHOLD) { - pr_err("test failed: probe was too quick\n"); - error = -ETIMEDOUT; - goto err_unregister_sync_dev_1; + dev_err(&(*pdev)->dev, + "test failed: probe was too quick\n"); + err = -ETIMEDOUT; + goto err_unregister_sync_driver; } - pr_info("completed successfully"); + pr_info("registering second synchronous device...\n"); + pdev = &sync_dev[sync_id]; + calltime = ktime_get(); - return 0; + *pdev = test_platform_device_register_node("test_sync_driver", + sync_id, + NUMA_NO_NODE); + if (IS_ERR(*pdev)) { + err = PTR_ERR(*pdev); + *pdev = NULL; + pr_err("failed to create sync_dev: %d\n", err); + goto err_unregister_sync_driver; + } -err_unregister_sync_dev_1: - platform_device_unregister(sync_dev_1); + sync_id++; -err_unregister_sync_driver: - platform_driver_unregister(&sync_driver); + delta = ktime_sub(ktime_get(), calltime); + duration = (unsigned long long) ktime_to_ms(delta); + dev_info(&(*pdev)->dev, + "registration took %lld msecs\n", duration); + if (duration < TEST_PROBE_THRESHOLD) { + dev_err(&(*pdev)->dev, + "test failed: probe was too quick\n"); + err = -ETIMEDOUT; + goto err_unregister_sync_driver; + } -err_unregister_async_dev_2: - platform_device_unregister(async_dev_2); + /* + * The async events should have completed while we were taking care + * of the synchronous events. We will now terminate any outstanding + * asynchronous probe calls remaining by forcing timeout and remove + * the driver before we return which should force the flush of the + * pending asynchronous probe calls. + * + * Otherwise if they completed without errors or warnings then + * report successful completion. + */ + if (atomic_read(&async_completed) != async_id) { + pr_err("async events still pending, forcing timeout\n"); + atomic_inc(&timeout); + err = -ETIMEDOUT; + } else if (!atomic_read(&errors) && !atomic_read(&warnings)) { + pr_info("completed successfully\n"); + return 0; + } +err_unregister_sync_driver: + platform_driver_unregister(&sync_driver); +err_unregister_sync_devs: + while (sync_id--) + platform_device_unregister(sync_dev[sync_id]); err_unregister_async_driver: platform_driver_unregister(&async_driver); +err_unregister_async_devs: + while (async_id--) + platform_device_unregister(async_dev[async_id]); + + /* + * If err is already set then count that as an additional error for + * the test. Otherwise we will report an invalid argument error and + * not count that as we should have reached here as a result of + * errors or warnings being reported by the probe routine. + */ + if (err) + atomic_inc(&errors); + else + err = -EINVAL; -err_unregister_async_dev_1: - platform_device_unregister(async_dev_1); + pr_err("Test failed with %d errors and %d warnings\n", + atomic_read(&errors), atomic_read(&warnings)); - return error; + return err; } module_init(test_async_probe_init); static void __exit test_async_probe_exit(void) { + int id = 2; + platform_driver_unregister(&async_driver); platform_driver_unregister(&sync_driver); - platform_device_unregister(async_dev_1); - platform_device_unregister(async_dev_2); - platform_device_unregister(sync_dev_1); + + while (id--) + platform_device_unregister(sync_dev[id]); + + id = NR_CPUS * 2; + while (id--) + platform_device_unregister(async_dev[id]); } module_exit(test_async_probe_exit); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 1e92b61d0bd5..282e2e82d849 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -428,14 +428,13 @@ static bool single_major = true; module_param(single_major, bool, 0444); MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: true)"); -static ssize_t rbd_add(struct bus_type *bus, const char *buf, - size_t count); -static ssize_t rbd_remove(struct bus_type *bus, const char *buf, - size_t count); -static ssize_t rbd_add_single_major(struct bus_type *bus, const char *buf, - size_t count); -static ssize_t rbd_remove_single_major(struct bus_type *bus, const char *buf, - size_t count); +static ssize_t add_store(struct bus_type *bus, const char *buf, size_t count); +static ssize_t remove_store(struct bus_type *bus, const char *buf, + size_t count); +static ssize_t add_single_major_store(struct bus_type *bus, const char *buf, + size_t count); +static ssize_t remove_single_major_store(struct bus_type *bus, const char *buf, + size_t count); static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth); static int rbd_dev_id_to_minor(int dev_id) @@ -464,16 +463,16 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev) return is_lock_owner; } -static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf) +static ssize_t supported_features_show(struct bus_type *bus, char *buf) { return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED); } -static BUS_ATTR(add, 0200, NULL, rbd_add); -static BUS_ATTR(remove, 0200, NULL, rbd_remove); -static BUS_ATTR(add_single_major, 0200, NULL, rbd_add_single_major); -static BUS_ATTR(remove_single_major, 0200, NULL, rbd_remove_single_major); -static BUS_ATTR(supported_features, 0444, rbd_supported_features_show, NULL); +static BUS_ATTR_WO(add); +static BUS_ATTR_WO(remove); +static BUS_ATTR_WO(add_single_major); +static BUS_ATTR_WO(remove_single_major); +static BUS_ATTR_RO(supported_features); static struct attribute *rbd_bus_attrs[] = { &bus_attr_add.attr, @@ -5934,9 +5933,7 @@ err_out_args: goto out; } -static ssize_t rbd_add(struct bus_type *bus, - const char *buf, - size_t count) +static ssize_t add_store(struct bus_type *bus, const char *buf, size_t count) { if (single_major) return -EINVAL; @@ -5944,9 +5941,8 @@ static ssize_t rbd_add(struct bus_type *bus, return do_rbd_add(bus, buf, count); } -static ssize_t rbd_add_single_major(struct bus_type *bus, - const char *buf, - size_t count) +static ssize_t add_single_major_store(struct bus_type *bus, const char *buf, + size_t count) { return do_rbd_add(bus, buf, count); } @@ -6049,9 +6045,7 @@ static ssize_t do_rbd_remove(struct bus_type *bus, return count; } -static ssize_t rbd_remove(struct bus_type *bus, - const char *buf, - size_t count) +static ssize_t remove_store(struct bus_type *bus, const char *buf, size_t count) { if (single_major) return -EINVAL; @@ -6059,9 +6053,8 @@ static ssize_t rbd_remove(struct bus_type *bus, return do_rbd_remove(bus, buf, count); } -static ssize_t rbd_remove_single_major(struct bus_type *bus, - const char *buf, - size_t count) +static ssize_t remove_single_major_store(struct bus_type *bus, const char *buf, + size_t count) { return do_rbd_remove(bus, buf, count); } diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 4e557684f792..fe69dccfa0c0 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -203,6 +203,7 @@ struct at_xdmac_chan { u32 save_cim; u32 save_cnda; u32 save_cndc; + u32 irq_status; unsigned long status; struct tasklet_struct tasklet; struct dma_slave_config sconfig; @@ -1580,8 +1581,8 @@ static void at_xdmac_tasklet(unsigned long data) struct at_xdmac_desc *desc; u32 error_mask; - dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n", - __func__, atchan->status); + dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n", + __func__, atchan->irq_status); error_mask = AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS @@ -1589,15 +1590,15 @@ static void at_xdmac_tasklet(unsigned long data) if (at_xdmac_chan_is_cyclic(atchan)) { at_xdmac_handle_cyclic(atchan); - } else if ((atchan->status & AT_XDMAC_CIS_LIS) - || (atchan->status & error_mask)) { + } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS) + || (atchan->irq_status & error_mask)) { struct dma_async_tx_descriptor *txd; - if (atchan->status & AT_XDMAC_CIS_RBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_RBEIS) dev_err(chan2dev(&atchan->chan), "read bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_WBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_WBEIS) dev_err(chan2dev(&atchan->chan), "write bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_ROIS) + if (atchan->irq_status & AT_XDMAC_CIS_ROIS) dev_err(chan2dev(&atchan->chan), "request overflow error!!!"); spin_lock(&atchan->lock); @@ -1652,7 +1653,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) atchan = &atxdmac->chan[i]; chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM); chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS); - atchan->status = chan_status & chan_imr; + atchan->irq_status = chan_status & chan_imr; dev_vdbg(atxdmac->dma.dev, "%s: chan%d: imr=0x%x, status=0x%x\n", __func__, i, chan_imr, chan_status); @@ -1666,7 +1667,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) at_xdmac_chan_read(atchan, AT_XDMAC_CDA), at_xdmac_chan_read(atchan, AT_XDMAC_CUBC)); - if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) + if (atchan->irq_status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask); tasklet_schedule(&atchan->tasklet); diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 1a44c8086d77..ae10f5614f95 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -406,38 +406,32 @@ static void bcm2835_dma_fill_cb_chain_with_sg( } } -static int bcm2835_dma_abort(void __iomem *chan_base) +static int bcm2835_dma_abort(struct bcm2835_chan *c) { - unsigned long cs; + void __iomem *chan_base = c->chan_base; long int timeout = 10000; - cs = readl(chan_base + BCM2835_DMA_CS); - if (!(cs & BCM2835_DMA_ACTIVE)) + /* + * A zero control block address means the channel is idle. + * (The ACTIVE flag in the CS register is not a reliable indicator.) + */ + if (!readl(chan_base + BCM2835_DMA_ADDR)) return 0; /* Write 0 to the active bit - Pause the DMA */ writel(0, chan_base + BCM2835_DMA_CS); /* Wait for any current AXI transfer to complete */ - while ((cs & BCM2835_DMA_ISPAUSED) && --timeout) { + while ((readl(chan_base + BCM2835_DMA_CS) & + BCM2835_DMA_WAITING_FOR_WRITES) && --timeout) cpu_relax(); - cs = readl(chan_base + BCM2835_DMA_CS); - } - /* We'll un-pause when we set of our next DMA */ + /* Peripheral might be stuck and fail to signal AXI write responses */ if (!timeout) - return -ETIMEDOUT; - - if (!(cs & BCM2835_DMA_ACTIVE)) - return 0; - - /* Terminate the control block chain */ - writel(0, chan_base + BCM2835_DMA_NEXTCB); - - /* Abort the whole DMA */ - writel(BCM2835_DMA_ABORT | BCM2835_DMA_ACTIVE, - chan_base + BCM2835_DMA_CS); + dev_err(c->vc.chan.device->dev, + "failed to complete outstanding writes\n"); + writel(BCM2835_DMA_RESET, chan_base + BCM2835_DMA_CS); return 0; } @@ -476,8 +470,15 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) spin_lock_irqsave(&c->vc.lock, flags); - /* Acknowledge interrupt */ - writel(BCM2835_DMA_INT, c->chan_base + BCM2835_DMA_CS); + /* + * Clear the INT flag to receive further interrupts. Keep the channel + * active in case the descriptor is cyclic or in case the client has + * already terminated the descriptor and issued a new one. (May happen + * if this IRQ handler is threaded.) If the channel is finished, it + * will remain idle despite the ACTIVE flag being set. + */ + writel(BCM2835_DMA_INT | BCM2835_DMA_ACTIVE, + c->chan_base + BCM2835_DMA_CS); d = c->desc; @@ -485,11 +486,7 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) if (d->cyclic) { /* call the cyclic callback */ vchan_cyclic_callback(&d->vd); - - /* Keep the DMA engine running */ - writel(BCM2835_DMA_ACTIVE, - c->chan_base + BCM2835_DMA_CS); - } else { + } else if (!readl(c->chan_base + BCM2835_DMA_ADDR)) { vchan_cookie_complete(&c->desc->vd); bcm2835_dma_start_desc(c); } @@ -779,7 +776,6 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) struct bcm2835_chan *c = to_bcm2835_dma_chan(chan); struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device); unsigned long flags; - int timeout = 10000; LIST_HEAD(head); spin_lock_irqsave(&c->vc.lock, flags); @@ -789,27 +785,11 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) list_del_init(&c->node); spin_unlock(&d->lock); - /* - * Stop DMA activity: we assume the callback will not be called - * after bcm_dma_abort() returns (even if it does, it will see - * c->desc is NULL and exit.) - */ + /* stop DMA activity */ if (c->desc) { vchan_terminate_vdesc(&c->desc->vd); c->desc = NULL; - bcm2835_dma_abort(c->chan_base); - - /* Wait for stopping */ - while (--timeout) { - if (!(readl(c->chan_base + BCM2835_DMA_CS) & - BCM2835_DMA_ACTIVE)) - break; - - cpu_relax(); - } - - if (!timeout) - dev_err(d->ddev.dev, "DMA transfer could not be terminated\n"); + bcm2835_dma_abort(c); } vchan_get_all_descriptors(&c->vc, &head); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 2eea4ef72915..6511928b4cdf 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -711,11 +711,9 @@ static int dmatest_func(void *data) srcs[i] = um->addr[i] + src_off; ret = dma_mapping_error(dev->dev, um->addr[i]); if (ret) { - dmaengine_unmap_put(um); result("src mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->to_cnt++; } @@ -730,11 +728,9 @@ static int dmatest_func(void *data) DMA_BIDIRECTIONAL); ret = dma_mapping_error(dev->dev, dsts[i]); if (ret) { - dmaengine_unmap_put(um); result("dst mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->bidi_cnt++; } @@ -762,12 +758,10 @@ static int dmatest_func(void *data) } if (!tx) { - dmaengine_unmap_put(um); result("prep error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } done->done = false; @@ -776,12 +770,10 @@ static int dmatest_func(void *data) cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { - dmaengine_unmap_put(um); result("submit error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } dma_async_issue_pending(chan); @@ -790,22 +782,20 @@ static int dmatest_func(void *data) status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); - dmaengine_unmap_put(um); - if (!done->done) { result("test timed out", total_tests, src_off, dst_off, len, 0); - failed_tests++; - continue; + goto error_unmap_continue; } else if (status != DMA_COMPLETE) { result(status == DMA_ERROR ? "completion error status" : "completion busy status", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } + dmaengine_unmap_put(um); + if (params->noverify) { verbose_result("test passed", total_tests, src_off, dst_off, len, 0); @@ -846,6 +836,12 @@ static int dmatest_func(void *data) verbose_result("test passed", total_tests, src_off, dst_off, len, 0); } + + continue; + +error_unmap_continue: + dmaengine_unmap_put(um); + failed_tests++; } ktime = ktime_sub(ktime_get(), ktime); ktime = ktime_sub(ktime, comparetime); diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index c2fff3f6c9ca..4a09af3cd546 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -618,7 +618,7 @@ static void imxdma_tasklet(unsigned long data) { struct imxdma_channel *imxdmac = (void *)data; struct imxdma_engine *imxdma = imxdmac->imxdma; - struct imxdma_desc *desc; + struct imxdma_desc *desc, *next_desc; unsigned long flags; spin_lock_irqsave(&imxdma->lock, flags); @@ -648,10 +648,10 @@ static void imxdma_tasklet(unsigned long data) list_move_tail(imxdmac->ld_active.next, &imxdmac->ld_free); if (!list_empty(&imxdmac->ld_queue)) { - desc = list_first_entry(&imxdmac->ld_queue, struct imxdma_desc, - node); + next_desc = list_first_entry(&imxdmac->ld_queue, + struct imxdma_desc, node); list_move_tail(imxdmac->ld_queue.next, &imxdmac->ld_active); - if (imxdma_xfer_desc(desc) < 0) + if (imxdma_xfer_desc(next_desc) < 0) dev_warn(imxdma->dev, "%s: channel: %d couldn't xfer desc\n", __func__, imxdmac->channel); } diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index f754578414f0..cac16c4b0df3 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -218,7 +218,7 @@ config FW_CFG_SYSFS_CMDLINE config INTEL_STRATIX10_SERVICE tristate "Intel Stratix10 Service Layer" - depends on HAVE_ARM_SMCCC + depends on ARCH_STRATIX10 && HAVE_ARM_SMCCC default n help Intel Stratix10 service layer runs at privileged exception level, diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 472c88ae1c0f..92f843eaf1e0 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -119,6 +119,11 @@ void scmi_driver_unregister(struct scmi_driver *driver) } EXPORT_SYMBOL_GPL(scmi_driver_unregister); +static void scmi_device_release(struct device *dev) +{ + kfree(to_scmi_dev(dev)); +} + struct scmi_device * scmi_device_create(struct device_node *np, struct device *parent, int protocol) { @@ -138,6 +143,7 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol) scmi_dev->dev.parent = parent; scmi_dev->dev.of_node = np; scmi_dev->dev.bus = &scmi_bus_type; + scmi_dev->dev.release = scmi_device_release; dev_set_name(&scmi_dev->dev, "scmi_dev.%d", id); retval = device_register(&scmi_dev->dev); @@ -156,9 +162,8 @@ free_mem: void scmi_device_destroy(struct scmi_device *scmi_dev) { scmi_handle_put(scmi_dev->handle); - device_unregister(&scmi_dev->dev); ida_simple_remove(&scmi_bus_id, scmi_dev->id); - kfree(scmi_dev); + device_unregister(&scmi_dev->dev); } void scmi_set_handle(struct scmi_device *scmi_dev) diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index a1a09e04fab8..13851b3d1c56 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -508,14 +508,11 @@ static int __init s10_init(void) return -ENODEV; np = of_find_matching_node(fw_np, s10_of_match); - if (!np) { - of_node_put(fw_np); + if (!np) return -ENODEV; - } of_node_put(np); ret = of_platform_populate(fw_np, s10_of_match, NULL, NULL); - of_node_put(fw_np); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 6896dec97fc7..0ed41a9d2d77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -1686,7 +1686,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, effective_mode &= ~S_IWUSR; if ((adev->flags & AMD_IS_APU) && - (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || + (attr == &sensor_dev_attr_power1_average.dev_attr.attr || + attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr|| attr == &sensor_dev_attr_power1_cap.dev_attr.attr)) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index 71913a18d142..a38e0fb4a6fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -38,6 +38,7 @@ #include "amdgpu_gem.h" #include <drm/amdgpu_drm.h> #include <linux/dma-buf.h> +#include <linux/dma-fence-array.h> /** * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table @@ -187,6 +188,48 @@ error: return ERR_PTR(ret); } +static int +__reservation_object_make_exclusive(struct reservation_object *obj) +{ + struct dma_fence **fences; + unsigned int count; + int r; + + if (!reservation_object_get_list(obj)) /* no shared fences to convert */ + return 0; + + r = reservation_object_get_fences_rcu(obj, NULL, &count, &fences); + if (r) + return r; + + if (count == 0) { + /* Now that was unexpected. */ + } else if (count == 1) { + reservation_object_add_excl_fence(obj, fences[0]); + dma_fence_put(fences[0]); + kfree(fences); + } else { + struct dma_fence_array *array; + + array = dma_fence_array_create(count, fences, + dma_fence_context_alloc(1), 0, + false); + if (!array) + goto err_fences_put; + + reservation_object_add_excl_fence(obj, &array->base); + dma_fence_put(&array->base); + } + + return 0; + +err_fences_put: + while (count--) + dma_fence_put(fences[count]); + kfree(fences); + return -ENOMEM; +} + /** * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation * @dma_buf: Shared DMA buffer @@ -218,16 +261,16 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf, if (attach->dev->driver != adev->dev->driver) { /* - * Wait for all shared fences to complete before we switch to future - * use of exclusive fence on this prime shared bo. + * We only create shared fences for internal use, but importers + * of the dmabuf rely on exclusive fences for implicitly + * tracking write hazards. As any of the current fences may + * correspond to a write, we need to convert all existing + * fences on the reservation object into a single exclusive + * fence. */ - r = reservation_object_wait_timeout_rcu(bo->tbo.resv, - true, false, - MAX_SCHEDULE_TIMEOUT); - if (unlikely(r < 0)) { - DRM_DEBUG_PRIME("Fence wait failed: %li\n", r); + r = __reservation_object_make_exclusive(bo->tbo.resv); + if (r) goto error_unreserve; - } } /* pin buffer into GTT */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index d2ea5ce2cefb..7c108e687683 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3363,14 +3363,15 @@ void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid, struct amdgpu_task_info *task_info) { struct amdgpu_vm *vm; + unsigned long flags; - spin_lock(&adev->vm_manager.pasid_lock); + spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); if (vm) *task_info = vm->task_info; - spin_unlock(&adev->vm_manager.pasid_lock); + spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 4cd31a276dcd..186db182f924 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -93,7 +93,20 @@ static void nbio_v7_4_enable_doorbell_aperture(struct amdgpu_device *adev, static void nbio_v7_4_enable_doorbell_selfring_aperture(struct amdgpu_device *adev, bool enable) { + u32 tmp = 0; + if (enable) { + tmp = REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_EN, 1) | + REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_MODE, 1) | + REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_SIZE, 0); + + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_LOW, + lower_32_bits(adev->doorbell.base)); + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_HIGH, + upper_32_bits(adev->doorbell.base)); + } + + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_CNTL, tmp); } static void nbio_v7_4_ih_doorbell_range(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 8849b74078d6..9b639974c70c 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -729,11 +729,13 @@ static int soc15_common_early_init(void *handle) case CHIP_RAVEN: adev->asic_funcs = &soc15_asic_funcs; if (adev->rev_id >= 0x8) - adev->external_rev_id = adev->rev_id + 0x81; + adev->external_rev_id = adev->rev_id + 0x79; else if (adev->pdev->device == 0x15d8) adev->external_rev_id = adev->rev_id + 0x41; + else if (adev->rev_id == 1) + adev->external_rev_id = adev->rev_id + 0x20; else - adev->external_rev_id = 0x1; + adev->external_rev_id = adev->rev_id + 0x01; if (adev->rev_id >= 0x8) { adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 5d85ff341385..2e7c44955f43 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -863,7 +863,7 @@ static int kfd_fill_mem_info_for_cpu(int numa_node_id, int *avail_size, return 0; } -#if CONFIG_X86_64 +#ifdef CONFIG_X86_64 static int kfd_fill_iolink_info_for_cpu(int numa_node_id, int *avail_size, uint32_t *num_entries, struct crat_subtype_iolink *sub_type_hdr) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f4fa40c387d3..0b392bfca284 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4082,7 +4082,8 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, } if (connector_type == DRM_MODE_CONNECTOR_HDMIA || - connector_type == DRM_MODE_CONNECTOR_DisplayPort) { + connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector_type == DRM_MODE_CONNECTOR_eDP) { drm_connector_attach_vrr_capable_property( &aconnector->base); } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c index afd287f08bc9..19801bdba0d2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c @@ -591,7 +591,15 @@ static void dce11_pplib_apply_display_requirements( dc, context->bw.dce.sclk_khz); - pp_display_cfg->min_dcfclock_khz = pp_display_cfg->min_engine_clock_khz; + /* + * As workaround for >4x4K lightup set dcfclock to min_engine_clock value. + * This is not required for less than 5 displays, + * thus don't request decfclk in dc to avoid impact + * on power saving. + * + */ + pp_display_cfg->min_dcfclock_khz = (context->stream_count > 4)? + pp_display_cfg->min_engine_clock_khz : 0; pp_display_cfg->min_engine_clock_deep_sleep_khz = context->bw.dce.sclk_deep_sleep_khz; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index f95c5f50eb0f..5273de3c5b98 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -1033,6 +1033,7 @@ static int smu10_get_clock_by_type_with_latency(struct pp_hwmgr *hwmgr, break; case amd_pp_dpp_clock: pclk_vol_table = pinfo->vdd_dep_on_dppclk; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 24a750436559..f91e02c87fd8 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -758,7 +758,7 @@ int drm_mode_hsync(const struct drm_display_mode *mode) if (mode->hsync) return mode->hsync; - if (mode->htotal < 0) + if (mode->htotal <= 0) return 0; calc_val = (mode->clock * 1000) / mode->htotal; /* hsync in Hz */ diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f3e1d6a0b7dd..4079050f9d6c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1086,7 +1086,7 @@ static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder, return DDI_CLK_SEL_TBT_810; default: MISSING_CASE(clock); - break; + return DDI_CLK_SEL_NONE; } case DPLL_ID_ICL_MGPLL1: case DPLL_ID_ICL_MGPLL2: diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3da9c0f9e948..248128126422 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15415,16 +15415,45 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc, } } +static bool has_bogus_dpll_config(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + + /* + * Some SNB BIOSen (eg. ASUS K53SV) are known to misprogram + * the hardware when a high res displays plugged in. DPLL P + * divider is zero, and the pipe timings are bonkers. We'll + * try to disable everything in that case. + * + * FIXME would be nice to be able to sanitize this state + * without several WARNs, but for now let's take the easy + * road. + */ + return IS_GEN6(dev_priv) && + crtc_state->base.active && + crtc_state->shared_dpll && + crtc_state->port_clock == 0; +} + static void intel_sanitize_encoder(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_connector *connector; + struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); + struct intel_crtc_state *crtc_state = crtc ? + to_intel_crtc_state(crtc->base.state) : NULL; /* We need to check both for a crtc link (meaning that the * encoder is active and trying to read from a pipe) and the * pipe itself being active. */ - bool has_active_crtc = encoder->base.crtc && - to_intel_crtc(encoder->base.crtc)->active; + bool has_active_crtc = crtc_state && + crtc_state->base.active; + + if (crtc_state && has_bogus_dpll_config(crtc_state)) { + DRM_DEBUG_KMS("BIOS has misprogrammed the hardware. Disabling pipe %c\n", + pipe_name(crtc->pipe)); + has_active_crtc = false; + } connector = intel_encoder_find_connector(encoder); if (connector && !has_active_crtc) { @@ -15435,16 +15464,25 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) /* Connector is active, but has no active pipe. This is * fallout from our resume register restoring. Disable * the encoder manually again. */ - if (encoder->base.crtc) { - struct drm_crtc_state *crtc_state = encoder->base.crtc->state; + if (crtc_state) { + struct drm_encoder *best_encoder; DRM_DEBUG_KMS("[ENCODER:%d:%s] manually disabled\n", encoder->base.base.id, encoder->base.name); + + /* avoid oopsing in case the hooks consult best_encoder */ + best_encoder = connector->base.state->best_encoder; + connector->base.state->best_encoder = &encoder->base; + if (encoder->disable) - encoder->disable(encoder, to_intel_crtc_state(crtc_state), connector->base.state); + encoder->disable(encoder, crtc_state, + connector->base.state); if (encoder->post_disable) - encoder->post_disable(encoder, to_intel_crtc_state(crtc_state), connector->base.state); + encoder->post_disable(encoder, crtc_state, + connector->base.state); + + connector->base.state->best_encoder = best_encoder; } encoder->base.crtc = NULL; diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index d2e003d8f3db..5170a0f5fe7b 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -494,7 +494,7 @@ skl_program_plane(struct intel_plane *plane, keymax = (key->max_value & 0xffffff) | PLANE_KEYMAX_ALPHA(alpha); - keymsk = key->channel_mask & 0x3ffffff; + keymsk = key->channel_mask & 0x7ffffff; if (alpha < 0xff) keymsk |= PLANE_KEYMSK_ALPHA_ENABLE; diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index 00a9c2ab9e6c..64fb788b6647 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -1406,7 +1406,7 @@ static void dsi_pll_disable(struct dss_pll *pll) static int dsi_dump_dsi_clocks(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; struct dss_pll_clock_info *cinfo = &dsi->pll.cinfo; enum dss_clk_source dispc_clk_src, dsi_clk_src; int dsi_module = dsi->module_id; @@ -1467,7 +1467,7 @@ static int dsi_dump_dsi_clocks(struct seq_file *s, void *p) #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; unsigned long flags; struct dsi_irq_stats stats; @@ -1558,7 +1558,7 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) static int dsi_dump_dsi_regs(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; if (dsi_runtime_get(dsi)) return 0; @@ -4751,6 +4751,17 @@ static int dsi_set_config(struct omap_dss_device *dssdev, dsi->vm.flags |= DISPLAY_FLAGS_HSYNC_HIGH; dsi->vm.flags &= ~DISPLAY_FLAGS_VSYNC_LOW; dsi->vm.flags |= DISPLAY_FLAGS_VSYNC_HIGH; + /* + * HACK: These flags should be handled through the omap_dss_device bus + * flags, but this will only be possible when the DSI encoder will be + * converted to the omapdrm-managed encoder model. + */ + dsi->vm.flags &= ~DISPLAY_FLAGS_PIXDATA_NEGEDGE; + dsi->vm.flags |= DISPLAY_FLAGS_PIXDATA_POSEDGE; + dsi->vm.flags &= ~DISPLAY_FLAGS_DE_LOW; + dsi->vm.flags |= DISPLAY_FLAGS_DE_HIGH; + dsi->vm.flags &= ~DISPLAY_FLAGS_SYNC_POSEDGE; + dsi->vm.flags |= DISPLAY_FLAGS_SYNC_NEGEDGE; dss_mgr_set_timings(&dsi->output, &dsi->vm); @@ -5083,15 +5094,15 @@ static int dsi_bind(struct device *dev, struct device *master, void *data) snprintf(name, sizeof(name), "dsi%u_regs", dsi->module_id + 1); dsi->debugfs.regs = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_regs, &dsi); + dsi_dump_dsi_regs, dsi); #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS snprintf(name, sizeof(name), "dsi%u_irqs", dsi->module_id + 1); dsi->debugfs.irqs = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_irqs, &dsi); + dsi_dump_dsi_irqs, dsi); #endif snprintf(name, sizeof(name), "dsi%u_clks", dsi->module_id + 1); dsi->debugfs.clks = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_clocks, &dsi); + dsi_dump_dsi_clocks, dsi); return 0; } @@ -5104,8 +5115,6 @@ static void dsi_unbind(struct device *dev, struct device *master, void *data) dss_debugfs_remove_file(dsi->debugfs.irqs); dss_debugfs_remove_file(dsi->debugfs.regs); - of_platform_depopulate(dev); - WARN_ON(dsi->scp_clk_refcount > 0); dss_pll_unregister(&dsi->pll); @@ -5457,6 +5466,8 @@ static int dsi_remove(struct platform_device *pdev) dsi_uninit_output(dsi); + of_platform_depopulate(&pdev->dev); + pm_runtime_disable(&pdev->dev); if (dsi->vdds_dsi_reg != NULL && dsi->vdds_dsi_enabled) { diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index d587779a80b4..a97294ac96d5 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -5676,7 +5676,7 @@ int ci_dpm_init(struct radeon_device *rdev) u16 data_offset, size; u8 frev, crev; struct ci_power_info *pi; - enum pci_bus_speed speed_cap; + enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN; struct pci_dev *root = rdev->pdev->bus->self; int ret; @@ -5685,7 +5685,8 @@ int ci_dpm_init(struct radeon_device *rdev) return -ENOMEM; rdev->pm.dpm.priv = pi; - speed_cap = pcie_get_speed_cap(root); + if (!pci_is_root_bus(rdev->pdev->bus)) + speed_cap = pcie_get_speed_cap(root); if (speed_cap == PCI_SPEED_UNKNOWN) { pi->sys_pcie_mask = 0; } else { diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 8fb60b3af015..0a785ef0ab66 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -6899,7 +6899,7 @@ int si_dpm_init(struct radeon_device *rdev) struct ni_power_info *ni_pi; struct si_power_info *si_pi; struct atom_clock_dividers dividers; - enum pci_bus_speed speed_cap; + enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN; struct pci_dev *root = rdev->pdev->bus->self; int ret; @@ -6911,7 +6911,8 @@ int si_dpm_init(struct radeon_device *rdev) eg_pi = &ni_pi->eg; pi = &eg_pi->rv7xx; - speed_cap = pcie_get_speed_cap(root); + if (!pci_is_root_bus(rdev->pdev->bus)) + speed_cap = pcie_get_speed_cap(root); if (speed_cap == PCI_SPEED_UNKNOWN) { si_pi->sys_pcie_mask = 0; } else { diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.c b/drivers/gpu/drm/rockchip/rockchip_rgb.c index 37f93022a106..c0351abf83a3 100644 --- a/drivers/gpu/drm/rockchip/rockchip_rgb.c +++ b/drivers/gpu/drm/rockchip/rockchip_rgb.c @@ -1,17 +1,8 @@ -//SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd * Author: * Sandy Huang <hjc@rock-chips.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include <drm/drmP.h> diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.h b/drivers/gpu/drm/rockchip/rockchip_rgb.h index 38b52e63b2b0..27b9635124bc 100644 --- a/drivers/gpu/drm/rockchip/rockchip_rgb.h +++ b/drivers/gpu/drm/rockchip/rockchip_rgb.h @@ -1,17 +1,8 @@ -//SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd * Author: * Sandy Huang <hjc@rock-chips.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifdef CONFIG_ROCKCHIP_RGB diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 0420f5c978b9..cf45d0f940f9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -761,6 +761,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, return PTR_ERR(tcon->sclk0); } } + clk_prepare_enable(tcon->sclk0); if (tcon->quirks->has_channel_1) { tcon->sclk1 = devm_clk_get(dev, "tcon-ch1"); @@ -775,6 +776,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, static void sun4i_tcon_free_clocks(struct sun4i_tcon *tcon) { + clk_disable_unprepare(tcon->sclk0); clk_disable_unprepare(tcon->clk); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 25afb1d594e3..7ef5dcb06104 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -26,6 +26,7 @@ **************************************************************************/ #include <linux/module.h> #include <linux/console.h> +#include <linux/dma-mapping.h> #include <drm/drmP.h> #include "vmwgfx_drv.h" @@ -34,7 +35,6 @@ #include <drm/ttm/ttm_placement.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_module.h> -#include <linux/intel-iommu.h> #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices" #define VMWGFX_CHIP_SVGAII 0 @@ -546,6 +546,21 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv) } /** + * vmw_assume_iommu - Figure out whether coherent dma-remapping might be + * taking place. + * @dev: Pointer to the struct drm_device. + * + * Return: true if iommu present, false otherwise. + */ +static bool vmw_assume_iommu(struct drm_device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev->dev); + + return !dma_is_direct(ops) && ops && + ops->map_page != dma_direct_map_page; +} + +/** * vmw_dma_select_mode - Determine how DMA mappings should be set up for this * system. * @@ -565,55 +580,27 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_alloc_coherent] = "Using coherent TTM pages.", [vmw_dma_map_populate] = "Keeping DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; -#ifdef CONFIG_X86 - const struct dma_map_ops *dma_ops = get_dma_ops(dev_priv->dev->dev); -#ifdef CONFIG_INTEL_IOMMU - if (intel_iommu_enabled) { + if (vmw_force_coherent) + dev_priv->map_mode = vmw_dma_alloc_coherent; + else if (vmw_assume_iommu(dev_priv->dev)) dev_priv->map_mode = vmw_dma_map_populate; - goto out_fixup; - } -#endif - - if (!(vmw_force_iommu || vmw_force_coherent)) { + else if (!vmw_force_iommu) dev_priv->map_mode = vmw_dma_phys; - DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); - return 0; - } - - dev_priv->map_mode = vmw_dma_map_populate; - - if (dma_ops && dma_ops->sync_single_for_cpu) + else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl()) dev_priv->map_mode = vmw_dma_alloc_coherent; -#ifdef CONFIG_SWIOTLB - if (swiotlb_nr_tbl() == 0) + else dev_priv->map_mode = vmw_dma_map_populate; -#endif -#ifdef CONFIG_INTEL_IOMMU -out_fixup: -#endif - if (dev_priv->map_mode == vmw_dma_map_populate && - vmw_restrict_iommu) + if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu) dev_priv->map_mode = vmw_dma_map_bind; - if (vmw_force_coherent) - dev_priv->map_mode = vmw_dma_alloc_coherent; - -#if !defined(CONFIG_SWIOTLB) && !defined(CONFIG_INTEL_IOMMU) - /* - * No coherent page pool - */ - if (dev_priv->map_mode == vmw_dma_alloc_coherent) + /* No TTM coherent page pool? FIXME: Ask TTM instead! */ + if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) && + (dev_priv->map_mode == vmw_dma_alloc_coherent)) return -EINVAL; -#endif - -#else /* CONFIG_X86 */ - dev_priv->map_mode = vmw_dma_map_populate; -#endif /* CONFIG_X86 */ DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); - return 0; } @@ -625,24 +612,20 @@ out_fixup: * With 32-bit we can only handle 32 bit PFNs. Optionally set that * restriction also for 64-bit systems. */ -#ifdef CONFIG_INTEL_IOMMU static int vmw_dma_masks(struct vmw_private *dev_priv) { struct drm_device *dev = dev_priv->dev; + int ret = 0; - if (intel_iommu_enabled && + ret = dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)); + if (dev_priv->map_mode != vmw_dma_phys && (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask)) { DRM_INFO("Restricting DMA addresses to 44 bits.\n"); - return dma_set_mask(dev->dev, DMA_BIT_MASK(44)); + return dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(44)); } - return 0; -} -#else -static int vmw_dma_masks(struct vmw_private *dev_priv) -{ - return 0; + + return ret; } -#endif static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index f2d13a72c05d..88b8178d4687 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3570,7 +3570,7 @@ int vmw_execbuf_fence_commands(struct drm_file *file_priv, *p_fence = NULL; } - return 0; + return ret; } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index b351fb5214d3..ed2f67822f45 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1646,7 +1646,7 @@ static int vmw_kms_check_topology(struct drm_device *dev, struct drm_connector_state *conn_state; struct vmw_connector_state *vmw_conn_state; - if (!du->pref_active) { + if (!du->pref_active && new_crtc_state->enable) { ret = -EINVAL; goto clean; } @@ -2554,8 +2554,8 @@ void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv, user_fence_rep) { struct vmw_fence_obj *fence = NULL; - uint32_t handle; - int ret; + uint32_t handle = 0; + int ret = 0; if (file_priv || user_fence_rep || vmw_validation_has_bos(ctx) || out_fence) diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index c530476edba6..ac9fda1b5a72 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -30,6 +30,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/kfifo.h> #include <linux/sched/signal.h> #include <linux/export.h> #include <linux/slab.h> @@ -661,17 +662,12 @@ EXPORT_SYMBOL_GPL(hid_dump_device); /* enqueue string to 'events' ring buffer */ void hid_debug_event(struct hid_device *hdev, char *buf) { - unsigned i; struct hid_debug_list *list; unsigned long flags; spin_lock_irqsave(&hdev->debug_list_lock, flags); - list_for_each_entry(list, &hdev->debug_list, node) { - for (i = 0; buf[i]; i++) - list->hid_debug_buf[(list->tail + i) % HID_DEBUG_BUFSIZE] = - buf[i]; - list->tail = (list->tail + i) % HID_DEBUG_BUFSIZE; - } + list_for_each_entry(list, &hdev->debug_list, node) + kfifo_in(&list->hid_debug_fifo, buf, strlen(buf)); spin_unlock_irqrestore(&hdev->debug_list_lock, flags); wake_up_interruptible(&hdev->debug_wait); @@ -722,8 +718,7 @@ void hid_dump_input(struct hid_device *hdev, struct hid_usage *usage, __s32 valu hid_debug_event(hdev, buf); kfree(buf); - wake_up_interruptible(&hdev->debug_wait); - + wake_up_interruptible(&hdev->debug_wait); } EXPORT_SYMBOL_GPL(hid_dump_input); @@ -1083,8 +1078,8 @@ static int hid_debug_events_open(struct inode *inode, struct file *file) goto out; } - if (!(list->hid_debug_buf = kzalloc(HID_DEBUG_BUFSIZE, GFP_KERNEL))) { - err = -ENOMEM; + err = kfifo_alloc(&list->hid_debug_fifo, HID_DEBUG_FIFOSIZE, GFP_KERNEL); + if (err) { kfree(list); goto out; } @@ -1104,77 +1099,57 @@ static ssize_t hid_debug_events_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct hid_debug_list *list = file->private_data; - int ret = 0, len; + int ret = 0, copied; DECLARE_WAITQUEUE(wait, current); mutex_lock(&list->read_mutex); - while (ret == 0) { - if (list->head == list->tail) { - add_wait_queue(&list->hdev->debug_wait, &wait); - set_current_state(TASK_INTERRUPTIBLE); - - while (list->head == list->tail) { - if (file->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } - if (signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } + if (kfifo_is_empty(&list->hid_debug_fifo)) { + add_wait_queue(&list->hdev->debug_wait, &wait); + set_current_state(TASK_INTERRUPTIBLE); + + while (kfifo_is_empty(&list->hid_debug_fifo)) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; + } - if (!list->hdev || !list->hdev->debug) { - ret = -EIO; - set_current_state(TASK_RUNNING); - goto out; - } + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } - /* allow O_NONBLOCK from other threads */ - mutex_unlock(&list->read_mutex); - schedule(); - mutex_lock(&list->read_mutex); - set_current_state(TASK_INTERRUPTIBLE); + /* if list->hdev is NULL we cannot remove_wait_queue(). + * if list->hdev->debug is 0 then hid_debug_unregister() + * was already called and list->hdev is being destroyed. + * if we add remove_wait_queue() here we can hit a race. + */ + if (!list->hdev || !list->hdev->debug) { + ret = -EIO; + set_current_state(TASK_RUNNING); + goto out; } - set_current_state(TASK_RUNNING); - remove_wait_queue(&list->hdev->debug_wait, &wait); + /* allow O_NONBLOCK from other threads */ + mutex_unlock(&list->read_mutex); + schedule(); + mutex_lock(&list->read_mutex); + set_current_state(TASK_INTERRUPTIBLE); } - if (ret) - goto out; + __set_current_state(TASK_RUNNING); + remove_wait_queue(&list->hdev->debug_wait, &wait); - /* pass the ringbuffer contents to userspace */ -copy_rest: - if (list->tail == list->head) + if (ret) goto out; - if (list->tail > list->head) { - len = list->tail - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - ret += len; - list->head += len; - } else { - len = HID_DEBUG_BUFSIZE - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - list->head = 0; - ret += len; - count -= len; - if (count > 0) - goto copy_rest; - } - } + + /* pass the fifo content to userspace, locking is not needed with only + * one concurrent reader and one concurrent writer + */ + ret = kfifo_to_user(&list->hid_debug_fifo, buffer, count, &copied); + if (ret) + goto out; + ret = copied; out: mutex_unlock(&list->read_mutex); return ret; @@ -1185,7 +1160,7 @@ static __poll_t hid_debug_events_poll(struct file *file, poll_table *wait) struct hid_debug_list *list = file->private_data; poll_wait(file, &list->hdev->debug_wait, wait); - if (list->head != list->tail) + if (!kfifo_is_empty(&list->hid_debug_fifo)) return EPOLLIN | EPOLLRDNORM; if (!list->hdev->debug) return EPOLLERR | EPOLLHUP; @@ -1200,7 +1175,7 @@ static int hid_debug_events_release(struct inode *inode, struct file *file) spin_lock_irqsave(&list->hdev->debug_list_lock, flags); list_del(&list->node); spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags); - kfree(list->hid_debug_buf); + kfifo_free(&list->hid_debug_fifo); kfree(list); return 0; @@ -1246,4 +1221,3 @@ void hid_debug_exit(void) { debugfs_remove_recursive(hid_debug_root); } - diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index b1086bfb0465..cd9c65f3d404 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1500,8 +1500,7 @@ static int omap_i2c_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM -static int omap_i2c_runtime_suspend(struct device *dev) +static int __maybe_unused omap_i2c_runtime_suspend(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1527,7 +1526,7 @@ static int omap_i2c_runtime_suspend(struct device *dev) return 0; } -static int omap_i2c_runtime_resume(struct device *dev) +static int __maybe_unused omap_i2c_runtime_resume(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1542,20 +1541,18 @@ static int omap_i2c_runtime_resume(struct device *dev) } static const struct dev_pm_ops omap_i2c_pm_ops = { + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) SET_RUNTIME_PM_OPS(omap_i2c_runtime_suspend, omap_i2c_runtime_resume, NULL) }; -#define OMAP_I2C_PM_OPS (&omap_i2c_pm_ops) -#else -#define OMAP_I2C_PM_OPS NULL -#endif /* CONFIG_PM */ static struct platform_driver omap_i2c_driver = { .probe = omap_i2c_probe, .remove = omap_i2c_remove, .driver = { .name = "omap_i2c", - .pm = OMAP_I2C_PM_OPS, + .pm = &omap_i2c_pm_ops, .of_match_table = of_match_ptr(omap_i2c_of_match), }, }; diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c index 031d568b4972..4e339cfd0c54 100644 --- a/drivers/iio/adc/axp288_adc.c +++ b/drivers/iio/adc/axp288_adc.c @@ -27,9 +27,18 @@ #include <linux/iio/machine.h> #include <linux/iio/driver.h> -#define AXP288_ADC_EN_MASK 0xF1 -#define AXP288_ADC_TS_PIN_GPADC 0xF2 -#define AXP288_ADC_TS_PIN_ON 0xF3 +/* + * This mask enables all ADCs except for the battery temp-sensor (TS), that is + * left as-is to avoid breaking charging on devices without a temp-sensor. + */ +#define AXP288_ADC_EN_MASK 0xF0 +#define AXP288_ADC_TS_ENABLE 0x01 + +#define AXP288_ADC_TS_CURRENT_ON_OFF_MASK GENMASK(1, 0) +#define AXP288_ADC_TS_CURRENT_OFF (0 << 0) +#define AXP288_ADC_TS_CURRENT_ON_WHEN_CHARGING (1 << 0) +#define AXP288_ADC_TS_CURRENT_ON_ONDEMAND (2 << 0) +#define AXP288_ADC_TS_CURRENT_ON (3 << 0) enum axp288_adc_id { AXP288_ADC_TS, @@ -44,6 +53,7 @@ enum axp288_adc_id { struct axp288_adc_info { int irq; struct regmap *regmap; + bool ts_enabled; }; static const struct iio_chan_spec axp288_adc_channels[] = { @@ -115,21 +125,33 @@ static int axp288_adc_read_channel(int *val, unsigned long address, return IIO_VAL_INT; } -static int axp288_adc_set_ts(struct regmap *regmap, unsigned int mode, - unsigned long address) +/* + * The current-source used for the battery temp-sensor (TS) is shared + * with the GPADC. For proper fuel-gauge and charger operation the TS + * current-source needs to be permanently on. But to read the GPADC we + * need to temporary switch the TS current-source to ondemand, so that + * the GPADC can use it, otherwise we will always read an all 0 value. + */ +static int axp288_adc_set_ts(struct axp288_adc_info *info, + unsigned int mode, unsigned long address) { int ret; - /* channels other than GPADC do not need to switch TS pin */ + /* No need to switch the current-source if the TS pin is disabled */ + if (!info->ts_enabled) + return 0; + + /* Channels other than GPADC do not need the current source */ if (address != AXP288_GP_ADC_H) return 0; - ret = regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, mode); + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, mode); if (ret) return ret; /* When switching to the GPADC pin give things some time to settle */ - if (mode == AXP288_ADC_TS_PIN_GPADC) + if (mode == AXP288_ADC_TS_CURRENT_ON_ONDEMAND) usleep_range(6000, 10000); return 0; @@ -145,14 +167,14 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); switch (mask) { case IIO_CHAN_INFO_RAW: - if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_GPADC, + if (axp288_adc_set_ts(info, AXP288_ADC_TS_CURRENT_ON_ONDEMAND, chan->address)) { dev_err(&indio_dev->dev, "GPADC mode\n"); ret = -EINVAL; break; } ret = axp288_adc_read_channel(val, chan->address, info->regmap); - if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_ON, + if (axp288_adc_set_ts(info, AXP288_ADC_TS_CURRENT_ON, chan->address)) dev_err(&indio_dev->dev, "TS pin restore\n"); break; @@ -164,13 +186,35 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, return ret; } -static int axp288_adc_set_state(struct regmap *regmap) +static int axp288_adc_initialize(struct axp288_adc_info *info) { - /* ADC should be always enabled for internal FG to function */ - if (regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, AXP288_ADC_TS_PIN_ON)) - return -EIO; + int ret, adc_enable_val; + + /* + * Determine if the TS pin is enabled and set the TS current-source + * accordingly. + */ + ret = regmap_read(info->regmap, AXP20X_ADC_EN1, &adc_enable_val); + if (ret) + return ret; + + if (adc_enable_val & AXP288_ADC_TS_ENABLE) { + info->ts_enabled = true; + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, + AXP288_ADC_TS_CURRENT_ON); + } else { + info->ts_enabled = false; + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, + AXP288_ADC_TS_CURRENT_OFF); + } + if (ret) + return ret; - return regmap_write(regmap, AXP20X_ADC_EN1, AXP288_ADC_EN_MASK); + /* Turn on the ADC for all channels except TS, leave TS as is */ + return regmap_update_bits(info->regmap, AXP20X_ADC_EN1, + AXP288_ADC_EN_MASK, AXP288_ADC_EN_MASK); } static const struct iio_info axp288_adc_iio_info = { @@ -200,7 +244,7 @@ static int axp288_adc_probe(struct platform_device *pdev) * Set ADC to enabled state at all time, including system suspend. * otherwise internal fuel gauge functionality may be affected. */ - ret = axp288_adc_set_state(axp20x->regmap); + ret = axp288_adc_initialize(info); if (ret) { dev_err(&pdev->dev, "unable to enable ADC device\n"); return ret; diff --git a/drivers/iio/adc/ti-ads8688.c b/drivers/iio/adc/ti-ads8688.c index 184d686ebd99..8b4568edd5cb 100644 --- a/drivers/iio/adc/ti-ads8688.c +++ b/drivers/iio/adc/ti-ads8688.c @@ -41,6 +41,7 @@ #define ADS8688_VREF_MV 4096 #define ADS8688_REALBITS 16 +#define ADS8688_MAX_CHANNELS 8 /* * enum ads8688_range - ADS8688 reference voltage range @@ -385,7 +386,7 @@ static irqreturn_t ads8688_trigger_handler(int irq, void *p) { struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; - u16 buffer[8]; + u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)]; int i, j = 0; for (i = 0; i < indio_dev->masklength; i++) { diff --git a/drivers/iio/chemical/atlas-ph-sensor.c b/drivers/iio/chemical/atlas-ph-sensor.c index a406ad31b096..3a20cb5d9bff 100644 --- a/drivers/iio/chemical/atlas-ph-sensor.c +++ b/drivers/iio/chemical/atlas-ph-sensor.c @@ -444,9 +444,8 @@ static int atlas_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_SCALE: switch (chan->type) { case IIO_TEMP: - *val = 1; /* 0.01 */ - *val2 = 100; - break; + *val = 10; + return IIO_VAL_INT; case IIO_PH: *val = 1; /* 0.001 */ *val2 = 1000; @@ -477,7 +476,7 @@ static int atlas_write_raw(struct iio_dev *indio_dev, int val, int val2, long mask) { struct atlas_data *data = iio_priv(indio_dev); - __be32 reg = cpu_to_be32(val); + __be32 reg = cpu_to_be32(val / 10); if (val2 != 0 || val < 0 || val > 20000) return -EINVAL; diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 1bd0cd7168df..05c6bc099d62 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1260,6 +1260,7 @@ static int exynos_iommu_add_device(struct device *dev) * direct calls to pm_runtime_get/put in this driver. */ data->link = device_link_add(dev, data->sysmmu, + DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME); } iommu_group_put(group); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 1457f931218e..78188bf7e90d 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -363,7 +363,7 @@ static int dmar_map_gfx = 1; static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; -static int intel_iommu_sm = 1; +static int intel_iommu_sm; static int iommu_identity_mapping; #define IDENTMAP_ALL 1 @@ -456,9 +456,9 @@ static int __init intel_iommu_setup(char *str) } else if (!strncmp(str, "sp_off", 6)) { pr_info("Disable supported super page\n"); intel_iommu_superpage = 0; - } else if (!strncmp(str, "sm_off", 6)) { - pr_info("Intel-IOMMU: disable scalable mode support\n"); - intel_iommu_sm = 0; + } else if (!strncmp(str, "sm_on", 5)) { + pr_info("Intel-IOMMU: scalable mode supported\n"); + intel_iommu_sm = 1; } else if (!strncmp(str, "tboot_noforce", 13)) { printk(KERN_INFO "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index c9ba9f377f63..77d4bd93fe4b 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1071,7 +1071,8 @@ static int rk_iommu_add_device(struct device *dev) iommu_group_put(group); iommu_device_link(&iommu->iommu, dev); - data->link = device_link_add(dev, iommu->dev, DL_FLAG_PM_RUNTIME); + data->link = device_link_add(dev, iommu->dev, + DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME); return 0; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 7f2a45445b00..c3aba3fc818d 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -97,9 +97,14 @@ struct its_device; * The ITS structure - contains most of the infrastructure, with the * top-level MSI domain, the command queue, the collections, and the * list of devices writing to it. + * + * dev_alloc_lock has to be taken for device allocations, while the + * spinlock must be taken to parse data structures such as the device + * list. */ struct its_node { raw_spinlock_t lock; + struct mutex dev_alloc_lock; struct list_head entry; void __iomem *base; phys_addr_t phys_base; @@ -156,6 +161,7 @@ struct its_device { void *itt; u32 nr_ites; u32 device_id; + bool shared; }; static struct { @@ -1580,6 +1586,9 @@ static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids) nr_irqs /= 2; } while (nr_irqs > 0); + if (!nr_irqs) + err = -ENOSPC; + if (err) goto out; @@ -2059,6 +2068,29 @@ static int __init allocate_lpi_tables(void) return 0; } +static u64 its_clear_vpend_valid(void __iomem *vlpi_base) +{ + u32 count = 1000000; /* 1s! */ + bool clean; + u64 val; + + val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val &= ~GICR_VPENDBASER_Valid; + gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + do { + val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + clean = !(val & GICR_VPENDBASER_Dirty); + if (!clean) { + count--; + cpu_relax(); + udelay(1); + } + } while (!clean && count); + + return val; +} + static void its_cpu_init_lpis(void) { void __iomem *rbase = gic_data_rdist_rd_base(); @@ -2144,6 +2176,30 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); + if (gic_rdists->has_vlpis) { + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + + /* + * It's possible for CPU to receive VLPIs before it is + * sheduled as a vPE, especially for the first CPU, and the + * VLPI with INTID larger than 2^(IDbits+1) will be considered + * as out of range and dropped by GIC. + * So we initialize IDbits to known value to avoid VLPI drop. + */ + val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; + pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n", + smp_processor_id(), val); + gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + + /* + * Also clear Valid bit of GICR_VPENDBASER, in case some + * ancient programming gets left in and has possibility of + * corrupting memory. + */ + val = its_clear_vpend_valid(vlpi_base); + WARN_ON(val & GICR_VPENDBASER_Dirty); + } + /* Make sure the GIC has seen the above */ dsb(sy); out: @@ -2422,6 +2478,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, struct its_device *its_dev; struct msi_domain_info *msi_info; u32 dev_id; + int err = 0; /* * We ignore "dev" entierely, and rely on the dev_id that has @@ -2444,6 +2501,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, return -EINVAL; } + mutex_lock(&its->dev_alloc_lock); its_dev = its_find_device(its, dev_id); if (its_dev) { /* @@ -2451,18 +2509,22 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, * another alias (PCI bridge of some sort). No need to * create the device. */ + its_dev->shared = true; pr_debug("Reusing ITT for devID %x\n", dev_id); goto out; } its_dev = its_create_device(its, dev_id, nvec, true); - if (!its_dev) - return -ENOMEM; + if (!its_dev) { + err = -ENOMEM; + goto out; + } pr_debug("ITT %d entries, %d bits\n", nvec, ilog2(nvec)); out: + mutex_unlock(&its->dev_alloc_lock); info->scratchpad[0].ptr = its_dev; - return 0; + return err; } static struct msi_domain_ops its_msi_domain_ops = { @@ -2566,6 +2628,7 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, { struct irq_data *d = irq_domain_get_irq_data(domain, virq); struct its_device *its_dev = irq_data_get_irq_chip_data(d); + struct its_node *its = its_dev->its; int i; for (i = 0; i < nr_irqs; i++) { @@ -2580,8 +2643,14 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, irq_domain_reset_irq_data(data); } - /* If all interrupts have been freed, start mopping the floor */ - if (bitmap_empty(its_dev->event_map.lpi_map, + mutex_lock(&its->dev_alloc_lock); + + /* + * If all interrupts have been freed, start mopping the + * floor. This is conditionned on the device not being shared. + */ + if (!its_dev->shared && + bitmap_empty(its_dev->event_map.lpi_map, its_dev->event_map.nr_lpis)) { its_lpi_free(its_dev->event_map.lpi_map, its_dev->event_map.lpi_base, @@ -2593,6 +2662,8 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, its_free_device(its_dev); } + mutex_unlock(&its->dev_alloc_lock); + irq_domain_free_irqs_parent(domain, virq, nr_irqs); } @@ -2755,26 +2826,11 @@ static void its_vpe_schedule(struct its_vpe *vpe) static void its_vpe_deschedule(struct its_vpe *vpe) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); - u32 count = 1000000; /* 1s! */ - bool clean; u64 val; - /* We're being scheduled out */ - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); - - do { - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - clean = !(val & GICR_VPENDBASER_Dirty); - if (!clean) { - count--; - cpu_relax(); - udelay(1); - } - } while (!clean && count); + val = its_clear_vpend_valid(vlpi_base); - if (unlikely(!clean && !count)) { + if (unlikely(val & GICR_VPENDBASER_Dirty)) { pr_err_ratelimited("ITS virtual pending table not cleaning\n"); vpe->idai = false; vpe->pending_last = true; @@ -3517,6 +3573,7 @@ static int __init its_probe_one(struct resource *res, } raw_spin_lock_init(&its->lock); + mutex_init(&its->dev_alloc_lock); INIT_LIST_HEAD(&its->entry); INIT_LIST_HEAD(&its->its_device_list); typer = gic_read_typer(its_base + GITS_TYPER); diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 25f32e1d7764..3496b61a312a 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -34,6 +34,9 @@ #define SEL_INT_PENDING (1 << 6) #define SEL_INT_NUM_MASK 0x3f +#define MMP2_ICU_INT_ROUTE_PJ4_IRQ (1 << 5) +#define MMP2_ICU_INT_ROUTE_PJ4_FIQ (1 << 6) + struct icu_chip_data { int nr_irqs; unsigned int virq_base; @@ -190,7 +193,8 @@ static const struct mmp_intc_conf mmp_conf = { static const struct mmp_intc_conf mmp2_conf = { .conf_enable = 0x20, .conf_disable = 0x0, - .conf_mask = 0x7f, + .conf_mask = MMP2_ICU_INT_ROUTE_PJ4_IRQ | + MMP2_ICU_INT_ROUTE_PJ4_FIQ, }; static void __exception_irq_entry mmp_handle_irq(struct pt_regs *regs) diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index 211ed6cffd10..578978711887 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -170,8 +170,8 @@ dev_expire_timer(struct timer_list *t) spin_lock_irqsave(&timer->dev->lock, flags); if (timer->id >= 0) list_move_tail(&timer->list, &timer->dev->expired); - spin_unlock_irqrestore(&timer->dev->lock, flags); wake_up_interruptible(&timer->dev->wait); + spin_unlock_irqrestore(&timer->dev->lock, flags); } static int diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 4eb5f8c56535..a20531e5f3b4 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -131,7 +131,7 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig) static void rq_completed(struct mapped_device *md) { /* nudge anyone waiting on suspend queue */ - if (unlikely(waitqueue_active(&md->wait))) + if (unlikely(wq_has_sleeper(&md->wait))) wake_up(&md->wait); /* diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 2b53c3841b53..515e6af9bed2 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -699,7 +699,7 @@ static void end_io_acct(struct dm_io *io) true, duration, &io->stats_aux); /* nudge anyone waiting on suspend queue */ - if (unlikely(waitqueue_active(&md->wait))) + if (unlikely(wq_has_sleeper(&md->wait))) wake_up(&md->wait); } @@ -1336,7 +1336,11 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, return r; } - bio_trim(clone, sector - clone->bi_iter.bi_sector, len); + bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); + clone->bi_iter.bi_size = to_bytes(len); + + if (bio_integrity(bio)) + bio_integrity_trim(clone); return 0; } diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 1fc8ea0f519b..ca4c9cc218a2 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -401,8 +401,11 @@ static void mei_io_list_flush_cl(struct list_head *head, struct mei_cl_cb *cb, *next; list_for_each_entry_safe(cb, next, head, list) { - if (cl == cb->cl) + if (cl == cb->cl) { list_del_init(&cb->list); + if (cb->fop_type == MEI_FOP_READ) + mei_io_cb_free(cb); + } } } diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 23739a60517f..bb1ee9834a02 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -139,6 +139,8 @@ #define MEI_DEV_ID_CNP_H 0xA360 /* Cannon Point H */ #define MEI_DEV_ID_CNP_H_4 0xA364 /* Cannon Point H 4 (iTouch) */ +#define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index e89497f858ae..3ab946ad3257 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -105,6 +105,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_4, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index 2bfa3a903bf9..744757f541be 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -47,7 +47,8 @@ * @dc: Virtio device control * @vpdev: VOP device which is the parent for this virtio device * @vr: Buffer for accessing the VRING - * @used: Buffer for used + * @used_virt: Virtual address of used ring + * @used: DMA address of used ring * @used_size: Size of the used buffer * @reset_done: Track whether VOP reset is complete * @virtio_cookie: Cookie returned upon requesting a interrupt @@ -61,6 +62,7 @@ struct _vop_vdev { struct mic_device_ctrl __iomem *dc; struct vop_device *vpdev; void __iomem *vr[VOP_MAX_VRINGS]; + void *used_virt[VOP_MAX_VRINGS]; dma_addr_t used[VOP_MAX_VRINGS]; int used_size[VOP_MAX_VRINGS]; struct completion reset_done; @@ -260,12 +262,12 @@ static bool vop_notify(struct virtqueue *vq) static void vop_del_vq(struct virtqueue *vq, int n) { struct _vop_vdev *vdev = to_vopvdev(vq->vdev); - struct vring *vr = (struct vring *)(vq + 1); struct vop_device *vpdev = vdev->vpdev; dma_unmap_single(&vpdev->dev, vdev->used[n], vdev->used_size[n], DMA_BIDIRECTIONAL); - free_pages((unsigned long)vr->used, get_order(vdev->used_size[n])); + free_pages((unsigned long)vdev->used_virt[n], + get_order(vdev->used_size[n])); vring_del_virtqueue(vq); vpdev->hw_ops->iounmap(vpdev, vdev->vr[n]); vdev->vr[n] = NULL; @@ -283,6 +285,26 @@ static void vop_del_vqs(struct virtio_device *dev) vop_del_vq(vq, idx++); } +static struct virtqueue *vop_new_virtqueue(unsigned int index, + unsigned int num, + struct virtio_device *vdev, + bool context, + void *pages, + bool (*notify)(struct virtqueue *vq), + void (*callback)(struct virtqueue *vq), + const char *name, + void *used) +{ + bool weak_barriers = false; + struct vring vring; + + vring_init(&vring, num, pages, MIC_VIRTIO_RING_ALIGN); + vring.used = used; + + return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context, + notify, callback, name); +} + /* * This routine will assign vring's allocated in host/io memory. Code in * virtio_ring.c however continues to access this io memory as if it were local @@ -302,7 +324,6 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, struct _mic_vring_info __iomem *info; void *used; int vr_size, _vr_size, err, magic; - struct vring *vr; u8 type = ioread8(&vdev->desc->type); if (index >= ioread8(&vdev->desc->num_vq)) @@ -322,17 +343,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, return ERR_PTR(-ENOMEM); vdev->vr[index] = va; memset_io(va, 0x0, _vr_size); - vq = vring_new_virtqueue( - index, - le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN, - dev, - false, - ctx, - (void __force *)va, vop_notify, callback, name); - if (!vq) { - err = -ENOMEM; - goto unmap; - } + info = va + _vr_size; magic = ioread32(&info->magic); @@ -341,18 +352,27 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, goto unmap; } - /* Allocate and reassign used ring now */ vdev->used_size[index] = PAGE_ALIGN(sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * le16_to_cpu(config.num)); used = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(vdev->used_size[index])); + vdev->used_virt[index] = used; if (!used) { err = -ENOMEM; dev_err(_vop_dev(vdev), "%s %d err %d\n", __func__, __LINE__, err); - goto del_vq; + goto unmap; + } + + vq = vop_new_virtqueue(index, le16_to_cpu(config.num), dev, ctx, + (void __force *)va, vop_notify, callback, + name, used); + if (!vq) { + err = -ENOMEM; + goto free_used; } + vdev->used[index] = dma_map_single(&vpdev->dev, used, vdev->used_size[index], DMA_BIDIRECTIONAL); @@ -360,26 +380,17 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, err = -ENOMEM; dev_err(_vop_dev(vdev), "%s %d err %d\n", __func__, __LINE__, err); - goto free_used; + goto del_vq; } writeq(vdev->used[index], &vqconfig->used_address); - /* - * To reassign the used ring here we are directly accessing - * struct vring_virtqueue which is a private data structure - * in virtio_ring.c. At the minimum, a BUILD_BUG_ON() in - * vring_new_virtqueue() would ensure that - * (&vq->vring == (struct vring *) (&vq->vq + 1)); - */ - vr = (struct vring *)(vq + 1); - vr->used = used; vq->priv = vdev; return vq; +del_vq: + vring_del_virtqueue(vq); free_used: free_pages((unsigned long)used, get_order(vdev->used_size[index])); -del_vq: - vring_del_virtqueue(vq); unmap: vpdev->hw_ops->iounmap(vpdev, vdev->vr[index]); return ERR_PTR(err); @@ -581,6 +592,8 @@ static int _vop_remove_device(struct mic_device_desc __iomem *d, int ret = -1; if (ioread8(&dc->config_change) == MIC_VIRTIO_PARAM_DEV_REMOVE) { + struct device *dev = get_device(&vdev->vdev.dev); + dev_dbg(&vpdev->dev, "%s %d config_change %d type %d vdev %p\n", __func__, __LINE__, @@ -592,7 +605,7 @@ static int _vop_remove_device(struct mic_device_desc __iomem *d, iowrite8(-1, &dc->h2c_vdev_db); if (status & VIRTIO_CONFIG_S_DRIVER_OK) wait_for_completion(&vdev->reset_done); - put_device(&vdev->vdev.dev); + put_device(dev); iowrite8(1, &dc->guest_ack); dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n", __func__, __LINE__, ioread8(&dc->guest_ack)); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 60104e1079c5..37f174ccbcec 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -480,6 +480,10 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, /* let's register it anyway to preserve ordering */ slave->offset = 0; slave->mtd.size = 0; + + /* Initialize ->erasesize to make add_mtd_device() happy. */ + slave->mtd.erasesize = parent->erasesize; + printk(KERN_ERR"mtd: partition \"%s\" is out of reach -- disabled\n", part->name); goto out_register; @@ -632,7 +636,6 @@ err_remove_part: mutex_unlock(&mtd_partitions_mutex); free_partition(new); - pr_info("%s:%i\n", __func__, __LINE__); return ret; } diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c index bd4cfac6b5aa..a4768df5083f 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c @@ -155,9 +155,10 @@ int gpmi_init(struct gpmi_nand_data *this) /* * Reset BCH here, too. We got failures otherwise :( - * See later BCH reset for explanation of MX23 handling + * See later BCH reset for explanation of MX23 and MX28 handling */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out; @@ -263,12 +264,10 @@ int bch_set_geometry(struct gpmi_nand_data *this) /* * Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this * chip, otherwise it will lock up. So we skip resetting BCH on the MX23. - * On the other hand, the MX28 needs the reset, because one case has been - * seen where the BCH produced ECC errors constantly after 10000 - * consecutive reboots. The latter case has not been seen on the MX23 - * yet, still we don't know if it could happen there as well. + * and MX28. */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index cca4b24d2ffa..839494ac457c 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -410,6 +410,7 @@ static int nand_check_wp(struct nand_chip *chip) /** * nand_fill_oob - [INTERN] Transfer client buffer to oob + * @chip: NAND chip object * @oob: oob data buffer * @len: oob data write length * @ops: oob ops structure diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index 1b722fe9213c..19a2b563acdf 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -158,7 +158,7 @@ static u32 add_marker_len(struct nand_bbt_descr *td) /** * read_bbt - [GENERIC] Read the bad block table starting from page - * @chip: NAND chip object + * @this: NAND chip object * @buf: temporary buffer * @page: the starting page * @num: the number of bbt descriptors to read diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 479c2f2cf17f..fa87ae28cdfe 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -304,24 +304,30 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, struct nand_device *nand = spinand_to_nand(spinand); struct mtd_info *mtd = nanddev_to_mtd(nand); struct nand_page_io_req adjreq = *req; - unsigned int nbytes = 0; - void *buf = NULL; + void *buf = spinand->databuf; + unsigned int nbytes; u16 column = 0; int ret; - memset(spinand->databuf, 0xff, - nanddev_page_size(nand) + - nanddev_per_page_oobsize(nand)); + /* + * Looks like PROGRAM LOAD (AKA write cache) does not necessarily reset + * the cache content to 0xFF (depends on vendor implementation), so we + * must fill the page cache entirely even if we only want to program + * the data portion of the page, otherwise we might corrupt the BBM or + * user data previously programmed in OOB area. + */ + nbytes = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); + memset(spinand->databuf, 0xff, nbytes); + adjreq.dataoffs = 0; + adjreq.datalen = nanddev_page_size(nand); + adjreq.databuf.out = spinand->databuf; + adjreq.ooblen = nanddev_per_page_oobsize(nand); + adjreq.ooboffs = 0; + adjreq.oobbuf.out = spinand->oobbuf; - if (req->datalen) { + if (req->datalen) memcpy(spinand->databuf + req->dataoffs, req->databuf.out, req->datalen); - adjreq.dataoffs = 0; - adjreq.datalen = nanddev_page_size(nand); - adjreq.databuf.out = spinand->databuf; - nbytes = adjreq.datalen; - buf = spinand->databuf; - } if (req->ooblen) { if (req->mode == MTD_OPS_AUTO_OOB) @@ -332,14 +338,6 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, else memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out, req->ooblen); - - adjreq.ooblen = nanddev_per_page_oobsize(nand); - adjreq.ooboffs = 0; - nbytes += nanddev_per_page_oobsize(nand); - if (!buf) { - buf = spinand->oobbuf; - column = nanddev_page_size(nand); - } } spinand_cache_op_adjust_colum(spinand, &adjreq, &column); @@ -370,8 +368,8 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, /* * We need to use the RANDOM LOAD CACHE operation if there's - * more than one iteration, because the LOAD operation resets - * the cache to 0xff. + * more than one iteration, because the LOAD operation might + * reset the cache to 0xff. */ if (nbytes) { column = op.addr.val; @@ -1018,11 +1016,11 @@ static int spinand_init(struct spinand_device *spinand) for (i = 0; i < nand->memorg.ntargets; i++) { ret = spinand_select_target(spinand, i); if (ret) - goto err_free_bufs; + goto err_manuf_cleanup; ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED); if (ret) - goto err_free_bufs; + goto err_manuf_cleanup; } ret = nanddev_init(nand, &spinand_ops, THIS_MODULE); diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 90f514252987..d9c56a779c08 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -511,9 +511,6 @@ static void b53_srab_prepare_irq(struct platform_device *pdev) /* Clear all pending interrupts */ writel(0xffffffff, priv->regs + B53_SRAB_INTR); - if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) - return; - for (i = 0; i < B53_N_PORTS; i++) { port = &priv->port_intrs[i]; diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 5200e4bdce93..ea243840ee0f 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -314,6 +314,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) { struct mv88e6xxx_chip *chip = dev_id; struct mv88e6xxx_atu_entry entry; + int spid; int err; u16 val; @@ -336,6 +337,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (err) goto out; + spid = entry.state; + if (val & MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU age out violation for %pM\n", @@ -344,23 +347,23 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU member violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_member_violation++; + "ATU member violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_member_violation++; } if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU miss violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_miss_violation++; + "ATU miss violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_miss_violation++; } if (val & MV88E6XXX_G1_ATU_OP_FULL_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU full violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_full_violation++; + "ATU full violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_full_violation++; } mutex_unlock(&chip->reg_lock); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f9521d0274b7..28c9b0bdf2f6 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -520,7 +520,6 @@ static void bcm_sysport_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bcm_sysport_priv *priv = netdev_priv(dev); - u32 reg; wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; wol->wolopts = priv->wolopts; @@ -528,11 +527,7 @@ static void bcm_sysport_get_wol(struct net_device *dev, if (!(priv->wolopts & WAKE_MAGICSECURE)) return; - /* Return the programmed SecureOn password */ - reg = umac_readl(priv, UMAC_PSW_MS); - put_unaligned_be16(reg, &wol->sopass[0]); - reg = umac_readl(priv, UMAC_PSW_LS); - put_unaligned_be32(reg, &wol->sopass[2]); + memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass)); } static int bcm_sysport_set_wol(struct net_device *dev, @@ -548,13 +543,8 @@ static int bcm_sysport_set_wol(struct net_device *dev, if (wol->wolopts & ~supported) return -EINVAL; - /* Program the SecureOn password */ - if (wol->wolopts & WAKE_MAGICSECURE) { - umac_writel(priv, get_unaligned_be16(&wol->sopass[0]), - UMAC_PSW_MS); - umac_writel(priv, get_unaligned_be32(&wol->sopass[2]), - UMAC_PSW_LS); - } + if (wol->wolopts & WAKE_MAGICSECURE) + memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass)); /* Flag the device and relevant IRQ as wakeup capable */ if (wol->wolopts) { @@ -2649,13 +2639,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv) unsigned int index, i = 0; u32 reg; - /* Password has already been programmed */ reg = umac_readl(priv, UMAC_MPD_CTRL); if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) reg |= MPD_EN; reg &= ~PSW_EN; - if (priv->wolopts & WAKE_MAGICSECURE) + if (priv->wolopts & WAKE_MAGICSECURE) { + /* Program the SecureOn password */ + umac_writel(priv, get_unaligned_be16(&priv->sopass[0]), + UMAC_PSW_MS); + umac_writel(priv, get_unaligned_be32(&priv->sopass[2]), + UMAC_PSW_LS); reg |= PSW_EN; + } umac_writel(priv, reg, UMAC_MPD_CTRL); if (priv->wolopts & WAKE_FILTER) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 0887e6356649..0b192fea9c5d 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -12,6 +12,7 @@ #define __BCM_SYSPORT_H #include <linux/bitmap.h> +#include <linux/ethtool.h> #include <linux/if_vlan.h> #include <linux/net_dim.h> @@ -778,6 +779,7 @@ struct bcm_sysport_priv { unsigned int crc_fwd:1; u16 rev; u32 wolopts; + u8 sopass[SOPASS_MAX]; unsigned int wol_irq_disabled:1; /* MIB related fields */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6a512871176b..8bc7e495b027 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4973,12 +4973,18 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; u32 map_idx = ring->map_idx; + unsigned int vector; + vector = bp->irq_tbl[map_idx].vector; + disable_irq_nosync(vector); rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); - if (rc) + if (rc) { + enable_irq(vector); goto err_out; + } bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id); bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons); + enable_irq(vector); bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id; if (!i) { diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 5db9f4158e62..134ae2862efa 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -1288,7 +1288,7 @@ static void sbdma_tx_process(struct sbmac_softc *sc, struct sbmacdma *d, * for transmits, we just free buffers. */ - dev_kfree_skb_irq(sb); + dev_consume_skb_irq(sb); /* * .. and advance to the next buffer. diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 5f03199a3acf..05f4a3b21e29 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -54,7 +54,6 @@ config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" depends on 64BIT && PCI imply PTP_1588_CLOCK - default y ---help--- This driver adds support for the Precision Time Protocol Clocks and Timestamping coprocessor (PTP) found on Cavium processors. diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 60641e202534..9a7f70db20c7 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, * csum is correct or is zero. */ if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc && - tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) { + tcp_udp_csum_ok && outer_csum_ok && + (ipv4_csum_ok || ipv6)) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = encap; } diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index 13430f75496c..f1a2da15dd0a 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -585,7 +585,7 @@ static void de_tx (struct de_private *de) netif_dbg(de, tx_done, de->dev, "tx done, slot %d\n", tx_tail); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } next: diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index b90bab72efdb..c1968b3ecec8 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -369,7 +369,7 @@ static irqreturn_t mpc52xx_fec_tx_interrupt(int irq, void *dev_id) dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } spin_unlock(&priv->lock); diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index c3d539e209ed..eb3e65e8868f 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1879,6 +1879,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth) u16 i, j; u8 __iomem *bd; + netdev_reset_queue(ugeth->ndev); + ug_info = ugeth->ug_info; uf_info = &ug_info->uf_info; diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 04fd1f135011..654ac534b10e 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs, memset(p, 0, regs->len); memcpy_fromio(p, io, B3_RAM_ADDR); - memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, - regs->len - B3_RI_WTO_R1); + if (regs->len > B3_RI_WTO_R1) { + memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, + regs->len - B3_RI_WTO_R1); + } } /* Wake on Lan only supported on Yukon chips with rev 1 or above */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 046948ead152..f3c7ab6faea5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -256,6 +256,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -369,6 +370,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's importent to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -612,16 +614,18 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v) + void *headers_v, u8 *match_level) { int tunnel_type; int err = 0; tunnel_type = mlx5e_tc_tun_get_type(filter_dev); if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + *match_level = MLX5_MATCH_L4; err = mlx5e_tc_tun_parse_vxlan(priv, spec, f, headers_c, headers_v); } else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) { + *match_level = MLX5_MATCH_L3; err = mlx5e_tc_tun_parse_gretap(priv, spec, f, headers_c, headers_v); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 706ce7bf15e7..b63f15de899d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -39,6 +39,6 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v); + void *headers_v, u8 *match_level); #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index f2573c2d2b5c..ef9e472daffb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -596,6 +596,10 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); + /* Update the encap source mac, in case that we delete + * the flows when encap source mac changed. + */ + ether_addr_copy(eth->h_source, e->route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index edd722824697..36eafc877e6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -148,6 +148,7 @@ struct mlx5e_encap_entry { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; + struct net_device *route_dev; int tunnel_type; int tunnel_hlen; int reformat_type; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index cae6c6d48984..b5c1b039375a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -128,6 +128,7 @@ struct mlx5e_tc_flow_parse_attr { struct net_device *filter_dev; struct mlx5_flow_spec spec; int num_mod_hdr_actions; + int max_mod_hdr_actions; void *mod_hdr_actions; int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; }; @@ -1302,7 +1303,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, - struct net_device *filter_dev) + struct net_device *filter_dev, u8 *match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, @@ -1317,7 +1318,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, int err = 0; err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f, - headers_c, headers_v); + headers_c, headers_v, match_level); if (err) { NL_SET_ERR_MSG_MOD(extack, "failed to parse tunnel attributes"); @@ -1426,7 +1427,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, struct net_device *filter_dev, - u8 *match_level) + u8 *match_level, u8 *tunnel_match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, @@ -1477,7 +1478,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, switch (key->addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: case FLOW_DISSECTOR_KEY_IPV6_ADDRS: - if (parse_tunnel_attr(priv, spec, f, filter_dev)) + if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level)) return -EOPNOTSUPP; break; default: @@ -1826,11 +1827,11 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_core_dev *dev = priv->mdev; struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; + u8 match_level, tunnel_match_level = MLX5_MATCH_NONE; struct mlx5_eswitch_rep *rep; - u8 match_level; int err; - err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level); + err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level, &tunnel_match_level); if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { rep = rpriv->rep; @@ -1846,10 +1847,12 @@ static int parse_cls_flower(struct mlx5e_priv *priv, } } - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { flow->esw_attr->match_level = match_level; - else + flow->esw_attr->tunnel_match_level = tunnel_match_level; + } else { flow->nic_attr->match_level = match_level; + } return err; } @@ -1934,9 +1937,9 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 2, udp.dest, 0), }; -/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at - * max from the SW pedit action. On success, it says how many HW actions were - * actually parsed. +/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at + * max from the SW pedit action. On success, attr->num_mod_hdr_actions + * says how many HW actions were actually parsed. */ static int offload_pedit_fields(struct pedit_headers *masks, struct pedit_headers *vals, @@ -1960,9 +1963,11 @@ static int offload_pedit_fields(struct pedit_headers *masks, add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD]; action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto); - action = parse_attr->mod_hdr_actions; - max_actions = parse_attr->num_mod_hdr_actions; - nactions = 0; + action = parse_attr->mod_hdr_actions + + parse_attr->num_mod_hdr_actions * action_size; + + max_actions = parse_attr->max_mod_hdr_actions; + nactions = parse_attr->num_mod_hdr_actions; for (i = 0; i < ARRAY_SIZE(fields); i++) { f = &fields[i]; @@ -2073,7 +2078,7 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv, if (!parse_attr->mod_hdr_actions) return -ENOMEM; - parse_attr->num_mod_hdr_actions = max_actions; + parse_attr->max_mod_hdr_actions = max_actions; return 0; } @@ -2119,9 +2124,11 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, goto out_err; } - err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr); - if (err) - goto out_err; + if (!parse_attr->mod_hdr_actions) { + err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr); + if (err) + goto out_err; + } err = offload_pedit_fields(masks, vals, parse_attr, extack); if (err < 0) @@ -2179,6 +2186,7 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, static bool modify_header_match_supported(struct mlx5_flow_spec *spec, struct tcf_exts *exts, + u32 actions, struct netlink_ext_ack *extack) { const struct tc_action *a; @@ -2188,7 +2196,11 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, u16 ethertype; int nkeys, i; - headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers); + else + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); /* for non-IP we only re-write MACs, so we're okay */ @@ -2245,7 +2257,7 @@ static bool actions_match_supported(struct mlx5e_priv *priv, if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return modify_header_match_supported(&parse_attr->spec, exts, - extack); + actions, extack); return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 598ad7e4d5c9..0e55cd1f2e98 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -387,8 +387,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); if (unlikely(contig_wqebbs_room < num_wqebbs)) { +#ifdef CONFIG_MLX5_EN_IPSEC + struct mlx5_wqe_eth_seg cur_eth = wqe->eth; +#endif mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); mlx5e_sq_fetch_wqe(sq, &wqe, &pi); +#ifdef CONFIG_MLX5_EN_IPSEC + wqe->eth = cur_eth; +#endif } /* fill wqe */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 9c89eea9b2c3..748ff178a1d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -312,6 +312,7 @@ struct mlx5_esw_flow_attr { } dests[MLX5_MAX_FLOW_FWD_VPORTS]; u32 mod_hdr_id; u8 match_level; + u8 tunnel_match_level; struct mlx5_fc *counter; u32 chain; u16 prio; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 53065b6ae593..d4e6fe5b9300 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -160,14 +160,15 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_eswitch_owner_vhca_id); - if (attr->match_level == MLX5_MATCH_NONE) - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; - else - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | - MLX5_MATCH_MISC_PARAMETERS; - - if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) - spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + if (attr->tunnel_match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + if (attr->match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + } else if (attr->match_level != MLX5_MATCH_NONE) { + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) flow_act.modify_id = attr->mod_hdr_id; diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 24a90163775e..2d8a77cc156b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -53,7 +53,7 @@ extern const struct qed_common_ops qed_common_ops_pass; #define QED_MAJOR_VERSION 8 -#define QED_MINOR_VERSION 33 +#define QED_MINOR_VERSION 37 #define QED_REVISION_VERSION 0 #define QED_ENGINEERING_VERSION 20 diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index e68ca83ae915..58be1c4c6668 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2216,7 +2216,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 num_queues = 0; /* Since the feature controls only queue-zones, - * make sure we have the contexts [rx, tx, xdp] to + * make sure we have the contexts [rx, xdp, tcs] to * match. */ for_each_hwfn(cdev, i) { @@ -2226,7 +2226,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 cids; cids = hwfn->pf_params.eth_pf_params.num_cons; - num_queues += min_t(u16, l2_queues, cids / 3); + cids /= (2 + info->num_tc); + num_queues += min_t(u16, l2_queues, cids); } /* queues might theoretically be >256, but interrupts' @@ -2870,7 +2871,8 @@ static int qed_get_coalesce(struct qed_dev *cdev, u16 *coal, void *handle) p_hwfn = p_cid->p_owner; rc = qed_get_queue_coalesce(p_hwfn, coal, handle); if (rc) - DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n"); + DP_VERBOSE(cdev, QED_MSG_DEBUG, + "Unable to read queue coalescing\n"); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 4179c9013fc6..96ab77ae6af5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -382,6 +382,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn); * @param p_hwfn */ void qed_consq_free(struct qed_hwfn *p_hwfn); +int qed_spq_pend_post(struct qed_hwfn *p_hwfn); /** * @file diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 888274fa208b..5a495fda9e9d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -604,6 +604,9 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn) p_ent->ramrod.pf_update.update_mf_vlan_flag = true; p_ent->ramrod.pf_update.mf_vlan = cpu_to_le16(p_hwfn->hw_info.ovlan); + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + p_ent->ramrod.pf_update.mf_vlan |= + cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13)); return qed_spq_post(p_hwfn, p_ent, NULL); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index eb88bbc6b193..ba64ff9bedbd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -397,6 +397,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie) qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain)); + /* Attempt to post pending requests */ + spin_lock_bh(&p_hwfn->p_spq->lock); + rc = qed_spq_pend_post(p_hwfn); + spin_unlock_bh(&p_hwfn->p_spq->lock); + return rc; } @@ -767,7 +772,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn, return 0; } -static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) +int qed_spq_pend_post(struct qed_hwfn *p_hwfn) { struct qed_spq *p_spq = p_hwfn->p_spq; struct qed_spq_entry *p_ent = NULL; @@ -905,7 +910,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent = NULL; struct qed_spq_entry *tmp; struct qed_spq_entry *found = NULL; - int rc; if (!p_hwfn) return -EINVAL; @@ -963,12 +967,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, */ qed_spq_return_entry(p_hwfn, found); - /* Attempt to post pending requests */ - spin_lock_bh(&p_spq->lock); - rc = qed_spq_pend_post(p_hwfn); - spin_unlock_bh(&p_spq->lock); - - return rc; + return 0; } int qed_consq_alloc(struct qed_hwfn *p_hwfn) diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 613249d1e967..730997b13747 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -56,7 +56,7 @@ #include <net/tc_act/tc_gact.h> #define QEDE_MAJOR_VERSION 8 -#define QEDE_MINOR_VERSION 33 +#define QEDE_MINOR_VERSION 37 #define QEDE_REVISION_VERSION 0 #define QEDE_ENGINEERING_VERSION 20 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "." \ @@ -494,6 +494,9 @@ struct qede_reload_args { /* Datapath functions definition */ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev); +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback); netdev_features_t qede_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index bdf816fe5a16..31b046e24565 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1695,6 +1695,19 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) +{ + struct qede_dev *edev = netdev_priv(dev); + int total_txq; + + total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc; + + return QEDE_TSS_COUNT(edev) ? + fallback(dev, skb, NULL) % total_txq : 0; +} + /* 8B udp header + 8B base tunnel header + 32B option length */ #define QEDE_MAX_TUN_HDR_LEN 48 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 5a74fcbdbc2b..9790f26d17c4 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -631,6 +631,7 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -666,6 +667,7 @@ static const struct net_device_ops qede_netdev_vf_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -684,6 +686,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 15c62c160953..be47d864f8b9 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1037,7 +1037,7 @@ static void epic_tx(struct net_device *dev, struct epic_private *ep) skb = ep->tx_skbuff[entry]; pci_unmap_single(ep->pci_dev, ep->tx_ring[entry].bufaddr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); ep->tx_skbuff[entry] = NULL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index d1f61c25d82b..5d85742a2be0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -721,8 +721,11 @@ static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (usec * (clk / 1000000)) / 256; } @@ -731,8 +734,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (riwt * 256) / (clk / 1000000); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5afba69981cf..685d20472358 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3023,10 +3023,22 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q = &priv->tx_queue[queue]; + if (priv->tx_path_in_lpi_mode) + stmmac_disable_eee_mode(priv); + /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { - if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) + if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { + /* + * There is no way to determine the number of TSO + * capable Queues. Let's use always the Queue 0 + * because if TSO is supported then at least this + * one will be capable. + */ + skb_set_queue_mapping(skb, 0); + return stmmac_tso_xmit(skb, dev); + } } if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { @@ -3041,9 +3053,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - if (priv->tx_path_in_lpi_mode) - stmmac_disable_eee_mode(priv); - entry = tx_q->cur_tx; first_entry = entry; WARN_ON(tx_q->tx_skbuff[first_entry]); diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 7ec4eb74fe21..6fc05c106afc 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -1898,7 +1898,7 @@ static inline void cas_tx_ringN(struct cas *cp, int ring, int limit) cp->net_stats[ring].tx_packets++; cp->net_stats[ring].tx_bytes += skb->len; spin_unlock(&cp->stat_lock[ring]); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } cp->tx_old[ring] = entry; diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 720b7ac77f3b..e9b757b03b56 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -781,7 +781,7 @@ static void bigmac_tx(struct bigmac *bp) DTX(("skb(%p) ", skb)); bp->tx_skbs[elem] = NULL; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); elem = NEXT_TX(elem); } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index ff641cf30a4e..d007dfeba5c3 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1962,7 +1962,7 @@ static void happy_meal_tx(struct happy_meal *hp) this = &txbase[elem]; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dev->stats.tx_packets++; } hp->tx_old = elem; diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index dc966ddb6d81..b24c11187017 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1739,7 +1739,7 @@ static void bdx_tx_cleanup(struct bdx_priv *priv) tx_level -= db->rptr->len; /* '-' koz len is negative */ /* now should come skb pointer - free it */ - dev_kfree_skb_irq(db->rptr->addr.skb); + dev_consume_skb_irq(db->rptr->addr.skb); bdx_tx_db_inc_rptr(db); } diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 82412691ee66..27f6cf140845 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -1740,7 +1740,7 @@ static void velocity_free_tx_buf(struct velocity_info *vptr, dma_unmap_single(vptr->dev, tdinfo->skb_dma[i], le16_to_cpu(pktlen), DMA_TO_DEVICE); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tdinfo->skb = NULL; } diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 38ac8ef41f5f..56b7791911bf 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -3512,7 +3512,7 @@ static int dfx_xmt_done(DFX_board_t *bp) bp->descr_block_virt->xmt_data[comp].long_1, p_xmt_drv_descr->p_skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(p_xmt_drv_descr->p_skb); + dev_consume_skb_irq(p_xmt_drv_descr->p_skb); /* * Move to start of next packet by updating completion index diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 58bbba8582b0..3377ac66a347 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1512,9 +1512,13 @@ static void geneve_link_config(struct net_device *dev, } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { - struct rt6_info *rt = rt6_lookup(geneve->net, - &info->key.u.ipv6.dst, NULL, 0, - NULL, 0); + struct rt6_info *rt; + + if (!__in6_dev_get(dev)) + break; + + rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, + NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 44de81e5f140..c589f5ae75bb 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -905,9 +905,9 @@ mcr20a_irq_clean_complete(void *context) } break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_SEQIRQ): - /* rx is starting */ - dev_dbg(printdev(lp), "RX is starting\n"); - mcr20a_handle_rx(lp); + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ): if (lp->is_tx) { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 19bdde60680c..7cdac77d0c68 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -100,12 +100,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, err = ipvlan_register_nf_hook(read_pnet(&port->pnet)); if (!err) { mdev->l3mdev_ops = &ipvl_l3mdev_ops; - mdev->priv_flags |= IFF_L3MDEV_MASTER; + mdev->priv_flags |= IFF_L3MDEV_RX_HANDLER; } else goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ - mdev->priv_flags &= ~IFF_L3MDEV_MASTER; + mdev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); mdev->l3mdev_ops = NULL; } @@ -167,7 +167,7 @@ static void ipvlan_port_destroy(struct net_device *dev) struct sk_buff *skb; if (port->mode == IPVLAN_MODE_L3S) { - dev->priv_flags &= ~IFF_L3MDEV_MASTER; + dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(dev_net(dev)); dev->l3mdev_ops = NULL; } diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 18b41bc345ab..6e8807212aa3 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -898,14 +898,14 @@ static void decode_txts(struct dp83640_private *dp83640, struct phy_txts *phy_txts) { struct skb_shared_hwtstamps shhwtstamps; + struct dp83640_skb_info *skb_info; struct sk_buff *skb; - u64 ns; u8 overflow; + u64 ns; /* We must already have the skb that triggered this. */ - +again: skb = skb_dequeue(&dp83640->tx_queue); - if (!skb) { pr_debug("have timestamp but tx_queue empty\n"); return; @@ -920,6 +920,11 @@ static void decode_txts(struct dp83640_private *dp83640, } return; } + skb_info = (struct dp83640_skb_info *)skb->cb; + if (time_after(jiffies, skb_info->tmo)) { + kfree_skb(skb); + goto again; + } ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); @@ -1472,6 +1477,7 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, static void dp83640_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { + struct dp83640_skb_info *skb_info = (struct dp83640_skb_info *)skb->cb; struct dp83640_private *dp83640 = phydev->priv; switch (dp83640->hwts_tx_en) { @@ -1484,6 +1490,7 @@ static void dp83640_txtstamp(struct phy_device *phydev, /* fall through */ case HWTSTAMP_TX_ON: skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; skb_queue_tail(&dp83640->tx_queue, skb); break; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 2e12f982534f..abb7876a8776 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -847,7 +847,6 @@ static int m88e1510_config_init(struct phy_device *phydev) /* SGMII-to-Copper mode initialization */ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { - /* Select page 18 */ err = marvell_set_page(phydev, 18); if (err < 0) @@ -870,21 +869,6 @@ static int m88e1510_config_init(struct phy_device *phydev) err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); if (err < 0) return err; - - /* There appears to be a bug in the 88e1512 when used in - * SGMII to copper mode, where the AN advertisement register - * clears the pause bits each time a negotiation occurs. - * This means we can never be truely sure what was advertised, - * so disable Pause support. - */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->advertising); } return m88e1318_config_init(phydev); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 18656c4094b3..fed298c0cb39 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -866,8 +866,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file, if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); - tun_set_real_num_queues(tun); - /* device is allowed to go away first, so no need to hold extra * refcnt. */ @@ -879,6 +877,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; + tun_set_real_num_queues(tun); out: return err; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8fadd8eaf601..4cfceb789eea 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -57,6 +57,8 @@ module_param(napi_tx, bool, 0644); #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) +#define VIRTIO_XDP_FLAG BIT(0) + /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- @@ -252,6 +254,21 @@ struct padded_vnet_hdr { char padding[4]; }; +static bool is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & VIRTIO_XDP_FLAG; +} + +static void *xdp_to_ptr(struct xdp_frame *ptr) +{ + return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG); +} + +static struct xdp_frame *ptr_to_xdp(void *ptr) +{ + return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); +} + /* Converting between virtqueue no. and kernel tx/rx queue no. * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq */ @@ -462,7 +479,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, sg_init_one(sq->sg, xdpf->data, xdpf->len); - err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC); + err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf), + GFP_ATOMIC); if (unlikely(err)) return -ENOSPC; /* Caller handle free/refcnt */ @@ -482,36 +500,47 @@ static int virtnet_xdp_xmit(struct net_device *dev, { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = vi->rq; - struct xdp_frame *xdpf_sent; struct bpf_prog *xdp_prog; struct send_queue *sq; unsigned int len; + int packets = 0; + int bytes = 0; int drops = 0; int kicks = 0; int ret, err; + void *ptr; int i; - sq = virtnet_xdp_sq(vi); - - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { - ret = -EINVAL; - drops = n; - goto out; - } - /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. */ xdp_prog = rcu_dereference(rq->xdp_prog); - if (!xdp_prog) { - ret = -ENXIO; + if (!xdp_prog) + return -ENXIO; + + sq = virtnet_xdp_sq(vi); + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { + ret = -EINVAL; drops = n; goto out; } /* Free up any pending old buffers before queueing new ones. */ - while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) - xdp_return_frame(xdpf_sent); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(is_xdp_frame(ptr))) { + struct xdp_frame *frame = ptr_to_xdp(ptr); + + bytes += frame->len; + xdp_return_frame(frame); + } else { + struct sk_buff *skb = ptr; + + bytes += skb->len; + napi_consume_skb(skb, false); + } + packets++; + } for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; @@ -530,6 +559,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, } out: u64_stats_update_begin(&sq->stats.syncp); + sq->stats.bytes += bytes; + sq->stats.packets += packets; sq->stats.xdp_tx += n; sq->stats.xdp_tx_drops += drops; sq->stats.kicks += kicks; @@ -1332,18 +1363,26 @@ static int virtnet_receive(struct receive_queue *rq, int budget, static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) { - struct sk_buff *skb; unsigned int len; unsigned int packets = 0; unsigned int bytes = 0; + void *ptr; - while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) { - pr_debug("Sent skb %p\n", skb); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(!is_xdp_frame(ptr))) { + struct sk_buff *skb = ptr; - bytes += skb->len; - packets++; + pr_debug("Sent skb %p\n", skb); + + bytes += skb->len; + napi_consume_skb(skb, in_napi); + } else { + struct xdp_frame *frame = ptr_to_xdp(ptr); - napi_consume_skb(skb, in_napi); + bytes += frame->len; + xdp_return_frame(frame); + } + packets++; } /* Avoid overhead when no packets have been processed @@ -1358,6 +1397,16 @@ static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) u64_stats_update_end(&sq->stats.syncp); } +static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) +{ + if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) + return false; + else if (q < vi->curr_queue_pairs) + return true; + else + return false; +} + static void virtnet_poll_cleantx(struct receive_queue *rq) { struct virtnet_info *vi = rq->vq->vdev->priv; @@ -1365,7 +1414,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq) struct send_queue *sq = &vi->sq[index]; struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); - if (!sq->napi.weight) + if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index)) return; if (__netif_tx_trylock(txq)) { @@ -1442,8 +1491,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) { struct send_queue *sq = container_of(napi, struct send_queue, napi); struct virtnet_info *vi = sq->vq->vdev->priv; - struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); + unsigned int index = vq2txq(sq->vq); + struct netdev_queue *txq; + if (unlikely(is_xdp_raw_buffer_queue(vi, index))) { + /* We don't need to enable cb for XDP */ + napi_complete_done(napi, 0); + return 0; + } + + txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); free_old_xmit_skbs(sq, true); __netif_tx_unlock(txq); @@ -2395,6 +2452,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, return -ENOMEM; } + old_prog = rtnl_dereference(vi->rq[0].xdp_prog); + if (!prog && !old_prog) + return 0; + if (prog) { prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); if (IS_ERR(prog)) @@ -2402,36 +2463,62 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } /* Make sure NAPI is not using any XDP TX queues for RX. */ - if (netif_running(dev)) - for (i = 0; i < vi->max_queue_pairs; i++) + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) { napi_disable(&vi->rq[i].napi); + virtnet_napi_tx_disable(&vi->sq[i].napi); + } + } + + if (!prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0) + virtnet_restore_guest_offloads(vi); + } + synchronize_net(); + } - netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); if (err) goto err; + netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); vi->xdp_queue_pairs = xdp_qp; - for (i = 0; i < vi->max_queue_pairs; i++) { - old_prog = rtnl_dereference(vi->rq[i].xdp_prog); - rcu_assign_pointer(vi->rq[i].xdp_prog, prog); - if (i == 0) { - if (!old_prog) + if (prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0 && !old_prog) virtnet_clear_guest_offloads(vi); - if (!prog) - virtnet_restore_guest_offloads(vi); } + } + + for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev)) + if (netif_running(dev)) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } } return 0; err: - for (i = 0; i < vi->max_queue_pairs; i++) - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + if (!prog) { + virtnet_clear_guest_offloads(vi); + for (i = 0; i < vi->max_queue_pairs; i++) + rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); + } + + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) { + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } + } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); return err; @@ -2613,16 +2700,6 @@ static void free_receive_page_frags(struct virtnet_info *vi) put_page(vi->rq[i].alloc_frag.page); } -static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) -{ - if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) - return false; - else if (q < vi->curr_queue_pairs) - return true; - else - return false; -} - static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -2631,10 +2708,10 @@ static void free_unused_bufs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (!is_xdp_raw_buffer_queue(vi, i)) + if (!is_xdp_frame(buf)) dev_kfree_skb(buf); else - put_page(virt_to_head_page(buf)); + xdp_return_frame(ptr_to_xdp(buf)); } } diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c index c0b0f525c87c..27decf8ae840 100644 --- a/drivers/net/wan/dscc4.c +++ b/drivers/net/wan/dscc4.c @@ -1575,7 +1575,7 @@ try: dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dpriv->tx_skbuff[cur] = NULL; ++dpriv->tx_dirty; } else { diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 66d889d54e58..a08f04c3f644 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -482,7 +482,7 @@ static int hdlc_tx_done(struct ucc_hdlc_private *priv) memset(priv->tx_buffer + (be32_to_cpu(bd->buf) - priv->dma_tx_addr), 0, skb->len); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); priv->tx_skbuff[priv->skb_dirtytx] = NULL; priv->skb_dirtytx = diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 399b501f3c3c..e8891f5fc83a 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -548,7 +548,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { { .id = WCN3990_HW_1_0_DEV_VERSION, .dev_id = 0, - .bus = ATH10K_BUS_PCI, + .bus = ATH10K_BUS_SNOC, .name = "wcn3990 hw1.0", .continuous_frag_desc = true, .tx_chain_mask = 0x7, diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index 491ca3c8b43c..83d5bceea08f 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -1,6 +1,6 @@ config IWLWIFI tristate "Intel Wireless WiFi Next Gen AGN - Wireless-N/Advanced-N/Ultimate-N (iwlwifi) " - depends on PCI && HAS_IOMEM + depends on PCI && HAS_IOMEM && CFG80211 select FW_LOADER ---help--- Select to build the driver supporting the: @@ -47,6 +47,7 @@ if IWLWIFI config IWLWIFI_LEDS bool depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI + depends on IWLMVM || IWLDVM select LEDS_TRIGGERS select MAC80211_LEDS default y diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c index 497e762978cc..b2cabce1d74d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c @@ -212,24 +212,24 @@ void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev) mt76x02_add_rate_power_offset(t, delta); } -void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) +void mt76x0_get_power_info(struct mt76x02_dev *dev, s8 *tp) { struct mt76x0_chan_map { u8 chan; u8 offset; } chan_map[] = { - { 2, 0 }, { 4, 1 }, { 6, 2 }, { 8, 3 }, - { 10, 4 }, { 12, 5 }, { 14, 6 }, { 38, 0 }, - { 44, 1 }, { 48, 2 }, { 54, 3 }, { 60, 4 }, - { 64, 5 }, { 102, 6 }, { 108, 7 }, { 112, 8 }, - { 118, 9 }, { 124, 10 }, { 128, 11 }, { 134, 12 }, - { 140, 13 }, { 151, 14 }, { 157, 15 }, { 161, 16 }, - { 167, 17 }, { 171, 18 }, { 173, 19 }, + { 2, 0 }, { 4, 2 }, { 6, 4 }, { 8, 6 }, + { 10, 8 }, { 12, 10 }, { 14, 12 }, { 38, 0 }, + { 44, 2 }, { 48, 4 }, { 54, 6 }, { 60, 8 }, + { 64, 10 }, { 102, 12 }, { 108, 14 }, { 112, 16 }, + { 118, 18 }, { 124, 20 }, { 128, 22 }, { 134, 24 }, + { 140, 26 }, { 151, 28 }, { 157, 30 }, { 161, 32 }, + { 167, 34 }, { 171, 36 }, { 175, 38 }, }; struct ieee80211_channel *chan = dev->mt76.chandef.chan; u8 offset, addr; + int i, idx = 0; u16 data; - int i; if (mt76x0_tssi_enabled(dev)) { s8 target_power; @@ -239,14 +239,14 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) else data = mt76x02_eeprom_get(dev, MT_EE_2G_TARGET_POWER); target_power = (data & 0xff) - dev->mt76.rate_power.ofdm[7]; - info[0] = target_power + mt76x0_get_delta(dev); - info[1] = 0; + *tp = target_power + mt76x0_get_delta(dev); return; } for (i = 0; i < ARRAY_SIZE(chan_map); i++) { - if (chan_map[i].chan <= chan->hw_value) { + if (chan->hw_value <= chan_map[i].chan) { + idx = (chan->hw_value == chan_map[i].chan); offset = chan_map[i].offset; break; } @@ -258,13 +258,16 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) addr = MT_EE_TX_POWER_DELTA_BW80 + offset; } else { switch (chan->hw_value) { + case 42: + offset = 2; + break; case 58: offset = 8; break; case 106: offset = 14; break; - case 112: + case 122: offset = 20; break; case 155: @@ -277,14 +280,9 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) } data = mt76x02_eeprom_get(dev, addr); - - info[0] = data; - if (!info[0] || info[0] > 0x3f) - info[0] = 5; - - info[1] = data >> 8; - if (!info[1] || info[1] > 0x3f) - info[1] = 5; + *tp = data >> (8 * idx); + if (*tp < 0 || *tp > 0x3f) + *tp = 5; } static int mt76x0_check_eeprom(struct mt76x02_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h index ee9ade9f3c8b..42b259f90b6d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h @@ -26,7 +26,7 @@ struct mt76x02_dev; int mt76x0_eeprom_init(struct mt76x02_dev *dev); void mt76x0_read_rx_gain(struct mt76x02_dev *dev); void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev); -void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info); +void mt76x0_get_power_info(struct mt76x02_dev *dev, s8 *tp); static inline s8 s6_to_s8(u32 val) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c index 1eb1a802ed20..b6166703ad76 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c @@ -845,17 +845,17 @@ static void mt76x0_phy_tssi_calibrate(struct mt76x02_dev *dev) void mt76x0_phy_set_txpower(struct mt76x02_dev *dev) { struct mt76_rate_power *t = &dev->mt76.rate_power; - u8 info[2]; + s8 info; mt76x0_get_tx_power_per_rate(dev); - mt76x0_get_power_info(dev, info); + mt76x0_get_power_info(dev, &info); - mt76x02_add_rate_power_offset(t, info[0]); + mt76x02_add_rate_power_offset(t, info); mt76x02_limit_rate_power(t, dev->mt76.txpower_conf); dev->mt76.txpower_cur = mt76x02_get_max_rate_power(t); - mt76x02_add_rate_power_offset(t, -info[0]); + mt76x02_add_rate_power_offset(t, -info); - mt76x02_phy_set_txpower(dev, info[0], info[1]); + mt76x02_phy_set_txpower(dev, info, info); } void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on) diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index bd10165d7eec..4d4b07701149 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -164,6 +164,12 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) } sdio_claim_host(func); + /* + * To guarantee that the SDIO card is power cycled, as required to make + * the FW programming to succeed, let's do a brute force HW reset. + */ + mmc_hw_reset(card->host); + sdio_enable_func(func); sdio_release_host(func); @@ -174,20 +180,13 @@ static int wl12xx_sdio_power_off(struct wl12xx_sdio_glue *glue) { struct sdio_func *func = dev_to_sdio_func(glue->dev); struct mmc_card *card = func->card; - int error; sdio_claim_host(func); sdio_disable_func(func); sdio_release_host(func); /* Let runtime PM know the card is powered off */ - error = pm_runtime_put(&card->dev); - if (error < 0 && error != -EBUSY) { - dev_err(&card->dev, "%s failed: %i\n", __func__, error); - - return error; - } - + pm_runtime_put(&card->dev); return 0; } diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index dca5f7a805cb..7bbff0af29b2 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -23,6 +23,7 @@ #include <linux/ndctl.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <linux/fs.h> #include <linux/io.h> #include <linux/mm.h> @@ -534,11 +535,15 @@ void __nd_device_register(struct device *dev) set_dev_node(dev, to_nd_region(dev)->numa_node); dev->bus = &nvdimm_bus_type; - if (dev->parent) + if (dev->parent) { get_device(dev->parent); + if (dev_to_node(dev) == NUMA_NO_NODE) + set_dev_node(dev, dev_to_node(dev->parent)); + } get_device(dev); - async_schedule_domain(nd_async_device_register, dev, - &nd_async_domain); + + async_schedule_dev_domain(nd_async_device_register, dev, + &nd_async_domain); } void nd_device_register(struct device *dev) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 150e49723c15..6a9dd68c0f4f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1253,6 +1253,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, * effects say only one namespace is affected. */ if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { + mutex_lock(&ctrl->scan_lock); nvme_start_freeze(ctrl); nvme_wait_freeze(ctrl); } @@ -1281,8 +1282,10 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) */ if (effects & NVME_CMD_EFFECTS_LBCC) nvme_update_formats(ctrl); - if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) + if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { nvme_unfreeze(ctrl); + mutex_unlock(&ctrl->scan_lock); + } if (effects & NVME_CMD_EFFECTS_CCC) nvme_init_identify(ctrl); if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) @@ -3401,6 +3404,7 @@ static void nvme_scan_work(struct work_struct *work) if (nvme_identify_ctrl(ctrl, &id)) return; + mutex_lock(&ctrl->scan_lock); nn = le32_to_cpu(id->nn); if (ctrl->vs >= NVME_VS(1, 1, 0) && !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { @@ -3409,6 +3413,7 @@ static void nvme_scan_work(struct work_struct *work) } nvme_scan_ns_sequential(ctrl, nn); out_free_id: + mutex_unlock(&ctrl->scan_lock); kfree(id); down_write(&ctrl->namespaces_rwsem); list_sort(NULL, &ctrl->namespaces, ns_cmp); @@ -3652,6 +3657,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->state = NVME_CTRL_NEW; spin_lock_init(&ctrl->lock); + mutex_init(&ctrl->scan_lock); INIT_LIST_HEAD(&ctrl->namespaces); init_rwsem(&ctrl->namespaces_rwsem); ctrl->dev = dev; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ab961bdeea89..c4a1bb41abf0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -154,6 +154,7 @@ struct nvme_ctrl { enum nvme_ctrl_state state; bool identified; spinlock_t lock; + struct mutex scan_lock; const struct nvme_ctrl_ops *ops; struct request_queue *admin_q; struct request_queue *connect_q; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9bc585415d9b..022ea1ee63f8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2557,16 +2557,7 @@ static void nvme_reset_work(struct work_struct *work) if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); - /* - * Introduce CONNECTING state from nvme-fc/rdma transports to mark the - * initializing procedure here. - */ - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { - dev_warn(dev->ctrl.device, - "failed to mark controller CONNECTING\n"); - goto out; - } - + mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) goto out; @@ -2585,6 +2576,17 @@ static void nvme_reset_work(struct work_struct *work) */ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1; dev->ctrl.max_segments = NVME_MAX_SEGS; + mutex_unlock(&dev->shutdown_lock); + + /* + * Introduce CONNECTING state from nvme-fc/rdma transports to mark the + * initializing procedure here. + */ + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { + dev_warn(dev->ctrl.device, + "failed to mark controller CONNECTING\n"); + goto out; + } result = nvme_init_identify(&dev->ctrl); if (result) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 9ecfe13157c0..25794c27c7a4 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -412,8 +412,7 @@ static ssize_t msi_bus_store(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RW(msi_bus); -static ssize_t bus_rescan_store(struct bus_type *bus, const char *buf, - size_t count) +static ssize_t rescan_store(struct bus_type *bus, const char *buf, size_t count) { unsigned long val; struct pci_bus *b = NULL; @@ -429,7 +428,7 @@ static ssize_t bus_rescan_store(struct bus_type *bus, const char *buf, } return count; } -static BUS_ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, bus_rescan_store); +static BUS_ATTR_WO(rescan); static struct attribute *pci_bus_attrs[] = { &bus_attr_rescan.attr, diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c25acace7d91..db55acf32a7e 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6034,19 +6034,18 @@ static ssize_t pci_get_resource_alignment_param(char *buf, size_t size) return count; } -static ssize_t pci_resource_alignment_show(struct bus_type *bus, char *buf) +static ssize_t resource_alignment_show(struct bus_type *bus, char *buf) { return pci_get_resource_alignment_param(buf, PAGE_SIZE); } -static ssize_t pci_resource_alignment_store(struct bus_type *bus, +static ssize_t resource_alignment_store(struct bus_type *bus, const char *buf, size_t count) { return pci_set_resource_alignment_param(buf, count); } -static BUS_ATTR(resource_alignment, 0644, pci_resource_alignment_show, - pci_resource_alignment_store); +static BUS_ATTR_RW(resource_alignment); static int __init pci_resource_alignment_sysfs_init(void) { diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index b0a413f3f7ca..e2a879e93d86 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -639,8 +639,9 @@ static void quirk_synopsys_haps(struct pci_dev *pdev) break; } } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SYNOPSYS, PCI_ANY_ID, - quirk_synopsys_haps); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_SYNOPSYS, PCI_ANY_ID, + PCI_CLASS_SERIAL_USB_XHCI, 0, + quirk_synopsys_haps); /* * Let's make the southbridge information explicit instead of having to diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 05044e323ea5..03ec7a5d9d0b 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1513,7 +1513,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1521,7 +1521,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1529,7 +1529,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Cyan"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1537,7 +1537,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Celes"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, {} diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index 1817786ab6aa..a005cbccb4f7 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -45,12 +45,14 @@ config PINCTRL_MT2701 config PINCTRL_MT7623 bool "Mediatek MT7623 pin control with generic binding" depends on MACH_MT7623 || COMPILE_TEST + depends on OF default MACH_MT7623 select PINCTRL_MTK_MOORE config PINCTRL_MT7629 bool "Mediatek MT7629 pin control" depends on MACH_MT7629 || COMPILE_TEST + depends on OF default MACH_MT7629 select PINCTRL_MTK_MOORE @@ -92,6 +94,7 @@ config PINCTRL_MT6797 config PINCTRL_MT7622 bool "MediaTek MT7622 pin control" + depends on OF depends on ARM64 || COMPILE_TEST default ARM64 && ARCH_MEDIATEK select PINCTRL_MTK_MOORE diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index b03481ef99a1..98905d4a79ca 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -832,8 +832,13 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, break; case MCP_TYPE_S18: + one_regmap_config = + devm_kmemdup(dev, &mcp23x17_regmap, + sizeof(struct regmap_config), GFP_KERNEL); + if (!one_regmap_config) + return -ENOMEM; mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, - &mcp23x17_regmap); + one_regmap_config); mcp->reg_shift = 1; mcp->chip.ngpio = 16; mcp->chip.label = "mcp23s18"; diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c index aa8b58125568..ef4268cc6227 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c @@ -588,7 +588,7 @@ static const unsigned int h6_irq_bank_map[] = { 1, 5, 6, 7 }; static const struct sunxi_pinctrl_desc h6_pinctrl_data = { .pins = h6_pins, .npins = ARRAY_SIZE(h6_pins), - .irq_banks = 3, + .irq_banks = 4, .irq_bank_map = h6_irq_bank_map, .irq_read_needs_mux = true, }; diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 5d9184d18c16..0e7fa69e93df 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -698,26 +698,24 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); unsigned short bank = offset / PINS_PER_BANK; - struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank]; - struct regulator *reg; + unsigned short bank_offset = bank - pctl->desc->pin_base / + PINS_PER_BANK; + struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank_offset]; + struct regulator *reg = s_reg->regulator; + char supply[16]; int ret; - reg = s_reg->regulator; - if (!reg) { - char supply[16]; - - snprintf(supply, sizeof(supply), "vcc-p%c", 'a' + bank); - reg = regulator_get(pctl->dev, supply); - if (IS_ERR(reg)) { - dev_err(pctl->dev, "Couldn't get bank P%c regulator\n", - 'A' + bank); - return PTR_ERR(reg); - } - - s_reg->regulator = reg; - refcount_set(&s_reg->refcount, 1); - } else { + if (reg) { refcount_inc(&s_reg->refcount); + return 0; + } + + snprintf(supply, sizeof(supply), "vcc-p%c", 'a' + bank); + reg = regulator_get(pctl->dev, supply); + if (IS_ERR(reg)) { + dev_err(pctl->dev, "Couldn't get bank P%c regulator\n", + 'A' + bank); + return PTR_ERR(reg); } ret = regulator_enable(reg); @@ -727,13 +725,13 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset) goto out; } + s_reg->regulator = reg; + refcount_set(&s_reg->refcount, 1); + return 0; out: - if (refcount_dec_and_test(&s_reg->refcount)) { - regulator_put(s_reg->regulator); - s_reg->regulator = NULL; - } + regulator_put(s_reg->regulator); return ret; } @@ -742,7 +740,9 @@ static int sunxi_pmx_free(struct pinctrl_dev *pctldev, unsigned offset) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); unsigned short bank = offset / PINS_PER_BANK; - struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank]; + unsigned short bank_offset = bank - pctl->desc->pin_base / + PINS_PER_BANK; + struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank_offset]; if (!refcount_dec_and_test(&s_reg->refcount)) return 0; diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h index e340d2a24b44..034c0317c8d6 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h @@ -136,7 +136,7 @@ struct sunxi_pinctrl { struct gpio_chip *chip; const struct sunxi_pinctrl_desc *desc; struct device *dev; - struct sunxi_pinctrl_regulator regulators[12]; + struct sunxi_pinctrl_regulator regulators[9]; struct irq_domain *domain; struct sunxi_pinctrl_function *functions; unsigned nfunctions; diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c index 73e4b407f162..ad5e303dda05 100644 --- a/drivers/rapidio/rio-sysfs.c +++ b/drivers/rapidio/rio-sysfs.c @@ -290,8 +290,7 @@ const struct attribute_group *rio_dev_groups[] = { NULL, }; -static ssize_t bus_scan_store(struct bus_type *bus, const char *buf, - size_t count) +static ssize_t scan_store(struct bus_type *bus, const char *buf, size_t count) { long val; int rc; @@ -314,7 +313,7 @@ exit: return rc; } -static BUS_ATTR(scan, (S_IWUSR|S_IWGRP), NULL, bus_scan_store); +static BUS_ATTR_WO(scan); static struct attribute *rio_bus_attrs[] = { &bus_attr_scan.attr, diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 0ee026947f20..122059ecad84 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -22,6 +22,7 @@ #include <linux/hashtable.h> #include <linux/ip.h> #include <linux/refcount.h> +#include <linux/workqueue.h> #include <net/ipv6.h> #include <net/if_inet6.h> @@ -789,6 +790,7 @@ struct qeth_card { struct qeth_seqno seqno; struct qeth_card_options options; + struct workqueue_struct *event_wq; wait_queue_head_t wait_q; spinlock_t mclock; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; @@ -962,7 +964,6 @@ extern const struct attribute_group *qeth_osn_attr_groups[]; extern const struct attribute_group qeth_device_attr_group; extern const struct attribute_group qeth_device_blkt_group; extern const struct device_type qeth_generic_devtype; -extern struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *); const char *qeth_get_cardname_short(struct qeth_card *); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index e63e03143ca7..89f912213e62 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -74,8 +74,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf); static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); -struct workqueue_struct *qeth_wq; -EXPORT_SYMBOL_GPL(qeth_wq); +static struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *card) { @@ -566,6 +565,7 @@ static int __qeth_issue_next_read(struct qeth_card *card) QETH_DBF_MESSAGE(2, "error %i on device %x when starting next read ccw!\n", rc, CARD_DEVID(card)); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); card->read_or_write_problem = 1; qeth_schedule_recovery(card); wake_up(&card->wait_q); @@ -1127,6 +1127,8 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, rc = qeth_get_problem(card, cdev, irb); if (rc) { card->read_or_write_problem = 1; + if (iob) + qeth_release_buffer(iob->channel, iob); qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); goto out; @@ -1466,6 +1468,10 @@ static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev) CARD_RDEV(card) = gdev->cdev[0]; CARD_WDEV(card) = gdev->cdev[1]; CARD_DDEV(card) = gdev->cdev[2]; + + card->event_wq = alloc_ordered_workqueue("%s", 0, dev_name(&gdev->dev)); + if (!card->event_wq) + goto out_wq; if (qeth_setup_channel(&card->read, true)) goto out_ip; if (qeth_setup_channel(&card->write, true)) @@ -1481,6 +1487,8 @@ out_data: out_channel: qeth_clean_channel(&card->read); out_ip: + destroy_workqueue(card->event_wq); +out_wq: dev_set_drvdata(&gdev->dev, NULL); kfree(card); out: @@ -1809,6 +1817,7 @@ static int qeth_idx_activate_get_answer(struct qeth_card *card, QETH_DBF_MESSAGE(2, "Error2 in activating channel rc=%d\n", rc); QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); wake_up(&card->wait_q); return rc; } @@ -1878,6 +1887,7 @@ static int qeth_idx_activate_channel(struct qeth_card *card, rc); QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); wake_up(&card->wait_q); return rc; } @@ -2058,6 +2068,7 @@ int qeth_send_control_data(struct qeth_card *card, int len, } reply = qeth_alloc_reply(card); if (!reply) { + qeth_release_buffer(channel, iob); return -ENOMEM; } reply->callback = reply_cb; @@ -2389,11 +2400,12 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx) return 0; } -static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q) +static void qeth_free_output_queue(struct qeth_qdio_out_q *q) { if (!q) return; + qeth_clear_outq_buffers(q, 1); qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); kfree(q); } @@ -2467,10 +2479,8 @@ out_freeoutqbufs: card->qdio.out_qs[i]->bufs[j] = NULL; } out_freeoutq: - while (i > 0) { - qeth_free_qdio_out_buf(card->qdio.out_qs[--i]); - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); - } + while (i > 0) + qeth_free_output_queue(card->qdio.out_qs[--i]); kfree(card->qdio.out_qs); card->qdio.out_qs = NULL; out_freepool: @@ -2503,10 +2513,8 @@ static void qeth_free_qdio_buffers(struct qeth_card *card) qeth_free_buffer_pool(card); /* free outbound qdio_qs */ if (card->qdio.out_qs) { - for (i = 0; i < card->qdio.no_out_queues; ++i) { - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); - qeth_free_qdio_out_buf(card->qdio.out_qs[i]); - } + for (i = 0; i < card->qdio.no_out_queues; i++) + qeth_free_output_queue(card->qdio.out_qs[i]); kfree(card->qdio.out_qs); card->qdio.out_qs = NULL; } @@ -5028,6 +5036,7 @@ static void qeth_core_free_card(struct qeth_card *card) qeth_clean_channel(&card->read); qeth_clean_channel(&card->write); qeth_clean_channel(&card->data); + destroy_workqueue(card->event_wq); qeth_free_qdio_buffers(card); unregister_service_level(&card->qeth_service_level); dev_set_drvdata(&card->gdev->dev, NULL); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index f108d4b44605..a43de2f9bcac 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -369,6 +369,8 @@ static void qeth_l2_stop_card(struct qeth_card *card, int recovery_mode) qeth_clear_cmd_buffers(&card->read); qeth_clear_cmd_buffers(&card->write); } + + flush_workqueue(card->event_wq); } static int qeth_l2_process_inbound_buffer(struct qeth_card *card, @@ -801,6 +803,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l2_set_offline(cgdev); + + cancel_work_sync(&card->close_dev_work); if (qeth_netdev_is_registered(card->dev)) unregister_netdev(card->dev); } @@ -1434,7 +1438,7 @@ static void qeth_bridge_state_change(struct qeth_card *card, data->card = card; memcpy(&data->qports, qports, sizeof(struct qeth_sbp_state_change) + extrasize); - queue_work(qeth_wq, &data->worker); + queue_work(card->event_wq, &data->worker); } struct qeth_bridge_host_data { @@ -1506,7 +1510,7 @@ static void qeth_bridge_host_event(struct qeth_card *card, data->card = card; memcpy(&data->hostevs, hostevs, sizeof(struct qeth_ipacmd_addr_change) + extrasize); - queue_work(qeth_wq, &data->worker); + queue_work(card->event_wq, &data->worker); } /* SETBRIDGEPORT support; sending commands */ diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 42a7cdc59b76..df34bff4ac31 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1433,6 +1433,8 @@ static void qeth_l3_stop_card(struct qeth_card *card, int recovery_mode) qeth_clear_cmd_buffers(&card->read); qeth_clear_cmd_buffers(&card->write); } + + flush_workqueue(card->event_wq); } /* @@ -2338,6 +2340,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l3_set_offline(cgdev); + cancel_work_sync(&card->close_dev_work); if (qeth_netdev_is_registered(card->dev)) unregister_netdev(card->dev); qeth_l3_clear_ip_htable(card, 0); diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c index f83f79b07b50..07efcb9b5b94 100644 --- a/drivers/scsi/aic94xx/aic94xx_init.c +++ b/drivers/scsi/aic94xx/aic94xx_init.c @@ -280,7 +280,7 @@ static ssize_t asd_show_dev_rev(struct device *dev, return snprintf(buf, PAGE_SIZE, "%s\n", asd_dev_rev[asd_ha->revision_id]); } -static DEVICE_ATTR(revision, S_IRUGO, asd_show_dev_rev, NULL); +static DEVICE_ATTR(aic_revision, S_IRUGO, asd_show_dev_rev, NULL); static ssize_t asd_show_dev_bios_build(struct device *dev, struct device_attribute *attr,char *buf) @@ -477,7 +477,7 @@ static int asd_create_dev_attrs(struct asd_ha_struct *asd_ha) { int err; - err = device_create_file(&asd_ha->pcidev->dev, &dev_attr_revision); + err = device_create_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); if (err) return err; @@ -499,13 +499,13 @@ err_update_bios: err_biosb: device_remove_file(&asd_ha->pcidev->dev, &dev_attr_bios_build); err_rev: - device_remove_file(&asd_ha->pcidev->dev, &dev_attr_revision); + device_remove_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); return err; } static void asd_remove_dev_attrs(struct asd_ha_struct *asd_ha) { - device_remove_file(&asd_ha->pcidev->dev, &dev_attr_revision); + device_remove_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_bios_build); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_pcba_sn); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_update_bios); diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index bfa13e3b191c..c8bad2c093b8 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3687,6 +3687,7 @@ static int cxlflash_probe(struct pci_dev *pdev, host->max_cmd_len = CXLFLASH_MAX_CDB_LEN; cfg = shost_priv(host); + cfg->state = STATE_PROBING; cfg->host = host; rc = alloc_mem(cfg); if (rc) { @@ -3775,6 +3776,7 @@ out: return rc; out_remove: + cfg->state = STATE_PROBED; cxlflash_remove(pdev); goto out; } diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 9192a1d9dec6..dfba4921b265 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -184,7 +184,6 @@ void fc_rport_destroy(struct kref *kref) struct fc_rport_priv *rdata; rdata = container_of(kref, struct fc_rport_priv, kref); - WARN_ON(!list_empty(&rdata->peers)); kfree_rcu(rdata, rcu); } EXPORT_SYMBOL(fc_rport_destroy); diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 83365b29a4d8..fff86940388b 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -462,12 +462,16 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) sdkp->device->use_10_for_rw = 0; /* - * If something changed, revalidate the disk zone bitmaps once we have - * the capacity, that is on the second revalidate execution during disk - * scan and always during normal revalidate. + * Revalidate the disk zone bitmaps once the block device capacity is + * set on the second revalidate execution during disk scan and if + * something changed when executing a normal revalidate. */ - if (sdkp->first_scan) + if (sdkp->first_scan) { + sdkp->zone_blocks = zone_blocks; + sdkp->nr_zones = nr_zones; return 0; + } + if (sdkp->zone_blocks != zone_blocks || sdkp->nr_zones != nr_zones || disk->queue->nr_zones != nr_zones) { diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 52c153cd795a..636f83f781f5 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -1143,18 +1143,19 @@ static void qm_mr_process_task(struct work_struct *work); static irqreturn_t portal_isr(int irq, void *ptr) { struct qman_portal *p = ptr; - - u32 clear = QM_DQAVAIL_MASK | p->irq_sources; u32 is = qm_in(&p->p, QM_REG_ISR) & p->irq_sources; + u32 clear = 0; if (unlikely(!is)) return IRQ_NONE; /* DQRR-handling if it's interrupt-driven */ - if (is & QM_PIRQ_DQRI) + if (is & QM_PIRQ_DQRI) { __poll_portal_fast(p, QMAN_POLL_LIMIT); + clear = QM_DQAVAIL_MASK | QM_PIRQ_DQRI; + } /* Handling of anything else that's interrupt-driven */ - clear |= __poll_portal_slow(p, is); + clear |= __poll_portal_slow(p, is) & QM_PIRQ_SLOW; qm_out(&p->p, QM_REG_ISR, clear); return IRQ_HANDLED; } diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index 2848fa71a33d..d6248eecf123 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -170,7 +170,7 @@ int cvm_oct_phy_setup_device(struct net_device *dev) return -ENODEV; priv->last_link = 0; - phy_start_aneg(phydev); + phy_start(phydev); return 0; no_phy: diff --git a/drivers/staging/speakup/spk_ttyio.c b/drivers/staging/speakup/spk_ttyio.c index c92bbd05516e..005de0024dd4 100644 --- a/drivers/staging/speakup/spk_ttyio.c +++ b/drivers/staging/speakup/spk_ttyio.c @@ -265,7 +265,8 @@ static void spk_ttyio_send_xchar(char ch) return; } - speakup_tty->ops->send_xchar(speakup_tty, ch); + if (speakup_tty->ops->send_xchar) + speakup_tty->ops->send_xchar(speakup_tty, ch); mutex_unlock(&speakup_tty_mutex); } @@ -277,7 +278,8 @@ static void spk_ttyio_tiocmset(unsigned int set, unsigned int clear) return; } - speakup_tty->ops->tiocmset(speakup_tty, set, clear); + if (speakup_tty->ops->tiocmset) + speakup_tty->ops->tiocmset(speakup_tty, set, clear); mutex_unlock(&speakup_tty_mutex); } diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 72016d0dfca5..8e7fffbb8802 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -852,6 +852,12 @@ static ssize_t pi_prot_type_store(struct config_item *item, return count; } +/* always zero, but attr needs to remain RW to avoid userspace breakage */ +static ssize_t pi_prot_format_show(struct config_item *item, char *page) +{ + return snprintf(page, PAGE_SIZE, "0\n"); +} + static ssize_t pi_prot_format_store(struct config_item *item, const char *page, size_t count) { @@ -1132,7 +1138,7 @@ CONFIGFS_ATTR(, emulate_3pc); CONFIGFS_ATTR(, emulate_pr); CONFIGFS_ATTR(, pi_prot_type); CONFIGFS_ATTR_RO(, hw_pi_prot_type); -CONFIGFS_ATTR_WO(, pi_prot_format); +CONFIGFS_ATTR(, pi_prot_format); CONFIGFS_ATTR(, pi_prot_verify); CONFIGFS_ATTR(, enforce_pr_isids); CONFIGFS_ATTR(, is_nonrot); diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index e2c407656fa6..c1fdbc0b6840 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -357,6 +357,9 @@ static int mtk8250_probe_of(struct platform_device *pdev, struct uart_port *p, if (dmacnt == 2) { data->dma = devm_kzalloc(&pdev->dev, sizeof(*data->dma), GFP_KERNEL); + if (!data->dma) + return -ENOMEM; + data->dma->fn = mtk8250_dma_filter; data->dma->rx_size = MTK_UART_RX_SIZE; data->dma->rxconf.src_maxburst = MTK_UART_RX_TRIGGER; diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index f80a300b5d68..48bd694a5fa1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -3420,6 +3420,11 @@ static int serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) { int num_iomem, num_port, first_port = -1, i; + int rc; + + rc = serial_pci_is_class_communication(dev); + if (rc) + return rc; /* * Should we try to make guesses for multiport serial devices later? @@ -3647,10 +3652,6 @@ pciserial_init_one(struct pci_dev *dev, const struct pci_device_id *ent) board = &pci_boards[ent->driver_data]; - rc = serial_pci_is_class_communication(dev); - if (rc) - return rc; - rc = serial_pci_is_blacklisted(dev); if (rc) return rc; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 5c01bb6d1c24..556f50aa1b58 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -130,6 +130,9 @@ static void uart_start(struct tty_struct *tty) struct uart_port *port; unsigned long flags; + if (!state) + return; + port = uart_port_lock(state, flags); __uart_start(tty); uart_port_unlock(port, flags); @@ -727,6 +730,9 @@ static void uart_unthrottle(struct tty_struct *tty) upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; + if (!state) + return; + port = uart_port_ref(state); if (!port) return; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 8df0fd824520..64bbeb7d7e0c 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1921,7 +1921,7 @@ out_nomem: static void sci_free_irq(struct sci_port *port) { - int i; + int i, j; /* * Intentionally in reverse order so we iterate over the muxed @@ -1937,6 +1937,13 @@ static void sci_free_irq(struct sci_port *port) if (unlikely(irq < 0)) continue; + /* Check if already freed (irq was muxed) */ + for (j = 0; j < i; j++) + if (port->irqs[j] == irq) + j = i + 1; + if (j > i) + continue; + free_irq(port->irqs[i], port); kfree(port->irqstr[i]); diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index cb7fcd7c0ad8..c1e9ea621f41 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -78,7 +78,7 @@ static int dwc3_exynos_probe(struct platform_device *pdev) for (i = 0; i < exynos->num_clks; i++) { ret = clk_prepare_enable(exynos->clks[i]); if (ret) { - while (--i > 0) + while (i-- > 0) clk_disable_unprepare(exynos->clks[i]); return ret; } @@ -223,7 +223,7 @@ static int dwc3_exynos_resume(struct device *dev) for (i = 0; i < exynos->num_clks; i++) { ret = clk_prepare_enable(exynos->clks[i]); if (ret) { - while (--i > 0) + while (i-- > 0) clk_disable_unprepare(exynos->clks[i]); return ret; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index bed2ff42780b..6c9b76bcc2e1 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1119,7 +1119,7 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep, unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc); unsigned int rem = length % maxp; - if (rem && usb_endpoint_dir_out(dep->endpoint.desc)) { + if ((!length || rem) && usb_endpoint_dir_out(dep->endpoint.desc)) { struct dwc3 *dwc = dep->dwc; struct dwc3_trb *trb; diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 660878a19505..b77f3126580e 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -2083,7 +2083,7 @@ static irqreturn_t net2272_irq(int irq, void *_dev) #if defined(PLX_PCI_RDK2) /* see if PCI int for us by checking irqstat */ intcsr = readl(dev->rdk2.fpga_base_addr + RDK2_IRQSTAT); - if (!intcsr & (1 << NET2272_PCI_IRQ)) { + if (!(intcsr & (1 << NET2272_PCI_IRQ))) { spin_unlock(&dev->lock); return IRQ_NONE; } diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index eae8b1b1b45b..ffe462a657b1 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -452,13 +452,10 @@ void musb_g_tx(struct musb *musb, u8 epnum) } if (request) { - u8 is_dma = 0; - bool short_packet = false; trace_musb_req_tx(req); if (dma && (csr & MUSB_TXCSR_DMAENAB)) { - is_dma = 1; csr |= MUSB_TXCSR_P_WZC_BITS; csr &= ~(MUSB_TXCSR_DMAENAB | MUSB_TXCSR_P_UNDERRUN | MUSB_TXCSR_TXPKTRDY | MUSB_TXCSR_AUTOSET); @@ -476,16 +473,8 @@ void musb_g_tx(struct musb *musb, u8 epnum) */ if ((request->zero && request->length) && (request->length % musb_ep->packet_sz == 0) - && (request->actual == request->length)) - short_packet = true; + && (request->actual == request->length)) { - if ((musb_dma_inventra(musb) || musb_dma_ux500(musb)) && - (is_dma && (!dma->desired_mode || - (request->actual & - (musb_ep->packet_sz - 1))))) - short_packet = true; - - if (short_packet) { /* * On DMA completion, FIFO may not be * available yet... diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c index a688f7f87829..5fc6825745f2 100644 --- a/drivers/usb/musb/musbhsdma.c +++ b/drivers/usb/musb/musbhsdma.c @@ -346,12 +346,10 @@ static irqreturn_t dma_controller_irq(int irq, void *private_data) channel->status = MUSB_DMA_STATUS_FREE; /* completed */ - if ((devctl & MUSB_DEVCTL_HM) - && (musb_channel->transmit) - && ((channel->desired_mode == 0) - || (channel->actual_len & - (musb_channel->max_packet_sz - 1))) - ) { + if (musb_channel->transmit && + (!channel->desired_mode || + (channel->actual_len % + musb_channel->max_packet_sz))) { u8 epnum = musb_channel->epnum; int offset = musb->io.ep_offset(epnum, MUSB_TXCSR); @@ -363,11 +361,14 @@ static irqreturn_t dma_controller_irq(int irq, void *private_data) */ musb_ep_select(mbase, epnum); txcsr = musb_readw(mbase, offset); - txcsr &= ~(MUSB_TXCSR_DMAENAB + if (channel->desired_mode == 1) { + txcsr &= ~(MUSB_TXCSR_DMAENAB | MUSB_TXCSR_AUTOSET); - musb_writew(mbase, offset, txcsr); - /* Send out the packet */ - txcsr &= ~MUSB_TXCSR_DMAMODE; + musb_writew(mbase, offset, txcsr); + /* Send out the packet */ + txcsr &= ~MUSB_TXCSR_DMAMODE; + txcsr |= MUSB_TXCSR_DMAENAB; + } txcsr |= MUSB_TXCSR_TXPKTRDY; musb_writew(mbase, offset, txcsr); } diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index d7312eed6088..91ea3083e7ad 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -21,7 +21,7 @@ config AB8500_USB config FSL_USB2_OTG bool "Freescale USB OTG Transceiver Driver" - depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM && PM + depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM=y && PM depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help diff --git a/drivers/usb/phy/phy-am335x.c b/drivers/usb/phy/phy-am335x.c index 27bdb7222527..f5f0568d8533 100644 --- a/drivers/usb/phy/phy-am335x.c +++ b/drivers/usb/phy/phy-am335x.c @@ -61,9 +61,6 @@ static int am335x_phy_probe(struct platform_device *pdev) if (ret) return ret; - ret = usb_add_phy_dev(&am_phy->usb_phy_gen.phy); - if (ret) - return ret; am_phy->usb_phy_gen.phy.init = am335x_init; am_phy->usb_phy_gen.phy.shutdown = am335x_shutdown; @@ -82,7 +79,7 @@ static int am335x_phy_probe(struct platform_device *pdev) device_set_wakeup_enable(dev, false); phy_ctrl_power(am_phy->phy_ctrl, am_phy->id, am_phy->dr_mode, false); - return 0; + return usb_add_phy_dev(&am_phy->usb_phy_gen.phy); } static int am335x_phy_remove(struct platform_device *pdev) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 4bc29b586698..f1c39a3c7534 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2297,7 +2297,8 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) pdo_pps_apdo_max_voltage(snk)); port->pps_data.max_curr = min_pps_apdo_current(src, snk); port->pps_data.out_volt = min(port->pps_data.max_volt, - port->pps_data.out_volt); + max(port->pps_data.min_volt, + port->pps_data.out_volt)); port->pps_data.op_curr = min(port->pps_data.max_curr, port->pps_data.op_curr); } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index cd7e755484e3..a0b07c331255 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -152,7 +152,12 @@ struct vring_virtqueue { /* Available for packed ring */ struct { /* Actual memory layout for this queue. */ - struct vring_packed vring; + struct { + unsigned int num; + struct vring_packed_desc *desc; + struct vring_packed_desc_event *driver; + struct vring_packed_desc_event *device; + } vring; /* Driver ring wrap counter. */ bool avail_wrap_counter; @@ -1609,6 +1614,9 @@ static struct virtqueue *vring_create_virtqueue_packed( !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) + vq->weak_barriers = false; + vq->packed.ring_dma_addr = ring_dma_addr; vq->packed.driver_event_dma_addr = driver_event_dma_addr; vq->packed.device_event_dma_addr = device_event_dma_addr; @@ -2079,6 +2087,9 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) + vq->weak_barriers = false; + vq->split.queue_dma_addr = 0; vq->split.queue_size_in_bytes = 0; @@ -2213,6 +2224,8 @@ void vring_transport_features(struct virtio_device *vdev) break; case VIRTIO_F_RING_PACKED: break; + case VIRTIO_F_ORDER_PLATFORM: + break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); @@ -1436,6 +1436,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) if (unlikely(!req->ki_filp)) return -EBADF; req->ki_complete = aio_complete_rw; + req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = iocb_flags(req->ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) diff --git a/fs/buffer.c b/fs/buffer.c index 52d024bfdbc1..48318fb74938 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -200,6 +200,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct buffer_head *head; struct page *page; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); @@ -227,15 +228,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %pg blocksize: %d\n", bdev, - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 13b01351dd1c..95b5e78c22b1 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -324,7 +324,7 @@ static struct dentry *failed_creating(struct dentry *dentry) inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); - return NULL; + return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) @@ -347,7 +347,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, dentry = start_creating(name, parent); if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -386,7 +386,8 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -422,8 +423,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file); * debugfs core. * * It is your responsibility to protect your struct file_operation - * methods against file removals by means of debugfs_use_file_start() - * and debugfs_use_file_finish(). ->open() is still protected by + * methods against file removals by means of debugfs_file_get() + * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of @@ -464,7 +465,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -495,7 +497,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -506,7 +509,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -545,7 +548,7 @@ struct dentry *debugfs_create_automount(const char *name, struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -581,8 +584,8 @@ EXPORT_SYMBOL(debugfs_create_automount); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is - * unloaded, you are responsible here.) If an error occurs, %NULL will be - * returned. + * unloaded, you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) + * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -594,12 +597,12 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) - return NULL; + return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); - return NULL; + return dentry; } inode = debugfs_get_inode(dentry->d_sb); @@ -787,6 +790,13 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *dentry = NULL, *trap; struct name_snapshot old_name; + if (IS_ERR(old_dir)) + return old_dir; + if (IS_ERR(new_dir)) + return new_dir; + if (IS_ERR_OR_NULL(old_dentry)) + return old_dentry; + trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) @@ -820,7 +830,9 @@ exit: if (dentry && !IS_ERR(dentry)) dput(dentry); unlock_rename(new_dir, old_dir); - return NULL; + if (IS_ERR(dentry)) + return dentry; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(debugfs_rename); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index ebcc121920ba..fd7f170e2f2d 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -506,30 +506,16 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi) kvfree(si); } -int __init f2fs_create_root_stats(void) +void __init f2fs_create_root_stats(void) { - struct dentry *file; - f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); - if (!f2fs_debugfs_root) - return -ENOMEM; - file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, - NULL, &stat_fops); - if (!file) { - debugfs_remove(f2fs_debugfs_root); - f2fs_debugfs_root = NULL; - return -ENOMEM; - } - - return 0; + debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL, + &stat_fops); } void f2fs_destroy_root_stats(void) { - if (!f2fs_debugfs_root) - return; - debugfs_remove_recursive(f2fs_debugfs_root); f2fs_debugfs_root = NULL; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 12fabd6735dd..8f23ee6e8eb9 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3328,7 +3328,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) int f2fs_build_stats(struct f2fs_sb_info *sbi); void f2fs_destroy_stats(struct f2fs_sb_info *sbi); -int __init f2fs_create_root_stats(void); +void __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); #else #define stat_inc_cp_count(si) do { } while (0) @@ -3366,7 +3366,7 @@ void f2fs_destroy_root_stats(void); static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } -static inline int __init f2fs_create_root_stats(void) { return 0; } +static inline void __init f2fs_create_root_stats(void) { } static inline void f2fs_destroy_root_stats(void) { } #endif diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index c46a1d4318d4..3d3ce9eb6d13 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3545,9 +3545,7 @@ static int __init init_f2fs_fs(void) err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; - err = f2fs_create_root_stats(); - if (err) - goto free_filesystem; + f2fs_create_root_stats(); err = f2fs_init_post_read_processing(); if (err) goto free_root_stats; @@ -3555,7 +3553,6 @@ static int __init init_f2fs_fs(void) free_root_stats: f2fs_destroy_root_stats(); -free_filesystem: unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index a5e516a40e7a..809c0f2f9942 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1742,7 +1742,6 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.h.nodeid = outarg->nodeid; req->in.numargs = 2; req->in.argpages = 1; - req->page_descs[0].offset = offset; req->end = fuse_retrieve_end; index = outarg->offset >> PAGE_SHIFT; @@ -1757,6 +1756,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, this_num = min_t(unsigned, num, PAGE_SIZE - offset); req->pages[req->num_pages] = page; + req->page_descs[req->num_pages].offset = offset; req->page_descs[req->num_pages].length = this_num; req->num_pages++; @@ -2077,8 +2077,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); + pipe_lock(pipe); for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); + pipe_unlock(pipe); out: kvfree(bufs); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index ffaffe18352a..a59c16bd90ac 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1782,7 +1782,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, spin_unlock(&fc->lock); dec_wb_stat(&bdi->wb, WB_WRITEBACK); - dec_node_page_state(page, NR_WRITEBACK_TEMP); + dec_node_page_state(new_req->pages[0], NR_WRITEBACK_TEMP); wb_writeout_inc(&bdi->wb); fuse_writepage_free(fc, new_req); fuse_request_free(new_req); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 76baaa6be393..c2d4099429be 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -628,6 +628,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns) get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); fc->pid_ns = get_pid_ns(task_active_pid_ns(current)); fc->user_ns = get_user_ns(user_ns); + fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; } EXPORT_SYMBOL_GPL(fuse_conn_init); @@ -1162,7 +1163,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->user_id = d.user_id; fc->group_id = d.group_id; fc->max_read = max_t(unsigned, 4096, d.max_read); - fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; /* Used by get_root_inode() */ sb->s_fs_info = fc; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 4ca0b5c18192..b84d635567d3 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -536,8 +536,8 @@ void kernfs_put(struct kernfs_node *kn) security_release_secctx(kn->iattr->ia_secdata, kn->iattr->ia_secdata_len); simple_xattrs_free(&kn->iattr->xattrs); + kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } - kfree(kn->iattr); spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, kn->id.ino); spin_unlock(&kernfs_idr_lock); diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 80cebcd94c90..0c1fd945ce42 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -42,7 +42,7 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) if (kn->iattr) goto out_unlock; - kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL); + kn->iattr = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL); if (!kn->iattr) goto out_unlock; iattrs = &kn->iattr->ia_iattr; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 3d83b114bb08..dba810cd83b1 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -78,7 +78,7 @@ static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) } extern const struct super_operations kernfs_sops; -extern struct kmem_cache *kernfs_node_cache; +extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index fdf527b6d79c..450eb388bae6 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -20,7 +20,7 @@ #include "kernfs-internal.h" -struct kmem_cache *kernfs_node_cache; +struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data) { @@ -417,4 +417,9 @@ void __init kernfs_init(void) 0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL); + + /* Creates slab cache for kernfs inode attributes */ + kernfs_iattrs_cache = kmem_cache_create("kernfs_iattrs_cache", + sizeof(struct kernfs_iattrs), + 0, SLAB_PANIC, NULL); } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9824e32b2f23..7dc98e14655d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -557,9 +557,11 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, loff_t cloned; cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); + if (cloned < 0) + return nfserrno(cloned); if (count && cloned != count) - cloned = -EINVAL; - return nfserrno(cloned < 0 ? cloned : 0); + return nfserrno(-EINVAL); + return 0; } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 51398457fe00..130fc6fbcc03 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -17,7 +17,6 @@ #include <linux/seq_file.h> #include "sysfs.h" -#include "../kernfs/kernfs-internal.h" /* * Determine ktype->sysfs_ops for the given kernfs_node. This function @@ -497,6 +496,7 @@ bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { int i; + for (i = 0; ptr[i]; i++) sysfs_remove_file(kobj, ptr[i]); } diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 1c8eecfe52b8..6acf1bfa0bfe 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -768,18 +768,23 @@ xrep_findroot_block( if (!uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) goto out; + /* + * Read verifiers can reference b_ops, so we set the pointer + * here. If the verifier fails we'll reset the buffer state + * to what it was before we touched the buffer. + */ + bp->b_ops = fab->buf_ops; fab->buf_ops->verify_read(bp); if (bp->b_error) { + bp->b_ops = NULL; bp->b_error = 0; goto out; } /* * Some read verifiers will (re)set b_ops, so we must be - * careful not to blow away any such assignment. + * careful not to change b_ops after running the verifier. */ - if (!bp->b_ops) - bp->b_ops = fab->buf_ops; } /* diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 338b9d9984e0..d9048bcea49c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -449,6 +449,7 @@ xfs_map_blocks( } wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap); return 0; allocate_blocks: @@ -459,6 +460,7 @@ allocate_blocks: ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF || imap.br_startoff + imap.br_blockcount <= cow_fsb); wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap); return 0; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index eedc5e0156ff..4f5f2ff3f70f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -776,10 +776,26 @@ _xfs_buf_read( } /* + * Set buffer ops on an unchecked buffer and validate it, if possible. + * * If the caller passed in an ops structure and the buffer doesn't have ops * assigned, set the ops and use them to verify the contents. If the contents * cannot be verified, we'll clear XBF_DONE. We assume the buffer has no * recorded errors and is already in XBF_DONE state. + * + * Under normal operations, every in-core buffer must have buffer ops assigned + * to them when the buffer is read in from disk so that we can validate the + * metadata. + * + * However, there are two scenarios where one can encounter in-core buffers + * that don't have buffer ops. The first is during log recovery of buffers on + * a V4 filesystem, though these buffers are purged at the end of recovery. + * + * The other is online repair, which tries to match arbitrary metadata blocks + * with btree types in order to find the root. If online repair doesn't match + * the buffer with /any/ btree type, the buffer remains in memory in DONE state + * with no ops, and a subsequent read_buf call from elsewhere will not set the + * ops. This function helps us fix this situation. */ int xfs_buf_ensure_ops( @@ -1536,8 +1552,7 @@ __xfs_buf_submit( xfs_buf_ioerror(bp, -EIO); bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); - if (bp->b_flags & XBF_ASYNC) - xfs_buf_ioend(bp); + xfs_buf_ioend(bp); return -EIO; } diff --git a/include/dt-bindings/clock/imx8mq-clock.h b/include/dt-bindings/clock/imx8mq-clock.h index b53be41929be..04f7ac345984 100644 --- a/include/dt-bindings/clock/imx8mq-clock.h +++ b/include/dt-bindings/clock/imx8mq-clock.h @@ -350,7 +350,7 @@ #define IMX8MQ_CLK_VPU_G2_ROOT 241 /* SCCG PLL GATE */ -#define IMX8MQ_SYS1_PLL_OUT 232 +#define IMX8MQ_SYS1_PLL_OUT 242 #define IMX8MQ_SYS2_PLL_OUT 243 #define IMX8MQ_SYS3_PLL_OUT 244 #define IMX8MQ_DRAM_PLL_OUT 245 @@ -372,24 +372,24 @@ /* txesc clock */ #define IMX8MQ_CLK_DSI_IPG_DIV 256 -#define IMX8MQ_CLK_TMU_ROOT 265 +#define IMX8MQ_CLK_TMU_ROOT 257 /* Display root clocks */ -#define IMX8MQ_CLK_DISP_AXI_ROOT 266 -#define IMX8MQ_CLK_DISP_APB_ROOT 267 -#define IMX8MQ_CLK_DISP_RTRM_ROOT 268 +#define IMX8MQ_CLK_DISP_AXI_ROOT 258 +#define IMX8MQ_CLK_DISP_APB_ROOT 259 +#define IMX8MQ_CLK_DISP_RTRM_ROOT 260 -#define IMX8MQ_CLK_OCOTP_ROOT 269 +#define IMX8MQ_CLK_OCOTP_ROOT 261 -#define IMX8MQ_CLK_DRAM_ALT_ROOT 270 -#define IMX8MQ_CLK_DRAM_CORE 271 +#define IMX8MQ_CLK_DRAM_ALT_ROOT 262 +#define IMX8MQ_CLK_DRAM_CORE 263 -#define IMX8MQ_CLK_MU_ROOT 272 -#define IMX8MQ_VIDEO2_PLL_OUT 273 +#define IMX8MQ_CLK_MU_ROOT 264 +#define IMX8MQ_VIDEO2_PLL_OUT 265 -#define IMX8MQ_CLK_CLKO2 274 +#define IMX8MQ_CLK_CLKO2 266 -#define IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK 275 +#define IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK 267 -#define IMX8MQ_CLK_END 276 +#define IMX8MQ_CLK_END 268 #endif /* __DT_BINDINGS_CLOCK_IMX8MQ_H */ diff --git a/include/linux/async.h b/include/linux/async.h index 6b0226bdaadc..f81d6dbffe68 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -14,6 +14,8 @@ #include <linux/types.h> #include <linux/list.h> +#include <linux/numa.h> +#include <linux/device.h> typedef u64 async_cookie_t; typedef void (*async_func_t) (void *data, async_cookie_t cookie); @@ -37,9 +39,83 @@ struct async_domain { struct async_domain _name = { .pending = LIST_HEAD_INIT(_name.pending), \ .registered = 0 } -extern async_cookie_t async_schedule(async_func_t func, void *data); -extern async_cookie_t async_schedule_domain(async_func_t func, void *data, - struct async_domain *domain); +async_cookie_t async_schedule_node(async_func_t func, void *data, + int node); +async_cookie_t async_schedule_node_domain(async_func_t func, void *data, + int node, + struct async_domain *domain); + +/** + * async_schedule - schedule a function for asynchronous execution + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * + * Returns an async_cookie_t that may be used for checkpointing later. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t async_schedule(async_func_t func, void *data) +{ + return async_schedule_node(func, data, NUMA_NO_NODE); +} + +/** + * async_schedule_domain - schedule a function for asynchronous execution within a certain domain + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * @domain: the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t +async_schedule_domain(async_func_t func, void *data, + struct async_domain *domain) +{ + return async_schedule_node_domain(func, data, NUMA_NO_NODE, domain); +} + +/** + * async_schedule_dev - A device specific version of async_schedule + * @func: function to execute asynchronously + * @dev: device argument to be passed to function + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @dev is used as both the argument for the function and to provide NUMA + * context for where to run the function. By doing this we can try to + * provide for the best possible outcome by operating on the device on the + * CPUs closest to the device. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t +async_schedule_dev(async_func_t func, struct device *dev) +{ + return async_schedule_node(func, dev, dev_to_node(dev)); +} + +/** + * async_schedule_dev_domain - A device specific version of async_schedule_domain + * @func: function to execute asynchronously + * @dev: device argument to be passed to function + * @domain: the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @dev is used as both the argument for the function and to provide NUMA + * context for where to run the function. By doing this we can try to + * provide for the best possible outcome by operating on the device on the + * CPUs closest to the device. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. + * Note: This function may be called from atomic or non-atomic contexts. + */ +static inline async_cookie_t +async_schedule_dev_domain(async_func_t func, struct device *dev, + struct async_domain *domain) +{ + return async_schedule_node_domain(func, dev, dev_to_node(dev), domain); +} + void async_unregister_domain(struct async_domain *domain); extern void async_synchronize_full(void); extern void async_synchronize_full_domain(struct async_domain *domain); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8804753805ac..7bb2d8de9f30 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); static inline sector_t blk_rq_trace_sector(struct request *rq) { - return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); + /* + * Tracing should ignore starting sector for passthrough requests and + * requests where starting sector didn't get set. + */ + if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1) + return 0; + return blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) diff --git a/include/linux/device.h b/include/linux/device.h index 6cb4640b6160..292b720c4bc2 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -341,6 +341,7 @@ struct device *driver_find_device(struct device_driver *drv, struct device *start, void *data, int (*match)(struct device *dev, void *data)); +void driver_deferred_probe_add(struct device *dev); int driver_deferred_probe_check_state(struct device *dev); /** @@ -827,12 +828,14 @@ enum device_link_state { * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. + * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) +#define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) /** * struct device_link - Device link representation. @@ -853,7 +856,7 @@ struct device_link { struct list_head c_node; enum device_link_state status; u32 flags; - bool rpm_active; + refcount_t rpm_active; struct kref kref; #ifdef CONFIG_SRCU struct rcu_head rcu_head; @@ -985,7 +988,7 @@ struct device { void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with - dev_set/get_drvdata */ + dev_set_drvdata/dev_get_drvdata */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; @@ -1035,7 +1038,6 @@ struct device { spinlock_t devres_lock; struct list_head devres_head; - struct klist_node knode_class; struct class *class; const struct attribute_group **groups; /* optional groups */ @@ -1382,28 +1384,28 @@ void device_link_remove(void *consumer, struct device *supplier); #ifdef CONFIG_PRINTK -__printf(3, 0) +__printf(3, 0) __cold int dev_vprintk_emit(int level, const struct device *dev, const char *fmt, va_list args); -__printf(3, 4) +__printf(3, 4) __cold int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); -__printf(3, 4) +__printf(3, 4) __cold void dev_printk(const char *level, const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_emerg(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_alert(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_crit(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_err(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_warn(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_notice(const struct device *dev, const char *fmt, ...); -__printf(2, 3) +__printf(2, 3) __cold void _dev_info(const struct device *dev, const char *fmt, ...); #else diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..e532fcc6e4b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } -static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) +static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; @@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, return res; } +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u32 res; + + preempt_disable(); + res = __bpf_prog_run_save_cb(prog, skb); + preempt_enable(); + return res; +} + static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); + u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h index 8663f216c563..2d6100edf204 100644 --- a/include/linux/hid-debug.h +++ b/include/linux/hid-debug.h @@ -24,7 +24,10 @@ #ifdef CONFIG_DEBUG_FS +#include <linux/kfifo.h> + #define HID_DEBUG_BUFSIZE 512 +#define HID_DEBUG_FIFOSIZE 512 void hid_dump_input(struct hid_device *, struct hid_usage *, __s32); void hid_dump_report(struct hid_device *, int , u8 *, int); @@ -37,11 +40,8 @@ void hid_debug_init(void); void hid_debug_exit(void); void hid_debug_event(struct hid_device *, char *); - struct hid_debug_list { - char *hid_debug_buf; - int head; - int tail; + DECLARE_KFIFO_PTR(hid_debug_fifo, char); struct fasync_struct *fasync; struct hid_device *hdev; struct list_head node; @@ -64,4 +64,3 @@ struct hid_debug_list { #endif #endif - diff --git a/include/linux/ihex.h b/include/linux/ihex.h index 75c194391869..98cb5ce0b0a0 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -21,12 +21,24 @@ struct ihex_binrec { uint8_t data[0]; } __attribute__((packed)); +static inline uint16_t ihex_binrec_size(const struct ihex_binrec *p) +{ + return be16_to_cpu(p->len) + sizeof(*p); +} + /* Find the next record, taking into account the 4-byte alignment */ static inline const struct ihex_binrec * +__ihex_next_binrec(const struct ihex_binrec *rec) +{ + const void *p = rec; + + return p + ALIGN(ihex_binrec_size(rec), 4); +} + +static inline const struct ihex_binrec * ihex_next_binrec(const struct ihex_binrec *rec) { - int next = ((be16_to_cpu(rec->len) + 5) & ~3) - 2; - rec = (void *)&rec->data[next]; + rec = __ihex_next_binrec(rec); return be16_to_cpu(rec->len) ? rec : NULL; } @@ -34,18 +46,15 @@ ihex_next_binrec(const struct ihex_binrec *rec) /* Check that ihex_next_binrec() won't take us off the end of the image... */ static inline int ihex_validate_fw(const struct firmware *fw) { - const struct ihex_binrec *rec; - size_t ofs = 0; + const struct ihex_binrec *end, *rec; - while (ofs <= fw->size - sizeof(*rec)) { - rec = (void *)&fw->data[ofs]; + rec = (const void *)fw->data; + end = (const void *)&fw->data[fw->size - sizeof(*end)]; + for (; rec <= end; rec = __ihex_next_binrec(rec)) { /* Zero length marks end of records */ - if (!be16_to_cpu(rec->len)) + if (rec == end && !be16_to_cpu(rec->len)) return 0; - - /* Point to next record... */ - ofs += (sizeof(*rec) + be16_to_cpu(rec->len) + 3) & ~3; } return -EINVAL; } diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 071b4cbdf010..c848a7cc502e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -319,7 +319,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1377d085ef99..86dbb3e29139 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1483,6 +1483,7 @@ struct net_device_ops { * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device + * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1514,6 +1515,7 @@ enum netdev_priv_flags { IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, + IFF_L3MDEV_RX_HANDLER = 1<<29, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1544,6 +1546,7 @@ enum netdev_priv_flags { #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE +#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER /** * struct net_device - The DEVICE structure. @@ -4549,6 +4552,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_has_l3_rx_handler(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; +} + static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; diff --git a/include/linux/signal.h b/include/linux/signal.h index cc7e2c1cd444..9702016734b1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig); #endif #define siginmask(sig, mask) \ - ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) + ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7ddfc65586b0..4335bd771ce5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -184,6 +184,7 @@ struct plat_stmmacenet_data { struct clk *pclk; struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; + unsigned int clk_ref_rate; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 60d673e15632..1f50c1e586e7 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -463,6 +463,8 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); +extern bool queue_work_node(int node, struct workqueue_struct *wq, + struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 78fa0ac4613c..5175fd63cd82 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -153,7 +153,8 @@ struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); - else if (netif_is_l3_master(skb->dev)) + else if (netif_is_l3_master(skb->dev) || + netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 841835a387e1..b4984bbbe157 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -469,9 +469,7 @@ struct nft_set_binding { int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding); + struct nft_set_binding *binding, bool commit); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** @@ -721,6 +719,13 @@ struct nft_expr_type { #define NFT_EXPR_STATEFUL 0x1 #define NFT_EXPR_GC 0x2 +enum nft_trans_phase { + NFT_TRANS_PREPARE, + NFT_TRANS_ABORT, + NFT_TRANS_COMMIT, + NFT_TRANS_RELEASE +}; + /** * struct nft_expr_ops - nf_tables expression operations * @@ -750,7 +755,8 @@ struct nft_expr_ops { void (*activate)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*deactivate)(const struct nft_ctx *ctx, - const struct nft_expr *expr); + const struct nft_expr *expr, + enum nft_trans_phase phase); void (*destroy)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*destroy_clone)(const struct nft_ctx *ctx, @@ -1323,12 +1329,15 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_set *set; u32 set_id; + bool bound; }; #define nft_trans_set(trans) \ (((struct nft_trans_set *)trans->data)->set) #define nft_trans_set_id(trans) \ (((struct nft_trans_set *)trans->data)->set_id) +#define nft_trans_set_bound(trans) \ + (((struct nft_trans_set *)trans->data)->bound) struct nft_trans_chain { bool update; diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index 0cdc3999ecfa..c5188ff724d1 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -173,7 +173,11 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) if (snd_BUG_ON(!stream)) return; - stream->runtime->state = SNDRV_PCM_STATE_SETUP; + if (stream->direction == SND_COMPRESS_PLAYBACK) + stream->runtime->state = SNDRV_PCM_STATE_SETUP; + else + stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + wake_up(&stream->runtime->sleep); } diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 7fa48b100936..cc7c8d42d4fd 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -68,6 +68,7 @@ struct hda_bus { unsigned int response_reset:1; /* controller was reset */ unsigned int in_reset:1; /* during reset operation */ unsigned int no_response_fallback:1; /* don't fallback at RIRB error */ + unsigned int bus_probing :1; /* during probing process */ int primary_dig_out_type; /* primary digital out PCM type */ unsigned int mixer_assigned; /* codec addr for mixer name */ diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 1196e1c1d4f6..ff8e7dc9d4dd 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -79,6 +79,12 @@ #define VIRTIO_F_RING_PACKED 34 /* + * This feature indicates that memory accesses by the driver and the + * device are ordered in a way described by the platform. + */ +#define VIRTIO_F_ORDER_PLATFORM 36 + +/* * Does the device support Single Root I/O Virtualization? */ #define VIRTIO_F_SR_IOV 37 diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 2414f8af26b3..4c4e24c291a5 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -213,14 +213,4 @@ struct vring_packed_desc { __le16 flags; }; -struct vring_packed { - unsigned int num; - - struct vring_packed_desc *desc; - - struct vring_packed_desc_event *driver; - - struct vring_packed_desc_event *device; -}; - #endif /* _UAPI_LINUX_VIRTIO_RING_H */ diff --git a/kernel/async.c b/kernel/async.c index a893d6170944..f6bd0d9885e1 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -149,7 +149,25 @@ static void async_run_entry_fn(struct work_struct *work) wake_up(&async_done); } -static async_cookie_t __async_schedule(async_func_t func, void *data, struct async_domain *domain) +/** + * async_schedule_node_domain - NUMA specific version of async_schedule_domain + * @func: function to execute asynchronously + * @data: data pointer to pass to the function + * @node: NUMA node that we want to schedule this on or close to + * @domain: the domain + * + * Returns an async_cookie_t that may be used for checkpointing later. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. + * + * Note: This function may be called from atomic or non-atomic contexts. + * + * The node requested will be honored on a best effort basis. If the node + * has no CPUs associated with it then the work is distributed among all + * available CPUs. + */ +async_cookie_t async_schedule_node_domain(async_func_t func, void *data, + int node, struct async_domain *domain) { struct async_entry *entry; unsigned long flags; @@ -195,43 +213,30 @@ static async_cookie_t __async_schedule(async_func_t func, void *data, struct asy current->flags |= PF_USED_ASYNC; /* schedule for execution */ - queue_work(system_unbound_wq, &entry->work); + queue_work_node(node, system_unbound_wq, &entry->work); return newcookie; } +EXPORT_SYMBOL_GPL(async_schedule_node_domain); /** - * async_schedule - schedule a function for asynchronous execution + * async_schedule_node - NUMA specific version of async_schedule * @func: function to execute asynchronously * @data: data pointer to pass to the function + * @node: NUMA node that we want to schedule this on or close to * * Returns an async_cookie_t that may be used for checkpointing later. * Note: This function may be called from atomic or non-atomic contexts. - */ -async_cookie_t async_schedule(async_func_t func, void *data) -{ - return __async_schedule(func, data, &async_dfl_domain); -} -EXPORT_SYMBOL_GPL(async_schedule); - -/** - * async_schedule_domain - schedule a function for asynchronous execution within a certain domain - * @func: function to execute asynchronously - * @data: data pointer to pass to the function - * @domain: the domain * - * Returns an async_cookie_t that may be used for checkpointing later. - * @domain may be used in the async_synchronize_*_domain() functions to - * wait within a certain synchronization domain rather than globally. A - * synchronization domain is specified via @domain. Note: This function - * may be called from atomic or non-atomic contexts. + * The node requested will be honored on a best effort basis. If the node + * has no CPUs associated with it then the work is distributed among all + * available CPUs. */ -async_cookie_t async_schedule_domain(async_func_t func, void *data, - struct async_domain *domain) +async_cookie_t async_schedule_node(async_func_t func, void *data, int node) { - return __async_schedule(func, data, domain); + return async_schedule_node_domain(func, data, node, &async_dfl_domain); } -EXPORT_SYMBOL_GPL(async_schedule_domain); +EXPORT_SYMBOL_GPL(async_schedule_node); /** * async_synchronize_full - synchronize all asynchronous function calls diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index befe570be5ba..c57bd10340ed 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1459,7 +1459,8 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, /* "typedef void new_void", "const void"...etc */ if (!btf_type_is_void(next_type) && - !btf_type_is_fwd(next_type)) { + !btf_type_is_fwd(next_type) && + !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ab612fe9862f..d17d05570a3f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -572,7 +572,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, bpf_compute_and_save_data_end(skb, &saved_data_end); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - bpf_prog_run_save_cb); + __bpf_prog_run_save_cb); bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4b7c76765d9d..f9274114c88d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -686,7 +686,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) } if (htab_is_prealloc(htab)) { - pcpu_freelist_push(&htab->freelist, &l->fnode); + __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); l->htab = htab; @@ -748,7 +748,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } else { struct pcpu_freelist_node *l; - l = pcpu_freelist_pop(&htab->freelist); + l = __pcpu_freelist_pop(&htab->freelist); if (!l) return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 673fa6fe2d73..0c1b4ba9e90e 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s) free_percpu(s->freelist); } -static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, - struct pcpu_freelist_node *node) +static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) { raw_spin_lock(&head->lock); node->next = head->first; @@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, raw_spin_unlock(&head->lock); } -void pcpu_freelist_push(struct pcpu_freelist *s, +void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - __pcpu_freelist_push(head, node); + ___pcpu_freelist_push(head, node); +} + +void pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + unsigned long flags; + + local_irq_save(flags); + __pcpu_freelist_push(s, node); + local_irq_restore(flags); } void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, @@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, for_each_possible_cpu(cpu) { again: head = per_cpu_ptr(s->freelist, cpu); - __pcpu_freelist_push(head, buf); + ___pcpu_freelist_push(head, buf); i++; buf += elem_size; if (i == nr_elems) @@ -74,14 +84,12 @@ again: local_irq_restore(flags); } -struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; - unsigned long flags; int orig_cpu, cpu; - local_irq_save(flags); orig_cpu = cpu = raw_smp_processor_id(); while (1) { head = per_cpu_ptr(s->freelist, cpu); @@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) node = head->first; if (node) { head->first = node->next; - raw_spin_unlock_irqrestore(&head->lock, flags); + raw_spin_unlock(&head->lock); return node; } raw_spin_unlock(&head->lock); cpu = cpumask_next(cpu, cpu_possible_mask); if (cpu >= nr_cpu_ids) cpu = 0; - if (cpu == orig_cpu) { - local_irq_restore(flags); + if (cpu == orig_cpu) return NULL; - } } } + +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +{ + struct pcpu_freelist_node *ret; + unsigned long flags; + + local_irq_save(flags); + ret = __pcpu_freelist_pop(s); + local_irq_restore(flags); + return ret; +} diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index 3049aae8ea1e..c3960118e617 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -22,8 +22,12 @@ struct pcpu_freelist_node { struct pcpu_freelist_node *next; }; +/* pcpu_freelist_* do spin_lock_irqsave. */ void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); +/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */ +void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *); void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems); int pcpu_freelist_init(struct pcpu_freelist *); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..8577bb7f8be6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -713,8 +713,13 @@ static int map_lookup_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + goto done; + } + + preempt_disable(); + this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); @@ -744,7 +749,10 @@ static int map_lookup_elem(union bpf_attr *attr) } rcu_read_unlock(); } + this_cpu_dec(bpf_prog_active); + preempt_enable(); +done: if (err) goto free_value; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 4a9937076331..309ef5a64af5 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -734,6 +734,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct ring_buffer); size += nr_pages * sizeof(void *); + if (order_base_2(size) >= MAX_ORDER) + goto fail; + rb = kzalloc(size, GFP_KERNEL); if (!rb) goto fail; diff --git a/kernel/futex.c b/kernel/futex.c index fdd312da0992..a0514e01c3eb 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2221,11 +2221,11 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) * decrement the counter at queue_unlock() when some error has * occurred and we don't end up adding the task to the list. */ - hb_waiters_inc(hb); + hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; - spin_lock(&hb->lock); /* implies smp_mb(); (A) */ + spin_lock(&hb->lock); return hb; } @@ -2861,35 +2861,39 @@ retry_private: * and BUG when futex_unlock_pi() interleaves with this. * * Therefore acquire wait_lock while holding hb->lock, but drop the - * latter before calling rt_mutex_start_proxy_lock(). This still fully - * serializes against futex_unlock_pi() as that does the exact same - * lock handoff sequence. + * latter before calling __rt_mutex_start_proxy_lock(). This + * interleaves with futex_unlock_pi() -- which does a similar lock + * handoff -- such that the latter can observe the futex_q::pi_state + * before __rt_mutex_start_proxy_lock() is done. */ raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter + * such that futex_unlock_pi() is guaranteed to observe the waiter when + * it sees the futex_q::pi_state. + */ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); if (ret) { if (ret == 1) ret = 0; - - spin_lock(q.lock_ptr); - goto no_block; + goto cleanup; } - if (unlikely(to)) hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS); ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); +cleanup: spin_lock(q.lock_ptr); /* - * If we failed to acquire the lock (signal/timeout), we must + * If we failed to acquire the lock (deadlock/signal/timeout), we must * first acquire the hb->lock before removing the lock from the - * rt_mutex waitqueue, such that we can keep the hb and rt_mutex - * wait lists consistent. + * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait + * lists consistent. * * In particular; it is important that futex_unlock_pi() can not * observe this inconsistency. @@ -3013,6 +3017,10 @@ retry: * there is no point where we hold neither; and therefore * wake_futex_pi() must observe a state consistent with what we * observed. + * + * In particular; this forces __rt_mutex_start_proxy() to + * complete such that we're guaranteed to observe the + * rt_waiter. Also see the WARN in wake_futex_pi(). */ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 581edcc63c26..978d63a8261c 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1726,12 +1726,33 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, rt_mutex_set_owner(lock, NULL); } +/** + * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: does _NOT_ remove the @waiter on failure; must either call + * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this. + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for PI-futex support. + */ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task) { int ret; + lockdep_assert_held(&lock->wait_lock); + if (try_to_take_rt_mutex(lock, task, NULL)) return 1; @@ -1749,9 +1770,6 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, ret = 0; } - if (unlikely(ret)) - remove_waiter(lock, waiter); - debug_rt_mutex_print_deadlock(waiter); return ret; @@ -1763,12 +1781,18 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, * @waiter: the pre-initialized rt_mutex_waiter * @task: the task to prepare * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter + * on failure. + * * Returns: * 0 - task blocked on lock * 1 - acquired the lock for task, caller should wake it up * <0 - error * - * Special API call for FUTEX_REQUEUE_PI support. + * Special API call for PI-futex support. */ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, @@ -1778,6 +1802,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, raw_spin_lock_irq(&lock->wait_lock); ret = __rt_mutex_start_proxy_lock(lock, waiter, task); + if (unlikely(ret)) + remove_waiter(lock, waiter); raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -1845,7 +1871,8 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, * @lock: the rt_mutex we were woken on * @waiter: the pre-initialized rt_mutex_waiter * - * Attempt to clean up after a failed rt_mutex_wait_proxy_lock(). + * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or + * rt_mutex_wait_proxy_lock(). * * Unless we acquired the lock; we're still enqueued on the wait-list and can * in fact still be granted ownership until we're removed. Therefore we can diff --git a/kernel/relay.c b/kernel/relay.c index 04f248644e06..9e0f52375487 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -428,6 +428,8 @@ static struct dentry *relay_create_buf_file(struct rchan *chan, dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, buf, &chan->is_global); + if (IS_ERR(dentry)) + dentry = NULL; kfree(tmpname); @@ -461,7 +463,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) dentry = chan->cb->create_buf_file(NULL, NULL, S_IRUSR, buf, &chan->is_global); - if (WARN_ON(dentry)) + if (IS_ERR_OR_NULL(dentry)) goto free_buf; } diff --git a/kernel/signal.c b/kernel/signal.c index e1d7ad8e6ab1..99fa8ff06fd9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -688,6 +688,48 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in } EXPORT_SYMBOL_GPL(dequeue_signal); +static int dequeue_synchronous_signal(kernel_siginfo_t *info) +{ + struct task_struct *tsk = current; + struct sigpending *pending = &tsk->pending; + struct sigqueue *q, *sync = NULL; + + /* + * Might a synchronous signal be in the queue? + */ + if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK)) + return 0; + + /* + * Return the first synchronous signal in the queue. + */ + list_for_each_entry(q, &pending->list, list) { + /* Synchronous signals have a postive si_code */ + if ((q->info.si_code > SI_USER) && + (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { + sync = q; + goto next; + } + } + return 0; +next: + /* + * Check if there is another siginfo for the same signal. + */ + list_for_each_entry_continue(q, &pending->list, list) { + if (q->info.si_signo == sync->info.si_signo) + goto still_pending; + } + + sigdelset(&pending->signal, sync->info.si_signo); + recalc_sigpending(); +still_pending: + list_del_init(&sync->list); + copy_siginfo(info, &sync->info); + __sigqueue_free(sync); + return info->si_signo; +} + /* * Tell a process that it has a new active signal.. * @@ -1057,10 +1099,9 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc result = TRACE_SIGNAL_DELIVERED; /* - * Skip useless siginfo allocation for SIGKILL SIGSTOP, - * and kernel threads. + * Skip useless siginfo allocation for SIGKILL and kernel threads. */ - if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD)) + if ((sig == SIGKILL) || (t->flags & PF_KTHREAD)) goto out_set; /* @@ -2394,6 +2435,11 @@ relock: goto relock; } + /* Has this task already been marked for death? */ + ksig->info.si_signo = signr = SIGKILL; + if (signal_group_exit(signal)) + goto fatal; + for (;;) { struct k_sigaction *ka; @@ -2407,7 +2453,15 @@ relock: goto relock; } - signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + /* + * Signals generated by the execution of an instruction + * need to be delivered before any other pending signals + * so that the instruction pointer in the signal stack + * frame points to the faulting instruction. + */ + signr = dequeue_synchronous_signal(&ksig->info); + if (!signr) + signr = dequeue_signal(current, ¤t->blocked, &ksig->info); if (!signr) break; /* will return 0 */ @@ -2489,6 +2543,7 @@ relock: continue; } + fatal: spin_unlock_irq(&sighand->siglock); /* diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8b068adb9da1..f1a86a0d881d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1204,22 +1204,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = __bpf_probe_register(btp, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return __bpf_probe_register(btp, prog); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index e335576b9411..9bde07c06362 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -5,7 +5,7 @@ * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com> */ -#define pr_fmt(fmt) "trace_kprobe: " fmt +#define pr_fmt(fmt) "trace_uprobe: " fmt #include <linux/ctype.h> #include <linux/module.h> @@ -160,6 +160,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base) if (ret >= 0) { if (ret == maxlen) dst[ret - 1] = '\0'; + else + /* + * Include the terminating null byte. In this case it + * was copied by strncpy_from_user but not accounted + * for in ret. + */ + ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index fc5d23d752a5..1ce2697254d1 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1512,6 +1512,90 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL(queue_work_on); +/** + * workqueue_select_cpu_near - Select a CPU based on NUMA node + * @node: NUMA node ID that we want to select a CPU from + * + * This function will attempt to find a "random" cpu available on a given + * node. If there are no CPUs available on the given node it will return + * WORK_CPU_UNBOUND indicating that we should just schedule to any + * available CPU if we need to schedule this work. + */ +static int workqueue_select_cpu_near(int node) +{ + int cpu; + + /* No point in doing this if NUMA isn't enabled for workqueues */ + if (!wq_numa_enabled) + return WORK_CPU_UNBOUND; + + /* Delay binding to CPU if node is not valid or online */ + if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) + return WORK_CPU_UNBOUND; + + /* Use local node/cpu if we are already there */ + cpu = raw_smp_processor_id(); + if (node == cpu_to_node(cpu)) + return cpu; + + /* Use "random" otherwise know as "first" online CPU of node */ + cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); + + /* If CPU is valid return that, otherwise just defer */ + return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; +} + +/** + * queue_work_node - queue work on a "random" cpu for a given NUMA node + * @node: NUMA node that we are targeting the work for + * @wq: workqueue to use + * @work: work to queue + * + * We queue the work to a "random" CPU within a given NUMA node. The basic + * idea here is to provide a way to somehow associate work with a given + * NUMA node. + * + * This function will only make a best effort attempt at getting this onto + * the right NUMA node. If no node is requested or the requested node is + * offline then we just fall back to standard queue_work behavior. + * + * Currently the "random" CPU ends up being the first available CPU in the + * intersection of cpu_online_mask and the cpumask of the node, unless we + * are running on the node. In that case we just use the current CPU. + * + * Return: %false if @work was already on a queue, %true otherwise. + */ +bool queue_work_node(int node, struct workqueue_struct *wq, + struct work_struct *work) +{ + unsigned long flags; + bool ret = false; + + /* + * This current implementation is specific to unbound workqueues. + * Specifically we only return the first available CPU for a given + * node instead of cycling through individual CPUs within the node. + * + * If this is used with a per-cpu workqueue then the logic in + * workqueue_select_cpu_near would need to be updated to allow for + * some round robin type logic. + */ + WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); + + local_irq_save(flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + int cpu = workqueue_select_cpu_near(node); + + __queue_work(cpu, wq, work); + ret = true; + } + + local_irq_restore(flags); + return ret; +} +EXPORT_SYMBOL_GPL(queue_work_node); + void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); diff --git a/lib/devres.c b/lib/devres.c index faccf1a037d0..69bed2f38306 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -134,7 +134,6 @@ EXPORT_SYMBOL(devm_iounmap); void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res) { resource_size_t size; - const char *name; void __iomem *dest_ptr; BUG_ON(!dev); @@ -145,9 +144,8 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res) } size = resource_size(res); - name = res->name ?: dev_name(dev); - if (!devm_request_mem_region(dev, res->start, size, name)) { + if (!devm_request_mem_region(dev, res->start, size, dev_name(dev))) { dev_err(dev, "can't request region for resource %pR\n", res); return IOMEM_ERR_PTR(-EBUSY); } diff --git a/lib/kobject.c b/lib/kobject.c index b72e00fd7d09..aa89edcd2b63 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -887,7 +887,7 @@ static void kset_release(struct kobject *kobj) kfree(kset); } -void kset_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) +static void kset_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 27c6118afd1c..f05802687ba4 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -200,7 +200,7 @@ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) r = kobject_action_type(buf, count, &action, &action_args); if (r) { - msg = "unknown uevent action string\n"; + msg = "unknown uevent action string"; goto out; } @@ -212,7 +212,7 @@ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) r = kobject_action_args(action_args, count - (action_args - buf), &env); if (r == -EINVAL) { - msg = "incorrect uevent action arguments\n"; + msg = "incorrect uevent action arguments"; goto out; } @@ -224,7 +224,7 @@ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) out: if (r) { devpath = kobject_get_path(kobj, GFP_KERNEL); - printk(KERN_WARNING "synth uevent: %s: %s", + pr_warn("synth uevent: %s: %s\n", devpath ?: "unknown device", msg ?: "failed to send uevent"); kfree(devpath); @@ -765,8 +765,7 @@ static int uevent_net_init(struct net *net) ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { - printk(KERN_ERR - "kobject_uevent: unable to create netlink socket!\n"); + pr_err("kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 6a8ac7626797..e52f8cafe227 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -541,38 +541,45 @@ static unsigned int __init print_ht(struct rhltable *rhlt) static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects, int cnt, bool slow) { - struct rhltable rhlt; + struct rhltable *rhlt; unsigned int i, ret; const char *key; int err = 0; - err = rhltable_init(&rhlt, &test_rht_params_dup); - if (WARN_ON(err)) + rhlt = kmalloc(sizeof(*rhlt), GFP_KERNEL); + if (WARN_ON(!rhlt)) + return -EINVAL; + + err = rhltable_init(rhlt, &test_rht_params_dup); + if (WARN_ON(err)) { + kfree(rhlt); return err; + } for (i = 0; i < cnt; i++) { rhl_test_objects[i].value.tid = i; - key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead); + key = rht_obj(&rhlt->ht, &rhl_test_objects[i].list_node.rhead); key += test_rht_params_dup.key_offset; if (slow) { - err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key, + err = PTR_ERR(rhashtable_insert_slow(&rhlt->ht, key, &rhl_test_objects[i].list_node.rhead)); if (err == -EAGAIN) err = 0; } else - err = rhltable_insert(&rhlt, + err = rhltable_insert(rhlt, &rhl_test_objects[i].list_node, test_rht_params_dup); if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast")) goto skip_print; } - ret = print_ht(&rhlt); + ret = print_ht(rhlt); WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast"); skip_print: - rhltable_destroy(&rhlt); + rhltable_destroy(rhlt); + kfree(rhlt); return 0; } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index e8090f099eb8..ef0dec20c7d8 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo); + /* free the TID stats immediately */ + cfg80211_sinfo_release_content(&sinfo); + dev_put(real_netdev); if (ret == -ENOENT) { /* Node is not associated anymore! It would be diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 508f4416dfc9..415d494cbe22 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -20,7 +20,6 @@ #include "main.h" #include <linux/atomic.h> -#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/gfp.h> @@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) parent_dev = __dev_get_by_index((struct net *)parent_net, dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ - if (WARN(!parent_dev, "Cannot find parent device")) + if (!parent_dev) { + pr_err("Cannot find parent device\n"); return false; + } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5db5a0a4c959..b85ca809e509 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -221,6 +221,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, netif_trans_update(soft_iface); vid = batadv_get_vid(skb, 0); + + skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { diff --git a/net/core/filter.c b/net/core/filter.c index 7559d6835ecb..7a54dc11ac2d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4112,10 +4112,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: + val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_SNDBUF: + val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); break; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index d6d5c20d7044..8c826603bf36 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -545,8 +545,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc) struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ - if (psock->parser.enabled) - strp_done(&psock->parser.strp); + strp_done(&psock->parser.strp); cancel_work_sync(&psock->work); diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6eb837a47b5c..baaaeb2b2c42 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } @@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } diff --git a/net/dsa/master.c b/net/dsa/master.c index 71bb15f491c8..54f5551fb799 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -205,6 +205,8 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } +static struct lock_class_key dsa_master_addr_list_lock_key; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -218,6 +220,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; + lockdep_set_class(&dev->addr_list_lock, + &dsa_master_addr_list_lock_key); ret = dsa_master_ethtool_setup(dev); if (ret) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a3fcc1d01615..a1c9fe155057 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct net_device *master = dsa_slave_to_master(dev); - - if (change & IFF_ALLMULTI) - dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(master, + dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(master, + dev->flags & IFF_PROMISC ? 1 : -1); + } } static void dsa_slave_set_rx_mode(struct net_device *dev) @@ -639,7 +642,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -659,7 +662,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 20a64fe6254b..3978f807fa8b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1455,12 +1455,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((t->erspan_ver == 1 || t->erspan_ver == 2) && + !t->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4416368dbd49..801a9a0c217e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2098,12 +2098,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((p->erspan_ver == 1 || p->erspan_ver == 2) && + !p->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 8b075f0bc351..6d0b1f3e927b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; + int strict = (ipv6_addr_type(&iph->daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, + strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 8181ee7e1e27..ee5403cbe655 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); } hdr->nexthdr = NEXTHDR_ROUTING; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1e03305c0549..e8a1dabef803 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) } err = 0; - if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) + if (__in6_dev_get(skb->dev) && + !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 26f1d435696a..fed6becc5daf 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -83,8 +83,7 @@ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff -#define L2TP_HDR_SIZE_SEQ 10 -#define L2TP_HDR_SIZE_NOSEQ 6 +#define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 @@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) { + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { l2tp_info(tunnel, L2TP_MSG_DATA, "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); @@ -884,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) goto error; } + if (tunnel->version == L2TP_HDR_VER_3 && + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto error; + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9c9afe94d389..b2ce90260c35 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) } #endif +static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb, + unsigned char **ptr, unsigned char **optr) +{ + int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session); + + if (opt_len > 0) { + int off = *ptr - *optr; + + if (!pskb_may_pull(skb, off + opt_len)) + return -1; + + if (skb->data != *optr) { + *optr = skb->data; + *ptr = skb->data + off; + } + } + + return 0; +} + #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 35f6f86d4dcc..d4c60523c549 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 237f1a4a0b0c..0ae6899edac0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f170d6c6629a..928f13a208b0 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1938,9 +1938,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, int head_need, bool may_encrypt) { struct ieee80211_local *local = sdata->local; + struct ieee80211_hdr *hdr; + bool enc_tailroom; int tail_need = 0; - if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) { + hdr = (struct ieee80211_hdr *) skb->data; + enc_tailroom = may_encrypt && + (sdata->crypto_tx_tailroom_needed_cnt || + ieee80211_is_mgmt(hdr->frame_control)); + + if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); @@ -1948,8 +1955,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, if (skb_cloned(skb) && (!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) || - !skb_clone_writable(skb, ETH_HLEN) || - (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt))) + !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 741b533148ba..db4d46332e86 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1007,6 +1007,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, } if (nf_ct_key_equal(h, tuple, zone, net)) { + /* Tuple is taken already, so caller will need to find + * a new source port to use. + * + * Only exception: + * If the *original tuples* are identical, then both + * conntracks refer to the same flow. + * This is a rare situation, it can occur e.g. when + * more than one UDP packet is sent from same socket + * in different threads. + * + * Let nf_ct_resolve_clash() deal with this later. + */ + if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + continue; + NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fb07f6cfc719..5a92f23f179f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -116,6 +116,23 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_set_is_anonymous(set)) + return; + + list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + nft_trans_set(trans) == set) { + nft_trans_set_bound(trans) = true; + break; + } + } +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -211,18 +228,6 @@ static int nft_delchain(struct nft_ctx *ctx) return err; } -/* either expr ops provide both activate/deactivate, or neither */ -static bool nft_expr_check_ops(const struct nft_expr_ops *ops) -{ - if (!ops) - return true; - - if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate))) - return false; - - return true; -} - static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { @@ -238,14 +243,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule) + struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { if (expr->ops->deactivate) - expr->ops->deactivate(ctx, expr); + expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } @@ -296,7 +302,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) nft_trans_destroy(trans); return err; } - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } @@ -1929,9 +1935,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, */ int nft_register_expr(struct nft_expr_type *type) { - if (!nft_expr_check_ops(type->ops)) - return -EINVAL; - nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); @@ -2079,10 +2082,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); goto err1; } - if (!nft_expr_check_ops(ops)) { - err = -EINVAL; - goto err1; - } } else ops = type->ops; @@ -2511,7 +2510,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -3708,39 +3707,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, bind: binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); + nft_set_trans_bind(ctx, set); + return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) -{ - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) - list_add_tail_rcu(&set->list, &ctx->table->sets); - - list_add_tail_rcu(&binding->list, &set->bindings); -} -EXPORT_SYMBOL_GPL(nf_tables_rebind_set); - void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) + struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + if (event) + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, + GFP_KERNEL); + } } EXPORT_SYMBOL_GPL(nf_tables_unbind_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) { - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC); + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) nft_set_destroy(set); - } } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); @@ -6535,6 +6525,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_DELRULE); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_COMMIT); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -6621,7 +6614,8 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: - nft_set_destroy(nft_trans_set(trans)); + if (!nft_trans_set_bound(trans)) + nft_set_destroy(nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), @@ -6682,7 +6676,9 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWRULE: trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans)); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_ABORT); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; @@ -6692,7 +6688,8 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - list_del_rcu(&nft_trans_set(trans)->list); + if (!nft_trans_set_bound(trans)) + list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: trans->ctx.table->use++; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 5eb269428832..fe64df848365 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -61,6 +61,21 @@ static struct nft_compat_net *nft_compat_pernet(struct net *net) return net_generic(net, nft_compat_net_id); } +static void nft_xt_get(struct nft_xt *xt) +{ + /* refcount_inc() warns on 0 -> 1 transition, but we can't + * init the reference count to 1 in .select_ops -- we can't + * undo such an increase when another expression inside the same + * rule fails afterwards. + */ + if (xt->listcnt == 0) + refcount_set(&xt->refcnt, 1); + else + refcount_inc(&xt->refcnt); + + xt->listcnt++; +} + static bool nft_xt_put(struct nft_xt *xt) { if (refcount_dec_and_test(&xt->refcnt)) { @@ -291,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; nft_xt = container_of(expr->ops, struct nft_xt, ops); - refcount_inc(&nft_xt->refcnt); + nft_xt_get(nft_xt); return 0; } @@ -504,7 +519,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; nft_xt = container_of(expr->ops, struct nft_xt, ops); - refcount_inc(&nft_xt->refcnt); + nft_xt_get(nft_xt); return 0; } @@ -558,41 +573,16 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } -static void nft_compat_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - struct list_head *h) -{ - struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - - if (xt->listcnt == 0) - list_add(&xt->head, h); - - xt->listcnt++; -} - -static void nft_compat_activate_mt(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_compat_net *cn = nft_compat_pernet(ctx->net); - - nft_compat_activate(ctx, expr, &cn->nft_match_list); -} - -static void nft_compat_activate_tg(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_compat_net *cn = nft_compat_pernet(ctx->net); - - nft_compat_activate(ctx, expr, &cn->nft_target_list); -} - static void nft_compat_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - if (--xt->listcnt == 0) - list_del_init(&xt->head); + if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) { + if (--xt->listcnt == 0) + list_del_init(&xt->head); + } } static void @@ -848,7 +838,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; nft_match->ops.destroy = nft_match_destroy; - nft_match->ops.activate = nft_compat_activate_mt; nft_match->ops.deactivate = nft_compat_deactivate; nft_match->ops.dump = nft_match_dump; nft_match->ops.validate = nft_match_validate; @@ -866,7 +855,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.size = matchsize; - nft_match->listcnt = 1; + nft_match->listcnt = 0; list_add(&nft_match->head, &cn->nft_match_list); return &nft_match->ops; @@ -953,7 +942,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; nft_target->ops.destroy = nft_target_destroy; - nft_target->ops.activate = nft_compat_activate_tg; nft_target->ops.deactivate = nft_compat_deactivate; nft_target->ops.dump = nft_target_dump; nft_target->ops.validate = nft_target_validate; @@ -964,7 +952,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, else nft_target->ops.eval = nft_target_eval_xt; - nft_target->listcnt = 1; + nft_target->listcnt = 0; list_add(&nft_target->head, &cn->nft_target_list); return &nft_target->ops; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 07d4efd3d851..f1172f99752b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -235,20 +235,17 @@ err1: return err; } -static void nft_dynset_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_dynset *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_dynset_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_dynset *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_dynset_destroy(const struct nft_ctx *ctx, @@ -296,7 +293,6 @@ static const struct nft_expr_ops nft_dynset_ops = { .eval = nft_dynset_eval, .init = nft_dynset_init, .destroy = nft_dynset_destroy, - .activate = nft_dynset_activate, .deactivate = nft_dynset_deactivate, .dump = nft_dynset_dump, }; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 0777a93211e2..3f6d1d2a6281 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, } static void nft_immediate_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 227b2b15a19c..14496da5141d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } -static void nft_lookup_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_lookup *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_lookup_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_lookup_destroy(const struct nft_ctx *ctx, @@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), .eval = nft_lookup_eval, .init = nft_lookup_init, - .activate = nft_lookup_activate, .deactivate = nft_lookup_deactivate, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index a3185ca2a3a9..ae178e914486 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -155,20 +155,17 @@ nla_put_failure: return -1; } -static void nft_objref_map_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_objref_map *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_objref_map_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_objref_map *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, @@ -185,7 +182,6 @@ static const struct nft_expr_ops nft_objref_map_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), .eval = nft_objref_map_eval, .init = nft_objref_map_init, - .activate = nft_objref_map_activate, .deactivate = nft_objref_map_deactivate, .destroy = nft_objref_map_destroy, .dump = nft_objref_map_dump, diff --git a/net/rds/bind.c b/net/rds/bind.c index 762d2c6788a3..17c9d9f0c848 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); - if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) - rds_sock_addref(rs); - else + if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || + !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index eaf19ebaa964..3f7bb11f3290 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -596,6 +596,7 @@ error_requeue_call: } error_no_call: release_sock(&rx->sk); +error_trace: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); return ret; @@ -604,7 +605,7 @@ wait_interrupted: wait_error: finish_wait(sk_sleep(&rx->sk), &wait); call = NULL; - goto error_no_call; + goto error_trace; } /** diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6aa57fbbbaf..12ca9d13db83 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1371,7 +1371,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); if (err) - goto errout_mask; + goto errout_mask_ht; } if (!tc_in_hw(fnew->flags)) @@ -1401,6 +1401,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, kfree(mask); return 0; +errout_mask_ht: + rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); + errout_mask: fl_mask_put(head, fnew->mask, false); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f93c3cf9e567..65d6d04546ae 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; - struct sctp_association *asoc; + struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; @@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { - list_for_each_entry(asoc, &ep->asocs, asocs) { + list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 80e0ae5534ec..f24633114dfd 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count) } } +static size_t fa_index(struct flex_array *fa, void *elem, size_t count) +{ + size_t index = 0; + + while (count--) { + if (elem == flex_array_get(fa, index)) + break; + index++; + } + + return index; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -147,6 +160,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, if (stream->out) { fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + if (stream->out_curr) { + size_t index = fa_index(stream->out, stream->out_curr, + stream->outcnt); + + BUG_ON(index == stream->outcnt); + stream->out_curr = flex_array_get(out, index); + } fa_free(stream->out); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c4e56602e0c6..b04a813fc865 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1505,6 +1505,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, smc = smc_sk(sk); lock_sock(sk); + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) || (sk->sk_state == SMC_CLOSED)) @@ -1840,7 +1845,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if (sk->sk_state == SMC_INIT || sk->sk_state == SMC_LISTEN || sk->sk_state == SMC_CLOSED) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index db83332ac1c8..a712c9f8699b 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -21,13 +21,6 @@ /********************************** send *************************************/ -struct smc_cdc_tx_pend { - struct smc_connection *conn; /* socket connection */ - union smc_host_cursor cursor; /* tx sndbuf cursor sent */ - union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ - u16 ctrl_seq; /* conn. tx sequence # */ -}; - /* handler for send/transmission completion of a CDC msg */ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, struct smc_link *link, @@ -61,12 +54,14 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend) { struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int rc; rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, + wr_rdma_buf, (struct smc_wr_tx_pend_priv **)pend); if (!conn->alert_token_local) /* abnormal termination */ @@ -96,6 +91,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend) { + union smc_host_cursor cfed; struct smc_link *link; int rc; @@ -107,10 +103,10 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, &conn->local_tx_ctrl, conn); + smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); if (!rc) - smc_curs_copy(&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); + smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); return rc; } @@ -121,11 +117,14 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend); if (rc) return rc; - return smc_cdc_msg_send(conn, wr_buf, pend); + spin_lock_bh(&conn->send_lock); + rc = smc_cdc_msg_send(conn, wr_buf, pend); + spin_unlock_bh(&conn->send_lock); + return rc; } int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index b5bfe38c7f9b..271e2524dc8f 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -160,7 +160,9 @@ static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, #endif } -/* calculate cursor difference between old and new, where old <= new */ +/* calculate cursor difference between old and new, where old <= new and + * difference cannot exceed size + */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) @@ -185,6 +187,28 @@ static inline int smc_curs_comp(unsigned int size, return smc_curs_diff(size, old, new); } +/* calculate cursor difference between old and new, where old <= new and + * difference may exceed size + */ +static inline int smc_curs_diff_large(unsigned int size, + union smc_host_cursor *old, + union smc_host_cursor *new) +{ + if (old->wrap < new->wrap) + return min_t(int, + (size - old->count) + new->count + + (new->wrap - old->wrap - 1) * size, + size); + + if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */ + return min_t(int, + (size - old->count) + new->count + + (new->wrap + 0xffff - old->wrap) * size, + size); + + return max_t(int, 0, (new->count - old->count)); +} + static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, struct smc_connection *conn) @@ -270,10 +294,16 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, smcr_cdc_msg_to_host(local, peer, conn); } -struct smc_cdc_tx_pend; +struct smc_cdc_tx_pend { + struct smc_connection *conn; /* socket connection */ + union smc_host_cursor cursor; /* tx sndbuf cursor sent */ + union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ + u16 ctrl_seq; /* conn. tx sequence # */ +}; int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 776e9dfc915d..d53fd588d1f5 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) vec.iov_len = sizeof(struct smc_clc_msg_decline); len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(struct smc_clc_msg_decline)); - if (len < sizeof(struct smc_clc_msg_decline)) + if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) len = -EPROTO; return len > 0 ? 0 : len; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ea2b87f29469..e39cadda1bf5 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -345,14 +345,7 @@ static void smc_close_passive_work(struct work_struct *work) switch (sk->sk_state) { case SMC_INIT: - if (atomic_read(&conn->bytes_to_rcv) || - (rxflags->peer_done_writing && - !smc_cdc_rxed_any_close(conn))) { - sk->sk_state = SMC_APPCLOSEWAIT1; - } else { - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - } + sk->sk_state = SMC_APPCLOSEWAIT1; break; case SMC_ACTIVE: sk->sk_state = SMC_APPCLOSEWAIT1; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 35c1cdc93e1c..aa1c551cee81 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!lgr) + return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); @@ -300,13 +302,13 @@ static void smc_buf_unuse(struct smc_connection *conn, conn->sndbuf_desc->used = 0; if (conn->rmb_desc) { if (!conn->rmb_desc->regerr) { - conn->rmb_desc->used = 0; if (!lgr->is_smcd) { /* unregister rmb with peer */ smc_llc_do_delete_rkey( &lgr->lnk[SMC_SINGLE_LINK], conn->rmb_desc); } + conn->rmb_desc->used = 0; } else { /* buf registration failed, reuse not possible */ write_lock_bh(&lgr->rmbs_lock); @@ -628,6 +630,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; smc_lgr_register_conn(conn); /* add smc conn to lgr */ + if (delayed_work_pending(&lgr->free_work)) + cancel_delayed_work(&lgr->free_work); write_unlock_bh(&lgr->conns_lock); break; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index b00287989a3d..8806d2afa6ed 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -52,6 +52,24 @@ enum smc_wr_reg_state { FAILED /* ib_wr_reg_mr response: failure */ }; +struct smc_rdma_sge { /* sges for RDMA writes */ + struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; +}; + +#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per + * message send + */ + +struct smc_rdma_sges { /* sges per message send */ + struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; +}; + +struct smc_rdma_wr { /* work requests per message + * send + */ + struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; +}; + struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ @@ -64,6 +82,8 @@ struct smc_link { struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ + struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ + struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ /* above four vectors have wr_tx_cnt elements and use the same index */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index e519ef29c0ff..76487a16934e 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -289,8 +289,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { - struct smc_ib_device *smcibdev = - (struct smc_ib_device *)ibevent->device; + struct smc_link *lnk = (struct smc_link *)priv; + struct smc_ib_device *smcibdev = lnk->smcibdev; u8 port_idx; switch (ibevent->event) { @@ -298,7 +298,7 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) case IB_EVENT_GID_CHANGE: case IB_EVENT_PORT_ERR: case IB_EVENT_QP_ACCESS_ERR: - port_idx = ibevent->element.port_num - 1; + port_idx = ibevent->element.qp->port - 1; set_bit(port_idx, &smcibdev->port_event_mask); schedule_work(&smcibdev->port_event_work); break; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a6d3623d06f4..4fd60c522802 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -166,7 +166,8 @@ static int smc_llc_add_pending_send(struct smc_link *link, { int rc; - rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend); + rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL, + pend); if (rc < 0) return rc; BUILD_BUG_ON_MSG( diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7cb3e4f07c10..632c3109dee5 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -27,7 +27,7 @@ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNETID_LEN - 1 + .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index d8366ed51757..f93f3580c100 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -165,12 +165,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { + if (send_done) + return send_done; rc = smc_tx_wait(smc, msg->msg_flags); - if (rc) { - if (send_done) - return send_done; + if (rc) goto out_err; - } continue; } @@ -267,27 +266,23 @@ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, - int num_sges, struct ib_sge sges[]) + int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; - struct ib_rdma_wr rdma_wr; struct smc_link *link; int rc; - memset(&rdma_wr, 0, sizeof(rdma_wr)); link = &lgr->lnk[SMC_SINGLE_LINK]; - rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link); - rdma_wr.wr.sg_list = sges; - rdma_wr.wr.num_sge = num_sges; - rdma_wr.wr.opcode = IB_WR_RDMA_WRITE; - rdma_wr.remote_addr = + rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); + rdma_wr->wr.num_sge = num_sges; + rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; - rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; - rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL); + rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; + rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; smc_lgr_terminate(lgr); @@ -314,24 +309,25 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn, /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, - size_t dst_off, size_t dst_len) + size_t dst_off, size_t dst_len, + struct smc_rdma_wr *wr_rdma_buf) { dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); - struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int src_len_sum = src_len, dst_len_sum = dst_len; - struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { + struct ib_sge *sge = + wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list; + num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { - sges[srcchunk].addr = dma_addr + src_off; - sges[srcchunk].length = src_len; - sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; + sge[srcchunk].addr = dma_addr + src_off; + sge[srcchunk].length = src_len; num_sges++; src_off += src_len; @@ -344,7 +340,8 @@ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } - rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges); + rc = smc_tx_rdma_write(conn, dst_off, num_sges, + &wr_rdma_buf->wr_tx_rdma[dstchunk]); if (rc) return rc; if (dst_len_sum == len) @@ -403,7 +400,8 @@ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ -static int smc_tx_rdma_writes(struct smc_connection *conn) +static int smc_tx_rdma_writes(struct smc_connection *conn, + struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; @@ -464,7 +462,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, - dst_off, dst_len); + dst_off, dst_len, wr_rdma_buf); if (rc) return rc; @@ -485,31 +483,30 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags; + struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; - spin_lock_bh(&conn->send_lock); - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); - if (smc->sk.sk_err == ECONNABORTED) { - rc = sock_error(&smc->sk); - goto out_unlock; - } + if (smc->sk.sk_err == ECONNABORTED) + return sock_error(&smc->sk); rc = 0; if (conn->alert_token_local) /* connection healthy */ mod_delayed_work(system_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } - goto out_unlock; + return rc; } + spin_lock_bh(&conn->send_lock); if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], (struct smc_wr_tx_pend_priv *)pend); @@ -536,7 +533,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); @@ -598,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - - smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + smc_curs_diff_large(conn->rmb_desc->len, + &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index c2694750a6a8..253aa75dc2b6 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -160,6 +160,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) * @link: Pointer to smc_link used to later send the message. * @handler: Send completion handler function pointer. * @wr_buf: Out value returns pointer to message buffer. + * @wr_rdma_buf: Out value returns pointer to rdma work request. * @wr_pend_priv: Out value returns pointer serving as handler context. * * Return: 0 on success, or -errno on error. @@ -167,6 +168,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_wr_tx_pend_priv **wr_pend_priv) { struct smc_wr_tx_pend *wr_pend; @@ -204,6 +206,8 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, wr_ib = &link->wr_tx_ibs[idx]; wr_ib->wr_id = wr_id; *wr_buf = &link->wr_tx_bufs[idx]; + if (wr_rdma_buf) + *wr_rdma_buf = &link->wr_tx_rdmas[idx]; *wr_pend_priv = &wr_pend->priv; return 0; } @@ -218,10 +222,10 @@ int smc_wr_tx_put_slot(struct smc_link *link, u32 idx = pend->idx; /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pend->idx], 0, - sizeof(link->wr_tx_pends[pend->idx])); - memset(&link->wr_tx_bufs[pend->idx], 0, - sizeof(link->wr_tx_bufs[pend->idx])); + memset(&link->wr_tx_pends[idx], 0, + sizeof(link->wr_tx_pends[idx])); + memset(&link->wr_tx_bufs[idx], 0, + sizeof(link->wr_tx_bufs[idx])); test_and_clear_bit(idx, link->wr_tx_mask); return 1; } @@ -465,12 +469,26 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE; lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE; lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; lnk->wr_tx_ibs[i].next = NULL; lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i]; lnk->wr_tx_ibs[i].num_sge = 1; lnk->wr_tx_ibs[i].opcode = IB_WR_SEND; lnk->wr_tx_ibs[i].send_flags = IB_SEND_SIGNALED | IB_SEND_SOLICITED; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge; } for (i = 0; i < lnk->wr_rx_cnt; i++) { lnk->wr_rx_sges[i].addr = @@ -521,8 +539,12 @@ void smc_wr_free_link_mem(struct smc_link *lnk) lnk->wr_tx_mask = NULL; kfree(lnk->wr_tx_sges); lnk->wr_tx_sges = NULL; + kfree(lnk->wr_tx_rdma_sges); + lnk->wr_tx_rdma_sges = NULL; kfree(lnk->wr_rx_sges); lnk->wr_rx_sges = NULL; + kfree(lnk->wr_tx_rdmas); + lnk->wr_tx_rdmas = NULL; kfree(lnk->wr_rx_ibs); lnk->wr_rx_ibs = NULL; kfree(lnk->wr_tx_ibs); @@ -552,10 +574,20 @@ int smc_wr_alloc_link_mem(struct smc_link *link) GFP_KERNEL); if (!link->wr_rx_ibs) goto no_mem_wr_tx_ibs; + link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdmas[0]), + GFP_KERNEL); + if (!link->wr_tx_rdmas) + goto no_mem_wr_rx_ibs; + link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdma_sges[0]), + GFP_KERNEL); + if (!link->wr_tx_rdma_sges) + goto no_mem_wr_tx_rdmas; link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]), GFP_KERNEL); if (!link->wr_tx_sges) - goto no_mem_wr_rx_ibs; + goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, sizeof(link->wr_rx_sges[0]), GFP_KERNEL); @@ -579,6 +611,10 @@ no_mem_wr_rx_sges: kfree(link->wr_rx_sges); no_mem_wr_tx_sges: kfree(link->wr_tx_sges); +no_mem_wr_tx_rdma_sges: + kfree(link->wr_tx_rdma_sges); +no_mem_wr_tx_rdmas: + kfree(link->wr_tx_rdmas); no_mem_wr_rx_ibs: kfree(link->wr_rx_ibs); no_mem_wr_tx_ibs: diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 1d85bb14fd6f..09bf32fd3959 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -85,6 +85,7 @@ void smc_wr_add_dev(struct smc_ib_device *smcibdev); int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wrs, struct smc_wr_tx_pend_priv **wr_pend_priv); int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); diff --git a/net/socket.c b/net/socket.c index e89884e2197b..d80d87a395ea 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,8 +941,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg, - unsigned int ifreq_size) + unsigned int cmd, unsigned long arg) { int err; void __user *argp = (void __user *)arg; @@ -968,11 +967,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, ifreq_size)) + if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, ifreq_size)) + if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } return err; @@ -1071,8 +1070,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct ifreq)); + err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; @@ -2780,8 +2778,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2797,8 +2794,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -2994,6 +2990,54 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, return dev_ioctl(net, cmd, &ifreq, NULL); } +static int compat_ifreq_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, + struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + /* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ + + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + return -EFAULT; + + err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); + + if (!err) { + switch (cmd) { + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFMEM: + case SIOCGIFHWADDR: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCGIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCGIFNAME: + if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) + err = -EFAULT; + break; + } + } + return err; +} + static int compat_sioc_ifmap(struct net *net, unsigned int cmd, struct compat_ifreq __user *uifr32) { @@ -3109,8 +3153,7 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, - sizeof(struct compat_ifreq)); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); set_fs(old_fs); out: @@ -3210,21 +3253,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: + case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - case SIOCSARP: - case SIOCGARP: - case SIOCDARP: - case SIOCATMARK: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct compat_ifreq)); + return compat_ifreq_ioctl(net, sock, cmd, argp); + + case SIOCSARP: + case SIOCGARP: + case SIOCDARP: + case SIOCATMARK: + return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index cf51b8f9b15f..1f200119268c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -537,6 +537,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma, DMA_TO_DEVICE); } +/* If the xdr_buf has more elements than the device can + * transmit in a single RDMA Send, then the reply will + * have to be copied into a bounce buffer. + */ +static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma, + struct xdr_buf *xdr, + __be32 *wr_lst) +{ + int elements; + + /* xdr->head */ + elements = 1; + + /* xdr->pages */ + if (!wr_lst) { + unsigned int remaining; + unsigned long pageoff; + + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + ++elements; + remaining -= min_t(u32, PAGE_SIZE - pageoff, + remaining); + pageoff = 0; + } + } + + /* xdr->tail */ + if (xdr->tail[0].iov_len) + ++elements; + + /* assume 1 SGE is needed for the transport header */ + return elements >= rdma->sc_max_send_sges; +} + +/* The device is not capable of sending the reply directly. + * Assemble the elements of @xdr into the transport header + * buffer. + */ +static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt, + struct xdr_buf *xdr, __be32 *wr_lst) +{ + unsigned char *dst, *tailbase; + unsigned int taillen; + + dst = ctxt->sc_xprt_buf; + dst += ctxt->sc_sges[0].length; + + memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len); + dst += xdr->head[0].iov_len; + + tailbase = xdr->tail[0].iov_base; + taillen = xdr->tail[0].iov_len; + if (wr_lst) { + u32 xdrpad; + + xdrpad = xdr_padsize(xdr->page_len); + if (taillen && xdrpad) { + tailbase += xdrpad; + taillen -= xdrpad; + } + } else { + unsigned int len, remaining; + unsigned long pageoff; + struct page **ppages; + + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + len = min_t(u32, PAGE_SIZE - pageoff, remaining); + + memcpy(dst, page_address(*ppages), len); + remaining -= len; + dst += len; + pageoff = 0; + } + } + + if (taillen) + memcpy(dst, tailbase, taillen); + + ctxt->sc_sges[0].length += xdr->len; + ib_dma_sync_single_for_device(rdma->sc_pd->device, + ctxt->sc_sges[0].addr, + ctxt->sc_sges[0].length, + DMA_TO_DEVICE); + + return 0; +} + /* svc_rdma_map_reply_msg - Map the buffer holding RPC message * @rdma: controlling transport * @ctxt: send_ctxt for the Send WR @@ -559,8 +652,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, u32 xdr_pad; int ret; - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst)) + return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst); + + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, xdr->head[0].iov_base, xdr->head[0].iov_len); @@ -591,8 +686,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - page_off, remaining); - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++, page_off, len); if (ret < 0) @@ -606,8 +700,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, len = xdr->tail[0].iov_len; tail: if (len) { - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len); if (ret < 0) return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 924c17d46903..57f86c63a463 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -419,12 +419,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Transport header, head iovec, tail iovec */ newxprt->sc_max_send_sges = 3; /* Add one SGE per page list entry */ - newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE; - if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) { - pr_err("svcrdma: too few Send SGEs available (%d needed)\n", - newxprt->sc_max_send_sges); - goto errout; - } + newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1; + if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) + newxprt->sc_max_send_sges = dev->attrs.max_send_sge; newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 5d3cce9e8744..15eb5d3d4750 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock = virtio_vsock_get(); + if (!vsock) + return VMADDR_CID_ANY; + return vsock->guest_cid; } @@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) virtio_vsock_update_guest_cid(vsock); - ret = vsock_core_init(&virtio_transport.transport); - if (ret < 0) - goto out_vqs; - vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); @@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_unlock(&the_virtio_vsock_mutex); return 0; -out_vqs: - vsock->vdev->config->del_vqs(vsock->vdev); out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev) flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + /* Reset all connected sockets when the device disappear */ + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vdev->config->reset(vdev); mutex_lock(&vsock->rx_lock); @@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev) mutex_lock(&the_virtio_vsock_mutex); the_virtio_vsock = NULL; - vsock_core_exit(); mutex_unlock(&the_virtio_vsock_mutex); vdev->config->del_vqs(vdev); @@ -702,14 +701,28 @@ static int __init virtio_vsock_init(void) virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); if (ret) - destroy_workqueue(virtio_vsock_workqueue); + goto out_wq; + + ret = vsock_core_init(&virtio_transport.transport); + if (ret) + goto out_vdr; + + return 0; + +out_vdr: + unregister_virtio_driver(&virtio_vsock_driver); +out_wq: + destroy_workqueue(virtio_vsock_workqueue); return ret; + } static void __exit virtio_vsock_exit(void) { + vsock_core_exit(); unregister_virtio_driver(&virtio_vsock_driver); destroy_workqueue(virtio_vsock_workqueue); } diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 882d97bdc6bf..550ac9d827fe 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, cfg80211_sched_dfs_chan_update(rdev); } + schedule_work(&cfg80211_disconnect_work); + return err; } diff --git a/net/wireless/core.h b/net/wireless/core.h index c5d6f3418601..f6b40563dc63 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -445,6 +445,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz); +extern struct work_struct cfg80211_disconnect_work; + /** * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable * @wiphy: the wiphy to validate against diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f741d8376a46..7d34cb884840 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work) rtnl_unlock(); } -static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); +DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); /* diff --git a/samples/mei/mei-amt-version.c b/samples/mei/mei-amt-version.c index 33e67bd1dc34..32234481ad7d 100644 --- a/samples/mei/mei-amt-version.c +++ b/samples/mei/mei-amt-version.c @@ -117,7 +117,7 @@ static bool mei_init(struct mei *me, const uuid_le *guid, me->verbose = verbose; - me->fd = open("/dev/mei", O_RDWR); + me->fd = open("/dev/mei0", O_RDWR); if (me->fd == -1) { mei_err(me, "Cannot establish a handle to the Intel MEI driver\n"); goto err; diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 9174f1b3a987..1ec706ced75c 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -115,7 +115,8 @@ static int hda_codec_driver_probe(struct device *dev) err = snd_hda_codec_build_controls(codec); if (err < 0) goto error_module; - if (codec->card->registered) { + /* only register after the bus probe finished; otherwise it's racy */ + if (!codec->bus->bus_probing && codec->card->registered) { err = snd_card_register(codec->card); if (err < 0) goto error_module; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e784130ea4e0..e5c49003e75f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2185,6 +2185,7 @@ static int azx_probe_continue(struct azx *chip) int dev = chip->dev_index; int err; + to_hda_bus(bus)->bus_probing = 1; hda->probe_continued = 1; /* bind with i915 if needed */ @@ -2269,6 +2270,7 @@ out_free: if (err < 0) hda->init_failed = 1; complete_all(&hda->probe_wait); + to_hda_bus(bus)->bus_probing = 0; return err; } diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e5bdbc245682..29882bda7632 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -8451,8 +8451,10 @@ static void ca0132_free(struct hda_codec *codec) ca0132_exit_chip(codec); snd_hda_power_down(codec); - if (IS_ENABLED(CONFIG_PCI) && spec->mem_base) +#ifdef CONFIG_PCI + if (spec->mem_base) pci_iounmap(codec->bus->pci, spec->mem_base); +#endif kfree(spec->spec_init_verbs); kfree(codec->spec); } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4139aced63f8..6df758adff84 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -515,6 +515,15 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type) } } +/* get a primary headphone pin if available */ +static hda_nid_t alc_get_hp_pin(struct alc_spec *spec) +{ + if (spec->gen.autocfg.hp_pins[0]) + return spec->gen.autocfg.hp_pins[0]; + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + return spec->gen.autocfg.line_out_pins[0]; + return 0; +} /* * Realtek SSID verification @@ -725,9 +734,7 @@ do_sku: * 15 : 1 --> enable the function "Mute internal speaker * when the external headphone out jack is plugged" */ - if (!spec->gen.autocfg.hp_pins[0] && - !(spec->gen.autocfg.line_out_pins[0] && - spec->gen.autocfg.line_out_type == AUTO_PIN_HP_OUT)) { + if (!alc_get_hp_pin(spec)) { hda_nid_t nid; tmp = (ass >> 11) & 0x3; /* HP to chassis */ nid = ports[tmp]; @@ -2959,7 +2966,7 @@ static void alc282_restore_default_value(struct hda_codec *codec) static void alc282_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; int coef78; @@ -2996,7 +3003,7 @@ static void alc282_init(struct hda_codec *codec) static void alc282_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; int coef78; @@ -3074,14 +3081,9 @@ static void alc283_restore_default_value(struct hda_codec *codec) static void alc283_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - alc283_restore_default_value(codec); if (!hp_pin) @@ -3115,14 +3117,9 @@ static void alc283_init(struct hda_codec *codec) static void alc283_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) { alc269_shutup(codec); return; @@ -3156,7 +3153,7 @@ static void alc283_shutup(struct hda_codec *codec) static void alc256_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) @@ -3192,7 +3189,7 @@ static void alc256_init(struct hda_codec *codec) static void alc256_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) { @@ -3228,7 +3225,7 @@ static void alc256_shutup(struct hda_codec *codec) static void alc225_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; if (!hp_pin) @@ -3271,7 +3268,7 @@ static void alc225_init(struct hda_codec *codec) static void alc225_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; if (!hp_pin) { @@ -3315,7 +3312,7 @@ static void alc225_shutup(struct hda_codec *codec) static void alc_default_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) @@ -3344,7 +3341,7 @@ static void alc_default_init(struct hda_codec *codec) static void alc_default_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) { @@ -3376,7 +3373,7 @@ static void alc_default_shutup(struct hda_codec *codec) static void alc294_hp_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); int i, val; if (!hp_pin) @@ -4780,7 +4777,7 @@ static void alc_update_headset_mode(struct hda_codec *codec) struct alc_spec *spec = codec->spec; hda_nid_t mux_pin = spec->gen.imux_pins[spec->gen.cur_mux[0]]; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); int new_headset_mode; @@ -5059,7 +5056,7 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, static void alc_shutup_dell_xps13(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int hp_pin = spec->gen.autocfg.hp_pins[0]; + int hp_pin = alc_get_hp_pin(spec); /* Prevent pop noises when headphones are plugged in */ snd_hda_codec_write(codec, hp_pin, 0, @@ -5152,7 +5149,7 @@ static void alc271_hp_gate_mic_jack(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PROBE) { int mic_pin = find_ext_mic_pin(codec); - int hp_pin = spec->gen.autocfg.hp_pins[0]; + int hp_pin = alc_get_hp_pin(spec); if (snd_BUG_ON(!mic_pin || !hp_pin)) return; @@ -5634,6 +5631,7 @@ enum { ALC294_FIXUP_ASUS_HEADSET_MIC, ALC294_FIXUP_ASUS_SPK, ALC225_FIXUP_HEADSET_JACK, + ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6580,6 +6578,15 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_headset_jack, }, + [ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6758,6 +6765,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index bb8372833fc2..7e65fe853ee3 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1567,6 +1567,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case 0x20b1: /* XMOS based devices */ case 0x152a: /* Thesycon devices */ case 0x25ce: /* Mytek devices */ + case 0x2ab6: /* T+A devices */ if (fp->dsd_raw) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 897483457bf0..f7261fad45c1 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -297,10 +297,8 @@ char *get_fdinfo(int fd, const char *key) snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd); fdi = fopen(path, "r"); - if (!fdi) { - p_err("can't open fdinfo: %s", strerror(errno)); + if (!fdi) return NULL; - } while ((n = getline(&line, &line_n, fdi)) > 0) { char *value; @@ -313,7 +311,6 @@ char *get_fdinfo(int fd, const char *key) value = strchr(line, '\t'); if (!value || !value[1]) { - p_err("malformed fdinfo!?"); free(line); return NULL; } @@ -326,7 +323,6 @@ char *get_fdinfo(int fd, const char *key) return line; } - p_err("key '%s' not found in fdinfo", key); free(line); fclose(fdi); return NULL; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 2037e3dc864b..1ef1ee2280a2 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -347,6 +347,20 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val, return argv + i; } +/* on per cpu maps we must copy the provided value on all value instances */ +static void fill_per_cpu_value(struct bpf_map_info *info, void *value) +{ + unsigned int i, n, step; + + if (!map_is_per_cpu(info->type)) + return; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + for (i = 1; i < n; i++) + memcpy(value + i * step, value, info->value_size); +} + static int parse_elem(char **argv, struct bpf_map_info *info, void *key, void *value, __u32 key_size, __u32 value_size, __u32 *flags, __u32 **value_fd) @@ -426,6 +440,8 @@ static int parse_elem(char **argv, struct bpf_map_info *info, argv = parse_bytes(argv, "value", value, value_size); if (!argv) return -1; + + fill_per_cpu_value(info, value); } return parse_elem(argv, info, key, NULL, key_size, value_size, @@ -497,10 +513,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_uint_field(json_wtr, "owner_prog_type", prog_type); } - if (atoi(owner_jited)) - jsonw_bool_field(json_wtr, "owner_jited", true); - else - jsonw_bool_field(json_wtr, "owner_jited", false); + if (owner_jited) + jsonw_bool_field(json_wtr, "owner_jited", + !!atoi(owner_jited)); free(owner_prog_type); free(owner_jited); @@ -553,7 +568,8 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) char *owner_prog_type = get_fdinfo(fd, "owner_prog_type"); char *owner_jited = get_fdinfo(fd, "owner_jited"); - printf("\n\t"); + if (owner_prog_type || owner_jited) + printf("\n\t"); if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); @@ -563,10 +579,9 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) else printf("owner_prog_type %d ", prog_type); } - if (atoi(owner_jited)) - printf("owner jited"); - else - printf("owner not jited"); + if (owner_jited) + printf("owner%s jited", + atoi(owner_jited) ? "" : " not"); free(owner_prog_type); free(owner_jited); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2d1bb7d6ff51..b54ed82b9589 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -78,13 +78,14 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) static int prog_fd_by_tag(unsigned char *tag) { - struct bpf_prog_info info = {}; - __u32 len = sizeof(info); unsigned int id = 0; int err; int fd; while (true) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + err = bpf_prog_get_next_id(id, &id); if (err) { p_err("%s", strerror(errno)); diff --git a/tools/firmware/ihex2fw.c b/tools/firmware/ihex2fw.c index b58dd061e978..8925b60e51f5 100644 --- a/tools/firmware/ihex2fw.c +++ b/tools/firmware/ihex2fw.c @@ -24,6 +24,10 @@ #include <getopt.h> +#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) + struct ihex_binrec { struct ihex_binrec *next; /* not part of the real data structure */ uint32_t addr; @@ -131,6 +135,7 @@ int main(int argc, char **argv) static int process_ihex(uint8_t *data, ssize_t size) { struct ihex_binrec *record; + size_t record_size; uint32_t offset = 0; uint32_t data32; uint8_t type, crc = 0, crcbyte = 0; @@ -157,12 +162,13 @@ next_record: len <<= 8; len += hex(data + i, &crc); i += 2; } - record = malloc((sizeof (*record) + len + 3) & ~3); + record_size = ALIGN(sizeof(*record) + len, 4); + record = malloc(record_size); if (!record) { fprintf(stderr, "out of memory for records\n"); return -ENOMEM; } - memset(record, 0, (sizeof(*record) + len + 3) & ~3); + memset(record, 0, record_size); record->len = len; /* now check if we have enough data to read everything */ @@ -259,13 +265,18 @@ static void file_record(struct ihex_binrec *record) *p = record; } +static uint16_t ihex_binrec_size(struct ihex_binrec *p) +{ + return p->len + sizeof(p->addr) + sizeof(p->len); +} + static int output_records(int outfd) { unsigned char zeroes[6] = {0, 0, 0, 0, 0, 0}; struct ihex_binrec *p = records; while (p) { - uint16_t writelen = (p->len + 9) & ~3; + uint16_t writelen = ALIGN(ihex_binrec_size(p), 4); p->addr = htonl(p->addr); p->len = htons(p->len); diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index 3040830d7797..84545666a09c 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -330,7 +330,7 @@ static const struct option longopts[] = { int main(int argc, char **argv) { - unsigned long long num_loops = 2; + long long num_loops = 2; unsigned long timedelay = 1000000; unsigned long buf_len = 128; diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index f6052e70bf40..a55cb8b10165 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -268,7 +268,7 @@ struct sockaddr_in { #define IN_MULTICAST(a) IN_CLASSD(a) #define IN_MULTICAST_NET 0xe0000000 -#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff) +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) #define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) #define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 095aebdc5bb7..e6150f21267d 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -19,8 +19,11 @@ C2C stands for Cache To Cache. The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows you to track down the cacheline contentions. -The tool is based on x86's load latency and precise store facility events -provided by Intel CPUs. These events provide: +On x86, the tool is based on load latency and precise store facility events +provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling +with thresholding feature. + +These events provide: - memory address of the access - type of the access (load and store details) - latency (in cycles) of the load access @@ -46,7 +49,7 @@ RECORD OPTIONS -l:: --ldlat:: - Configure mem-loads latency. + Configure mem-loads latency. (x86 only) -k:: --all-kernel:: @@ -119,11 +122,16 @@ Following perf record options are configured by default: -W,-d,--phys-data,--sample-cpu Unless specified otherwise with '-e' option, following events are monitored by -default: +default on x86: cpu/mem-loads,ldlat=30/P cpu/mem-stores/P +and following on PowerPC: + + cpu/mem-loads/ + cpu/mem-stores/ + User can pass any 'perf record' option behind '--' mark, like (to enable callchains and system wide monitoring): diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index f8d2167cf3e7..199ea0f0a6c0 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -82,7 +82,7 @@ RECORD OPTIONS Be more verbose (show counter open errors, etc) --ldlat <n>:: - Specify desired latency for loads event. + Specify desired latency for loads event. (x86 only) In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 2e6595310420..ba98bd006488 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -2,6 +2,7 @@ libperf-y += header.o libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-y += perf_regs.o +libperf-y += mem-events.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c new file mode 100644 index 000000000000..d08311f04e95 --- /dev/null +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "mem-events.h" + +/* PowerPC does not support 'ldlat' parameter. */ +char *perf_mem_events__name(int i) +{ + if (i == PERF_MEM_EVENTS__LOAD) + return (char *) "cpu/mem-loads/"; + + return (char *) "cpu/mem-stores/"; +} diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ed4583128b9c..b36061cd1ab8 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) { - struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname"); + bool found = false; + struct perf_evsel *evsel, *tmp; + struct parse_events_error err = { .idx = 0, }; + int ret = parse_events(evlist, "probe:vfs_getname*", &err); - if (IS_ERR(evsel)) + if (ret) return false; - if (perf_evsel__field(evsel, "pathname") == NULL) { + evlist__for_each_entry_safe(evlist, evsel, tmp) { + if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname")) + continue; + + if (perf_evsel__field(evsel, "pathname")) { + evsel->handler = trace__vfs_getname; + found = true; + continue; + } + + list_del_init(&evsel->node); + evsel->evlist = NULL; perf_evsel__delete(evsel); - return false; } - evsel->handler = trace__vfs_getname; - perf_evlist__add(evlist, evsel); - return true; + return found; } static struct perf_evsel *perf_evsel__new_pgfault(u64 config) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 44090a9a19f3..e952127e4fb0 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -1,6 +1,8 @@ #! /usr/bin/python # SPDX-License-Identifier: GPL-2.0 +from __future__ import print_function + import os import sys import glob @@ -8,7 +10,11 @@ import optparse import tempfile import logging import shutil -import ConfigParser + +try: + import configparser +except ImportError: + import ConfigParser as configparser def data_equal(a, b): # Allow multiple values in assignment separated by '|' @@ -100,20 +106,20 @@ class Event(dict): def equal(self, other): for t in Event.terms: log.debug(" [%s] %s %s" % (t, self[t], other[t])); - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: return False if not data_equal(self[t], other[t]): return False return True def optional(self): - if self.has_key('optional') and self['optional'] == '1': + if 'optional' in self and self['optional'] == '1': return True return False def diff(self, other): for t in Event.terms: - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: continue if not data_equal(self[t], other[t]): log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) @@ -134,7 +140,7 @@ class Event(dict): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = ConfigParser.SafeConfigParser() + parser = configparser.SafeConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -193,7 +199,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = ConfigParser.SafeConfigParser() + parser_event = configparser.SafeConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -207,7 +213,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = ConfigParser.SafeConfigParser() + parser_base = configparser.SafeConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') @@ -322,9 +328,9 @@ def run_tests(options): for f in glob.glob(options.test_dir + '/' + options.test): try: Test(f, options).run() - except Unsup, obj: + except Unsup as obj: log.warning("unsupp %s" % obj.getMsg()) - except Notest, obj: + except Notest as obj: log.warning("skipped %s" % obj.getMsg()) def setup_log(verbose): @@ -363,7 +369,7 @@ def main(): parser.add_option("-p", "--perf", action="store", type="string", dest="perf") parser.add_option("-v", "--verbose", - action="count", dest="verbose") + default=0, action="count", dest="verbose") options, args = parser.parse_args() if args: @@ -373,7 +379,7 @@ def main(): setup_log(options.verbose) if not options.test_dir: - print 'FAILED no -d option specified' + print('FAILED no -d option specified') sys.exit(-1) if not options.test: @@ -382,8 +388,8 @@ def main(): try: run_tests(options) - except Fail, obj: - print "FAILED %s" % obj.getMsg(); + except Fail as obj: + print("FAILED %s" % obj.getMsg()) sys.exit(-1) sys.exit(0) diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 5f8501c68da4..5cbba70bcdd0 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return -1; } - is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED); + is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED); if (should_be_signed && !is_signed) { pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", evsel->name, name, is_signed, should_be_signed); diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index 89512504551b..39c0004f2886 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module) } PM.run(*Module); - return std::move(Buffer); + return Buffer; } } diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 93f74d8d3cdd..42c3e5a229d2 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { static char mem_loads_name[100]; static bool mem_loads_name__init; -char *perf_mem_events__name(int i) +char * __weak perf_mem_events__name(int i) { if (i == PERF_MEM_EVENTS__LOAD) { if (!mem_loads_name__init) { diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66a84d5846c8..dca7dfae69ad 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -19,6 +19,20 @@ #define EM_AARCH64 183 /* ARM 64 bit */ #endif +#ifndef ELF32_ST_VISIBILITY +#define ELF32_ST_VISIBILITY(o) ((o) & 0x03) +#endif + +/* For ELF64 the definitions are the same. */ +#ifndef ELF64_ST_VISIBILITY +#define ELF64_ST_VISIBILITY(o) ELF32_ST_VISIBILITY (o) +#endif + +/* How to extract information held in the st_other field. */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(val) ELF64_ST_VISIBILITY (val) +#endif + typedef Elf64_Nhdr GElf_Nhdr; #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT @@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +static inline uint8_t elf_sym__visibility(const GElf_Sym *sym) +{ + return GELF_ST_VISIBILITY(sym->st_other); +} + #ifndef STT_GNU_IFUNC #define STT_GNU_IFUNC 10 #endif @@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) return elf_sym__type(sym) == STT_NOTYPE && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; + sym->st_shndx != SHN_ABS && + elf_sym__visibility(sym) != STV_HIDDEN && + elf_sym__visibility(sym) != STV_INTERNAL; } static bool elf_sym__filter(GElf_Sym *sym) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1a2bd15c5b6e..400ee81a3043 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -10,6 +10,7 @@ TARGETS += drivers/dma-buf TARGETS += efivarfs TARGETS += exec TARGETS += filesystems +TARGETS += filesystems/binderfs TARGETS += firmware TARGETS += ftrace TARGETS += futex diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 315a44fa32af..84fd6f1bf33e 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -13,7 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; - int n; + int len, n, i, j = 0; fp = fopen(fcpu, "r"); if (!fp) { @@ -21,17 +21,27 @@ static inline unsigned int bpf_num_possible_cpus(void) exit(1); } - while (fgets(buff, sizeof(buff), fp)) { - n = sscanf(buff, "%u-%u", &start, &end); - if (n == 0) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } else if (n == 1) { - end = start; + if (!fgets(buff, sizeof(buff), fp)) { + printf("Failed to read %s!\n", fcpu); + exit(1); + } + + len = strlen(buff); + for (i = 0; i <= len; i++) { + if (buff[i] == ',' || buff[i] == '\0') { + buff[i] = '\0'; + n = sscanf(&buff[j], "%u-%u", &start, &end); + if (n <= 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; + } + possible_cpus += end - start + 1; + j = i + 1; } - possible_cpus = start == 0 ? end + 1 : 0; - break; } + fclose(fp); return possible_cpus; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index a0bd04befe87..91420fa83b08 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -1881,13 +1881,12 @@ static struct btf_raw_test raw_tests[] = { }, { - .descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)", + .descr = "func proto (TYPEDEF=>FUNC_PROTO)", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ - BTF_CONST_ENC(4), /* [3] */ - BTF_TYPEDEF_ENC(NAME_TBD, 5), /* [4] */ - BTF_FUNC_PROTO_ENC(0, 2), /* [5] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [4] */ BTF_FUNC_PROTO_ARG_ENC(0, 1), BTF_FUNC_PROTO_ARG_ENC(0, 2), BTF_END_RAW, @@ -1901,8 +1900,6 @@ static struct btf_raw_test raw_tests[] = { .key_type_id = 1, .value_type_id = 1, .max_entries = 4, - .btf_load_err = true, - .err_str = "Invalid type_id", }, { diff --git a/tools/testing/selftests/filesystems/binderfs/.gitignore b/tools/testing/selftests/filesystems/binderfs/.gitignore new file mode 100644 index 000000000000..8a5d9bf63dd4 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/.gitignore @@ -0,0 +1 @@ +binderfs_test diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile new file mode 100644 index 000000000000..58cb659b56b4 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += -I../../../../../usr/include/ +TEST_GEN_PROGS := binderfs_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c new file mode 100644 index 000000000000..8c2ed962e1c7 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <linux/android/binder.h> +#include <linux/android/binderfs.h> +#include "../../kselftest.h" + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; +again: + ret = write(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +static void write_to_file(const char *filename, const void *buf, size_t count, + int allowed_errno) +{ + int fd, saved_errno; + ssize_t ret; + + fd = open(filename, O_WRONLY | O_CLOEXEC); + if (fd < 0) + ksft_exit_fail_msg("%s - Failed to open file %s\n", + strerror(errno), filename); + + ret = write_nointr(fd, buf, count); + if (ret < 0) { + if (allowed_errno && (errno == allowed_errno)) { + close(fd); + return; + } + + goto on_error; + } + + if ((size_t)ret != count) + goto on_error; + + close(fd); + return; + +on_error: + saved_errno = errno; + close(fd); + errno = saved_errno; + + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to write to file %s\n", + strerror(errno), filename); + + ksft_exit_fail_msg("Failed to write to file %s\n", filename); +} + +static void change_to_userns(void) +{ + int ret; + uid_t uid; + gid_t gid; + /* {g,u}id_map files only allow a max of 4096 bytes written to them */ + char idmap[4096]; + + uid = getuid(); + gid = getgid(); + + ret = unshare(CLONE_NEWUSER); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", + strerror(errno)); + + write_to_file("/proc/self/setgroups", "deny", strlen("deny"), ENOENT); + + ret = snprintf(idmap, sizeof(idmap), "0 %d 1", uid); + if (ret < 0 || (size_t)ret >= sizeof(idmap)) + ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", + strerror(errno)); + + write_to_file("/proc/self/uid_map", idmap, strlen(idmap), 0); + + ret = snprintf(idmap, sizeof(idmap), "0 %d 1", gid); + if (ret < 0 || (size_t)ret >= sizeof(idmap)) + ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", + strerror(errno)); + + write_to_file("/proc/self/gid_map", idmap, strlen(idmap), 0); + + ret = setgid(0); + if (ret) + ksft_exit_fail_msg("%s - Failed to setgid(0)\n", + strerror(errno)); + + ret = setuid(0); + if (ret) + ksft_exit_fail_msg("%s - Failed to setgid(0)\n", + strerror(errno)); +} + +static void change_to_mountns(void) +{ + int ret; + + ret = unshare(CLONE_NEWNS); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n", + strerror(errno)); + + ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to mount / as private\n", + strerror(errno)); +} + +static void rmdir_protect_errno(const char *dir) +{ + int saved_errno = errno; + (void)rmdir(dir); + errno = saved_errno; +} + +static void __do_binderfs_test(void) +{ + int fd, ret, saved_errno; + size_t len; + ssize_t wret; + bool keep = false; + struct binderfs_device device = { 0 }; + struct binder_version version = { 0 }; + + change_to_mountns(); + + ret = mkdir("/dev/binderfs", 0755); + if (ret < 0) { + if (errno != EEXIST) + ksft_exit_fail_msg( + "%s - Failed to create binderfs mountpoint\n", + strerror(errno)); + + keep = true; + } + + ret = mount(NULL, "/dev/binderfs", "binder", 0, 0); + if (ret < 0) { + if (errno != ENODEV) + ksft_exit_fail_msg("%s - Failed to mount binderfs\n", + strerror(errno)); + + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_skip( + "The Android binderfs filesystem is not available\n"); + } + + /* binderfs mount test passed */ + ksft_inc_pass_cnt(); + + memcpy(device.name, "my-binder", strlen("my-binder")); + + fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); + if (fd < 0) + ksft_exit_fail_msg( + "%s - Failed to open binder-control device\n", + strerror(errno)); + + ret = ioctl(fd, BINDER_CTL_ADD, &device); + saved_errno = errno; + close(fd); + errno = saved_errno; + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to allocate new binder device\n", + strerror(errno)); + } + + ksft_print_msg( + "Allocated new binder device with major %d, minor %d, and name %s\n", + device.major, device.minor, device.name); + + /* binder device allocation test passed */ + ksft_inc_pass_cnt(); + + fd = open("/dev/binderfs/my-binder", O_CLOEXEC | O_RDONLY); + if (fd < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("%s - Failed to open my-binder device\n", + strerror(errno)); + } + + ret = ioctl(fd, BINDER_VERSION, &version); + saved_errno = errno; + close(fd); + errno = saved_errno; + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to open perform BINDER_VERSION request\n", + strerror(errno)); + } + + ksft_print_msg("Detected binder version: %d\n", + version.protocol_version); + + /* binder transaction with binderfs binder device passed */ + ksft_inc_pass_cnt(); + + ret = unlink("/dev/binderfs/my-binder"); + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("%s - Failed to delete binder device\n", + strerror(errno)); + } + + /* binder device removal passed */ + ksft_inc_pass_cnt(); + + ret = unlink("/dev/binderfs/binder-control"); + if (!ret) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("Managed to delete binder-control device\n"); + } else if (errno != EPERM) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to delete binder-control device but exited with unexpected error code\n", + strerror(errno)); + } + + /* binder-control device removal failed as expected */ + ksft_inc_xfail_cnt(); + +on_error: + ret = umount2("/dev/binderfs", MNT_DETACH); + keep ?: rmdir_protect_errno("/dev/binderfs"); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unmount binderfs\n", + strerror(errno)); + + /* binderfs unmount test passed */ + ksft_inc_pass_cnt(); +} + +static void binderfs_test_privileged() +{ + if (geteuid() != 0) + ksft_print_msg( + "Tests are not run as root. Skipping privileged tests\n"); + else + __do_binderfs_test(); +} + +static void binderfs_test_unprivileged() +{ + change_to_userns(); + __do_binderfs_test(); +} + +int main(int argc, char *argv[]) +{ + binderfs_test_privileged(); + binderfs_test_unprivileged(); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/filesystems/binderfs/config b/tools/testing/selftests/filesystems/binderfs/config new file mode 100644 index 000000000000..02dd6cc9cf99 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/config @@ -0,0 +1,3 @@ +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDERFS=y +CONFIG_ANDROID_BINDER_IPC=y diff --git a/tools/testing/selftests/firmware/config b/tools/testing/selftests/firmware/config index 913a25a4a32b..bf634dda0720 100644 --- a/tools/testing/selftests/firmware/config +++ b/tools/testing/selftests/firmware/config @@ -1,6 +1,5 @@ CONFIG_TEST_FIRMWARE=y CONFIG_FW_LOADER=y CONFIG_FW_LOADER_USER_HELPER=y -CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh index 466cf2f91ba0..a4320c4b44dc 100755 --- a/tools/testing/selftests/firmware/fw_filesystem.sh +++ b/tools/testing/selftests/firmware/fw_filesystem.sh @@ -155,8 +155,11 @@ read_firmwares() { for i in $(seq 0 3); do config_set_read_fw_idx $i - # Verify the contents match - if ! diff -q "$FW" $DIR/read_firmware 2>/dev/null ; then + # Verify the contents are what we expect. + # -Z required for now -- check for yourself, md5sum + # on $FW and DIR/read_firmware will yield the same. Even + # cmp agrees, so something is off. + if ! diff -q -Z "$FW" $DIR/read_firmware 2>/dev/null ; then echo "request #$i: firmware was not loaded" >&2 exit 1 fi @@ -168,7 +171,7 @@ read_firmwares_expect_nofile() for i in $(seq 0 3); do config_set_read_fw_idx $i # Ensures contents differ - if diff -q "$FW" $DIR/read_firmware 2>/dev/null ; then + if diff -q -Z "$FW" $DIR/read_firmware 2>/dev/null ; then echo "request $i: file was not expected to match" >&2 exit 1 fi diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh index 6c5f1b2ffb74..1cbb12e284a6 100755 --- a/tools/testing/selftests/firmware/fw_lib.sh +++ b/tools/testing/selftests/firmware/fw_lib.sh @@ -91,7 +91,7 @@ verify_reqs() if [ "$TEST_REQS_FW_SYSFS_FALLBACK" = "yes" ]; then if [ ! "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then echo "usermode helper disabled so ignoring test" - exit $ksft_skip + exit 0 fi fi } diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 47ed6cef93fb..c9ff2b47bd1c 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config index 1017313e41a8..59caa8f71cd8 100644 --- a/tools/testing/selftests/netfilter/config +++ b/tools/testing/selftests/netfilter/config @@ -1,2 +1,2 @@ CONFIG_NET_NS=y -NF_TABLES_INET=y +CONFIG_NF_TABLES_INET=y diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh new file mode 100755 index 000000000000..8ec76681605c --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -0,0 +1,762 @@ +#!/bin/bash +# +# This test is for basic NAT functionality: snat, dnat, redirect, masquerade. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add ns0 +ip netns add ns1 +ip netns add ns2 + +ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 +ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 + +ip -net ns0 link set lo up +ip -net ns0 link set veth0 up +ip -net ns0 addr add 10.0.1.1/24 dev veth0 +ip -net ns0 addr add dead:1::1/64 dev veth0 + +ip -net ns0 link set veth1 up +ip -net ns0 addr add 10.0.2.1/24 dev veth1 +ip -net ns0 addr add dead:2::1/64 dev veth1 + +for i in 1 2; do + ip -net ns$i link set lo up + ip -net ns$i link set eth0 up + ip -net ns$i addr add 10.0.$i.99/24 dev eth0 + ip -net ns$i route add default via 10.0.$i.1 + ip -net ns$i addr add dead:$i::99/64 dev eth0 + ip -net ns$i route add default via dead:$i::1 +done + +bad_counter() +{ + local ns=$1 + local counter=$2 + local expect=$3 + + echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter $counter 1>&2 +} + +check_counters() +{ + ns=$1 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in "packets 1 bytes 84" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out "packets 1 bytes 84" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in6 "$expect" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out6 "$expect" + lret=1 + fi + + return $lret +} + +check_ns0_counters() +{ + local ns=$1 + local lret=0 + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in6 "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out "packets 0 bytes 0" + lret=1 + fi + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out6 "packets 0 bytes 0" + lret=1 + fi + + for dir in "in" "out" ; do + expect="packets 1 bytes 84" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir "$expect" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir6 "$expect" + lret=1 + fi + done + + return $lret +} + +reset_counters() +{ + for i in 0 1 2;do + ip netns exec ns$i nft reset counters inet > /dev/null + done +} + +test_local_dnat6() +{ + local lret=0 +ip netns exec ns0 nft -f - <<EOF +table ip6 nat { + chain output { + type nat hook output priority 0; policy accept; + ip6 daddr dead:1::99 dnat to dead:2::99 + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add ip6 dnat hook" + return $ksft_skip + fi + + # ping netns1, expect rewrite to netns2 + ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping6 failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2" + ip netns exec ns0 nft flush chain ip6 nat output + + return $lret +} + +test_local_dnat() +{ + local lret=0 +ip netns exec ns0 nft -f - <<EOF +table ip nat { + chain output { + type nat hook output priority 0; policy accept; + ip daddr 10.0.1.99 dnat to 10.0.2.99 + } +} +EOF + # ping netns1, expect rewrite to netns2 + ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2" + + ip netns exec ns0 nft flush chain ip nat output + + reset_counters + ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns1$dir "$expect" + lret=1 + fi + done + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 1 count in ns1 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0$dir "$expect" + lret=1 + fi + done + + # expect 0 packet in ns2 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns2$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush" + + return $lret +} + + +test_masquerade6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 via ipv6" + return 1 + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - <<EOF +table ip6 nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip6 nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + + return $lret +} + +test_masquerade() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: canot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - <<EOF +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + + return $lret +} + +test_redirect6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannnot ping ns1 from ns2 via ipv6" + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - <<EOF +table ip6 nat { + chain prerouting { + type nat hook prerouting priority 0; policy accept; + meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect + } +} +EOF + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip6 nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete ip6 nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2" + + return $lret +} + +test_redirect() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - <<EOF +table ip nat { + chain prerouting { + type nat hook prerouting priority 0; policy accept; + meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect + } +} +EOF + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP redirection for ns2" + + return $lret +} + + +# ip netns exec ns0 ping -c 1 -q 10.0.$i.99 +for i in 0 1 2; do +ip netns exec ns$i nft -f - <<EOF +table inet filter { + counter ns0in {} + counter ns1in {} + counter ns2in {} + + counter ns0out {} + counter ns1out {} + counter ns2out {} + + counter ns0in6 {} + counter ns1in6 {} + counter ns2in6 {} + + counter ns0out6 {} + counter ns1out6 {} + counter ns2out6 {} + + map nsincounter { + type ipv4_addr : counter + elements = { 10.0.1.1 : "ns0in", + 10.0.2.1 : "ns0in", + 10.0.1.99 : "ns1in", + 10.0.2.99 : "ns2in" } + } + + map nsincounter6 { + type ipv6_addr : counter + elements = { dead:1::1 : "ns0in6", + dead:2::1 : "ns0in6", + dead:1::99 : "ns1in6", + dead:2::99 : "ns2in6" } + } + + map nsoutcounter { + type ipv4_addr : counter + elements = { 10.0.1.1 : "ns0out", + 10.0.2.1 : "ns0out", + 10.0.1.99: "ns1out", + 10.0.2.99: "ns2out" } + } + + map nsoutcounter6 { + type ipv6_addr : counter + elements = { dead:1::1 : "ns0out6", + dead:2::1 : "ns0out6", + dead:1::99 : "ns1out6", + dead:2::99 : "ns2out6" } + } + + chain input { + type filter hook input priority 0; policy accept; + counter name ip saddr map @nsincounter + icmpv6 type { "echo-request", "echo-reply" } counter name ip6 saddr map @nsincounter6 + } + chain output { + type filter hook output priority 0; policy accept; + counter name ip daddr map @nsoutcounter + icmpv6 type { "echo-request", "echo-reply" } counter name ip6 daddr map @nsoutcounter6 + } +} +EOF +done + +sleep 3 +# test basic connectivity +for i in 1 2; do + ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s)" 1>&2 + ret=1 + fi + + ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2 + ret=1 + fi + check_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + + check_ns0_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + reset_counters +done + +if [ $ret -eq 0 ];then + echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2" +fi + +reset_counters +test_local_dnat +test_local_dnat6 + +reset_counters +test_masquerade +test_masquerade6 + +reset_counters +test_redirect +test_redirect6 + +for i in 0 1 2; do ip netns del ns$i;done + +exit $ret diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5ecea812cb6a..585845203db8 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3000,8 +3000,10 @@ static int kvm_ioctl_create_device(struct kvm *kvm, if (ops->init) ops->init(dev); + kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { + kvm_put_kvm(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); @@ -3009,7 +3011,6 @@ static int kvm_ioctl_create_device(struct kvm *kvm, return ret; } - kvm_get_kvm(kvm); cd->fd = ret; return 0; } |
