diff options
417 files changed, 5051 insertions, 1994 deletions
diff --git a/Documentation/devicetree/bindings/staging/ion/hi6220-ion.txt b/Documentation/devicetree/bindings/staging/ion/hi6220-ion.txt deleted file mode 100644 index c59e27c632c1..000000000000 --- a/Documentation/devicetree/bindings/staging/ion/hi6220-ion.txt +++ /dev/null @@ -1,31 +0,0 @@ -Hi6220 SoC ION -=================================================================== -Required properties: -- compatible : "hisilicon,hi6220-ion" -- list of the ION heaps - - heap name : maybe heap_sys_user@0 - - heap id : id should be unique in the system. - - heap base : base ddr address of the heap,0 means that - it is dynamic. - - heap size : memory size and 0 means it is dynamic. - - heap type : the heap type of the heap, please also - see the define in ion.h(drivers/staging/android/uapi/ion.h) -------------------------------------------------------------------- -Example: - hi6220-ion { - compatible = "hisilicon,hi6220-ion"; - heap_sys_user@0 { - heap-name = "sys_user"; - heap-id = <0x0>; - heap-base = <0x0>; - heap-size = <0x0>; - heap-type = "ion_system"; - }; - heap_sys_contig@0 { - heap-name = "sys_contig"; - heap-id = <0x1>; - heap-base = <0x0>; - heap-size = <0x0>; - heap-type = "ion_system_contig"; - }; - }; diff --git a/Documentation/usb/typec.rst b/Documentation/usb/typec.rst index b67a46779de9..8a7249f2ff04 100644 --- a/Documentation/usb/typec.rst +++ b/Documentation/usb/typec.rst @@ -114,8 +114,7 @@ the details during registration. The class offers the following API for registering/unregistering cables and their plugs: .. kernel-doc:: drivers/usb/typec/typec.c - :functions: typec_register_cable typec_unregister_cable typec_register_plug - typec_unregister_plug + :functions: typec_register_cable typec_unregister_cable typec_register_plug typec_unregister_plug The class will provide a handle to struct typec_cable and struct typec_plug if the registration is successful, or NULL if it isn't. @@ -137,8 +136,7 @@ during connection of a partner or cable, the port driver must use the following APIs to report it to the class: .. kernel-doc:: drivers/usb/typec/typec.c - :functions: typec_set_data_role typec_set_pwr_role typec_set_vconn_role - typec_set_pwr_opmode + :functions: typec_set_data_role typec_set_pwr_role typec_set_vconn_role typec_set_pwr_opmode Alternate Modes ~~~~~~~~~~~~~~~ diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 4029943887a3..912b7df8215a 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3255,6 +3255,141 @@ Otherwise, if the MCE is a corrected error, KVM will just store it in the corresponding bank (provided this bank is not holding a previously reported uncorrected error). +4.107 KVM_S390_GET_CMMA_BITS + +Capability: KVM_CAP_S390_CMMA_MIGRATION +Architectures: s390 +Type: vm ioctl +Parameters: struct kvm_s390_cmma_log (in, out) +Returns: 0 on success, a negative value on error + +This ioctl is used to get the values of the CMMA bits on the s390 +architecture. It is meant to be used in two scenarios: +- During live migration to save the CMMA values. Live migration needs + to be enabled via the KVM_REQ_START_MIGRATION VM property. +- To non-destructively peek at the CMMA values, with the flag + KVM_S390_CMMA_PEEK set. + +The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired +values are written to a buffer whose location is indicated via the "values" +member in the kvm_s390_cmma_log struct. The values in the input struct are +also updated as needed. +Each CMMA value takes up one byte. + +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +start_gfn is the number of the first guest frame whose CMMA values are +to be retrieved, + +count is the length of the buffer in bytes, + +values points to the buffer where the result will be written to. + +If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be +KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with +other ioctls. + +The result is written in the buffer pointed to by the field values, and +the values of the input parameter are updated as follows. + +Depending on the flags, different actions are performed. The only +supported flag so far is KVM_S390_CMMA_PEEK. + +The default behaviour if KVM_S390_CMMA_PEEK is not set is: +start_gfn will indicate the first page frame whose CMMA bits were dirty. +It is not necessarily the same as the one passed as input, as clean pages +are skipped. + +count will indicate the number of bytes actually written in the buffer. +It can (and very often will) be smaller than the input value, since the +buffer is only filled until 16 bytes of clean values are found (which +are then not copied in the buffer). Since a CMMA migration block needs +the base address and the length, for a total of 16 bytes, we will send +back some clean data if there is some dirty data afterwards, as long as +the size of the clean data does not exceed the size of the header. This +allows to minimize the amount of data to be saved or transferred over +the network at the expense of more roundtrips to userspace. The next +invocation of the ioctl will skip over all the clean values, saving +potentially more than just the 16 bytes we found. + +If KVM_S390_CMMA_PEEK is set: +the existing storage attributes are read even when not in migration +mode, and no other action is performed; + +the output start_gfn will be equal to the input start_gfn, + +the output count will be equal to the input count, except if the end of +memory has been reached. + +In both cases: +the field "remaining" will indicate the total number of dirty CMMA values +still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is +not enabled. + +mask is unused. + +values points to the userspace buffer where the result will be stored. + +This ioctl can fail with -ENOMEM if not enough memory can be allocated to +complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if +KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with +-EFAULT if the userspace address is invalid or if no page table is +present for the addresses (e.g. when using hugepages). + +4.108 KVM_S390_SET_CMMA_BITS + +Capability: KVM_CAP_S390_CMMA_MIGRATION +Architectures: s390 +Type: vm ioctl +Parameters: struct kvm_s390_cmma_log (in) +Returns: 0 on success, a negative value on error + +This ioctl is used to set the values of the CMMA bits on the s390 +architecture. It is meant to be used during live migration to restore +the CMMA values, but there are no restrictions on its use. +The ioctl takes parameters via the kvm_s390_cmma_values struct. +Each CMMA value takes up one byte. + +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +start_gfn indicates the starting guest frame number, + +count indicates how many values are to be considered in the buffer, + +flags is not used and must be 0. + +mask indicates which PGSTE bits are to be considered. + +remaining is not used. + +values points to the buffer in userspace where to store the values. + +This ioctl can fail with -ENOMEM if not enough memory can be allocated to +complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if +the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or +if the flags field was not 0, with -EFAULT if the userspace address is +invalid, if invalid pages are written to (e.g. after the end of memory) +or if no page table is present for the addresses (e.g. when using +hugepages). + 5. The kvm_run structure ------------------------ diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt index c2518cea8ab4..2f1cbf1301d2 100644 --- a/Documentation/virtual/kvm/devices/s390_flic.txt +++ b/Documentation/virtual/kvm/devices/s390_flic.txt @@ -16,6 +16,7 @@ FLIC provides support to - register and modify adapter interrupt sources (KVM_DEV_FLIC_ADAPTER_*) - modify AIS (adapter-interruption-suppression) mode state (KVM_DEV_FLIC_AISM) - inject adapter interrupts on a specified adapter (KVM_DEV_FLIC_AIRQ_INJECT) +- get/set all AIS mode states (KVM_DEV_FLIC_AISM_ALL) Groups: KVM_DEV_FLIC_ENQUEUE @@ -136,6 +137,20 @@ struct kvm_s390_ais_req { an isc according to the adapter-interruption-suppression mode on condition that the AIS capability is enabled. + KVM_DEV_FLIC_AISM_ALL + Gets or sets the adapter-interruption-suppression mode for all ISCs. Takes + a kvm_s390_ais_all describing: + +struct kvm_s390_ais_all { + __u8 simm; /* Single-Interruption-Mode mask */ + __u8 nimm; /* No-Interruption-Mode mask * +}; + + simm contains Single-Interruption-Mode mask for all ISCs, nimm contains + No-Interruption-Mode mask for all ISCs. Each bit in simm and nimm corresponds + to an ISC (MSB0 bit 0 to ISC 0 and so on). The combination of simm bit and + nimm bit presents AIS mode for a ISC. + Note: The KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR device ioctls executed on FLIC with an unknown group or attribute gives the error code EINVAL (instead of ENXIO, as specified in the API documentation). It is not possible to conclude diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt index 575ccb022aac..903fc926860b 100644 --- a/Documentation/virtual/kvm/devices/vm.txt +++ b/Documentation/virtual/kvm/devices/vm.txt @@ -222,3 +222,36 @@ Allows user space to disable dea key wrapping, clearing the wrapping key. Parameters: none Returns: 0 + +5. GROUP: KVM_S390_VM_MIGRATION +Architectures: s390 + +5.1. ATTRIBUTE: KVM_S390_VM_MIGRATION_STOP (w/o) + +Allows userspace to stop migration mode, needed for PGSTE migration. +Setting this attribute when migration mode is not active will have no +effects. + +Parameters: none +Returns: 0 + +5.2. ATTRIBUTE: KVM_S390_VM_MIGRATION_START (w/o) + +Allows userspace to start migration mode, needed for PGSTE migration. +Setting this attribute when migration mode is already active will have +no effects. + +Parameters: none +Returns: -ENOMEM if there is not enough free memory to start migration mode + -EINVAL if the state of the VM is invalid (e.g. no memory defined) + 0 in case of success. + +5.3. ATTRIBUTE: KVM_S390_VM_MIGRATION_STATUS (r/o) + +Allows userspace to query the status of migration mode. + +Parameters: address of a buffer in user space to store the data (u64) to; + the data itself is either 0 if migration mode is disabled or 1 + if it is enabled +Returns: -EFAULT if the given address is not accessible from kernel space + 0 in case of success. diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt index 4f7d86dd0a5d..914518aeb972 100644 --- a/Documentation/watchdog/watchdog-parameters.txt +++ b/Documentation/watchdog/watchdog-parameters.txt @@ -117,7 +117,7 @@ nowayout: Watchdog cannot be stopped once started ------------------------------------------------- iTCO_wdt: heartbeat: Watchdog heartbeat in seconds. - (2<heartbeat<39 (TCO v1) or 613 (TCO v2), default=30) + (5<=heartbeat<=74 (TCO v1) or 1226 (TCO v2), default=30) nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) ------------------------------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index f7d568b8f133..9e984645c4b0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -846,7 +846,6 @@ M: Laura Abbott <labbott@redhat.com> M: Sumit Semwal <sumit.semwal@linaro.org> L: devel@driverdev.osuosl.org S: Supported -F: Documentation/devicetree/bindings/staging/ion/ F: drivers/staging/android/ion F: drivers/staging/android/uapi/ion.h F: drivers/staging/android/uapi/ion_test.h @@ -3116,6 +3115,14 @@ F: drivers/net/ieee802154/cc2520.c F: include/linux/spi/cc2520.h F: Documentation/devicetree/bindings/net/ieee802154/cc2520.txt +CCREE ARM TRUSTZONE CRYPTOCELL 700 REE DRIVER +M: Gilad Ben-Yossef <gilad@benyossef.com> +L: linux-crypto@vger.kernel.org +L: driverdev-devel@linuxdriverproject.org +S: Supported +F: drivers/staging/ccree/ +W: https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family + CEC FRAMEWORK M: Hans Verkuil <hans.verkuil@cisco.com> L: linux-media@vger.kernel.org @@ -5695,7 +5702,7 @@ M: Alex Elder <elder@kernel.org> M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> S: Maintained F: drivers/staging/greybus/ -L: greybus-dev@lists.linaro.org +L: greybus-dev@lists.linaro.org (moderated for non-subscribers) GREYBUS AUDIO PROTOCOLS DRIVERS M: Vaibhav Agarwal <vaibhav.sr@gmail.com> @@ -9553,10 +9560,6 @@ F: drivers/net/wireless/intersil/orinoco/ OSD LIBRARY and FILESYSTEM M: Boaz Harrosh <ooo@electrozaur.com> -M: Benny Halevy <bhalevy@primarydata.com> -L: osd-dev@open-osd.org -W: http://open-osd.org -T: git git://git.open-osd.org/open-osd.git S: Maintained F: drivers/scsi/osd/ F: include/scsi/osd_* @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Fearless Coyote # *DOCUMENTATION* @@ -1172,7 +1172,7 @@ headers_check_all: headers_install_all PHONY += headers_check headers_check: headers_install $(Q)$(MAKE) $(hdr-inst)=include/uapi HDRCHECK=1 - $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi/ $(hdr-dst) HDRCHECK=1 + $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) HDRCHECK=1 # --------------------------------------------------------------------------- # Kernel selftest diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 9ec56dc97374..ce93124a850b 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1201,8 +1201,10 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur))) return -EFAULT; - err = 0; - err |= put_user(status, ustatus); + err = put_user(status, ustatus); + if (ret < 0) + return err ? err : ret; + err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec); err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec); err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec); diff --git a/arch/arm/boot/dts/bcm283x-rpi-smsc9512.dtsi b/arch/arm/boot/dts/bcm283x-rpi-smsc9512.dtsi index 12c981e51134..9a0599f711ff 100644 --- a/arch/arm/boot/dts/bcm283x-rpi-smsc9512.dtsi +++ b/arch/arm/boot/dts/bcm283x-rpi-smsc9512.dtsi @@ -1,6 +1,6 @@ / { aliases { - ethernet = ðernet; + ethernet0 = ðernet; }; }; diff --git a/arch/arm/boot/dts/bcm283x-rpi-smsc9514.dtsi b/arch/arm/boot/dts/bcm283x-rpi-smsc9514.dtsi index 3f0a56ebcf1f..dc7ae776db5f 100644 --- a/arch/arm/boot/dts/bcm283x-rpi-smsc9514.dtsi +++ b/arch/arm/boot/dts/bcm283x-rpi-smsc9514.dtsi @@ -1,6 +1,6 @@ / { aliases { - ethernet = ðernet; + ethernet0 = ðernet; }; }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 35cea3fcaf5c..561f27d8d922 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -198,8 +198,8 @@ brcm,pins = <0 1>; brcm,function = <BCM2835_FSEL_ALT0>; }; - i2c0_gpio32: i2c0_gpio32 { - brcm,pins = <32 34>; + i2c0_gpio28: i2c0_gpio28 { + brcm,pins = <28 29>; brcm,function = <BCM2835_FSEL_ALT0>; }; i2c0_gpio44: i2c0_gpio44 { @@ -295,20 +295,28 @@ /* Separate from the uart0_gpio14 group * because it conflicts with spi1_gpio16, and * people often run uart0 on the two pins - * without flow contrl. + * without flow control. */ uart0_ctsrts_gpio16: uart0_ctsrts_gpio16 { brcm,pins = <16 17>; brcm,function = <BCM2835_FSEL_ALT3>; }; - uart0_gpio30: uart0_gpio30 { + uart0_ctsrts_gpio30: uart0_ctsrts_gpio30 { brcm,pins = <30 31>; brcm,function = <BCM2835_FSEL_ALT3>; }; - uart0_ctsrts_gpio32: uart0_ctsrts_gpio32 { + uart0_gpio32: uart0_gpio32 { brcm,pins = <32 33>; brcm,function = <BCM2835_FSEL_ALT3>; }; + uart0_gpio36: uart0_gpio36 { + brcm,pins = <36 37>; + brcm,function = <BCM2835_FSEL_ALT2>; + }; + uart0_ctsrts_gpio38: uart0_ctsrts_gpio38 { + brcm,pins = <38 39>; + brcm,function = <BCM2835_FSEL_ALT2>; + }; uart1_gpio14: uart1_gpio14 { brcm,pins = <14 15>; @@ -326,10 +334,6 @@ brcm,pins = <30 31>; brcm,function = <BCM2835_FSEL_ALT5>; }; - uart1_gpio36: uart1_gpio36 { - brcm,pins = <36 37 38 39>; - brcm,function = <BCM2835_FSEL_ALT2>; - }; uart1_gpio40: uart1_gpio40 { brcm,pins = <40 41>; brcm,function = <BCM2835_FSEL_ALT5>; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index 4bc4b575c99b..31a9e061ddd0 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -204,6 +204,8 @@ tps659038: tps659038@58 { compatible = "ti,tps659038"; reg = <0x58>; + ti,palmas-override-powerhold; + ti,system-power-controller; tps659038_pmic { compatible = "ti,tps659038-pmic"; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 57892f264cea..e7144662af45 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -2017,4 +2017,8 @@ coefficients = <0 2000>; }; +&cpu_crit { + temperature = <120000>; /* milli Celsius */ +}; + /include/ "dra7xx-clocks.dtsi" diff --git a/arch/arm/boot/dts/imx53-qsrb.dts b/arch/arm/boot/dts/imx53-qsrb.dts index de2215832372..4e103a905dc9 100644 --- a/arch/arm/boot/dts/imx53-qsrb.dts +++ b/arch/arm/boot/dts/imx53-qsrb.dts @@ -23,7 +23,7 @@ imx53-qsrb { pinctrl_pmic: pmicgrp { fsl,pins = < - MX53_PAD_CSI0_DAT5__GPIO5_23 0x1e4 /* IRQ */ + MX53_PAD_CSI0_DAT5__GPIO5_23 0x1c4 /* IRQ */ >; }; }; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts index 5bb8fd57e7f5..d71da30c9cff 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dts +++ b/arch/arm/boot/dts/imx6sx-sdb.dts @@ -12,23 +12,6 @@ model = "Freescale i.MX6 SoloX SDB RevB Board"; }; -&cpu0 { - operating-points = < - /* kHz uV */ - 996000 1250000 - 792000 1175000 - 396000 1175000 - 198000 1175000 - >; - fsl,soc-operating-points = < - /* ARM kHz SOC uV */ - 996000 1250000 - 792000 1175000 - 396000 1175000 - 198000 1175000 - >; -}; - &i2c1 { clock-frequency = <100000>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/include/arm b/arch/arm/boot/dts/include/arm deleted file mode 120000 index a96aa0ea9d8c..000000000000 --- a/arch/arm/boot/dts/include/arm +++ /dev/null @@ -1 +0,0 @@ -..
\ No newline at end of file diff --git a/arch/arm/boot/dts/include/arm64 b/arch/arm/boot/dts/include/arm64 deleted file mode 120000 index 074a835fca3e..000000000000 --- a/arch/arm/boot/dts/include/arm64 +++ /dev/null @@ -1 +0,0 @@ -../../../../arm64/boot/dts
\ No newline at end of file diff --git a/arch/arm/boot/dts/include/dt-bindings b/arch/arm/boot/dts/include/dt-bindings deleted file mode 120000 index 08c00e4972fa..000000000000 --- a/arch/arm/boot/dts/include/dt-bindings +++ /dev/null @@ -1 +0,0 @@ -../../../../../include/dt-bindings
\ No newline at end of file diff --git a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts index 08cce17a25a0..43e9364083de 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts @@ -249,9 +249,9 @@ OMAP3_CORE1_IOPAD(0x2110, PIN_INPUT | MUX_MODE0) /* cam_xclka.cam_xclka */ OMAP3_CORE1_IOPAD(0x2112, PIN_INPUT | MUX_MODE0) /* cam_pclk.cam_pclk */ - OMAP3_CORE1_IOPAD(0x2114, PIN_INPUT | MUX_MODE0) /* cam_d0.cam_d0 */ - OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0) /* cam_d1.cam_d1 */ - OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0) /* cam_d2.cam_d2 */ + OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0) /* cam_d0.cam_d0 */ + OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0) /* cam_d1.cam_d1 */ + OMAP3_CORE1_IOPAD(0x211a, PIN_INPUT | MUX_MODE0) /* cam_d2.cam_d2 */ OMAP3_CORE1_IOPAD(0x211c, PIN_INPUT | MUX_MODE0) /* cam_d3.cam_d3 */ OMAP3_CORE1_IOPAD(0x211e, PIN_INPUT | MUX_MODE0) /* cam_d4.cam_d4 */ OMAP3_CORE1_IOPAD(0x2120, PIN_INPUT | MUX_MODE0) /* cam_d5.cam_d5 */ diff --git a/arch/arm/boot/dts/mt7623.dtsi b/arch/arm/boot/dts/mt7623.dtsi index 402579ab70d2..3a9e9b6aea68 100644 --- a/arch/arm/boot/dts/mt7623.dtsi +++ b/arch/arm/boot/dts/mt7623.dtsi @@ -72,6 +72,8 @@ <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>, <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>, <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>; + clock-frequency = <13000000>; + arm,cpu-registers-not-fw-configured; }; watchdog: watchdog@10007000 { diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index b3a8b1f24499..9ec737069369 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -55,7 +55,8 @@ simple-audio-card,bitclock-master = <&telephony_link_master>; simple-audio-card,frame-master = <&telephony_link_master>; simple-audio-card,format = "i2s"; - + simple-audio-card,bitclock-inversion; + simple-audio-card,frame-inversion; simple-audio-card,cpu { sound-dai = <&mcbsp4>; }; diff --git a/arch/arm/boot/dts/omap4-panda-a4.dts b/arch/arm/boot/dts/omap4-panda-a4.dts index 78d363177762..f1a6476af371 100644 --- a/arch/arm/boot/dts/omap4-panda-a4.dts +++ b/arch/arm/boot/dts/omap4-panda-a4.dts @@ -13,7 +13,7 @@ /* Pandaboard Rev A4+ have external pullups on SCL & SDA */ &dss_hdmi_pins { pinctrl-single,pins = < - OMAP4_IOPAD(0x09a, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_cec.hdmi_cec */ + OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */ OMAP4_IOPAD(0x09c, PIN_INPUT | MUX_MODE0) /* hdmi_scl.hdmi_scl */ OMAP4_IOPAD(0x09e, PIN_INPUT | MUX_MODE0) /* hdmi_sda.hdmi_sda */ >; diff --git a/arch/arm/boot/dts/omap4-panda-es.dts b/arch/arm/boot/dts/omap4-panda-es.dts index 119f8e657edc..940fe4f7c5f6 100644 --- a/arch/arm/boot/dts/omap4-panda-es.dts +++ b/arch/arm/boot/dts/omap4-panda-es.dts @@ -34,7 +34,7 @@ /* PandaboardES has external pullups on SCL & SDA */ &dss_hdmi_pins { pinctrl-single,pins = < - OMAP4_IOPAD(0x09a, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_cec.hdmi_cec */ + OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */ OMAP4_IOPAD(0x09c, PIN_INPUT | MUX_MODE0) /* hdmi_scl.hdmi_scl */ OMAP4_IOPAD(0x09e, PIN_INPUT | MUX_MODE0) /* hdmi_sda.hdmi_sda */ >; diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig new file mode 100644 index 000000000000..d2d75fa664a6 --- /dev/null +++ b/arch/arm/configs/gemini_defconfig @@ -0,0 +1,68 @@ +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_SYSVIPC=y +CONFIG_NO_HZ_IDLE=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_USER_NS=y +CONFIG_RELAY=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_ARCH_MULTI_V4=y +# CONFIG_ARCH_MULTI_V7 is not set +CONFIG_ARCH_GEMINI=y +CONFIG_PCI=y +CONFIG_PREEMPT=y +CONFIG_AEABI=y +CONFIG_CMDLINE="console=ttyS0,115200n8" +CONFIG_KEXEC=y +CONFIG_BINFMT_MISC=y +CONFIG_PM=y +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_MTD=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_CFI_STAA=y +CONFIG_MTD_PHYSMAP=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=16384 +# CONFIG_SCSI_PROC_FS is not set +CONFIG_BLK_DEV_SD=y +# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_ATA=y +CONFIG_INPUT_EVDEV=y +CONFIG_KEYBOARD_GPIO=y +# CONFIG_INPUT_MOUSE is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_WATCHDOG=y +CONFIG_GEMINI_WATCHDOG=y +CONFIG_USB=y +CONFIG_USB_MON=y +CONFIG_USB_FOTG210_HCD=y +CONFIG_USB_STORAGE=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_TRIGGERS=y +CONFIG_LEDS_TRIGGER_HEARTBEAT=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GEMINI=y +CONFIG_DMADEVICES=y +# CONFIG_DNOTIFY is not set +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_ROMFS_FS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_DEBUG_FS=y diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 2cd27c830ab6..283e79ab587d 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -335,7 +335,7 @@ static const struct ramc_info ramc_infos[] __initconst = { { .idle = sama5d3_ddr_standby, .memctrl = AT91_MEMCTRL_DDRSDR}, }; -static const struct of_device_id const ramc_ids[] __initconst = { +static const struct of_device_id ramc_ids[] __initconst = { { .compatible = "atmel,at91rm9200-sdramc", .data = &ramc_infos[0] }, { .compatible = "atmel,at91sam9260-sdramc", .data = &ramc_infos[1] }, { .compatible = "atmel,at91sam9g45-ddramc", .data = &ramc_infos[2] }, diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c index cf3f8658f0e5..a55a7ecf146a 100644 --- a/arch/arm/mach-bcm/bcm_kona_smc.c +++ b/arch/arm/mach-bcm/bcm_kona_smc.c @@ -33,7 +33,7 @@ struct bcm_kona_smc_data { unsigned result; }; -static const struct of_device_id const bcm_kona_smc_ids[] __initconst = { +static const struct of_device_id bcm_kona_smc_ids[] __initconst = { {.compatible = "brcm,kona-smc"}, {.compatible = "bcm,kona-smc"}, /* deprecated name */ {}, diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c index 03da3813f1ab..7d5a44a06648 100644 --- a/arch/arm/mach-cns3xxx/core.c +++ b/arch/arm/mach-cns3xxx/core.c @@ -346,7 +346,7 @@ static struct usb_ohci_pdata cns3xxx_usb_ohci_pdata = { .power_off = csn3xxx_usb_power_off, }; -static const struct of_dev_auxdata const cns3xxx_auxdata[] __initconst = { +static const struct of_dev_auxdata cns3xxx_auxdata[] __initconst = { { "intel,usb-ehci", CNS3XXX_USB_BASE, "ehci-platform", &cns3xxx_usb_ehci_pdata }, { "intel,usb-ohci", CNS3XXX_USB_OHCI_BASE, "ohci-platform", &cns3xxx_usb_ohci_pdata }, { "cavium,cns3420-ahci", CNS3XXX_SATA2_BASE, "ahci", NULL }, diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h index 3089d3bfa19b..8cc6338fcb12 100644 --- a/arch/arm/mach-omap2/common.h +++ b/arch/arm/mach-omap2/common.h @@ -266,11 +266,12 @@ extern int omap4_cpu_kill(unsigned int cpu); extern const struct smp_operations omap4_smp_ops; #endif +extern u32 omap4_get_cpu1_ns_pa_addr(void); + #if defined(CONFIG_SMP) && defined(CONFIG_PM) extern int omap4_mpuss_init(void); extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state); extern int omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state); -extern u32 omap4_get_cpu1_ns_pa_addr(void); #else static inline int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state) diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c index 03ec6d307c82..4cfc4f9b2c69 100644 --- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c +++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c @@ -213,11 +213,6 @@ static void __init save_l2x0_context(void) {} #endif -u32 omap4_get_cpu1_ns_pa_addr(void) -{ - return old_cpu1_ns_pa_addr; -} - /** * omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function * The purpose of this function is to manage low power programming @@ -457,6 +452,11 @@ int __init omap4_mpuss_init(void) #endif +u32 omap4_get_cpu1_ns_pa_addr(void) +{ + return old_cpu1_ns_pa_addr; +} + /* * For kexec, we must set CPU1_WAKEUP_NS_PA_ADDR to point to * current kernel's secondary_startup() early before diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index 3faf454ba487..33e4953c61a8 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -306,7 +306,6 @@ static void __init omap4_smp_maybe_reset_cpu1(struct omap_smp_config *c) cpu1_startup_pa = readl_relaxed(cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_1); - cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr(); /* Did the configured secondary_startup() get overwritten? */ if (!omap4_smp_cpu1_startup_valid(cpu1_startup_pa)) @@ -316,9 +315,13 @@ static void __init omap4_smp_maybe_reset_cpu1(struct omap_smp_config *c) * If omap4 or 5 has NS_PA_ADDR configured, CPU1 may be in a * deeper idle state in WFI and will wake to an invalid address. */ - if ((soc_is_omap44xx() || soc_is_omap54xx()) && - !omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr)) - needs_reset = true; + if ((soc_is_omap44xx() || soc_is_omap54xx())) { + cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr(); + if (!omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr)) + needs_reset = true; + } else { + cpu1_ns_pa_addr = 0; + } if (!needs_reset || !c->cpu1_rstctrl_va) return; diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c index 2b138b65129a..dc11841ca334 100644 --- a/arch/arm/mach-omap2/prm_common.c +++ b/arch/arm/mach-omap2/prm_common.c @@ -711,7 +711,7 @@ static struct omap_prcm_init_data scrm_data __initdata = { }; #endif -static const struct of_device_id const omap_prcm_dt_match_table[] __initconst = { +static const struct of_device_id omap_prcm_dt_match_table[] __initconst = { #ifdef CONFIG_SOC_AM33XX { .compatible = "ti,am3-prcm", .data = &am3_prm_data }, #endif diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c index 2028167fff31..d76b1e5eb8ba 100644 --- a/arch/arm/mach-omap2/vc.c +++ b/arch/arm/mach-omap2/vc.c @@ -559,7 +559,7 @@ struct i2c_init_data { u8 hsscll_12; }; -static const struct i2c_init_data const omap4_i2c_timing_data[] __initconst = { +static const struct i2c_init_data omap4_i2c_timing_data[] __initconst = { { .load = 50, .loadbits = 0x3, diff --git a/arch/arm/mach-spear/time.c b/arch/arm/mach-spear/time.c index 4878ba90026d..289e036c9c30 100644 --- a/arch/arm/mach-spear/time.c +++ b/arch/arm/mach-spear/time.c @@ -204,7 +204,7 @@ static void __init spear_clockevent_init(int irq) setup_irq(irq, &spear_timer_irq); } -static const struct of_device_id const timer_of_match[] __initconst = { +static const struct of_device_id timer_of_match[] __initconst = { { .compatible = "st,spear-timer", }, { }, }; diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 4afcffcb46cb..73272f43ca01 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -106,8 +106,13 @@ config ARCH_MVEBU select ARMADA_AP806_SYSCON select ARMADA_CP110_SYSCON select ARMADA_37XX_CLK + select GPIOLIB + select GPIOLIB_IRQCHIP select MVEBU_ODMI select MVEBU_PIC + select OF_GPIO + select PINCTRL + select PINCTRL_ARMADA_37XX help This enables support for Marvell EBU familly, including: - Armada 3700 SoC Family diff --git a/arch/arm64/boot/dts/include/arm b/arch/arm64/boot/dts/include/arm deleted file mode 120000 index cf63d80e2b93..000000000000 --- a/arch/arm64/boot/dts/include/arm +++ /dev/null @@ -1 +0,0 @@ -../../../../arm/boot/dts
\ No newline at end of file diff --git a/arch/arm64/boot/dts/include/arm64 b/arch/arm64/boot/dts/include/arm64 deleted file mode 120000 index a96aa0ea9d8c..000000000000 --- a/arch/arm64/boot/dts/include/arm64 +++ /dev/null @@ -1 +0,0 @@ -..
\ No newline at end of file diff --git a/arch/arm64/boot/dts/include/dt-bindings b/arch/arm64/boot/dts/include/dt-bindings deleted file mode 120000 index 08c00e4972fa..000000000000 --- a/arch/arm64/boot/dts/include/dt-bindings +++ /dev/null @@ -1 +0,0 @@ -../../../../../include/dt-bindings
\ No newline at end of file diff --git a/arch/arm64/boot/dts/marvell/armada-3720-db.dts b/arch/arm64/boot/dts/marvell/armada-3720-db.dts index cef5f976bc0f..a89855f57091 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-db.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-db.dts @@ -79,6 +79,8 @@ }; &i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; status = "okay"; gpio_exp: pca9555@22 { @@ -113,6 +115,8 @@ &spi0 { status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&spi_quad_pins>; m25p80@0 { compatible = "jedec,spi-nor"; @@ -143,6 +147,8 @@ /* Exported on the micro USB connector CON32 through an FTDI */ &uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart1_pins>; status = "okay"; }; @@ -184,6 +190,8 @@ }; ð0 { + pinctrl-names = "default"; + pinctrl-0 = <&rgmii_pins>; phy-mode = "rgmii-id"; phy = <&phy0>; status = "okay"; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index 58ae9e095af2..4d495ec39202 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -161,16 +161,83 @@ #clock-cells = <1>; }; - gpio1: gpio@13800 { - compatible = "marvell,mvebu-gpio-3700", + pinctrl_nb: pinctrl@13800 { + compatible = "marvell,armada3710-nb-pinctrl", "syscon", "simple-mfd"; - reg = <0x13800 0x500>; + reg = <0x13800 0x100>, <0x13C00 0x20>; + gpionb: gpio { + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_nb 0 0 36>; + gpio-controller; + interrupts = + <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>; + + }; xtalclk: xtal-clk { compatible = "marvell,armada-3700-xtal-clock"; clock-output-names = "xtal"; #clock-cells = <0>; }; + + spi_quad_pins: spi-quad-pins { + groups = "spi_quad"; + function = "spi"; + }; + + i2c1_pins: i2c1-pins { + groups = "i2c1"; + function = "i2c"; + }; + + i2c2_pins: i2c2-pins { + groups = "i2c2"; + function = "i2c"; + }; + + uart1_pins: uart1-pins { + groups = "uart1"; + function = "uart"; + }; + + uart2_pins: uart2-pins { + groups = "uart2"; + function = "uart"; + }; + }; + + pinctrl_sb: pinctrl@18800 { + compatible = "marvell,armada3710-sb-pinctrl", + "syscon", "simple-mfd"; + reg = <0x18800 0x100>, <0x18C00 0x20>; + gpiosb: gpio { + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_sb 0 0 29>; + gpio-controller; + interrupts = + <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>; + }; + + rgmii_pins: mii-pins { + groups = "rgmii"; + function = "mii"; + }; + }; eth0: ethernet@30000 { diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts index 0ecaad4333a7..1c3634fa94bf 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts @@ -134,6 +134,9 @@ bus-width = <8>; max-frequency = <50000000>; cap-mmc-highspeed; + mediatek,hs200-cmd-int-delay=<26>; + mediatek,hs400-cmd-int-delay=<14>; + mediatek,hs400-cmd-resp-sel-rising; vmmc-supply = <&mt6397_vemc_3v3_reg>; vqmmc-supply = <&mt6397_vio18_reg>; non-removable; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts index 658bb9dc9dfd..7bd31066399b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts @@ -44,7 +44,7 @@ /dts-v1/; #include "rk3399-gru.dtsi" -#include <include/dt-bindings/input/linux-event-codes.h> +#include <dt-bindings/input/linux-event-codes.h> /* * Kevin-specific things diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index ce072859e3b2..65cdd878cfbd 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -30,7 +30,6 @@ CONFIG_PROFILING=y CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set CONFIG_ARCH_SUNXI=y CONFIG_ARCH_ALPINE=y @@ -62,16 +61,15 @@ CONFIG_ARCH_XGENE=y CONFIG_ARCH_ZX=y CONFIG_ARCH_ZYNQMP=y CONFIG_PCI=y -CONFIG_PCI_MSI=y CONFIG_PCI_IOV=y -CONFIG_PCI_AARDVARK=y -CONFIG_PCIE_RCAR=y -CONFIG_PCI_HOST_GENERIC=y -CONFIG_PCI_XGENE=y CONFIG_PCI_LAYERSCAPE=y CONFIG_PCI_HISI=y CONFIG_PCIE_QCOM=y CONFIG_PCIE_ARMADA_8K=y +CONFIG_PCI_AARDVARK=y +CONFIG_PCIE_RCAR=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCI_XGENE=y CONFIG_ARM64_VA_BITS_48=y CONFIG_SCHED_MC=y CONFIG_NUMA=y @@ -80,12 +78,11 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y CONFIG_SECCOMP=y -CONFIG_XEN=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y +CONFIG_XEN=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y -CONFIG_CPU_IDLE=y CONFIG_HIBERNATION=y CONFIG_ARM_CPUIDLE=y CONFIG_CPU_FREQ=y @@ -155,8 +152,8 @@ CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=m CONFIG_VIRTIO_BLK=y -CONFIG_EEPROM_AT25=m CONFIG_SRAM=y +CONFIG_EEPROM_AT25=m # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y CONFIG_SCSI_SAS_ATA=y @@ -168,8 +165,8 @@ CONFIG_AHCI_CEVA=y CONFIG_AHCI_MVEBU=y CONFIG_AHCI_XGENE=y CONFIG_AHCI_QORIQ=y -CONFIG_SATA_RCAR=y CONFIG_SATA_SIL24=y +CONFIG_SATA_RCAR=y CONFIG_PATA_PLATFORM=y CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y @@ -186,18 +183,17 @@ CONFIG_HNS_ENET=y CONFIG_E1000E=y CONFIG_IGB=y CONFIG_IGBVF=y -CONFIG_MVPP2=y CONFIG_MVNETA=y +CONFIG_MVPP2=y CONFIG_SKY2=y CONFIG_RAVB=y CONFIG_SMC91X=y CONFIG_SMSC911X=y CONFIG_STMMAC_ETH=m -CONFIG_REALTEK_PHY=m +CONFIG_MDIO_BUS_MUX_MMIOREG=y CONFIG_MESON_GXL_PHY=m CONFIG_MICREL_PHY=y -CONFIG_MDIO_BUS_MUX=y -CONFIG_MDIO_BUS_MUX_MMIOREG=y +CONFIG_REALTEK_PHY=m CONFIG_USB_PEGASUS=m CONFIG_USB_RTL8150=m CONFIG_USB_RTL8152=m @@ -230,14 +226,14 @@ CONFIG_SERIAL_8250_UNIPHIER=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_SERIAL_MESON=y +CONFIG_SERIAL_MESON_CONSOLE=y CONFIG_SERIAL_SAMSUNG=y CONFIG_SERIAL_SAMSUNG_CONSOLE=y CONFIG_SERIAL_TEGRA=y CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=11 CONFIG_SERIAL_SH_SCI_CONSOLE=y -CONFIG_SERIAL_MESON=y -CONFIG_SERIAL_MESON_CONSOLE=y CONFIG_SERIAL_MSM=y CONFIG_SERIAL_MSM_CONSOLE=y CONFIG_SERIAL_XILINX_PS_UART=y @@ -261,14 +257,14 @@ CONFIG_I2C_UNIPHIER_F=y CONFIG_I2C_RCAR=y CONFIG_I2C_CROS_EC_TUNNEL=y CONFIG_SPI=y -CONFIG_SPI_MESON_SPIFC=m CONFIG_SPI_BCM2835=m CONFIG_SPI_BCM2835AUX=m +CONFIG_SPI_MESON_SPIFC=m CONFIG_SPI_ORION=y CONFIG_SPI_PL022=y CONFIG_SPI_QUP=y -CONFIG_SPI_SPIDEV=m CONFIG_SPI_S3C64XX=y +CONFIG_SPI_SPIDEV=m CONFIG_SPMI=y CONFIG_PINCTRL_SINGLE=y CONFIG_PINCTRL_MAX77620=y @@ -286,33 +282,30 @@ CONFIG_GPIO_PCA953X=y CONFIG_GPIO_PCA953X_IRQ=y CONFIG_GPIO_MAX77620=y CONFIG_POWER_RESET_MSM=y -CONFIG_BATTERY_BQ27XXX=y CONFIG_POWER_RESET_XGENE=y CONFIG_POWER_RESET_SYSCON=y +CONFIG_BATTERY_BQ27XXX=y +CONFIG_SENSORS_ARM_SCPI=y CONFIG_SENSORS_LM90=m CONFIG_SENSORS_INA2XX=m -CONFIG_SENSORS_ARM_SCPI=y -CONFIG_THERMAL=y -CONFIG_THERMAL_EMULATION=y CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y CONFIG_CPU_THERMAL=y -CONFIG_BCM2835_THERMAL=y +CONFIG_THERMAL_EMULATION=y CONFIG_EXYNOS_THERMAL=y CONFIG_WATCHDOG=y -CONFIG_BCM2835_WDT=y -CONFIG_RENESAS_WDT=y CONFIG_S3C2410_WATCHDOG=y CONFIG_MESON_GXBB_WATCHDOG=m CONFIG_MESON_WATCHDOG=m +CONFIG_RENESAS_WDT=y +CONFIG_BCM2835_WDT=y +CONFIG_MFD_CROS_EC=y +CONFIG_MFD_CROS_EC_I2C=y CONFIG_MFD_EXYNOS_LPASS=m +CONFIG_MFD_HI655X_PMIC=y CONFIG_MFD_MAX77620=y -CONFIG_MFD_RK808=y CONFIG_MFD_SPMI_PMIC=y +CONFIG_MFD_RK808=y CONFIG_MFD_SEC_CORE=y -CONFIG_MFD_HI655X_PMIC=y -CONFIG_REGULATOR=y -CONFIG_MFD_CROS_EC=y -CONFIG_MFD_CROS_EC_I2C=y CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_REGULATOR_GPIO=y CONFIG_REGULATOR_HI655X=y @@ -345,13 +338,12 @@ CONFIG_DRM_EXYNOS_DSI=y CONFIG_DRM_EXYNOS_HDMI=y CONFIG_DRM_EXYNOS_MIC=y CONFIG_DRM_RCAR_DU=m -CONFIG_DRM_RCAR_HDMI=y CONFIG_DRM_RCAR_LVDS=y CONFIG_DRM_RCAR_VSP=y CONFIG_DRM_TEGRA=m -CONFIG_DRM_VC4=m CONFIG_DRM_PANEL_SIMPLE=m CONFIG_DRM_I2C_ADV7511=m +CONFIG_DRM_VC4=m CONFIG_DRM_HISI_KIRIN=m CONFIG_DRM_MESON=m CONFIG_FB=y @@ -366,39 +358,37 @@ CONFIG_SOUND=y CONFIG_SND=y CONFIG_SND_SOC=y CONFIG_SND_BCM2835_SOC_I2S=m -CONFIG_SND_SOC_RCAR=y CONFIG_SND_SOC_SAMSUNG=y +CONFIG_SND_SOC_RCAR=y CONFIG_SND_SOC_AK4613=y CONFIG_USB=y CONFIG_USB_OTG=y CONFIG_USB_XHCI_HCD=y -CONFIG_USB_XHCI_PLATFORM=y -CONFIG_USB_XHCI_RCAR=y -CONFIG_USB_EHCI_EXYNOS=y CONFIG_USB_XHCI_TEGRA=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_MSM=y +CONFIG_USB_EHCI_EXYNOS=y CONFIG_USB_EHCI_HCD_PLATFORM=y -CONFIG_USB_OHCI_EXYNOS=y CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_EXYNOS=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_RENESAS_USBHS=m CONFIG_USB_STORAGE=y -CONFIG_USB_DWC2=y CONFIG_USB_DWC3=y +CONFIG_USB_DWC2=y CONFIG_USB_CHIPIDEA=y CONFIG_USB_CHIPIDEA_UDC=y CONFIG_USB_CHIPIDEA_HOST=y CONFIG_USB_ISP1760=y CONFIG_USB_HSIC_USB3503=y CONFIG_USB_MSM_OTG=y +CONFIG_USB_QCOM_8X16_PHY=y CONFIG_USB_ULPI=y CONFIG_USB_GADGET=y CONFIG_USB_RENESAS_USBHS_UDC=m CONFIG_MMC=y CONFIG_MMC_BLOCK_MINORS=32 CONFIG_MMC_ARMMMCI=y -CONFIG_MMC_MESON_GX=y CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_ACPI=y CONFIG_MMC_SDHCI_PLTFM=y @@ -406,6 +396,7 @@ CONFIG_MMC_SDHCI_OF_ARASAN=y CONFIG_MMC_SDHCI_OF_ESDHC=y CONFIG_MMC_SDHCI_CADENCE=y CONFIG_MMC_SDHCI_TEGRA=y +CONFIG_MMC_MESON_GX=y CONFIG_MMC_SDHCI_MSM=y CONFIG_MMC_SPI=y CONFIG_MMC_SDHI=y @@ -414,32 +405,31 @@ CONFIG_MMC_DW_EXYNOS=y CONFIG_MMC_DW_K3=y CONFIG_MMC_DW_ROCKCHIP=y CONFIG_MMC_SUNXI=y -CONFIG_MMC_SDHCI_XENON=y CONFIG_MMC_BCM2835=y +CONFIG_MMC_SDHCI_XENON=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y CONFIG_LEDS_GPIO=y CONFIG_LEDS_PWM=y CONFIG_LEDS_SYSCON=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_LEDS_TRIGGER_CPU=y +CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_MAX77686=y +CONFIG_RTC_DRV_RK808=m CONFIG_RTC_DRV_S5M=y CONFIG_RTC_DRV_DS3232=y CONFIG_RTC_DRV_EFI=y +CONFIG_RTC_DRV_S3C=y CONFIG_RTC_DRV_PL031=y CONFIG_RTC_DRV_SUN6I=y -CONFIG_RTC_DRV_RK808=m CONFIG_RTC_DRV_TEGRA=y CONFIG_RTC_DRV_XGENE=y -CONFIG_RTC_DRV_S3C=y CONFIG_DMADEVICES=y +CONFIG_DMA_BCM2835=m CONFIG_MV_XOR_V2=y CONFIG_PL330_DMA=y -CONFIG_DMA_BCM2835=m CONFIG_TEGRA20_APB_DMA=y CONFIG_QCOM_BAM_DMA=y CONFIG_QCOM_HIDMA_MGMT=y @@ -452,52 +442,53 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_MMIO=y CONFIG_XEN_GNTDEV=y CONFIG_XEN_GRANT_DEV_ALLOC=y +CONFIG_COMMON_CLK_RK808=y CONFIG_COMMON_CLK_SCPI=y CONFIG_COMMON_CLK_CS2000_CP=y CONFIG_COMMON_CLK_S2MPS11=y -CONFIG_COMMON_CLK_PWM=y -CONFIG_COMMON_CLK_RK808=y CONFIG_CLK_QORIQ=y +CONFIG_COMMON_CLK_PWM=y CONFIG_COMMON_CLK_QCOM=y +CONFIG_QCOM_CLK_SMD_RPM=y CONFIG_MSM_GCC_8916=y CONFIG_MSM_GCC_8994=y CONFIG_MSM_MMCC_8996=y CONFIG_HWSPINLOCK_QCOM=y -CONFIG_MAILBOX=y CONFIG_ARM_MHU=y CONFIG_PLATFORM_MHU=y CONFIG_BCM2835_MBOX=y CONFIG_HI6220_MBOX=y CONFIG_ARM_SMMU=y CONFIG_ARM_SMMU_V3=y +CONFIG_RPMSG_QCOM_SMD=y CONFIG_RASPBERRYPI_POWER=y CONFIG_QCOM_SMEM=y -CONFIG_QCOM_SMD=y CONFIG_QCOM_SMD_RPM=y +CONFIG_QCOM_SMP2P=y +CONFIG_QCOM_SMSM=y CONFIG_ROCKCHIP_PM_DOMAINS=y CONFIG_ARCH_TEGRA_132_SOC=y CONFIG_ARCH_TEGRA_210_SOC=y CONFIG_ARCH_TEGRA_186_SOC=y CONFIG_EXTCON_USB_GPIO=y +CONFIG_IIO=y +CONFIG_EXYNOS_ADC=y CONFIG_PWM=y CONFIG_PWM_BCM2835=m +CONFIG_PWM_MESON=m CONFIG_PWM_ROCKCHIP=y +CONFIG_PWM_SAMSUNG=y CONFIG_PWM_TEGRA=m -CONFIG_PWM_MESON=m -CONFIG_COMMON_RESET_HI6220=y CONFIG_PHY_RCAR_GEN3_USB2=y CONFIG_PHY_HI6220_USB=y +CONFIG_PHY_SUN4I_USB=y CONFIG_PHY_ROCKCHIP_INNO_USB2=y CONFIG_PHY_ROCKCHIP_EMMC=y -CONFIG_PHY_SUN4I_USB=y CONFIG_PHY_XGENE=y CONFIG_PHY_TEGRA_XUSB=y CONFIG_ARM_SCPI_PROTOCOL=y -CONFIG_ACPI=y -CONFIG_IIO=y -CONFIG_EXYNOS_ADC=y -CONFIG_PWM_SAMSUNG=y CONFIG_RASPBERRYPI_FIRMWARE=y +CONFIG_ACPI=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y CONFIG_EXT4_FS_POSIX_ACL=y @@ -511,7 +502,6 @@ CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m CONFIG_VFAT_FS=y -CONFIG_TMPFS=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=y CONFIG_EFIVAR_FS=y @@ -539,11 +529,9 @@ CONFIG_MEMTEST=y CONFIG_SECURITY=y CONFIG_CRYPTO_ECHAINIV=y CONFIG_CRYPTO_ANSI_CPRNG=y -CONFIG_CRYPTO_DEV_SAFEXCEL=m CONFIG_ARM64_CRYPTO=y CONFIG_CRYPTO_SHA1_ARM64_CE=y CONFIG_CRYPTO_SHA2_ARM64_CE=y CONFIG_CRYPTO_GHASH_ARM64_CE=y CONFIG_CRYPTO_AES_ARM64_CE_CCM=y CONFIG_CRYPTO_AES_ARM64_CE_BLK=y -# CONFIG_CRYPTO_AES_ARM64_NEON_BLK is not set diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index f819fdcff1ac..f5a2d09afb38 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -264,7 +264,6 @@ __LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr, \ " st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ - " mov %" #w "[oldval], %" #w "[old]\n" \ "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ [v] "+Q" (*(unsigned long *)ptr) \ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index e7f84a7b4465..428ee1f2468c 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -115,6 +115,7 @@ struct arm64_cpu_capabilities { extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; +extern struct static_key_false arm64_const_caps_ready; bool this_cpu_has_cap(unsigned int cap); @@ -124,7 +125,7 @@ static inline bool cpu_have_feature(unsigned int num) } /* System capability check for constant caps */ -static inline bool cpus_have_const_cap(int num) +static inline bool __cpus_have_const_cap(int num) { if (num >= ARM64_NCAPS) return false; @@ -138,6 +139,14 @@ static inline bool cpus_have_cap(unsigned int num) return test_bit(num, cpu_hwcaps); } +static inline bool cpus_have_const_cap(int num) +{ + if (static_branch_likely(&arm64_const_caps_ready)) + return __cpus_have_const_cap(num); + else + return cpus_have_cap(num); +} + static inline void cpus_set_cap(unsigned int num) { if (num >= ARM64_NCAPS) { @@ -145,7 +154,6 @@ static inline void cpus_set_cap(unsigned int num) num, ARM64_NCAPS); } else { __set_bit(num, cpu_hwcaps); - static_branch_enable(&cpu_hwcap_keys[num]); } } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0c4fd1f46e10..d68630007b14 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -24,6 +24,7 @@ #include <linux/types.h> #include <linux/kvm_types.h> +#include <asm/cpufeature.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> @@ -355,9 +356,12 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, unsigned long vector_ptr) { /* - * Call initialization code, and switch to the full blown - * HYP code. + * Call initialization code, and switch to the full blown HYP code. + * If the cpucaps haven't been finalized yet, something has gone very + * wrong, and hyp will crash and burn when it uses any + * cpus_have_const_cap() wrapper. */ + BUG_ON(!static_branch_likely(&arm64_const_caps_ready)); __kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr); } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 94b8f7fc3310..817ce3365e20 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -985,8 +985,16 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, */ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) { - for (; caps->matches; caps++) - if (caps->enable && cpus_have_cap(caps->capability)) + for (; caps->matches; caps++) { + unsigned int num = caps->capability; + + if (!cpus_have_cap(num)) + continue; + + /* Ensure cpus_have_const_cap(num) works */ + static_branch_enable(&cpu_hwcap_keys[num]); + + if (caps->enable) { /* * Use stop_machine() as it schedules the work allowing * us to modify PSTATE, instead of on_each_cpu() which @@ -994,6 +1002,8 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) * we return. */ stop_machine(caps->enable, NULL, cpu_online_mask); + } + } } /* @@ -1096,6 +1106,14 @@ static void __init setup_feature_capabilities(void) enable_cpu_capabilities(arm64_features); } +DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready); +EXPORT_SYMBOL(arm64_const_caps_ready); + +static void __init mark_const_caps_ready(void) +{ + static_branch_enable(&arm64_const_caps_ready); +} + /* * Check if the current CPU has a given feature capability. * Should be called from non-preemptible context. @@ -1131,6 +1149,7 @@ void __init setup_cpu_features(void) /* Set the CPU feature capabilies */ setup_feature_capabilities(); enable_errata_workarounds(); + mark_const_caps_ready(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index bcc79471b38e..83a1b1ad189f 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -877,15 +877,24 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, if (attr->exclude_idle) return -EPERM; - if (is_kernel_in_hyp_mode() && - attr->exclude_kernel != attr->exclude_hv) - return -EINVAL; + + /* + * If we're running in hyp mode, then we *are* the hypervisor. + * Therefore we ignore exclude_hv in this configuration, since + * there's no hypervisor to sample anyway. This is consistent + * with other architectures (x86 and Power). + */ + if (is_kernel_in_hyp_mode()) { + if (!attr->exclude_kernel) + config_base |= ARMV8_PMU_INCLUDE_EL2; + } else { + if (attr->exclude_kernel) + config_base |= ARMV8_PMU_EXCLUDE_EL1; + if (!attr->exclude_hv) + config_base |= ARMV8_PMU_INCLUDE_EL2; + } if (attr->exclude_user) config_base |= ARMV8_PMU_EXCLUDE_EL0; - if (!is_kernel_in_hyp_mode() && attr->exclude_kernel) - config_base |= ARMV8_PMU_EXCLUDE_EL1; - if (!attr->exclude_hv) - config_base |= ARMV8_PMU_INCLUDE_EL2; /* * Install the filter into config_base as this is used to diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index c6e53580aefe..71f930501ade 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -253,8 +253,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) */ off = offsetof(struct bpf_array, ptrs); emit_a64_mov_i64(tmp, off, ctx); - emit(A64_LDR64(tmp, r2, tmp), ctx); - emit(A64_LDR64(prg, tmp, r3), ctx); + emit(A64_ADD(1, tmp, r2, tmp), ctx); + emit(A64_LSL(1, prg, r3, 3), ctx); + emit(A64_LDR64(prg, tmp, prg), ctx); emit(A64_CBZ(1, prg, jmp_offset), ctx); /* goto *(prog->bpf_func + prologue_size); */ diff --git a/arch/cris/boot/dts/include/dt-bindings b/arch/cris/boot/dts/include/dt-bindings deleted file mode 120000 index 08c00e4972fa..000000000000 --- a/arch/cris/boot/dts/include/dt-bindings +++ /dev/null @@ -1 +0,0 @@ -../../../../../include/dt-bindings
\ No newline at end of file diff --git a/arch/metag/boot/dts/include/dt-bindings b/arch/metag/boot/dts/include/dt-bindings deleted file mode 120000 index 08c00e4972fa..000000000000 --- a/arch/metag/boot/dts/include/dt-bindings +++ /dev/null @@ -1 +0,0 @@ -../../../../../include/dt-bindings
\ No newline at end of file diff --git a/arch/mips/boot/dts/include/dt-bindings b/arch/mips/boot/dts/include/dt-bindings deleted file mode 120000 index 08c00e4972fa..000000000000 --- a/arch/mips/boot/dts/include/dt-bindings +++ /dev/null @@ -1 +0,0 @@ -../../../../../include/dt-bindings
\ No newline at end of file diff --git a/arch/powerpc/boot/dts/include/dt-bindings b/arch/powerpc/boot/dts/include/dt-bindings deleted file mode 120000 index 08c00e4972fa..000000000000 --- a/arch/powerpc/boot/dts/include/dt-bindings +++ /dev/null @@ -1 +0,0 @@ -../../../../../include/dt-bindings
\ No newline at end of file diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 53885512b8d3..6c0132c7212f 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -14,6 +14,10 @@ #include <asm-generic/module.h> +#ifdef CC_USING_MPROFILE_KERNEL +#define MODULE_ARCH_VERMAGIC "mprofile-kernel" +#endif + #ifndef __powerpc64__ /* * Thanks to Paul M for explaining this. diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 2a32483c7b6c..8da5d4c1cab2 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,19 @@ extern long long virt_phys_offset; #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) + +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * On hash the vmalloc and other regions alias to the kernel region when passed + * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can + * return true for some vmalloc addresses, which is incorrect. So explicitly + * check that the address is in the kernel region. + */ +#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \ + pfn_valid(virt_to_pfn(kaddr))) +#else #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#endif /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 07d4e0ad60db..4898d676dcae 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -416,7 +416,7 @@ power9_dd1_recover_paca: * which needs to be restored from the stack. */ li r3, 1 - stb r0,PACA_NAPSTATELOST(r13) + stb r3,PACA_NAPSTATELOST(r13) blr /* diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 160ae0fa7d0d..fc4343514bed 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -305,16 +305,17 @@ int kprobe_handler(struct pt_regs *regs) save_previous_kprobe(kcb); set_current_kprobe(p, regs, kcb); kprobes_inc_nmissed_count(p); - prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_REENTER; if (p->ainsn.boostable >= 0) { ret = try_to_emulate(p, regs); if (ret > 0) { restore_previous_kprobe(kcb); + preempt_enable_no_resched(); return 1; } } + prepare_singlestep(p, regs); return 1; } else { if (*addr != BREAKPOINT_INSTRUCTION) { diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index d645da302bf2..baae104b16c7 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -864,6 +864,25 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; + /* + * If we are in a transaction and FP is off then we can't have + * used FP inside that transaction. Hence the checkpointed + * state is the same as the live state. We need to copy the + * live state to the checkpointed state so that when the + * transaction is restored, the checkpointed state is correct + * and the aborted transaction sees the correct state. We use + * ckpt_regs.msr here as that's what tm_reclaim will use to + * determine if it's going to write the checkpointed state or + * not. So either this will write the checkpointed registers, + * or reclaim will. Similarly for VMX. + */ + if ((thr->ckpt_regs.msr & MSR_FP) == 0) + memcpy(&thr->ckfp_state, &thr->fp_state, + sizeof(struct thread_fp_state)); + if ((thr->ckpt_regs.msr & MSR_VEC) == 0) + memcpy(&thr->ckvr_state, &thr->vr_state, + sizeof(struct thread_vr_state)); + giveup_all(container_of(thr, struct task_struct, thread)); tm_reclaim(thr, thr->ckpt_regs.msr, cause); diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 24de532c1736..0c52cb5d43f5 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -67,7 +67,7 @@ config KVM_BOOK3S_64 select KVM_BOOK3S_64_HANDLER select KVM select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE - select SPAPR_TCE_IOMMU if IOMMU_SUPPORT + select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV) ---help--- Support running unmodified book3s_64 and book3s_32 guest kernels in virtual machines on book3s_64 host processors. diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index d91a2604c496..381a6ec0ff3b 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -46,7 +46,7 @@ kvm-e500mc-objs := \ e500_emulate.o kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs) -kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \ +kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \ book3s_64_vio_hv.o kvm-pr-y := \ @@ -90,11 +90,11 @@ kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ book3s_xics.o kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o +kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o kvm-book3s_64-module-objs := \ $(common-objs-y) \ book3s.o \ - book3s_64_vio.o \ book3s_rtas.o \ $(kvm-book3s_64-objs-y) diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index eda0a8f6fae8..3adfd2f5301c 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -301,6 +301,10 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ /* liobn, ioba, tce); */ + /* For radix, we might be in virtual mode, so punt */ + if (kvm_is_radix(vcpu->kvm)) + return H_TOO_HARD; + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -381,6 +385,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, bool prereg = false; struct kvmppc_spapr_tce_iommu_table *stit; + /* For radix, we might be in virtual mode, so punt */ + if (kvm_is_radix(vcpu->kvm)) + return H_TOO_HARD; + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -491,6 +499,10 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, long i, ret; struct kvmppc_spapr_tce_iommu_table *stit; + /* For radix, we might be in virtual mode, so punt */ + if (kvm_is_radix(vcpu->kvm)) + return H_TOO_HARD; + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -527,6 +539,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, return H_SUCCESS; } +/* This can be called in either virtual mode or real mode */ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba) { diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 88a65923c649..ee4c2558c305 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -207,7 +207,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present); long kvmppc_h_random(struct kvm_vcpu *vcpu) { - if (powernv_get_random_real_mode(&vcpu->arch.gpr[4])) + int r; + + /* Only need to do the expensive mfmsr() on radix */ + if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR)) + r = powernv_get_random_long(&vcpu->arch.gpr[4]); + else + r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]); + if (r) return H_SUCCESS; return H_HARDWARE; diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index bcbeeb62dd13..8a4205fa774f 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -50,7 +50,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu) pteg_addr = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); - copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)); + ret = H_FUNCTION; + if (copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg))) + goto done; hpte = pteg; ret = H_PTEG_FULL; @@ -71,7 +73,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu) hpte[0] = cpu_to_be64(kvmppc_get_gpr(vcpu, 6)); hpte[1] = cpu_to_be64(kvmppc_get_gpr(vcpu, 7)); pteg_addr += i * HPTE_SIZE; - copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE); + ret = H_FUNCTION; + if (copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE)) + goto done; kvmppc_set_gpr(vcpu, 4, pte_index | i); ret = H_SUCCESS; @@ -93,7 +97,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu) pteg = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); - copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + ret = H_FUNCTION; + if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) + goto done; pte[0] = be64_to_cpu((__force __be64)pte[0]); pte[1] = be64_to_cpu((__force __be64)pte[1]); @@ -103,7 +109,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu) ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) goto done; - copy_to_user((void __user *)pteg, &v, sizeof(v)); + ret = H_FUNCTION; + if (copy_to_user((void __user *)pteg, &v, sizeof(v))) + goto done; rb = compute_tlbie_rb(pte[0], pte[1], pte_index); vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); @@ -171,7 +179,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu) } pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX); - copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) { + ret = H_FUNCTION; + break; + } pte[0] = be64_to_cpu((__force __be64)pte[0]); pte[1] = be64_to_cpu((__force __be64)pte[1]); @@ -184,7 +195,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu) tsh |= H_BULK_REMOVE_NOT_FOUND; } else { /* Splat the pteg in (userland) hpt */ - copy_to_user((void __user *)pteg, &v, sizeof(v)); + if (copy_to_user((void __user *)pteg, &v, sizeof(v))) { + ret = H_FUNCTION; + break; + } rb = compute_tlbie_rb(pte[0], pte[1], tsh & H_BULK_REMOVE_PTEX); @@ -211,7 +225,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) pteg = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); - copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + ret = H_FUNCTION; + if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) + goto done; pte[0] = be64_to_cpu((__force __be64)pte[0]); pte[1] = be64_to_cpu((__force __be64)pte[1]); @@ -234,7 +250,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); pte[0] = (__force u64)cpu_to_be64(pte[0]); pte[1] = (__force u64)cpu_to_be64(pte[1]); - copy_to_user((void __user *)pteg, pte, sizeof(pte)); + ret = H_FUNCTION; + if (copy_to_user((void __user *)pteg, pte, sizeof(pte))) + goto done; ret = H_SUCCESS; done: @@ -244,36 +262,37 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) return EMULATE_DONE; } -static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) +static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu) { - unsigned long liobn = kvmppc_get_gpr(vcpu, 4); - unsigned long ioba = kvmppc_get_gpr(vcpu, 5); - unsigned long tce = kvmppc_get_gpr(vcpu, 6); long rc; - rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce); + rc = kvmppc_h_logical_ci_load(vcpu); if (rc == H_TOO_HARD) return EMULATE_FAIL; kvmppc_set_gpr(vcpu, 3, rc); return EMULATE_DONE; } -static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu) +static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) { long rc; - rc = kvmppc_h_logical_ci_load(vcpu); + rc = kvmppc_h_logical_ci_store(vcpu); if (rc == H_TOO_HARD) return EMULATE_FAIL; kvmppc_set_gpr(vcpu, 3, rc); return EMULATE_DONE; } -static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) +#ifdef CONFIG_SPAPR_TCE_IOMMU +static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { + unsigned long liobn = kvmppc_get_gpr(vcpu, 4); + unsigned long ioba = kvmppc_get_gpr(vcpu, 5); + unsigned long tce = kvmppc_get_gpr(vcpu, 6); long rc; - rc = kvmppc_h_logical_ci_store(vcpu); + rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce); if (rc == H_TOO_HARD) return EMULATE_FAIL; kvmppc_set_gpr(vcpu, 3, rc); @@ -311,6 +330,23 @@ static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +#else /* CONFIG_SPAPR_TCE_IOMMU */ +static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) +{ + return EMULATE_FAIL; +} + +static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu) +{ + return EMULATE_FAIL; +} + +static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu) +{ + return EMULATE_FAIL; +} +#endif /* CONFIG_SPAPR_TCE_IOMMU */ + static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { long rc = kvmppc_xics_hcall(vcpu, cmd); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index fd64f087737c..c5aa3a42883a 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1748,7 +1748,7 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_enable_cap(kvm, &cap); break; } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_CREATE_SPAPR_TCE_64: { struct kvm_create_spapr_tce_64 create_tce_64; @@ -1779,6 +1779,8 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64); goto out; } +#endif +#ifdef CONFIG_PPC_BOOK3S_64 case KVM_PPC_GET_SMMU_INFO: { struct kvm_ppc_smmu_info info; struct kvm *kvm = filp->private_data; diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c index d659345a98d6..44fe4833910f 100644 --- a/arch/powerpc/mm/dump_linuxpagetables.c +++ b/arch/powerpc/mm/dump_linuxpagetables.c @@ -16,6 +16,7 @@ */ #include <linux/debugfs.h> #include <linux/fs.h> +#include <linux/hugetlb.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/sched.h> @@ -391,7 +392,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { addr = start + i * PMD_SIZE; - if (!pmd_none(*pmd)) + if (!pmd_none(*pmd) && !pmd_huge(*pmd)) /* pmd exists */ walk_pte(st, pmd, addr); else @@ -407,7 +408,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) for (i = 0; i < PTRS_PER_PUD; i++, pud++) { addr = start + i * PUD_SIZE; - if (!pud_none(*pud)) + if (!pud_none(*pud) && !pud_huge(*pud)) /* pud exists */ walk_pmd(st, pud, addr); else @@ -427,7 +428,7 @@ static void walk_pagetables(struct pg_state *st) */ for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { addr = KERN_VIRT_START + i * PGDIR_SIZE; - if (!pgd_none(*pgd)) + if (!pgd_none(*pgd) && !pgd_huge(*pgd)) /* pgd exists */ walk_pud(st, pgd, addr); else diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index d0441ad2a990..e508dff92535 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -59,7 +59,9 @@ union ctlreg0 { unsigned long lap : 1; /* Low-address-protection control */ unsigned long : 4; unsigned long edat : 1; /* Enhanced-DAT-enablement control */ - unsigned long : 4; + unsigned long : 2; + unsigned long iep : 1; /* Instruction-Execution-Protection */ + unsigned long : 1; unsigned long afp : 1; /* AFP-register control */ unsigned long vx : 1; /* Vector enablement control */ unsigned long : 7; diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 0206c8052328..df7b54ea956d 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -10,6 +10,7 @@ #include <linux/spinlock.h> #include <linux/kernel.h> #include <linux/time.h> +#include <linux/refcount.h> #include <uapi/asm/debug.h> #define DEBUG_MAX_LEVEL 6 /* debug levels range from 0 to 6 */ @@ -31,7 +32,7 @@ struct debug_view; typedef struct debug_info { struct debug_info* next; struct debug_info* prev; - atomic_t ref_count; + refcount_t ref_count; spinlock_t lock; int level; int nr_areas; diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h index 60323c21938b..37f617dfbede 100644 --- a/arch/s390/include/asm/dis.h +++ b/arch/s390/include/asm/dis.h @@ -40,6 +40,8 @@ static inline int insn_length(unsigned char code) return ((((int) code + 64) >> 7) + 1) << 1; } +struct pt_regs; + void show_code(struct pt_regs *regs); void print_fn_code(unsigned char *code, unsigned long len); int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len); diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 1293c4066cfc..28792ef82c83 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -27,12 +27,21 @@ * 2005-Dec Used as a template for s390 by Mike Grundy * <grundym@us.ibm.com> */ +#include <linux/types.h> #include <asm-generic/kprobes.h> #define BREAKPOINT_INSTRUCTION 0x0002 +#define FIXUP_PSW_NORMAL 0x08 +#define FIXUP_BRANCH_NOT_TAKEN 0x04 +#define FIXUP_RETURN_REGISTER 0x02 +#define FIXUP_NOT_REQUIRED 0x01 + +int probe_is_prohibited_opcode(u16 *insn); +int probe_get_fixup_type(u16 *insn); +int probe_is_insn_relative_long(u16 *insn); + #ifdef CONFIG_KPROBES -#include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> #include <linux/sched/task_stack.h> @@ -56,11 +65,6 @@ typedef u16 kprobe_opcode_t; #define KPROBE_SWAP_INST 0x10 -#define FIXUP_PSW_NORMAL 0x08 -#define FIXUP_BRANCH_NOT_TAKEN 0x04 -#define FIXUP_RETURN_REGISTER 0x02 -#define FIXUP_NOT_REQUIRED 0x01 - /* Architecture specific copy of original instruction */ struct arch_specific_insn { /* copy of original instruction */ @@ -90,10 +94,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr); int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); -int probe_is_prohibited_opcode(u16 *insn); -int probe_get_fixup_type(u16 *insn); -int probe_is_insn_relative_long(u16 *insn); - #define flush_insn_slot(p) do { } while (0) #endif /* CONFIG_KPROBES */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 9c3bd94204ac..495aedbaf447 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -45,6 +45,8 @@ #define KVM_REQ_ENABLE_IBS KVM_ARCH_REQ(0) #define KVM_REQ_DISABLE_IBS KVM_ARCH_REQ(1) #define KVM_REQ_ICPT_OPEREXC KVM_ARCH_REQ(2) +#define KVM_REQ_START_MIGRATION KVM_ARCH_REQ(3) +#define KVM_REQ_STOP_MIGRATION KVM_ARCH_REQ(4) #define SIGP_CTRL_C 0x80 #define SIGP_CTRL_SCN_MASK 0x3f @@ -56,7 +58,7 @@ union bsca_sigp_ctrl { __u8 r : 1; __u8 scn : 6; }; -} __packed; +}; union esca_sigp_ctrl { __u16 value; @@ -65,14 +67,14 @@ union esca_sigp_ctrl { __u8 reserved: 7; __u8 scn; }; -} __packed; +}; struct esca_entry { union esca_sigp_ctrl sigp_ctrl; __u16 reserved1[3]; __u64 sda; __u64 reserved2[6]; -} __packed; +}; struct bsca_entry { __u8 reserved0; @@ -80,7 +82,7 @@ struct bsca_entry { __u16 reserved[3]; __u64 sda; __u64 reserved2[2]; -} __attribute__((packed)); +}; union ipte_control { unsigned long val; @@ -97,7 +99,7 @@ struct bsca_block { __u64 mcn; __u64 reserved2; struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS]; -} __attribute__((packed)); +}; struct esca_block { union ipte_control ipte_control; @@ -105,7 +107,21 @@ struct esca_block { __u64 mcn[4]; __u64 reserved2[20]; struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS]; -} __packed; +}; + +/* + * This struct is used to store some machine check info from lowcore + * for machine checks that happen while the guest is running. + * This info in host's lowcore might be overwritten by a second machine + * check from host when host is in the machine check's high-level handling. + * The size is 24 bytes. + */ +struct mcck_volatile_info { + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 reserved; +}; #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 @@ -260,14 +276,15 @@ struct kvm_s390_sie_block { struct kvm_s390_itdb { __u8 data[256]; -} __packed; +}; struct sie_page { struct kvm_s390_sie_block sie_block; - __u8 reserved200[1024]; /* 0x0200 */ + struct mcck_volatile_info mcck_info; /* 0x0200 */ + __u8 reserved218[1000]; /* 0x0218 */ struct kvm_s390_itdb itdb; /* 0x0600 */ __u8 reserved700[2304]; /* 0x0700 */ -} __packed; +}; struct kvm_vcpu_stat { u64 exit_userspace; @@ -681,7 +698,7 @@ struct sie_page2 { __u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */ struct kvm_s390_crypto_cb crycb; /* 0x0800 */ u8 reserved900[0x1000 - 0x900]; /* 0x0900 */ -} __packed; +}; struct kvm_s390_vsie { struct mutex mutex; @@ -691,6 +708,12 @@ struct kvm_s390_vsie { struct page *pages[KVM_MAX_VCPUS]; }; +struct kvm_s390_migration_state { + unsigned long bitmap_size; /* in bits (number of guest pages) */ + atomic64_t dirty_pages; /* number of dirty pages */ + unsigned long *pgste_bitmap; +}; + struct kvm_arch{ void *sca; int use_esca; @@ -718,6 +741,7 @@ struct kvm_arch{ struct kvm_s390_crypto crypto; struct kvm_s390_vsie vsie; u64 epoch; + struct kvm_s390_migration_state *migration_state; /* subset of available cpu features enabled by user space */ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); }; diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h index e3e8895f5d3e..9d91cf3e427f 100644 --- a/arch/s390/include/asm/nmi.h +++ b/arch/s390/include/asm/nmi.h @@ -14,11 +14,24 @@ #include <linux/const.h> #include <linux/types.h> +#define MCIC_SUBCLASS_MASK (1ULL<<63 | 1ULL<<62 | 1ULL<<61 | \ + 1ULL<<59 | 1ULL<<58 | 1ULL<<56 | \ + 1ULL<<55 | 1ULL<<54 | 1ULL<<53 | \ + 1ULL<<52 | 1ULL<<47 | 1ULL<<46 | \ + 1ULL<<45 | 1ULL<<44) #define MCCK_CODE_SYSTEM_DAMAGE _BITUL(63) +#define MCCK_CODE_EXT_DAMAGE _BITUL(63 - 5) +#define MCCK_CODE_CP _BITUL(63 - 9) #define MCCK_CODE_CPU_TIMER_VALID _BITUL(63 - 46) #define MCCK_CODE_PSW_MWP_VALID _BITUL(63 - 20) #define MCCK_CODE_PSW_IA_VALID _BITUL(63 - 23) +#define MCCK_CR14_CR_PENDING_SUB_MASK (1 << 28) +#define MCCK_CR14_RECOVERY_SUB_MASK (1 << 27) +#define MCCK_CR14_DEGRAD_SUB_MASK (1 << 26) +#define MCCK_CR14_EXT_DAMAGE_SUB_MASK (1 << 25) +#define MCCK_CR14_WARN_SUB_MASK (1 << 24) + #ifndef __ASSEMBLY__ union mci { diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 60d395fdc864..5b1b247dfbca 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -20,6 +20,7 @@ #define CIF_FPU 4 /* restore FPU registers */ #define CIF_IGNORE_IRQ 5 /* ignore interrupt (for udelay) */ #define CIF_ENABLED_WAIT 6 /* in enabled wait state */ +#define CIF_MCCK_GUEST 7 /* machine check happening in guest */ #define _CIF_MCCK_PENDING _BITUL(CIF_MCCK_PENDING) #define _CIF_ASCE_PRIMARY _BITUL(CIF_ASCE_PRIMARY) @@ -28,6 +29,7 @@ #define _CIF_FPU _BITUL(CIF_FPU) #define _CIF_IGNORE_IRQ _BITUL(CIF_IGNORE_IRQ) #define _CIF_ENABLED_WAIT _BITUL(CIF_ENABLED_WAIT) +#define _CIF_MCCK_GUEST _BITUL(CIF_MCCK_GUEST) #ifndef __ASSEMBLY__ diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index 73bff45ced55..e784bed6ed7f 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -146,7 +146,7 @@ extern int topology_max_mnest; * Returns the maximum nesting level supported by the cpu topology code. * The current maximum level is 4 which is the drawer level. */ -static inline int topology_mnest_limit(void) +static inline unsigned char topology_mnest_limit(void) { return min(topology_max_mnest, 4); } diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 3dd2a1d308dd..69d09c39bbcd 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -28,6 +28,7 @@ #define KVM_DEV_FLIC_CLEAR_IO_IRQ 8 #define KVM_DEV_FLIC_AISM 9 #define KVM_DEV_FLIC_AIRQ_INJECT 10 +#define KVM_DEV_FLIC_AISM_ALL 11 /* * We can have up to 4*64k pending subchannels + 8 adapter interrupts, * as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts. @@ -53,6 +54,11 @@ struct kvm_s390_ais_req { __u16 mode; }; +struct kvm_s390_ais_all { + __u8 simm; + __u8 nimm; +}; + #define KVM_S390_IO_ADAPTER_MASK 1 #define KVM_S390_IO_ADAPTER_MAP 2 #define KVM_S390_IO_ADAPTER_UNMAP 3 @@ -70,6 +76,7 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_TOD 1 #define KVM_S390_VM_CRYPTO 2 #define KVM_S390_VM_CPU_MODEL 3 +#define KVM_S390_VM_MIGRATION 4 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 @@ -151,6 +158,11 @@ struct kvm_s390_vm_cpu_subfunc { #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW 2 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW 3 +/* kvm attributes for migration mode */ +#define KVM_S390_VM_MIGRATION_STOP 0 +#define KVM_S390_VM_MIGRATION_START 1 +#define KVM_S390_VM_MIGRATION_STATUS 2 + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 6bb29633e1f1..b65c414b6c0e 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -58,6 +58,9 @@ int main(void) OFFSET(__SF_BACKCHAIN, stack_frame, back_chain); OFFSET(__SF_GPRS, stack_frame, gprs); OFFSET(__SF_EMPTY, stack_frame, empty1); + OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]); + OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]); + OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]); BLANK(); /* timeval/timezone offsets for use by vdso */ OFFSET(__VDSO_UPD_COUNT, vdso_data, tb_update_count); diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 530226b6cb19..86b3e74f569e 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -277,7 +277,7 @@ debug_info_alloc(const char *name, int pages_per_area, int nr_areas, memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *)); memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS * sizeof(struct dentry*)); - atomic_set(&(rc->ref_count), 0); + refcount_set(&(rc->ref_count), 0); return rc; @@ -361,7 +361,7 @@ debug_info_create(const char *name, int pages_per_area, int nr_areas, debug_area_last = rc; rc->next = NULL; - debug_info_get(rc); + refcount_set(&rc->ref_count, 1); out: return rc; } @@ -416,7 +416,7 @@ static void debug_info_get(debug_info_t * db_info) { if (db_info) - atomic_inc(&db_info->ref_count); + refcount_inc(&db_info->ref_count); } /* @@ -431,7 +431,7 @@ debug_info_put(debug_info_t *db_info) if (!db_info) return; - if (atomic_dec_and_test(&db_info->ref_count)) { + if (refcount_dec_and_test(&db_info->ref_count)) { for (i = 0; i < DEBUG_MAX_VIEWS; i++) { if (!db_info->views[i]) continue; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index a5f5d3bb3dbc..3b4b158382ea 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -225,6 +225,7 @@ ENTRY(sie64a) jnz .Lsie_skip TSTMSK __LC_CPU_FLAGS,_CIF_FPU jo .Lsie_skip # exit if fp/vx regs changed +.Lsie_entry: sie 0(%r14) .Lsie_skip: ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE @@ -312,6 +313,7 @@ ENTRY(system_call) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) +.Lsysc_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) @@ -623,6 +625,7 @@ ENTRY(io_int_handler) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) +.Lio_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) @@ -1102,7 +1105,13 @@ cleanup_critical: .quad .Lsie_done .Lcleanup_sie: - lg %r9,__SF_EMPTY(%r15) # get control block pointer + cghi %r11,__LC_SAVE_AREA_ASYNC #Is this in normal interrupt? + je 1f + slg %r9,BASED(.Lsie_crit_mcck_start) + clg %r9,BASED(.Lsie_crit_mcck_length) + jh 1f + oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST +1: lg %r9,__SF_EMPTY(%r15) # get control block pointer ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce larl %r9,sie_exit # skip forward to sie_exit @@ -1174,15 +1183,23 @@ cleanup_critical: br %r14 .Lcleanup_sysc_restore: + # check if stpt has been executed clg %r9,BASED(.Lcleanup_sysc_restore_insn) + jh 0f + mvc __LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER + cghi %r11,__LC_SAVE_AREA_ASYNC je 0f + mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER +0: clg %r9,BASED(.Lcleanup_sysc_restore_insn+8) + je 1f lg %r9,24(%r11) # get saved pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) -0: lmg %r8,%r9,__LC_RETURN_PSW +1: lmg %r8,%r9,__LC_RETURN_PSW br %r14 .Lcleanup_sysc_restore_insn: + .quad .Lsysc_exit_timer .quad .Lsysc_done - 4 .Lcleanup_io_tif: @@ -1190,15 +1207,20 @@ cleanup_critical: br %r14 .Lcleanup_io_restore: + # check if stpt has been executed clg %r9,BASED(.Lcleanup_io_restore_insn) - je 0f + jh 0f + mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER +0: clg %r9,BASED(.Lcleanup_io_restore_insn+8) + je 1f lg %r9,24(%r11) # get saved r11 pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) -0: lmg %r8,%r9,__LC_RETURN_PSW +1: lmg %r8,%r9,__LC_RETURN_PSW br %r14 .Lcleanup_io_restore_insn: + .quad .Lio_exit_timer .quad .Lio_done - 4 .Lcleanup_idle: @@ -1274,6 +1296,10 @@ cleanup_critical: .quad .Lsie_gmap .Lsie_critical_length: .quad .Lsie_done - .Lsie_gmap +.Lsie_crit_mcck_start: + .quad .Lsie_entry +.Lsie_crit_mcck_length: + .quad .Lsie_skip - .Lsie_entry #endif .section .rodata, "a" diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 27477f34cc0a..d03a6d12c4bd 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -173,6 +173,8 @@ int __init ftrace_dyn_arch_init(void) return 0; } +#ifdef CONFIG_MODULES + static int __init ftrace_plt_init(void) { unsigned int *ip; @@ -191,6 +193,8 @@ static int __init ftrace_plt_init(void) } device_initcall(ftrace_plt_init); +#endif /* CONFIG_MODULES */ + #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * Hook the return address and push it in the stack of return addresses diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 985589523970..31d03a84126c 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -25,6 +25,8 @@ #include <asm/crw.h> #include <asm/switch_to.h> #include <asm/ctl_reg.h> +#include <asm/asm-offsets.h> +#include <linux/kvm_host.h> struct mcck_struct { unsigned int kill_task : 1; @@ -274,12 +276,39 @@ static int notrace s390_validate_registers(union mci mci, int umode) return kill_task; } +/* + * Backup the guest's machine check info to its description block + */ +static void notrace s390_backup_mcck_info(struct pt_regs *regs) +{ + struct mcck_volatile_info *mcck_backup; + struct sie_page *sie_page; + + /* r14 contains the sie block, which was set in sie64a */ + struct kvm_s390_sie_block *sie_block = + (struct kvm_s390_sie_block *) regs->gprs[14]; + + if (sie_block == NULL) + /* Something's seriously wrong, stop system. */ + s390_handle_damage(); + + sie_page = container_of(sie_block, struct sie_page, sie_block); + mcck_backup = &sie_page->mcck_info; + mcck_backup->mcic = S390_lowcore.mcck_interruption_code & + ~(MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE); + mcck_backup->ext_damage_code = S390_lowcore.external_damage_code; + mcck_backup->failing_storage_address + = S390_lowcore.failing_storage_address; +} + #define MAX_IPD_COUNT 29 #define MAX_IPD_TIME (5 * 60 * USEC_PER_SEC) /* 5 minutes */ #define ED_STP_ISLAND 6 /* External damage STP island check */ #define ED_STP_SYNC 7 /* External damage STP sync check */ +#define MCCK_CODE_NO_GUEST (MCCK_CODE_CP | MCCK_CODE_EXT_DAMAGE) + /* * machine check handler. */ @@ -291,6 +320,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) struct mcck_struct *mcck; unsigned long long tmp; union mci mci; + unsigned long mcck_dam_code; nmi_enter(); inc_irq_stat(NMI_NMI); @@ -301,7 +331,13 @@ void notrace s390_do_machine_check(struct pt_regs *regs) /* System damage -> stopping machine */ s390_handle_damage(); } - if (mci.pd) { + + /* + * Reinject the instruction processing damages' machine checks + * including Delayed Access Exception into the guest + * instead of damaging the host if they happen in the guest. + */ + if (mci.pd && !test_cpu_flag(CIF_MCCK_GUEST)) { if (mci.b) { /* Processing backup -> verify if we can survive this */ u64 z_mcic, o_mcic, t_mcic; @@ -345,6 +381,14 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck->mcck_code = mci.val; set_cpu_flag(CIF_MCCK_PENDING); } + + /* + * Backup the machine check's info if it happens when the guest + * is running. + */ + if (test_cpu_flag(CIF_MCCK_GUEST)) + s390_backup_mcck_info(regs); + if (mci.cd) { /* Timing facility damage */ s390_handle_damage(); @@ -358,15 +402,22 @@ void notrace s390_do_machine_check(struct pt_regs *regs) if (mcck->stp_queue) set_cpu_flag(CIF_MCCK_PENDING); } - if (mci.se) - /* Storage error uncorrected */ - s390_handle_damage(); - if (mci.ke) - /* Storage key-error uncorrected */ - s390_handle_damage(); - if (mci.ds && mci.fa) - /* Storage degradation */ - s390_handle_damage(); + + /* + * Reinject storage related machine checks into the guest if they + * happen when the guest is running. + */ + if (!test_cpu_flag(CIF_MCCK_GUEST)) { + if (mci.se) + /* Storage error uncorrected */ + s390_handle_damage(); + if (mci.ke) + /* Storage key-error uncorrected */ + s390_handle_damage(); + if (mci.ds && mci.fa) + /* Storage degradation */ + s390_handle_damage(); + } if (mci.cp) { /* Channel report word pending */ mcck->channel_report = 1; @@ -377,6 +428,19 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck->warning = 1; set_cpu_flag(CIF_MCCK_PENDING); } + + /* + * If there are only Channel Report Pending and External Damage + * machine checks, they will not be reinjected into the guest + * because they refer to host conditions only. + */ + mcck_dam_code = (mci.val & MCIC_SUBCLASS_MASK); + if (test_cpu_flag(CIF_MCCK_GUEST) && + (mcck_dam_code & MCCK_CODE_NO_GUEST) != mcck_dam_code) { + /* Set exit reason code for host's later handling */ + *((long *)(regs->gprs[15] + __SF_SIE_REASON)) = -EINTR; + } + clear_cpu_flag(CIF_MCCK_GUEST); nmi_exit(); } diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 72307f108c40..6e2c42bd1c3b 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -31,8 +31,14 @@ SECTIONS { . = 0x00000000; .text : { - _text = .; /* Text and read-only data */ + /* Text and read-only data */ HEAD_TEXT + /* + * E.g. perf doesn't like symbols starting at address zero, + * therefore skip the initial PSW and channel program located + * at address zero and let _text start at 0x200. + */ + _text = 0x200; TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 9da243d94cc3..17e3a4e71bc9 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -89,7 +89,7 @@ struct region3_table_entry_fc1 { unsigned long f : 1; /* Fetch-Protection Bit */ unsigned long fc : 1; /* Format-Control */ unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long co : 1; /* Change-Recording Override */ + unsigned long iep: 1; /* Instruction-Execution-Protection */ unsigned long : 2; unsigned long i : 1; /* Region-Invalid Bit */ unsigned long cr : 1; /* Common-Region Bit */ @@ -131,7 +131,7 @@ struct segment_entry_fc1 { unsigned long f : 1; /* Fetch-Protection Bit */ unsigned long fc : 1; /* Format-Control */ unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long co : 1; /* Change-Recording Override */ + unsigned long iep: 1; /* Instruction-Execution-Protection */ unsigned long : 2; unsigned long i : 1; /* Segment-Invalid Bit */ unsigned long cs : 1; /* Common-Segment Bit */ @@ -168,7 +168,8 @@ union page_table_entry { unsigned long z : 1; /* Zero Bit */ unsigned long i : 1; /* Page-Invalid Bit */ unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long : 9; + unsigned long iep: 1; /* Instruction-Execution-Protection */ + unsigned long : 8; }; }; @@ -241,7 +242,7 @@ struct ale { unsigned long asteo : 25; /* ASN-Second-Table-Entry Origin */ unsigned long : 6; unsigned long astesn : 32; /* ASTE Sequence Number */ -} __packed; +}; struct aste { unsigned long i : 1; /* ASX-Invalid Bit */ @@ -257,7 +258,7 @@ struct aste { unsigned long ald : 32; unsigned long astesn : 32; /* .. more fields there */ -} __packed; +}; int ipte_lock_held(struct kvm_vcpu *vcpu) { @@ -485,6 +486,7 @@ enum prot_type { PROT_TYPE_KEYC = 1, PROT_TYPE_ALC = 2, PROT_TYPE_DAT = 3, + PROT_TYPE_IEP = 4, }; static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, @@ -500,6 +502,9 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, switch (code) { case PGM_PROTECTION: switch (prot) { + case PROT_TYPE_IEP: + tec->b61 = 1; + /* FALL THROUGH */ case PROT_TYPE_LA: tec->b56 = 1; break; @@ -591,6 +596,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * @gpa: points to where guest physical (absolute) address should be stored * @asce: effective asce * @mode: indicates the access mode to be used + * @prot: returns the type for protection exceptions * * Translate a guest virtual address into a guest absolute address by means * of dynamic address translation as specified by the architecture. @@ -606,19 +612,21 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) */ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, unsigned long *gpa, const union asce asce, - enum gacc_mode mode) + enum gacc_mode mode, enum prot_type *prot) { union vaddress vaddr = {.addr = gva}; union raddress raddr = {.addr = gva}; union page_table_entry pte; int dat_protection = 0; + int iep_protection = 0; union ctlreg0 ctlreg0; unsigned long ptr; - int edat1, edat2; + int edat1, edat2, iep; ctlreg0.val = vcpu->arch.sie_block->gcr[0]; edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8); edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78); + iep = ctlreg0.iep && test_kvm_facility(vcpu->kvm, 130); if (asce.r) goto real_address; ptr = asce.origin * 4096; @@ -702,6 +710,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, return PGM_TRANSLATION_SPEC; if (rtte.fc && edat2) { dat_protection |= rtte.fc1.p; + iep_protection = rtte.fc1.iep; raddr.rfaa = rtte.fc1.rfaa; goto absolute_address; } @@ -729,6 +738,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, return PGM_TRANSLATION_SPEC; if (ste.fc && edat1) { dat_protection |= ste.fc1.p; + iep_protection = ste.fc1.iep; raddr.sfaa = ste.fc1.sfaa; goto absolute_address; } @@ -745,12 +755,19 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, if (pte.z) return PGM_TRANSLATION_SPEC; dat_protection |= pte.p; + iep_protection = pte.iep; raddr.pfra = pte.pfra; real_address: raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr); absolute_address: - if (mode == GACC_STORE && dat_protection) + if (mode == GACC_STORE && dat_protection) { + *prot = PROT_TYPE_DAT; return PGM_PROTECTION; + } + if (mode == GACC_IFETCH && iep_protection && iep) { + *prot = PROT_TYPE_IEP; + return PGM_PROTECTION; + } if (kvm_is_error_gpa(vcpu->kvm, raddr.addr)) return PGM_ADDRESSING; *gpa = raddr.addr; @@ -782,6 +799,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, { psw_t *psw = &vcpu->arch.sie_block->gpsw; int lap_enabled, rc = 0; + enum prot_type prot; lap_enabled = low_address_protection_enabled(vcpu, asce); while (nr_pages) { @@ -791,7 +809,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, PROT_TYPE_LA); ga &= PAGE_MASK; if (psw_bits(*psw).t) { - rc = guest_translate(vcpu, ga, pages, asce, mode); + rc = guest_translate(vcpu, ga, pages, asce, mode, &prot); if (rc < 0) return rc; } else { @@ -800,7 +818,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, rc = PGM_ADDRESSING; } if (rc) - return trans_exc(vcpu, rc, ga, ar, mode, PROT_TYPE_DAT); + return trans_exc(vcpu, rc, ga, ar, mode, prot); ga += PAGE_SIZE; pages++; nr_pages--; @@ -886,6 +904,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, unsigned long *gpa, enum gacc_mode mode) { psw_t *psw = &vcpu->arch.sie_block->gpsw; + enum prot_type prot; union asce asce; int rc; @@ -900,9 +919,9 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, } if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */ - rc = guest_translate(vcpu, gva, gpa, asce, mode); + rc = guest_translate(vcpu, gva, gpa, asce, mode, &prot); if (rc > 0) - return trans_exc(vcpu, rc, gva, 0, mode, PROT_TYPE_DAT); + return trans_exc(vcpu, rc, gva, 0, mode, prot); } else { *gpa = kvm_s390_real_to_abs(vcpu, gva); if (kvm_is_error_gpa(vcpu->kvm, *gpa)) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index caf15c8a8948..f2c78fc1852d 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -251,8 +251,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; + /* + * Check both floating and local interrupt's cr14 because + * bit IRQ_PEND_MCHK_REP could be set in both cases. + */ if (!(vcpu->arch.sie_block->gcr[14] & - vcpu->kvm->arch.float_int.mchk.cr14)) + (vcpu->kvm->arch.float_int.mchk.cr14 | + vcpu->arch.local_int.irq.mchk.cr14))) __clear_bit(IRQ_PEND_MCHK_REP, &active_mask); /* @@ -1876,6 +1881,28 @@ out: return ret < 0 ? ret : n; } +static int flic_ais_mode_get_all(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + struct kvm_s390_ais_all ais; + + if (attr->attr < sizeof(ais)) + return -EINVAL; + + if (!test_kvm_facility(kvm, 72)) + return -ENOTSUPP; + + mutex_lock(&fi->ais_lock); + ais.simm = fi->simm; + ais.nimm = fi->nimm; + mutex_unlock(&fi->ais_lock); + + if (copy_to_user((void __user *)attr->addr, &ais, sizeof(ais))) + return -EFAULT; + + return 0; +} + static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r; @@ -1885,6 +1912,9 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr, attr->attr); break; + case KVM_DEV_FLIC_AISM_ALL: + r = flic_ais_mode_get_all(dev->kvm, attr); + break; default: r = -EINVAL; } @@ -2235,6 +2265,25 @@ static int flic_inject_airq(struct kvm *kvm, struct kvm_device_attr *attr) return kvm_s390_inject_airq(kvm, adapter); } +static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + struct kvm_s390_ais_all ais; + + if (!test_kvm_facility(kvm, 72)) + return -ENOTSUPP; + + if (copy_from_user(&ais, (void __user *)attr->addr, sizeof(ais))) + return -EFAULT; + + mutex_lock(&fi->ais_lock); + fi->simm = ais.simm; + fi->nimm = ais.nimm; + mutex_unlock(&fi->ais_lock); + + return 0; +} + static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = 0; @@ -2277,6 +2326,9 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) case KVM_DEV_FLIC_AIRQ_INJECT: r = flic_inject_airq(dev->kvm, attr); break; + case KVM_DEV_FLIC_AISM_ALL: + r = flic_ais_mode_set_all(dev->kvm, attr); + break; default: r = -EINVAL; } @@ -2298,6 +2350,7 @@ static int flic_has_attr(struct kvm_device *dev, case KVM_DEV_FLIC_CLEAR_IO_IRQ: case KVM_DEV_FLIC_AISM: case KVM_DEV_FLIC_AIRQ_INJECT: + case KVM_DEV_FLIC_AISM_ALL: return 0; } return -ENXIO; @@ -2415,6 +2468,42 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e, return ret; } +/* + * Inject the machine check to the guest. + */ +void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, + struct mcck_volatile_info *mcck_info) +{ + struct kvm_s390_interrupt_info inti; + struct kvm_s390_irq irq; + struct kvm_s390_mchk_info *mchk; + union mci mci; + __u64 cr14 = 0; /* upper bits are not used */ + + mci.val = mcck_info->mcic; + if (mci.sr) + cr14 |= MCCK_CR14_RECOVERY_SUB_MASK; + if (mci.dg) + cr14 |= MCCK_CR14_DEGRAD_SUB_MASK; + if (mci.w) + cr14 |= MCCK_CR14_WARN_SUB_MASK; + + mchk = mci.ck ? &inti.mchk : &irq.u.mchk; + mchk->cr14 = cr14; + mchk->mcic = mcck_info->mcic; + mchk->ext_damage_code = mcck_info->ext_damage_code; + mchk->failing_storage_address = mcck_info->failing_storage_address; + if (mci.ck) { + /* Inject the floating machine check */ + inti.type = KVM_S390_MCHK; + WARN_ON_ONCE(__inject_vm(vcpu->kvm, &inti)); + } else { + /* Inject the machine check to specified vcpu */ + irq.type = KVM_S390_MCHK; + WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq)); + } +} + int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ad41e0fa3a21..ef6419654c16 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -30,6 +30,7 @@ #include <linux/vmalloc.h> #include <linux/bitmap.h> #include <linux/sched/signal.h> +#include <linux/string.h> #include <asm/asm-offsets.h> #include <asm/lowcore.h> @@ -386,6 +387,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_SKEYS: case KVM_CAP_S390_IRQ_STATE: case KVM_CAP_S390_USER_INSTR0: + case KVM_CAP_S390_CMMA_MIGRATION: case KVM_CAP_S390_AIS: r = 1; break; @@ -750,6 +752,129 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) return 0; } +static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) +{ + int cx; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(cx, vcpu, kvm) + kvm_s390_sync_request(req, vcpu); +} + +/* + * Must be called with kvm->srcu held to avoid races on memslots, and with + * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration. + */ +static int kvm_s390_vm_start_migration(struct kvm *kvm) +{ + struct kvm_s390_migration_state *mgs; + struct kvm_memory_slot *ms; + /* should be the only one */ + struct kvm_memslots *slots; + unsigned long ram_pages; + int slotnr; + + /* migration mode already enabled */ + if (kvm->arch.migration_state) + return 0; + + slots = kvm_memslots(kvm); + if (!slots || !slots->used_slots) + return -EINVAL; + + mgs = kzalloc(sizeof(*mgs), GFP_KERNEL); + if (!mgs) + return -ENOMEM; + kvm->arch.migration_state = mgs; + + if (kvm->arch.use_cmma) { + /* + * Get the last slot. They should be sorted by base_gfn, so the + * last slot is also the one at the end of the address space. + * We have verified above that at least one slot is present. + */ + ms = slots->memslots + slots->used_slots - 1; + /* round up so we only use full longs */ + ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG); + /* allocate enough bytes to store all the bits */ + mgs->pgste_bitmap = vmalloc(ram_pages / 8); + if (!mgs->pgste_bitmap) { + kfree(mgs); + kvm->arch.migration_state = NULL; + return -ENOMEM; + } + + mgs->bitmap_size = ram_pages; + atomic64_set(&mgs->dirty_pages, ram_pages); + /* mark all the pages in active slots as dirty */ + for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { + ms = slots->memslots + slotnr; + bitmap_set(mgs->pgste_bitmap, ms->base_gfn, ms->npages); + } + + kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION); + } + return 0; +} + +/* + * Must be called with kvm->lock to avoid races with ourselves and + * kvm_s390_vm_start_migration. + */ +static int kvm_s390_vm_stop_migration(struct kvm *kvm) +{ + struct kvm_s390_migration_state *mgs; + + /* migration mode already disabled */ + if (!kvm->arch.migration_state) + return 0; + mgs = kvm->arch.migration_state; + kvm->arch.migration_state = NULL; + + if (kvm->arch.use_cmma) { + kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); + vfree(mgs->pgste_bitmap); + } + kfree(mgs); + return 0; +} + +static int kvm_s390_vm_set_migration(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + int idx, res = -ENXIO; + + mutex_lock(&kvm->lock); + switch (attr->attr) { + case KVM_S390_VM_MIGRATION_START: + idx = srcu_read_lock(&kvm->srcu); + res = kvm_s390_vm_start_migration(kvm); + srcu_read_unlock(&kvm->srcu, idx); + break; + case KVM_S390_VM_MIGRATION_STOP: + res = kvm_s390_vm_stop_migration(kvm); + break; + default: + break; + } + mutex_unlock(&kvm->lock); + + return res; +} + +static int kvm_s390_vm_get_migration(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + u64 mig = (kvm->arch.migration_state != NULL); + + if (attr->attr != KVM_S390_VM_MIGRATION_STATUS) + return -ENXIO; + + if (copy_to_user((void __user *)attr->addr, &mig, sizeof(mig))) + return -EFAULT; + return 0; +} + static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) { u8 gtod_high; @@ -1090,6 +1215,9 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CRYPTO: ret = kvm_s390_vm_set_crypto(kvm, attr); break; + case KVM_S390_VM_MIGRATION: + ret = kvm_s390_vm_set_migration(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1112,6 +1240,9 @@ static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CPU_MODEL: ret = kvm_s390_get_cpu_model(kvm, attr); break; + case KVM_S390_VM_MIGRATION: + ret = kvm_s390_vm_get_migration(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1179,6 +1310,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) break; } break; + case KVM_S390_VM_MIGRATION: + ret = 0; + break; default: ret = -ENXIO; break; @@ -1286,6 +1420,182 @@ out: return r; } +/* + * Base address and length must be sent at the start of each block, therefore + * it's cheaper to send some clean data, as long as it's less than the size of + * two longs. + */ +#define KVM_S390_MAX_BIT_DISTANCE (2 * sizeof(void *)) +/* for consistency */ +#define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) + +/* + * This function searches for the next page with dirty CMMA attributes, and + * saves the attributes in the buffer up to either the end of the buffer or + * until a block of at least KVM_S390_MAX_BIT_DISTANCE clean bits is found; + * no trailing clean bytes are saved. + * In case no dirty bits were found, or if CMMA was not enabled or used, the + * output buffer will indicate 0 as length. + */ +static int kvm_s390_get_cmma_bits(struct kvm *kvm, + struct kvm_s390_cmma_log *args) +{ + struct kvm_s390_migration_state *s = kvm->arch.migration_state; + unsigned long bufsize, hva, pgstev, i, next, cur; + int srcu_idx, peek, r = 0, rr; + u8 *res; + + cur = args->start_gfn; + i = next = pgstev = 0; + + if (unlikely(!kvm->arch.use_cmma)) + return -ENXIO; + /* Invalid/unsupported flags were specified */ + if (args->flags & ~KVM_S390_CMMA_PEEK) + return -EINVAL; + /* Migration mode query, and we are not doing a migration */ + peek = !!(args->flags & KVM_S390_CMMA_PEEK); + if (!peek && !s) + return -EINVAL; + /* CMMA is disabled or was not used, or the buffer has length zero */ + bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX); + if (!bufsize || !kvm->mm->context.use_cmma) { + memset(args, 0, sizeof(*args)); + return 0; + } + + if (!peek) { + /* We are not peeking, and there are no dirty pages */ + if (!atomic64_read(&s->dirty_pages)) { + memset(args, 0, sizeof(*args)); + return 0; + } + cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, + args->start_gfn); + if (cur >= s->bitmap_size) /* nothing found, loop back */ + cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, 0); + if (cur >= s->bitmap_size) { /* again! (very unlikely) */ + memset(args, 0, sizeof(*args)); + return 0; + } + next = find_next_bit(s->pgste_bitmap, s->bitmap_size, cur + 1); + } + + res = vmalloc(bufsize); + if (!res) + return -ENOMEM; + + args->start_gfn = cur; + + down_read(&kvm->mm->mmap_sem); + srcu_idx = srcu_read_lock(&kvm->srcu); + while (i < bufsize) { + hva = gfn_to_hva(kvm, cur); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + break; + } + /* decrement only if we actually flipped the bit to 0 */ + if (!peek && test_and_clear_bit(cur, s->pgste_bitmap)) + atomic64_dec(&s->dirty_pages); + r = get_pgste(kvm->mm, hva, &pgstev); + if (r < 0) + pgstev = 0; + /* save the value */ + res[i++] = (pgstev >> 24) & 0x3; + /* + * if the next bit is too far away, stop. + * if we reached the previous "next", find the next one + */ + if (!peek) { + if (next > cur + KVM_S390_MAX_BIT_DISTANCE) + break; + if (cur == next) + next = find_next_bit(s->pgste_bitmap, + s->bitmap_size, cur + 1); + /* reached the end of the bitmap or of the buffer, stop */ + if ((next >= s->bitmap_size) || + (next >= args->start_gfn + bufsize)) + break; + } + cur++; + } + srcu_read_unlock(&kvm->srcu, srcu_idx); + up_read(&kvm->mm->mmap_sem); + args->count = i; + args->remaining = s ? atomic64_read(&s->dirty_pages) : 0; + + rr = copy_to_user((void __user *)args->values, res, args->count); + if (rr) + r = -EFAULT; + + vfree(res); + return r; +} + +/* + * This function sets the CMMA attributes for the given pages. If the input + * buffer has zero length, no action is taken, otherwise the attributes are + * set and the mm->context.use_cmma flag is set. + */ +static int kvm_s390_set_cmma_bits(struct kvm *kvm, + const struct kvm_s390_cmma_log *args) +{ + unsigned long hva, mask, pgstev, i; + uint8_t *bits; + int srcu_idx, r = 0; + + mask = args->mask; + + if (!kvm->arch.use_cmma) + return -ENXIO; + /* invalid/unsupported flags */ + if (args->flags != 0) + return -EINVAL; + /* Enforce sane limit on memory allocation */ + if (args->count > KVM_S390_CMMA_SIZE_MAX) + return -EINVAL; + /* Nothing to do */ + if (args->count == 0) + return 0; + + bits = vmalloc(sizeof(*bits) * args->count); + if (!bits) + return -ENOMEM; + + r = copy_from_user(bits, (void __user *)args->values, args->count); + if (r) { + r = -EFAULT; + goto out; + } + + down_read(&kvm->mm->mmap_sem); + srcu_idx = srcu_read_lock(&kvm->srcu); + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + break; + } + + pgstev = bits[i]; + pgstev = pgstev << 24; + mask &= _PGSTE_GPS_USAGE_MASK; + set_pgste_bits(kvm->mm, hva, mask, pgstev); + } + srcu_read_unlock(&kvm->srcu, srcu_idx); + up_read(&kvm->mm->mmap_sem); + + if (!kvm->mm->context.use_cmma) { + down_write(&kvm->mm->mmap_sem); + kvm->mm->context.use_cmma = 1; + up_write(&kvm->mm->mmap_sem); + } +out: + vfree(bits); + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1364,6 +1674,29 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_s390_set_skeys(kvm, &args); break; } + case KVM_S390_GET_CMMA_BITS: { + struct kvm_s390_cmma_log args; + + r = -EFAULT; + if (copy_from_user(&args, argp, sizeof(args))) + break; + r = kvm_s390_get_cmma_bits(kvm, &args); + if (!r) { + r = copy_to_user(argp, &args, sizeof(args)); + if (r) + r = -EFAULT; + } + break; + } + case KVM_S390_SET_CMMA_BITS: { + struct kvm_s390_cmma_log args; + + r = -EFAULT; + if (copy_from_user(&args, argp, sizeof(args))) + break; + r = kvm_s390_set_cmma_bits(kvm, &args); + break; + } default: r = -ENOTTY; } @@ -1633,6 +1966,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_s390_destroy_adapters(kvm); kvm_s390_clear_float_irqs(kvm); kvm_s390_vsie_destroy(kvm); + if (kvm->arch.migration_state) { + vfree(kvm->arch.migration_state->pgste_bitmap); + kfree(kvm->arch.migration_state); + } KVM_EVENT(3, "vm 0x%pK destroyed", kvm); } @@ -1977,7 +2314,6 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) if (!vcpu->arch.sie_block->cbrlo) return -ENOMEM; - vcpu->arch.sie_block->ecb2 |= ECB2_CMMA; vcpu->arch.sie_block->ecb2 &= ~ECB2_PFMFI; return 0; } @@ -2069,6 +2405,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, if (!vcpu) goto out; + BUILD_BUG_ON(sizeof(struct sie_page) != 4096); sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL); if (!sie_page) goto out_free_cpu; @@ -2489,6 +2826,27 @@ retry: goto retry; } + if (kvm_check_request(KVM_REQ_START_MIGRATION, vcpu)) { + /* + * Disable CMMA virtualization; we will emulate the ESSA + * instruction manually, in order to provide additional + * functionalities needed for live migration. + */ + vcpu->arch.sie_block->ecb2 &= ~ECB2_CMMA; + goto retry; + } + + if (kvm_check_request(KVM_REQ_STOP_MIGRATION, vcpu)) { + /* + * Re-enable CMMA virtualization if CMMA is available and + * was used. + */ + if ((vcpu->kvm->arch.use_cmma) && + (vcpu->kvm->mm->context.use_cmma)) + vcpu->arch.sie_block->ecb2 |= ECB2_CMMA; + goto retry; + } + /* nothing to do, just clear the request */ kvm_clear_request(KVM_REQ_UNHALT, vcpu); @@ -2683,6 +3041,9 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) { + struct mcck_volatile_info *mcck_info; + struct sie_page *sie_page; + VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode); @@ -2693,6 +3054,15 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14; vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15; + if (exit_reason == -EINTR) { + VCPU_EVENT(vcpu, 3, "%s", "machine check"); + sie_page = container_of(vcpu->arch.sie_block, + struct sie_page, sie_block); + mcck_info = &sie_page->mcck_info; + kvm_s390_reinject_machine_check(vcpu, mcck_info); + return 0; + } + if (vcpu->arch.sie_block->icptcode > 0) { int rc = kvm_handle_sie_intercept(vcpu); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 55f5c8457d6d..6fedc8bc7a37 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -397,4 +397,6 @@ static inline int kvm_s390_use_sca_entries(void) */ return sclp.has_sigpif; } +void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, + struct mcck_volatile_info *mcck_info); #endif diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index c03106c428cf..a226c459809b 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -24,6 +24,7 @@ #include <asm/ebcdic.h> #include <asm/sysinfo.h> #include <asm/pgtable.h> +#include <asm/page-states.h> #include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/io.h> @@ -949,13 +950,72 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) return 0; } +static inline int do_essa(struct kvm_vcpu *vcpu, const int orc) +{ + struct kvm_s390_migration_state *ms = vcpu->kvm->arch.migration_state; + int r1, r2, nappended, entries; + unsigned long gfn, hva, res, pgstev, ptev; + unsigned long *cbrlo; + + /* + * We don't need to set SD.FPF.SK to 1 here, because if we have a + * machine check here we either handle it or crash + */ + + kvm_s390_get_regs_rre(vcpu, &r1, &r2); + gfn = vcpu->run->s.regs.gprs[r2] >> PAGE_SHIFT; + hva = gfn_to_hva(vcpu->kvm, gfn); + entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3; + + if (kvm_is_error_hva(hva)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + nappended = pgste_perform_essa(vcpu->kvm->mm, hva, orc, &ptev, &pgstev); + if (nappended < 0) { + res = orc ? 0x10 : 0; + vcpu->run->s.regs.gprs[r1] = res; /* Exception Indication */ + return 0; + } + res = (pgstev & _PGSTE_GPS_USAGE_MASK) >> 22; + /* + * Set the block-content state part of the result. 0 means resident, so + * nothing to do if the page is valid. 2 is for preserved pages + * (non-present and non-zero), and 3 for zero pages (non-present and + * zero). + */ + if (ptev & _PAGE_INVALID) { + res |= 2; + if (pgstev & _PGSTE_GPS_ZERO) + res |= 1; + } + vcpu->run->s.regs.gprs[r1] = res; + /* + * It is possible that all the normal 511 slots were full, in which case + * we will now write in the 512th slot, which is reserved for host use. + * In both cases we let the normal essa handling code process all the + * slots, including the reserved one, if needed. + */ + if (nappended > 0) { + cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo & PAGE_MASK); + cbrlo[entries] = gfn << PAGE_SHIFT; + } + + if (orc) { + /* increment only if we are really flipping the bit to 1 */ + if (!test_and_set_bit(gfn, ms->pgste_bitmap)) + atomic64_inc(&ms->dirty_pages); + } + + return nappended; +} + static int handle_essa(struct kvm_vcpu *vcpu) { /* entries expected to be 1FF */ int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3; unsigned long *cbrlo; struct gmap *gmap; - int i; + int i, orc; VCPU_EVENT(vcpu, 4, "ESSA: release %d pages", entries); gmap = vcpu->arch.gmap; @@ -965,12 +1025,45 @@ static int handle_essa(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - - if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6) + /* Check for invalid operation request code */ + orc = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; + if (orc > ESSA_MAX) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - /* Retry the ESSA instruction */ - kvm_s390_retry_instr(vcpu); + if (likely(!vcpu->kvm->arch.migration_state)) { + /* + * CMMA is enabled in the KVM settings, but is disabled in + * the SIE block and in the mm_context, and we are not doing + * a migration. Enable CMMA in the mm_context. + * Since we need to take a write lock to write to the context + * to avoid races with storage keys handling, we check if the + * value really needs to be written to; if the value is + * already correct, we do nothing and avoid the lock. + */ + if (vcpu->kvm->mm->context.use_cmma == 0) { + down_write(&vcpu->kvm->mm->mmap_sem); + vcpu->kvm->mm->context.use_cmma = 1; + up_write(&vcpu->kvm->mm->mmap_sem); + } + /* + * If we are here, we are supposed to have CMMA enabled in + * the SIE block. Enabling CMMA works on a per-CPU basis, + * while the context use_cmma flag is per process. + * It's possible that the context flag is enabled and the + * SIE flag is not, so we set the flag always; if it was + * already set, nothing changes, otherwise we enable it + * on this CPU too. + */ + vcpu->arch.sie_block->ecb2 |= ECB2_CMMA; + /* Retry the ESSA instruction */ + kvm_s390_retry_instr(vcpu); + } else { + /* Account for the possible extra cbrl entry */ + i = do_essa(vcpu, orc); + if (i < 0) + return i; + entries += i; + } vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo); down_read(&gmap->mm->mmap_sem); diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 4719ecb9ab42..715c19c45d9a 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -26,16 +26,21 @@ struct vsie_page { struct kvm_s390_sie_block scb_s; /* 0x0000 */ + /* + * the backup info for machine check. ensure it's at + * the same offset as that in struct sie_page! + */ + struct mcck_volatile_info mcck_info; /* 0x0200 */ /* the pinned originial scb */ - struct kvm_s390_sie_block *scb_o; /* 0x0200 */ + struct kvm_s390_sie_block *scb_o; /* 0x0218 */ /* the shadow gmap in use by the vsie_page */ - struct gmap *gmap; /* 0x0208 */ + struct gmap *gmap; /* 0x0220 */ /* address of the last reported fault to guest2 */ - unsigned long fault_addr; /* 0x0210 */ - __u8 reserved[0x0700 - 0x0218]; /* 0x0218 */ + unsigned long fault_addr; /* 0x0228 */ + __u8 reserved[0x0700 - 0x0230]; /* 0x0230 */ struct kvm_s390_crypto_cb crycb; /* 0x0700 */ __u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */ -} __packed; +}; /* trigger a validity icpt for the given scb */ static int set_validity_icpt(struct kvm_s390_sie_block *scb, @@ -801,6 +806,8 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + struct mcck_volatile_info *mcck_info; + struct sie_page *sie_page; int rc; handle_last_fault(vcpu, vsie_page); @@ -822,6 +829,14 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) local_irq_enable(); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + if (rc == -EINTR) { + VCPU_EVENT(vcpu, 3, "%s", "machine check"); + sie_page = container_of(scb_s, struct sie_page, sie_block); + mcck_info = &sie_page->mcck_info; + kvm_s390_reinject_machine_check(vcpu, mcck_info); + return 0; + } + if (rc > 0) rc = 0; /* we could still have an icpt */ else if (rc == -EFAULT) diff --git a/arch/s390/lib/probes.c b/arch/s390/lib/probes.c index ae90e1ae3607..1963ddbf4ab3 100644 --- a/arch/s390/lib/probes.c +++ b/arch/s390/lib/probes.c @@ -4,6 +4,7 @@ * Copyright IBM Corp. 2014 */ +#include <linux/errno.h> #include <asm/kprobes.h> #include <asm/dis.h> diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 1e5bb2b86c42..b3bd3f23b8e8 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -337,8 +337,8 @@ long __strncpy_from_user(char *dst, const char __user *src, long size) return 0; done = 0; do { - offset = (size_t)src & ~PAGE_MASK; - len = min(size - done, PAGE_SIZE - offset); + offset = (size_t)src & (L1_CACHE_BYTES - 1); + len = min(size - done, L1_CACHE_BYTES - offset); if (copy_from_user(dst, src, len)) return -EFAULT; len_str = strnlen(dst, len); diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index dcbf985ab243..d1f837dc77a4 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -24,9 +24,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { - if (len & ~HPAGE_MASK) + struct hstate *h = hstate_file(file); + + if (len & ~huge_page_mask(h)) return -EINVAL; - if (addr & ~HPAGE_MASK) + if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; } diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index ce6f56980aef..cf190728360b 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -91,9 +91,9 @@ extern unsigned long pfn_base; * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page)) +#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) /* * In general all page table modifications should use the V8 atomic diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h index 478bf6bb4598..3fae200dd251 100644 --- a/arch/sparc/include/asm/setup.h +++ b/arch/sparc/include/asm/setup.h @@ -16,7 +16,7 @@ extern char reboot_command[]; */ extern unsigned char boot_cpu_id; -extern unsigned long empty_zero_page; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; extern int serial_console; static inline int con_is_present(void) diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 6bcff698069b..cec54dc4ab81 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -130,17 +130,16 @@ unsigned long prepare_ftrace_return(unsigned long parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return parent + 8UL; - if (ftrace_push_return_trace(parent, self_addr, &trace.depth, - frame_pointer, NULL) == -EBUSY) - return parent + 8UL; - trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; + if (!ftrace_graph_entry(&trace)) + return parent + 8UL; + + if (ftrace_push_return_trace(parent, self_addr, &trace.depth, + frame_pointer, NULL) == -EBUSY) return parent + 8UL; - } return return_hooker; } diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index c6afe98de4d9..3bd0d513bddb 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -290,7 +290,7 @@ void __init mem_init(void) /* Saves us work later. */ - memset((void *)&empty_zero_page, 0, PAGE_SIZE); + memset((void *)empty_zero_page, 0, PAGE_SIZE); i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5); i += 1; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 563979976fab..9be890893885 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -43,7 +43,7 @@ #define KVM_PRIVATE_MEM_SLOTS 3 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) -#define KVM_HALT_POLL_NS_DEFAULT 400000 +#define KVM_HALT_POLL_NS_DEFAULT 200000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 673f9ac50f6d..dbf266b0d14a 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -420,6 +420,8 @@ #define MSR_IA32_TSC_ADJUST 0x0000003b #define MSR_IA32_BNDCFGS 0x00000d90 +#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc + #define MSR_IA32_XSS 0x00000da0 #define FEATURE_CONTROL_LOCKED (1<<0) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 68766b276d9e..a059aac9e937 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -319,10 +319,10 @@ do { \ #define __get_user_asm_u64(x, ptr, retval, errret) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ - asm volatile(ASM_STAC "\n" \ + asm volatile("\n" \ "1: movl %2,%%eax\n" \ "2: movl %3,%%edx\n" \ - "3: " ASM_CLAC "\n" \ + "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: mov %4,%0\n" \ " xorl %%eax,%%eax\n" \ @@ -331,7 +331,7 @@ do { \ ".previous\n" \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ - : "=r" (retval), "=A"(x) \ + : "=r" (retval), "=&A"(x) \ : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ }) @@ -703,14 +703,15 @@ extern struct movsl_mask { #define unsafe_put_user(x, ptr, err_label) \ do { \ int __pu_err; \ - __put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __put_user_size(__pu_val, (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ if (unlikely(__pu_err)) goto err_label; \ } while (0) #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ - unsigned long __gu_val; \ + __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index c2f8dde3255c..d5d44c452624 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -90,6 +90,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) * Boot time FPU feature detection code: */ unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +EXPORT_SYMBOL_GPL(mxcsr_feature_mask); static void __init fpu__init_system_mxcsr(void) { diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index a6fd40aade7c..da6728383052 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -144,6 +144,14 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_RTM)); } +static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_MPX)); +} + static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c25cfaf584e7..0f0815c824de 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3941,6 +3941,25 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) } /* + * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but does save + * and restore MXCSR. + */ +static size_t __fxstate_size(int nregs) +{ + return offsetof(struct fxregs_state, xmm_space[0]) + nregs * 16; +} + +static inline size_t fxstate_size(struct x86_emulate_ctxt *ctxt) +{ + bool cr4_osfxsr; + if (ctxt->mode == X86EMUL_MODE_PROT64) + return __fxstate_size(16); + + cr4_osfxsr = ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR; + return __fxstate_size(cr4_osfxsr ? 8 : 0); +} + +/* * FXSAVE and FXRSTOR have 4 different formats depending on execution mode, * 1) 16 bit mode * 2) 32 bit mode @@ -3961,7 +3980,6 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) static int em_fxsave(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; - size_t size; int rc; rc = check_fxsr(ctxt); @@ -3977,68 +3995,42 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR) - size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]); - else - size = offsetof(struct fxregs_state, xmm_space[0]); - - return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); -} - -static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt, - struct fxregs_state *new) -{ - int rc = X86EMUL_CONTINUE; - struct fxregs_state old; - - rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old)); - if (rc != X86EMUL_CONTINUE) - return rc; - - /* - * 64 bit host will restore XMM 8-15, which is not correct on non-64 - * bit guests. Load the current values in order to preserve 64 bit - * XMMs after fxrstor. - */ -#ifdef CONFIG_X86_64 - /* XXX: accessing XMM 8-15 very awkwardly */ - memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16); -#endif - - /* - * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but - * does save and restore MXCSR. - */ - if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)) - memcpy(new->xmm_space, old.xmm_space, 8 * 16); - - return rc; + return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, + fxstate_size(ctxt)); } static int em_fxrstor(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; int rc; + size_t size; rc = check_fxsr(ctxt); if (rc != X86EMUL_CONTINUE) return rc; - rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512); - if (rc != X86EMUL_CONTINUE) - return rc; + ctxt->ops->get_fpu(ctxt); - if (fx_state.mxcsr >> 16) - return emulate_gp(ctxt, 0); + size = fxstate_size(ctxt); + if (size < __fxstate_size(16)) { + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + if (rc != X86EMUL_CONTINUE) + goto out; + } - ctxt->ops->get_fpu(ctxt); + rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); + if (rc != X86EMUL_CONTINUE) + goto out; - if (ctxt->mode < X86EMUL_MODE_PROT64) - rc = fxrstor_fixup(ctxt, &fx_state); + if (fx_state.mxcsr >> 16) { + rc = emulate_gp(ctxt, 0); + goto out; + } if (rc == X86EMUL_CONTINUE) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); +out: ctxt->ops->put_fpu(ctxt); return rc; @@ -4173,7 +4165,7 @@ static int check_dr_write(struct x86_emulate_ctxt *ctxt) static int check_svme(struct x86_emulate_ctxt *ctxt) { - u64 efer; + u64 efer = 0; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c329d2894905..2819d4c123eb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1495,31 +1495,65 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); static void cancel_hv_timer(struct kvm_lapic *apic) { + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + preempt_disable(); kvm_x86_ops->cancel_hv_timer(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; + preempt_enable(); } static bool start_hv_timer(struct kvm_lapic *apic) { - u64 tscdeadline = apic->lapic_timer.tscdeadline; + struct kvm_timer *ktimer = &apic->lapic_timer; + int r; - if ((atomic_read(&apic->lapic_timer.pending) && - !apic_lvtt_period(apic)) || - kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) { - if (apic->lapic_timer.hv_timer_in_use) - cancel_hv_timer(apic); - } else { - apic->lapic_timer.hv_timer_in_use = true; - hrtimer_cancel(&apic->lapic_timer.timer); + if (!kvm_x86_ops->set_hv_timer) + return false; + + if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) + return false; - /* In case the sw timer triggered in the window */ - if (atomic_read(&apic->lapic_timer.pending) && - !apic_lvtt_period(apic)) - cancel_hv_timer(apic); + r = kvm_x86_ops->set_hv_timer(apic->vcpu, ktimer->tscdeadline); + if (r < 0) + return false; + + ktimer->hv_timer_in_use = true; + hrtimer_cancel(&ktimer->timer); + + /* + * Also recheck ktimer->pending, in case the sw timer triggered in + * the window. For periodic timer, leave the hv timer running for + * simplicity, and the deadline will be recomputed on the next vmexit. + */ + if (!apic_lvtt_period(apic) && (r || atomic_read(&ktimer->pending))) { + if (r) + apic_timer_expired(apic); + return false; } - trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, - apic->lapic_timer.hv_timer_in_use); - return apic->lapic_timer.hv_timer_in_use; + + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, true); + return true; +} + +static void start_sw_timer(struct kvm_lapic *apic) +{ + struct kvm_timer *ktimer = &apic->lapic_timer; + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_timer(apic); + if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) + return; + + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) + start_sw_period(apic); + else if (apic_lvtt_tscdeadline(apic)) + start_sw_tscdeadline(apic); + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, false); +} + +static void restart_apic_timer(struct kvm_lapic *apic) +{ + if (!start_hv_timer(apic)) + start_sw_timer(apic); } void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) @@ -1533,19 +1567,14 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); - if (!start_hv_timer(apic)) - start_sw_period(apic); + restart_apic_timer(apic); } } EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu) { - struct kvm_lapic *apic = vcpu->arch.apic; - - WARN_ON(apic->lapic_timer.hv_timer_in_use); - - start_hv_timer(apic); + restart_apic_timer(vcpu->arch.apic); } EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer); @@ -1554,33 +1583,28 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; /* Possibly the TSC deadline timer is not enabled yet */ - if (!apic->lapic_timer.hv_timer_in_use) - return; - - cancel_hv_timer(apic); + if (apic->lapic_timer.hv_timer_in_use) + start_sw_timer(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); - if (atomic_read(&apic->lapic_timer.pending)) - return; +void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; - if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) - start_sw_period(apic); - else if (apic_lvtt_tscdeadline(apic)) - start_sw_tscdeadline(apic); + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + restart_apic_timer(apic); } -EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); static void start_apic_timer(struct kvm_lapic *apic) { atomic_set(&apic->lapic_timer.pending, 0); - if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { - if (set_target_expiration(apic) && - !(kvm_x86_ops->set_hv_timer && start_hv_timer(apic))) - start_sw_period(apic); - } else if (apic_lvtt_tscdeadline(apic)) { - if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic))) - start_sw_tscdeadline(apic); - } + if ((apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) + && !set_target_expiration(apic)) + return; + + restart_apic_timer(apic); } static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) @@ -1811,16 +1835,6 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) * LAPIC interface *---------------------------------------------------------------------- */ -u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - - if (!lapic_in_kernel(vcpu)) - return 0; - - return apic->lapic_timer.tscdeadline; -} - u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1934,7 +1948,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) for (i = 0; i < KVM_APIC_LVT_NUM; i++) kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic_update_lvtt(apic); - if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) + if (kvm_vcpu_is_reset_bsp(vcpu) && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) kvm_lapic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index bcbe811f3b97..29caa2c3dff9 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -87,7 +87,6 @@ int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); -u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); @@ -216,4 +215,5 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); +void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 56241746abbd..b0454c7e4cff 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -283,11 +283,13 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, pt_element_t pte; pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; - unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey; + u64 pt_access, pte_access; + unsigned index, accessed_dirty, pte_pkey; unsigned nested_access; gpa_t pte_gpa; bool have_ad; int offset; + u64 walk_nx_mask = 0; const int write_fault = access & PFERR_WRITE_MASK; const int user_fault = access & PFERR_USER_MASK; const int fetch_fault = access & PFERR_FETCH_MASK; @@ -302,6 +304,7 @@ retry_walk: have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 + walk_nx_mask = 1ULL << PT64_NX_SHIFT; if (walker->level == PT32E_ROOT_LEVEL) { pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); @@ -313,8 +316,6 @@ retry_walk: walker->max_level = walker->level; ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu))); - accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0; - /* * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging * by the MOV to CR instruction are treated as reads and do not cause the @@ -322,14 +323,14 @@ retry_walk: */ nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK; - pt_access = pte_access = ACC_ALL; + pte_access = ~0; ++walker->level; do { gfn_t real_gfn; unsigned long host_addr; - pt_access &= pte_access; + pt_access = pte_access; --walker->level; index = PT_INDEX(addr, walker->level); @@ -371,6 +372,12 @@ retry_walk: trace_kvm_mmu_paging_element(pte, walker->level); + /* + * Inverting the NX it lets us AND it like other + * permission bits. + */ + pte_access = pt_access & (pte ^ walk_nx_mask); + if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; @@ -379,14 +386,16 @@ retry_walk: goto error; } - accessed_dirty &= pte; - pte_access = pt_access & FNAME(gpte_access)(vcpu, pte); - walker->ptes[walker->level - 1] = pte; } while (!is_last_gpte(mmu, walker->level, pte)); pte_pkey = FNAME(gpte_pkeys)(vcpu, pte); - errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access); + accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; + + /* Convert to ACC_*_MASK flags for struct guest_walker. */ + walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask); + walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask); + errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) goto error; @@ -403,7 +412,7 @@ retry_walk: walker->gfn = real_gpa >> PAGE_SHIFT; if (!write_fault) - FNAME(protect_clean_gpte)(mmu, &pte_access, pte); + FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte); else /* * On a write fault, fold the dirty bit into accessed_dirty. @@ -421,10 +430,8 @@ retry_walk: goto retry_walk; } - walker->pt_access = pt_access; - walker->pte_access = pte_access; pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, pte_access, pt_access); + __func__, (u64)pte, walker->pte_access, walker->pt_access); return 1; error: @@ -452,7 +459,7 @@ error: */ if (!(errcode & PFERR_RSVD_MASK)) { vcpu->arch.exit_qualification &= 0x187; - vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3; + vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3; } #endif walker->fault.address = addr; diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index 9d4a8504a95a..5ab4a364348e 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) ((u64)1 << edx.split.bit_width_fixed) - 1; } - pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) | (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); pmu->global_ctrl_mask = ~pmu->global_ctrl; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c27ac6923a18..03df7c1da581 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -189,6 +189,7 @@ struct vcpu_svm { struct nested_state nested; bool nmi_singlestep; + u64 nmi_singlestep_guest_rflags; unsigned int3_injected; unsigned long int3_rip; @@ -963,6 +964,18 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +static void disable_nmi_singlestep(struct vcpu_svm *svm) +{ + svm->nmi_singlestep = false; + if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) { + /* Clear our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_RF; + } +} + /* Note: * This hash table is used to map VM_ID to a struct kvm_arch, * when handling AMD IOMMU GALOG notification to schedule in @@ -1272,7 +1285,8 @@ static void init_vmcb(struct vcpu_svm *svm) } -static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index) +static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, + unsigned int index) { u64 *avic_physical_id_table; struct kvm_arch *vm_data = &vcpu->kvm->arch; @@ -1711,11 +1725,24 @@ static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu) static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { - return to_svm(vcpu)->vmcb->save.rflags; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long rflags = svm->vmcb->save.rflags; + + if (svm->nmi_singlestep) { + /* Hide our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + rflags &= ~X86_EFLAGS_RF; + } + return rflags; } static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + if (to_svm(vcpu)->nmi_singlestep) + rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); + /* * Any change of EFLAGS.VM is accompanied by a reload of SS * (caused by either a task switch or an inter-privilege IRET), @@ -1806,7 +1833,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, * AMD's VMCB does not have an explicit unusable field, so emulate it * for cross vendor migration purposes by "not present" */ - var->unusable = !var->present || (var->type == 0); + var->unusable = !var->present; switch (seg) { case VCPU_SREG_TR: @@ -1839,6 +1866,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, */ if (var->unusable) var->db = 0; + /* This is symmetric with svm_set_segment() */ var->dpl = to_svm(vcpu)->vmcb->save.cpl; break; } @@ -1979,18 +2007,14 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->base = var->base; s->limit = var->limit; s->selector = var->selector; - if (var->unusable) - s->attrib = 0; - else { - s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); - s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; - s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; - s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT; - s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; - s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; - s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; - s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; - } + s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); + s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; + s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; + s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT; + s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; + s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; + s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; + s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; /* * This is always accurate, except if SYSRET returned to a segment @@ -1999,7 +2023,8 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, * would entail passing the CPL to userspace and back. */ if (seg == VCPU_SREG_SS) - svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; + /* This is symmetric with svm_get_segment() */ + svm->vmcb->save.cpl = (var->dpl & 3); mark_dirty(svm->vmcb, VMCB_SEG); } @@ -2112,10 +2137,7 @@ static int db_interception(struct vcpu_svm *svm) } if (svm->nmi_singlestep) { - svm->nmi_singlestep = false; - if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) - svm->vmcb->save.rflags &= - ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + disable_nmi_singlestep(svm); } if (svm->vcpu.guest_debug & @@ -2370,8 +2392,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static int nested_svm_check_permissions(struct vcpu_svm *svm) { - if (!(svm->vcpu.arch.efer & EFER_SVME) - || !is_paging(&svm->vcpu)) { + if (!(svm->vcpu.arch.efer & EFER_SVME) || + !is_paging(&svm->vcpu)) { kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } @@ -2381,7 +2403,7 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) return 1; } - return 0; + return 0; } static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, @@ -2534,6 +2556,31 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } +/* DB exceptions for our internal use must not cause vmexit */ +static int nested_svm_intercept_db(struct vcpu_svm *svm) +{ + unsigned long dr6; + + /* if we're not singlestepping, it's not ours */ + if (!svm->nmi_singlestep) + return NESTED_EXIT_DONE; + + /* if it's not a singlestep exception, it's not ours */ + if (kvm_get_dr(&svm->vcpu, 6, &dr6)) + return NESTED_EXIT_DONE; + if (!(dr6 & DR6_BS)) + return NESTED_EXIT_DONE; + + /* if the guest is singlestepping, it should get the vmexit */ + if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { + disable_nmi_singlestep(svm); + return NESTED_EXIT_DONE; + } + + /* it's ours, the nested hypervisor must not see this one */ + return NESTED_EXIT_HOST; +} + static int nested_svm_exit_special(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; @@ -2589,8 +2636,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) } case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); - if (svm->nested.intercept_exceptions & excp_bits) - vmexit = NESTED_EXIT_DONE; + if (svm->nested.intercept_exceptions & excp_bits) { + if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) + vmexit = nested_svm_intercept_db(svm); + else + vmexit = NESTED_EXIT_DONE; + } /* async page fault always cause vmexit */ else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && svm->apf_reason != 0) @@ -4627,10 +4678,17 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) == HF_NMI_MASK) return; /* IRET will cause a vm exit */ + if ((svm->vcpu.arch.hflags & HF_GIF_MASK) == 0) + return; /* STGI will cause a vm exit */ + + if (svm->nested.exit_required) + return; /* we're not going to run the guest yet */ + /* * Something prevents NMI from been injected. Single step over possible * problem (IRET or exception injection or interrupt shadow) */ + svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu); svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); } @@ -4771,6 +4829,22 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->nested.exit_required)) return; + /* + * Disable singlestep if we're injecting an interrupt/exception. + * We don't want our modified rflags to be pushed on the stack where + * we might not be able to easily reset them if we disabled NMI + * singlestep later. + */ + if (svm->nmi_singlestep && svm->vmcb->control.event_inj) { + /* + * Event injection happens before external interrupts cause a + * vmexit and interrupts are disabled here, so smp_send_reschedule + * is enough to force an immediate vmexit. + */ + disable_nmi_singlestep(svm); + smp_send_reschedule(vcpu->cpu); + } + pre_svm_run(svm); sync_lapic_to_cr8(vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c6f4ad44aa95..92ddea08f999 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2769,7 +2769,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) if (enable_ept_ad_bits) { vmx->nested.nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_PML; - vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; + vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; } } else vmx->nested.nested_vmx_ept_caps = 0; @@ -3195,7 +3195,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) + if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu)) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -3277,7 +3277,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) + if (!kvm_mpx_supported() || !guest_cpuid_has_mpx(vcpu)) + return 1; + if (is_noncanonical_address(data & PAGE_MASK) || + (data & MSR_IA32_BNDCFGS_RSVD)) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; @@ -6504,7 +6507,7 @@ static __init int hardware_setup(void) enable_ept_ad_bits = 0; } - if (!cpu_has_vmx_ept_ad_bits()) + if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; if (!cpu_has_vmx_unrestricted_guest()) @@ -6547,7 +6550,6 @@ static __init int hardware_setup(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); memcpy(vmx_msr_bitmap_legacy_x2apic_apicv, vmx_msr_bitmap_legacy, PAGE_SIZE); @@ -6914,97 +6916,21 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, return 0; } -/* - * This function performs the various checks including - * - if it's 4KB aligned - * - No bits beyond the physical address width are set - * - Returns 0 on success or else 1 - * (Intel SDM Section 30.3) - */ -static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, - gpa_t *vmpointer) +static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) { gva_t gva; - gpa_t vmptr; struct x86_exception e; - struct page *page; - struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) return 1; - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer, + sizeof(*vmpointer), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } - switch (exit_reason) { - case EXIT_REASON_VMON: - /* - * SDM 3: 24.11.5 - * The first 4 bytes of VMXON region contain the supported - * VMCS revision identifier - * - * Note - IA32_VMX_BASIC[48] will never be 1 - * for the nested case; - * which replaces physical address width with 32 - * - */ - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - - page = nested_get_page(vcpu, vmptr); - if (page == NULL) { - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - if (*(u32 *)kmap(page) != VMCS12_REVISION) { - kunmap(page); - nested_release_page_clean(page); - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - kunmap(page); - nested_release_page_clean(page); - vmx->nested.vmxon_ptr = vmptr; - break; - case EXIT_REASON_VMCLEAR: - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failValid(vcpu, - VMXERR_VMCLEAR_INVALID_ADDRESS); - return kvm_skip_emulated_instruction(vcpu); - } - - if (vmptr == vmx->nested.vmxon_ptr) { - nested_vmx_failValid(vcpu, - VMXERR_VMCLEAR_VMXON_POINTER); - return kvm_skip_emulated_instruction(vcpu); - } - break; - case EXIT_REASON_VMPTRLD: - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failValid(vcpu, - VMXERR_VMPTRLD_INVALID_ADDRESS); - return kvm_skip_emulated_instruction(vcpu); - } - - if (vmptr == vmx->nested.vmxon_ptr) { - nested_vmx_failValid(vcpu, - VMXERR_VMPTRLD_VMXON_POINTER); - return kvm_skip_emulated_instruction(vcpu); - } - break; - default: - return 1; /* shouldn't happen */ - } - - if (vmpointer) - *vmpointer = vmptr; return 0; } @@ -7066,6 +6992,8 @@ out_msr_bitmap: static int handle_vmon(struct kvm_vcpu *vcpu) { int ret; + gpa_t vmptr; + struct page *page; struct vcpu_vmx *vmx = to_vmx(vcpu); const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; @@ -7095,9 +7023,37 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; - + + /* + * SDM 3: 24.11.5 + * The first 4 bytes of VMXON region contain the supported + * VMCS revision identifier + * + * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case; + * which replaces physical address width with 32 + */ + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + + page = nested_get_page(vcpu, vmptr); + if (page == NULL) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + if (*(u32 *)kmap(page) != VMCS12_REVISION) { + kunmap(page); + nested_release_page_clean(page); + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + kunmap(page); + nested_release_page_clean(page); + + vmx->nested.vmxon_ptr = vmptr; ret = enter_vmx_operation(vcpu); if (ret) return ret; @@ -7213,9 +7169,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); + return kvm_skip_emulated_instruction(vcpu); + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); + return kvm_skip_emulated_instruction(vcpu); + } + if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vmx); @@ -7545,9 +7511,19 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); + return kvm_skip_emulated_instruction(vcpu); + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); + return kvm_skip_emulated_instruction(vcpu); + } + if (vmx->nested.current_vmptr != vmptr) { struct vmcs12 *new_vmcs12; struct page *page; @@ -7677,7 +7653,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) unsigned long type, types; gva_t gva; struct x86_exception e; - int vpid; + struct { + u64 vpid; + u64 gla; + } operand; if (!(vmx->nested.nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || @@ -7707,17 +7686,28 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), vmx_instruction_info, false, &gva)) return 1; - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid, - sizeof(u32), &e)) { + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, + sizeof(operand), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } + if (operand.vpid >> 16) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return kvm_skip_emulated_instruction(vcpu); + } switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: + if (is_noncanonical_address(operand.gla)) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return kvm_skip_emulated_instruction(vcpu); + } + /* fall through */ case VMX_VPID_EXTENT_SINGLE_CONTEXT: case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: - if (!vpid) { + if (!operand.vpid) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); return kvm_skip_emulated_instruction(vcpu); @@ -7913,11 +7903,13 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, { unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); int cr = exit_qualification & 15; - int reg = (exit_qualification >> 8) & 15; - unsigned long val = kvm_register_readl(vcpu, reg); + int reg; + unsigned long val; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ + reg = (exit_qualification >> 8) & 15; + val = kvm_register_readl(vcpu, reg); switch (cr) { case 0: if (vmcs12->cr0_guest_host_mask & @@ -7972,6 +7964,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, * lmsw can change bits 1..3 of cr0, and only set bit 0 of * cr0. Other attempted changes are ignored, with no exit. */ + val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) return true; @@ -10733,8 +10726,7 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); } - if (nested_cpu_has_ept(vmcs12)) - vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); + vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); if (nested_cpu_has_vid(vmcs12)) vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS); @@ -10759,8 +10751,6 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); if (kvm_mpx_supported()) vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); - if (nested_cpu_has_xsaves(vmcs12)) - vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP); } /* @@ -11157,7 +11147,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) vmx->hv_deadline_tsc = tscl + delta_tsc; vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); - return 0; + + return delta_tsc == 0; } static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) @@ -11213,7 +11204,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) if (!nested_cpu_has_pml(vmcs12)) return 0; - if (vmcs12->guest_pml_index > PML_ENTITY_NUM) { + if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { vmx->nested.pml_full = true; return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f81060518635..f2bd155883dd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1763,6 +1763,7 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + u64 ret; spin_lock(&ka->pvclock_gtod_sync_lock); if (!ka->use_master_clock) { @@ -1774,10 +1775,17 @@ u64 get_kvmclock_ns(struct kvm *kvm) hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; spin_unlock(&ka->pvclock_gtod_sync_lock); + /* both __this_cpu_read() and rdtsc() should be on the same cpu */ + get_cpu(); + kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); - return __pvclock_read_cycles(&hv_clock, rdtsc()); + ret = __pvclock_read_cycles(&hv_clock, rdtsc()); + + put_cpu(); + + return ret; } static void kvm_setup_pvclock_page(struct kvm_vcpu *v) @@ -2833,10 +2841,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } - if (kvm_lapic_hv_timer_in_use(vcpu) && - kvm_x86_ops->set_hv_timer(vcpu, - kvm_get_lapic_target_expiration_tsc(vcpu))) - kvm_lapic_switch_to_sw_timer(vcpu); + + if (kvm_lapic_hv_timer_in_use(vcpu)) + kvm_lapic_restart_hv_timer(vcpu); + /* * On a host with synchronized TSC, there is no need to update * kvmclock on vcpu->cpu migration @@ -3288,11 +3296,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, } } +#define XSAVE_MXCSR_OFFSET 24 + static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; if (boot_cpu_has(X86_FEATURE_XSAVE)) { /* @@ -3300,11 +3311,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility * with old userspace. */ - if (xstate_bv & ~kvm_supported_xcr0()) + if (xstate_bv & ~kvm_supported_xcr0() || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { - if (xstate_bv & ~XFEATURE_MASK_FPSSE) + if (xstate_bv & ~XFEATURE_MASK_FPSSE || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state.fxsave, guest_xsave->region, sizeof(struct fxregs_state)); @@ -4818,16 +4831,20 @@ emul_write: static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) { - /* TODO: String I/O for in kernel device */ - int r; + int r = 0, i; - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); - else - r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, - vcpu->arch.pio.port, vcpu->arch.pio.size, - pd); + for (i = 0; i < vcpu->arch.pio.count; i++) { + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + if (r) + break; + pd += vcpu->arch.pio.size; + } return r; } @@ -4865,6 +4882,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (vcpu->arch.pio.count) goto data_avail; + memset(vcpu->arch.pio_data, 0, size * count); + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); if (ret) { data_avail: @@ -5048,6 +5067,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, if (var.unusable) { memset(desc, 0, sizeof(*desc)); + if (base3) + *base3 = 0; return false; } @@ -8373,10 +8394,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (vcpu->arch.pv.pv_unhalted) return true; - if (atomic_read(&vcpu->arch.nmi_queued)) + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + (vcpu->arch.nmi_pending && + kvm_x86_ops->nmi_allowed(vcpu))) return true; - if (kvm_test_request(KVM_REQ_SMI, vcpu)) + if (kvm_test_request(KVM_REQ_SMI, vcpu) || + (vcpu->arch.smi_pending && !is_smm(vcpu))) return true; if (kvm_arch_interrupt_allowed(vcpu) && diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 7cd442690f9d..f33eef4ebd12 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -142,9 +142,7 @@ static void __init xen_banner(void) struct xen_extraversion extra; HYPERVISOR_xen_version(XENVER_extraversion, &extra); - pr_info("Booting paravirtualized kernel %son %s\n", - xen_feature(XENFEAT_auto_translated_physmap) ? - "with PVH extensions " : "", pv_info.name); + pr_info("Booting paravirtualized kernel on %s\n", pv_info.name); printk(KERN_INFO "Xen version: %d.%d%s%s\n", version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); @@ -957,15 +955,10 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high) void xen_setup_shared_info(void) { - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - set_fixmap(FIX_PARAVIRT_BOOTMAP, - xen_start_info->shared_info); + set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); - HYPERVISOR_shared_info = - (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); - } else - HYPERVISOR_shared_info = - (struct shared_info *)__va(xen_start_info->shared_info); + HYPERVISOR_shared_info = + (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); #ifndef CONFIG_SMP /* In UP this is as good a place as any to set up shared info */ diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5e375a5e815f..3be06f3caf3c 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,7 +42,7 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) } EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine); -void xen_flush_tlb_all(void) +static void xen_flush_tlb_all(void) { struct mmuext_op *op; struct multicall_space mcs; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 7397d8b8459d..1f386d7fdf70 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -355,10 +355,8 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) pteval_t flags = val & PTE_FLAGS_MASK; unsigned long mfn; - if (!xen_feature(XENFEAT_auto_translated_physmap)) - mfn = __pfn_to_mfn(pfn); - else - mfn = pfn; + mfn = __pfn_to_mfn(pfn); + /* * If there's no mfn for the pfn, then just create an * empty non-present pte. Unfortunately this loses @@ -647,9 +645,6 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, limit--; BUG_ON(limit >= FIXADDR_TOP); - if (xen_feature(XENFEAT_auto_translated_physmap)) - return 0; - /* * 64-bit has a great big hole in the middle of the address * space, which contains the Xen mappings. On 32-bit these @@ -1289,9 +1284,6 @@ static void __init xen_pagetable_cleanhighmap(void) static void __init xen_pagetable_p2m_setup(void) { - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - xen_vmalloc_p2m_tree(); #ifdef CONFIG_X86_64 @@ -1314,8 +1306,7 @@ static void __init xen_pagetable_init(void) xen_build_mfn_list_list(); /* Remap memory freed due to conflicts with E820 map */ - if (!xen_feature(XENFEAT_auto_translated_physmap)) - xen_remap_memory(); + xen_remap_memory(); xen_setup_shared_info(); } @@ -1925,21 +1916,20 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Zap identity mapping */ init_level4_pgt[0] = __pgd(0); - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - /* Pre-constructed entries are in pfn, so convert to mfn */ - /* L4[272] -> level3_ident_pgt - * L4[511] -> level3_kernel_pgt */ - convert_pfn_mfn(init_level4_pgt); + /* Pre-constructed entries are in pfn, so convert to mfn */ + /* L4[272] -> level3_ident_pgt */ + /* L4[511] -> level3_kernel_pgt */ + convert_pfn_mfn(init_level4_pgt); - /* L3_i[0] -> level2_ident_pgt */ - convert_pfn_mfn(level3_ident_pgt); - /* L3_k[510] -> level2_kernel_pgt - * L3_k[511] -> level2_fixmap_pgt */ - convert_pfn_mfn(level3_kernel_pgt); + /* L3_i[0] -> level2_ident_pgt */ + convert_pfn_mfn(level3_ident_pgt); + /* L3_k[510] -> level2_kernel_pgt */ + /* L3_k[511] -> level2_fixmap_pgt */ + convert_pfn_mfn(level3_kernel_pgt); + + /* L3_k[511][506] -> level1_fixmap_pgt */ + convert_pfn_mfn(level2_fixmap_pgt); - /* L3_k[511][506] -> level1_fixmap_pgt */ - convert_pfn_mfn(level2_fixmap_pgt); - } /* We get [511][511] and have Xen's version of level2_kernel_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud); @@ -1962,34 +1952,30 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) if (i && i < pgd_index(__START_KERNEL_map)) init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - /* Make pagetable pieces RO */ - set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); - set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); - - /* Pin down new L4 */ - pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa_symbol(init_level4_pgt))); - - /* Unpin Xen-provided one */ - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); + /* Make pagetable pieces RO */ + set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); + set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); + set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); + set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); + set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); + + /* Pin down new L4 */ + pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, + PFN_DOWN(__pa_symbol(init_level4_pgt))); + + /* Unpin Xen-provided one */ + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - /* - * At this stage there can be no user pgd, and no page - * structure to attach it to, so make sure we just set kernel - * pgd. - */ - xen_mc_batch(); - __xen_write_cr3(true, __pa(init_level4_pgt)); - xen_mc_issue(PARAVIRT_LAZY_CPU); - } else - native_write_cr3(__pa(init_level4_pgt)); + /* + * At this stage there can be no user pgd, and no page structure to + * attach it to, so make sure we just set kernel pgd. + */ + xen_mc_batch(); + __xen_write_cr3(true, __pa(init_level4_pgt)); + xen_mc_issue(PARAVIRT_LAZY_CPU); /* We can't that easily rip out L3 and L2, as the Xen pagetables are * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for @@ -2403,9 +2389,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) static void __init xen_post_allocator_init(void) { - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; @@ -2511,9 +2494,6 @@ void __init xen_init_mmu_ops(void) { x86_init.paging.pagetable_init = xen_pagetable_init; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); @@ -2650,9 +2630,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, * this function are redundant and can be ignored. */ - if (xen_feature(XENFEAT_auto_translated_physmap)) - return 0; - if (unlikely(order > MAX_CONTIG_ORDER)) return -ENOMEM; @@ -2689,9 +2666,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) int success; unsigned long vstart; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - if (unlikely(order > MAX_CONTIG_ORDER)) return; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index b5730e17b455..656624314f0d 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -315,24 +315,32 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m) } /* still holds resource->req_lock */ -static int drbd_req_put_completion_ref(struct drbd_request *req, struct bio_and_error *m, int put) +static void drbd_req_put_completion_ref(struct drbd_request *req, struct bio_and_error *m, int put) { struct drbd_device *device = req->device; D_ASSERT(device, m || (req->rq_state & RQ_POSTPONED)); + if (!put) + return; + if (!atomic_sub_and_test(put, &req->completion_ref)) - return 0; + return; drbd_req_complete(req, m); + /* local completion may still come in later, + * we need to keep the req object around. */ + if (req->rq_state & RQ_LOCAL_ABORTED) + return; + if (req->rq_state & RQ_POSTPONED) { /* don't destroy the req object just yet, * but queue it for retry */ drbd_restart_request(req); - return 0; + return; } - return 1; + kref_put(&req->kref, drbd_req_destroy); } static void set_if_null_req_next(struct drbd_peer_device *peer_device, struct drbd_request *req) @@ -519,12 +527,8 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, if (req->i.waiting) wake_up(&device->misc_wait); - if (c_put) { - if (drbd_req_put_completion_ref(req, m, c_put)) - kref_put(&req->kref, drbd_req_destroy); - } else { - kref_put(&req->kref, drbd_req_destroy); - } + drbd_req_put_completion_ref(req, m, c_put); + kref_put(&req->kref, drbd_req_destroy); } static void drbd_report_io_error(struct drbd_device *device, struct drbd_request *req) @@ -1366,8 +1370,7 @@ nodata: } out: - if (drbd_req_put_completion_ref(req, &m, 1)) - kref_put(&req->kref, drbd_req_destroy); + drbd_req_put_completion_ref(req, &m, 1); spin_unlock_irq(&resource->req_lock); /* Even though above is a kref_put(), this is safe. diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 8fe61b5dc5a6..1f3dfaa54d87 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -504,11 +504,13 @@ static int xen_blkbk_remove(struct xenbus_device *dev) dev_set_drvdata(&dev->dev, NULL); - if (be->blkif) + if (be->blkif) { xen_blkif_disconnect(be->blkif); - /* Put the reference we set in xen_blkif_alloc(). */ - xen_blkif_put(be->blkif); + /* Put the reference we set in xen_blkif_alloc(). */ + xen_blkif_put(be->blkif); + } + kfree(be->mode); kfree(be); return 0; diff --git a/drivers/char/lp.c b/drivers/char/lp.c index 565e4cf04a02..8249762192d5 100644 --- a/drivers/char/lp.c +++ b/drivers/char/lp.c @@ -859,7 +859,11 @@ static int __init lp_setup (char *str) } else if (!strcmp(str, "auto")) { parport_nr[0] = LP_PARPORT_AUTO; } else if (!strcmp(str, "none")) { - parport_nr[parport_ptr++] = LP_PARPORT_NONE; + if (parport_ptr < LP_NO) + parport_nr[parport_ptr++] = LP_PARPORT_NONE; + else + printk(KERN_INFO "lp: too many ports, %s ignored.\n", + str); } else if (!strcmp(str, "reset")) { reset = 1; } diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 7e4a9d1296bb..6e0cbe092220 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -340,6 +340,11 @@ static const struct vm_operations_struct mmap_mem_ops = { static int mmap_mem(struct file *file, struct vm_area_struct *vma) { size_t size = vma->vm_end - vma->vm_start; + phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; + + /* It's illegal to wrap around the end of the physical address space. */ + if (offset + (phys_addr_t)size < offset) + return -EINVAL; if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size)) return -EINVAL; diff --git a/drivers/dax/super.c b/drivers/dax/super.c index ebf43f531ada..6ed32aac8bbe 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -44,6 +44,7 @@ void dax_read_unlock(int id) } EXPORT_SYMBOL_GPL(dax_read_unlock); +#ifdef CONFIG_BLOCK int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, pgoff_t *pgoff) { @@ -112,6 +113,7 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize) return 0; } EXPORT_SYMBOL_GPL(__bdev_dax_supported); +#endif /** * struct dax_device - anchor object for dax services diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 82dab1692264..3aea55698165 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -782,24 +782,26 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan) static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl) { - u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases; - int dimm, size0, size1; + int dimm, size0, size1, cs0, cs1; edac_printk(KERN_DEBUG, EDAC_MC, "UMC%d chip selects:\n", ctrl); for (dimm = 0; dimm < 4; dimm++) { size0 = 0; + cs0 = dimm * 2; - if (dcsb[dimm*2] & DCSB_CS_ENABLE) - size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm); + if (csrow_enabled(cs0, ctrl, pvt)) + size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs0); size1 = 0; - if (dcsb[dimm*2 + 1] & DCSB_CS_ENABLE) - size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm); + cs1 = dimm * 2 + 1; + + if (csrow_enabled(cs1, ctrl, pvt)) + size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs1); amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n", - dimm * 2, size0, - dimm * 2 + 1, size1); + cs0, size0, + cs1, size1); } } @@ -2756,26 +2758,22 @@ skip: * encompasses * */ -static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr) +static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr_orig) { - u32 cs_mode, nr_pages; u32 dbam = dct ? pvt->dbam1 : pvt->dbam0; + int csrow_nr = csrow_nr_orig; + u32 cs_mode, nr_pages; + if (!pvt->umc) + csrow_nr >>= 1; - /* - * The math on this doesn't look right on the surface because x/2*4 can - * be simplified to x*2 but this expression makes use of the fact that - * it is integral math where 1/2=0. This intermediate value becomes the - * number of bits to shift the DBAM register to extract the proper CSROW - * field. - */ - cs_mode = DBAM_DIMM(csrow_nr / 2, dbam); + cs_mode = DBAM_DIMM(csrow_nr, dbam); - nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, (csrow_nr / 2)) - << (20 - PAGE_SHIFT); + nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, csrow_nr); + nr_pages <<= 20 - PAGE_SHIFT; edac_dbg(0, "csrow: %d, channel: %d, DBAM idx: %d\n", - csrow_nr, dct, cs_mode); + csrow_nr_orig, dct, cs_mode); edac_dbg(0, "nr_pages/channel: %u\n", nr_pages); return nr_pages; diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index ed3137c1ceb0..ab3a951a17e6 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -155,19 +155,14 @@ static int efi_pstore_scan_sysfs_exit(struct efivar_entry *pos, * efi_pstore_sysfs_entry_iter * * @record: pstore record to pass to callback - * @pos: entry to begin iterating from * * You MUST call efivar_enter_iter_begin() before this function, and * efivar_entry_iter_end() afterwards. * - * It is possible to begin iteration from an arbitrary entry within - * the list by passing @pos. @pos is updated on return to point to - * the next entry of the last one passed to efi_pstore_read_func(). - * To begin iterating from the beginning of the list @pos must be %NULL. */ -static int efi_pstore_sysfs_entry_iter(struct pstore_record *record, - struct efivar_entry **pos) +static int efi_pstore_sysfs_entry_iter(struct pstore_record *record) { + struct efivar_entry **pos = (struct efivar_entry **)&record->psi->data; struct efivar_entry *entry, *n; struct list_head *head = &efivar_sysfs_list; int size = 0; @@ -218,7 +213,6 @@ static int efi_pstore_sysfs_entry_iter(struct pstore_record *record, */ static ssize_t efi_pstore_read(struct pstore_record *record) { - struct efivar_entry *entry = (struct efivar_entry *)record->psi->data; ssize_t size; record->buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL); @@ -229,7 +223,7 @@ static ssize_t efi_pstore_read(struct pstore_record *record) size = -EINTR; goto out; } - size = efi_pstore_sysfs_entry_iter(record, &entry); + size = efi_pstore_sysfs_entry_iter(record); efivar_entry_iter_end(); out: diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c index 3ce813110d5e..1e7860f02f4f 100644 --- a/drivers/firmware/google/vpd.c +++ b/drivers/firmware/google/vpd.c @@ -116,9 +116,13 @@ static int vpd_section_attrib_add(const u8 *key, s32 key_len, return VPD_OK; info = kzalloc(sizeof(*info), GFP_KERNEL); - info->key = kzalloc(key_len + 1, GFP_KERNEL); - if (!info->key) + if (!info) return -ENOMEM; + info->key = kzalloc(key_len + 1, GFP_KERNEL); + if (!info->key) { + ret = -ENOMEM; + goto free_info; + } memcpy(info->key, key, key_len); @@ -135,12 +139,17 @@ static int vpd_section_attrib_add(const u8 *key, s32 key_len, list_add_tail(&info->list, &sec->attribs); ret = sysfs_create_bin_file(sec->kobj, &info->bin_attr); - if (ret) { - kfree(info->key); - return ret; - } + if (ret) + goto free_info_key; return 0; + +free_info_key: + kfree(info->key); +free_info: + kfree(info); + + return ret; } static void vpd_section_attrib_destroy(struct vpd_section *sec) diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c index 874ff32db366..00cfed3c3e1a 100644 --- a/drivers/firmware/ti_sci.c +++ b/drivers/firmware/ti_sci.c @@ -202,7 +202,8 @@ static int ti_sci_debugfs_create(struct platform_device *pdev, info->debug_buffer[info->debug_region_size] = 0; info->d = debugfs_create_file(strncat(debug_name, dev_name(dev), - sizeof(debug_name)), + sizeof(debug_name) - + sizeof("ti_sci_debug@")), 0444, NULL, info, &ti_sci_debug_fops); if (IS_ERR(info->d)) return PTR_ERR(info->d); diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c index 798a3cc480a2..1a3359c0f6cd 100644 --- a/drivers/gpu/drm/arm/hdlcd_crtc.c +++ b/drivers/gpu/drm/arm/hdlcd_crtc.c @@ -10,6 +10,7 @@ */ #include <drm/drmP.h> +#include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc.h> #include <drm/drm_crtc_helper.h> @@ -226,16 +227,33 @@ static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = { static int hdlcd_plane_atomic_check(struct drm_plane *plane, struct drm_plane_state *state) { - u32 src_w, src_h; + struct drm_rect clip = { 0 }; + struct drm_crtc_state *crtc_state; + u32 src_h = state->src_h >> 16; - src_w = state->src_w >> 16; - src_h = state->src_h >> 16; + /* only the HDLCD_REG_FB_LINE_COUNT register has a limit */ + if (src_h >= HDLCD_MAX_YRES) { + DRM_DEBUG_KMS("Invalid source width: %d\n", src_h); + return -EINVAL; + } + + if (!state->fb || !state->crtc) + return 0; - /* we can't do any scaling of the plane source */ - if ((src_w != state->crtc_w) || (src_h != state->crtc_h)) + crtc_state = drm_atomic_get_existing_crtc_state(state->state, + state->crtc); + if (!crtc_state) { + DRM_DEBUG_KMS("Invalid crtc state\n"); return -EINVAL; + } - return 0; + clip.x2 = crtc_state->adjusted_mode.hdisplay; + clip.y2 = crtc_state->adjusted_mode.vdisplay; + + return drm_plane_helper_check_state(state, &clip, + DRM_PLANE_HELPER_NO_SCALING, + DRM_PLANE_HELPER_NO_SCALING, + false, true); } static void hdlcd_plane_atomic_update(struct drm_plane *plane, @@ -244,21 +262,20 @@ static void hdlcd_plane_atomic_update(struct drm_plane *plane, struct drm_framebuffer *fb = plane->state->fb; struct hdlcd_drm_private *hdlcd; struct drm_gem_cma_object *gem; - u32 src_w, src_h, dest_w, dest_h; + u32 src_x, src_y, dest_h; dma_addr_t scanout_start; if (!fb) return; - src_w = plane->state->src_w >> 16; - src_h = plane->state->src_h >> 16; - dest_w = plane->state->crtc_w; - dest_h = plane->state->crtc_h; + src_x = plane->state->src.x1 >> 16; + src_y = plane->state->src.y1 >> 16; + dest_h = drm_rect_height(&plane->state->dst); gem = drm_fb_cma_get_gem_obj(fb, 0); + scanout_start = gem->paddr + fb->offsets[0] + - plane->state->crtc_y * fb->pitches[0] + - plane->state->crtc_x * - fb->format->cpp[0]; + src_y * fb->pitches[0] + + src_x * fb->format->cpp[0]; hdlcd = plane->dev->dev_private; hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, fb->pitches[0]); @@ -305,7 +322,6 @@ static struct drm_plane *hdlcd_plane_init(struct drm_device *drm) formats, ARRAY_SIZE(formats), DRM_PLANE_TYPE_PRIMARY, NULL); if (ret) { - devm_kfree(drm->dev, plane); return ERR_PTR(ret); } @@ -329,7 +345,6 @@ int hdlcd_setup_crtc(struct drm_device *drm) &hdlcd_crtc_funcs, NULL); if (ret) { hdlcd_plane_destroy(primary); - devm_kfree(drm->dev, primary); return ret; } diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c index 65a3bd7a0c00..423dda2785d4 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c @@ -152,8 +152,7 @@ static const struct drm_connector_funcs atmel_hlcdc_panel_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int atmel_hlcdc_attach_endpoint(struct drm_device *dev, - const struct device_node *np) +static int atmel_hlcdc_attach_endpoint(struct drm_device *dev, int endpoint) { struct atmel_hlcdc_dc *dc = dev->dev_private; struct atmel_hlcdc_rgb_output *output; @@ -161,6 +160,11 @@ static int atmel_hlcdc_attach_endpoint(struct drm_device *dev, struct drm_bridge *bridge; int ret; + ret = drm_of_find_panel_or_bridge(dev->dev->of_node, 0, endpoint, + &panel, &bridge); + if (ret) + return ret; + output = devm_kzalloc(dev->dev, sizeof(*output), GFP_KERNEL); if (!output) return -EINVAL; @@ -177,10 +181,6 @@ static int atmel_hlcdc_attach_endpoint(struct drm_device *dev, output->encoder.possible_crtcs = 0x1; - ret = drm_of_find_panel_or_bridge(np, 0, 0, &panel, &bridge); - if (ret) - return ret; - if (panel) { output->connector.dpms = DRM_MODE_DPMS_OFF; output->connector.polled = DRM_CONNECTOR_POLL_CONNECT; @@ -220,22 +220,14 @@ err_encoder_cleanup: int atmel_hlcdc_create_outputs(struct drm_device *dev) { - struct device_node *remote; - int ret = -ENODEV; - int endpoint = 0; - - while (true) { - /* Loop thru possible multiple connections to the output */ - remote = of_graph_get_remote_node(dev->dev->of_node, 0, - endpoint++); - if (!remote) - break; - - ret = atmel_hlcdc_attach_endpoint(dev, remote); - of_node_put(remote); - if (ret) - return ret; - } + int endpoint, ret = 0; + + for (endpoint = 0; !ret; endpoint++) + ret = atmel_hlcdc_attach_endpoint(dev, endpoint); + + /* At least one device was successfully attached.*/ + if (ret == -ENODEV && endpoint) + return 0; return ret; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index e1909429837e..de80ee1b71df 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -44,6 +44,7 @@ static struct etnaviv_gem_submit *submit_create(struct drm_device *dev, /* initially, until copy_from_user() and bo lookup succeeds: */ submit->nr_bos = 0; + submit->fence = NULL; ww_acquire_init(&submit->ticket, &reservation_ww_class); } @@ -294,7 +295,8 @@ static void submit_cleanup(struct etnaviv_gem_submit *submit) } ww_acquire_fini(&submit->ticket); - dma_fence_put(submit->fence); + if (submit->fence) + dma_fence_put(submit->fence); kfree(submit); } diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 0ad1a508e2af..c995e540ff96 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1244,7 +1244,7 @@ static int dma_ctrl_write(struct intel_vgpu *vgpu, unsigned int offset, mode = vgpu_vreg(vgpu, offset); if (GFX_MODE_BIT_SET_IN_MASK(mode, START_DMA)) { - WARN_ONCE(1, "VM(%d): iGVT-g doesn't supporte GuC\n", + WARN_ONCE(1, "VM(%d): iGVT-g doesn't support GuC\n", vgpu->id); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/render.c b/drivers/gpu/drm/i915/gvt/render.c index c6e7972ac21d..a5e11d89df2f 100644 --- a/drivers/gpu/drm/i915/gvt/render.c +++ b/drivers/gpu/drm/i915/gvt/render.c @@ -340,6 +340,9 @@ void intel_gvt_restore_render_mmio(struct intel_vgpu *vgpu, int ring_id) } else v = mmio->value; + if (mmio->in_context) + continue; + I915_WRITE(mmio->reg, v); POSTING_READ(mmio->reg); diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 79ba4b3440aa..f25ff133865f 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -129,9 +129,13 @@ static void try_to_schedule_next_vgpu(struct intel_gvt *gvt) struct vgpu_sched_data *vgpu_data; ktime_t cur_time; - /* no target to schedule */ - if (!scheduler->next_vgpu) + /* no need to schedule if next_vgpu is the same with current_vgpu, + * let scheduler chose next_vgpu again by setting it to NULL. + */ + if (scheduler->next_vgpu == scheduler->current_vgpu) { + scheduler->next_vgpu = NULL; return; + } /* * after the flag is set, workload dispatch thread will diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 2aa6b97fd22f..a0563e18d753 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -195,9 +195,12 @@ static int ppgtt_bind_vma(struct i915_vma *vma, u32 pte_flags; int ret; - ret = vma->vm->allocate_va_range(vma->vm, vma->node.start, vma->size); - if (ret) - return ret; + if (!(vma->flags & I915_VMA_LOCAL_BIND)) { + ret = vma->vm->allocate_va_range(vma->vm, vma->node.start, + vma->size); + if (ret) + return ret; + } vma->pages = vma->obj->mm.pages; @@ -2306,7 +2309,8 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma, if (flags & I915_VMA_LOCAL_BIND) { struct i915_hw_ppgtt *appgtt = i915->mm.aliasing_ppgtt; - if (appgtt->base.allocate_va_range) { + if (!(vma->flags & I915_VMA_LOCAL_BIND) && + appgtt->base.allocate_va_range) { ret = appgtt->base.allocate_va_range(&appgtt->base, vma->node.start, vma->node.size); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 11b12f412492..5a7c63e64381 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3051,10 +3051,14 @@ enum skl_disp_power_wells { #define CLKCFG_FSB_667 (3 << 0) /* hrawclk 166 */ #define CLKCFG_FSB_800 (2 << 0) /* hrawclk 200 */ #define CLKCFG_FSB_1067 (6 << 0) /* hrawclk 266 */ +#define CLKCFG_FSB_1067_ALT (0 << 0) /* hrawclk 266 */ #define CLKCFG_FSB_1333 (7 << 0) /* hrawclk 333 */ -/* Note, below two are guess */ -#define CLKCFG_FSB_1600 (4 << 0) /* hrawclk 400 */ -#define CLKCFG_FSB_1600_ALT (0 << 0) /* hrawclk 400 */ +/* + * Note that on at least on ELK the below value is reported for both + * 333 and 400 MHz BIOS FSB setting, but given that the gmch datasheet + * lists only 200/266/333 MHz FSB as supported let's decode it as 333 MHz. + */ +#define CLKCFG_FSB_1333_ALT (4 << 0) /* hrawclk 333 */ #define CLKCFG_FSB_MASK (7 << 0) #define CLKCFG_MEM_533 (1 << 4) #define CLKCFG_MEM_667 (2 << 4) diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index dd3ad52b7dfe..f29a226e24d8 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -1798,13 +1798,11 @@ static int g4x_hrawclk(struct drm_i915_private *dev_priv) case CLKCFG_FSB_800: return 200000; case CLKCFG_FSB_1067: + case CLKCFG_FSB_1067_ALT: return 266667; case CLKCFG_FSB_1333: + case CLKCFG_FSB_1333_ALT: return 333333; - /* these two are just a guess; one of them might be right */ - case CLKCFG_FSB_1600: - case CLKCFG_FSB_1600_ALT: - return 400000; default: return 133333; } diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 3ffe8b1f1d48..fc0ef492252a 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -410,11 +410,10 @@ static void glk_dsi_device_ready(struct intel_encoder *encoder) val |= (ULPS_STATE_ENTER | DEVICE_READY); I915_WRITE(MIPI_DEVICE_READY(port), val); - /* Wait for ULPS Not active */ + /* Wait for ULPS active */ if (intel_wait_for_register(dev_priv, - MIPI_CTRL(port), GLK_ULPS_NOT_ACTIVE, - GLK_ULPS_NOT_ACTIVE, 20)) - DRM_ERROR("ULPS is still active\n"); + MIPI_CTRL(port), GLK_ULPS_NOT_ACTIVE, 0, 20)) + DRM_ERROR("ULPS not active\n"); /* Exit ULPS */ val = I915_READ(MIPI_DEVICE_READY(port)); diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index 25d8e76489e4..668f00480d97 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -63,6 +63,7 @@ #include <linux/acpi.h> #include <linux/device.h> #include <linux/pci.h> +#include <linux/pm_runtime.h> #include "i915_drv.h" #include <linux/delay.h> @@ -121,6 +122,10 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv) kfree(rsc); + pm_runtime_forbid(&platdev->dev); + pm_runtime_set_active(&platdev->dev); + pm_runtime_enable(&platdev->dev); + return platdev; err: diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 21b10f9840c9..549763f5e17d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -360,6 +360,8 @@ nouveau_display_hpd_work(struct work_struct *work) pm_runtime_get_sync(drm->dev->dev); drm_helper_hpd_irq_event(drm->dev); + /* enable polling for external displays */ + drm_kms_helper_poll_enable(drm->dev); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); @@ -413,10 +415,6 @@ nouveau_display_init(struct drm_device *dev) if (ret) return ret; - /* enable polling for external displays */ - if (!dev->mode_config.poll_enabled) - drm_kms_helper_poll_enable(dev); - /* enable hotplug interrupts */ list_for_each_entry(connector, &dev->mode_config.connector_list, head) { struct nouveau_connector *conn = nouveau_connector(connector); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 2b6ac24ce690..36268e1802b5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -502,6 +502,9 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags) pm_runtime_allow(dev->dev); pm_runtime_mark_last_busy(dev->dev); pm_runtime_put(dev->dev); + } else { + /* enable polling for external displays */ + drm_kms_helper_poll_enable(dev); } return 0; @@ -774,9 +777,6 @@ nouveau_pmops_runtime_resume(struct device *dev) ret = nouveau_do_resume(drm_dev, true); - if (!drm_dev->mode_config.poll_enabled) - drm_kms_helper_poll_enable(drm_dev); - /* do magic */ nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25)); vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c index 3a24788c3185..a7e55c422501 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c @@ -148,7 +148,7 @@ gk104_fifo_runlist_commit(struct gk104_fifo *fifo, int runl) case NVKM_MEM_TARGET_NCOH: target = 3; break; default: WARN_ON(1); - return; + goto unlock; } nvkm_wr32(device, 0x002270, (nvkm_memory_addr(mem) >> 12) | @@ -160,6 +160,7 @@ gk104_fifo_runlist_commit(struct gk104_fifo *fifo, int runl) & 0x00100000), msecs_to_jiffies(2000)) == 0) nvkm_error(subdev, "runlist %d update timeout\n", runl); +unlock: mutex_unlock(&subdev->mutex); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_gr.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_gr.c index d1cf02d22db1..1b0c793c0192 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_gr.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_gr.c @@ -116,6 +116,7 @@ ls_ucode_img_load_gr(const struct nvkm_subdev *subdev, struct ls_ucode_img *img, ret = nvkm_firmware_get(subdev->device, f, &sig); if (ret) goto free_data; + img->sig = kmemdup(sig->data, sig->size, GFP_KERNEL); if (!img->sig) { ret = -ENOMEM; @@ -126,8 +127,9 @@ ls_ucode_img_load_gr(const struct nvkm_subdev *subdev, struct ls_ucode_img *img, img->ucode_data = ls_ucode_img_build(bl, code, data, &img->ucode_desc); if (IS_ERR(img->ucode_data)) { + kfree(img->sig); ret = PTR_ERR(img->ucode_data); - goto free_data; + goto free_sig; } img->ucode_size = img->ucode_desc.image_size; diff --git a/drivers/gpu/host1x/Kconfig b/drivers/gpu/host1x/Kconfig index b2fd029d67b3..91916326957f 100644 --- a/drivers/gpu/host1x/Kconfig +++ b/drivers/gpu/host1x/Kconfig @@ -1,6 +1,7 @@ config TEGRA_HOST1X tristate "NVIDIA Tegra host1x driver" depends on ARCH_TEGRA || (ARM && COMPILE_TEST) + select IOMMU_IOVA if IOMMU_SUPPORT help Driver for the NVIDIA Tegra host1x hardware. diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 3ac4c03ba77b..c13a4fd86b3c 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -605,6 +605,13 @@ static int coretemp_cpu_online(unsigned int cpu) struct platform_data *pdata; /* + * Don't execute this on resume as the offline callback did + * not get executed on suspend. + */ + if (cpuhp_tasks_frozen) + return 0; + + /* * CPUID.06H.EAX[0] indicates whether the CPU has thermal * sensors. We check this bit only, all the early CPUs * without thermal sensors will be filtered out. @@ -654,6 +661,13 @@ static int coretemp_cpu_offline(unsigned int cpu) struct temp_data *tdata; int indx, target; + /* + * Don't execute this on suspend as the device remove locks + * up the machine. + */ + if (cpuhp_tasks_frozen) + return 0; + /* If the physical CPU device does not exist, just return */ if (!pdev) return 0; diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index f2acd4b6bf01..6283b99d2b17 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -96,6 +96,7 @@ static int dw_i2c_acpi_configure(struct platform_device *pdev) struct dw_i2c_dev *dev = platform_get_drvdata(pdev); acpi_handle handle = ACPI_HANDLE(&pdev->dev); const struct acpi_device_id *id; + u32 ss_ht, fp_ht, hs_ht, fs_ht; struct acpi_device *adev; const char *uid; @@ -107,23 +108,24 @@ static int dw_i2c_acpi_configure(struct platform_device *pdev) * Try to get SDA hold time and *CNT values from an ACPI method for * selected speed modes. */ + dw_i2c_acpi_params(pdev, "SSCN", &dev->ss_hcnt, &dev->ss_lcnt, &ss_ht); + dw_i2c_acpi_params(pdev, "FPCN", &dev->fp_hcnt, &dev->fp_lcnt, &fp_ht); + dw_i2c_acpi_params(pdev, "HSCN", &dev->hs_hcnt, &dev->hs_lcnt, &hs_ht); + dw_i2c_acpi_params(pdev, "FMCN", &dev->fs_hcnt, &dev->fs_lcnt, &fs_ht); + switch (dev->clk_freq) { case 100000: - dw_i2c_acpi_params(pdev, "SSCN", &dev->ss_hcnt, &dev->ss_lcnt, - &dev->sda_hold_time); + dev->sda_hold_time = ss_ht; break; case 1000000: - dw_i2c_acpi_params(pdev, "FPCN", &dev->fp_hcnt, &dev->fp_lcnt, - &dev->sda_hold_time); + dev->sda_hold_time = fp_ht; break; case 3400000: - dw_i2c_acpi_params(pdev, "HSCN", &dev->hs_hcnt, &dev->hs_lcnt, - &dev->sda_hold_time); + dev->sda_hold_time = hs_ht; break; case 400000: default: - dw_i2c_acpi_params(pdev, "FMCN", &dev->fs_hcnt, &dev->fs_lcnt, - &dev->sda_hold_time); + dev->sda_hold_time = fs_ht; break; } diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index cf737ec8563b..5c4db65c5019 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -819,7 +819,6 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, rc = -EINVAL; goto out; } - drv_data->irq = irq_of_parse_and_map(np, 0); drv_data->rstc = devm_reset_control_get_optional(dev, NULL); if (IS_ERR(drv_data->rstc)) { @@ -902,10 +901,11 @@ mv64xxx_i2c_probe(struct platform_device *pd) if (!IS_ERR(drv_data->clk)) clk_prepare_enable(drv_data->clk); + drv_data->irq = platform_get_irq(pd, 0); + if (pdata) { drv_data->freq_m = pdata->freq_m; drv_data->freq_n = pdata->freq_n; - drv_data->irq = platform_get_irq(pd, 0); drv_data->adapter.timeout = msecs_to_jiffies(pdata->timeout); drv_data->offload_enabled = false; memcpy(&drv_data->reg_offsets, &mv64xxx_i2c_regs_mv64xxx, sizeof(drv_data->reg_offsets)); @@ -915,7 +915,7 @@ mv64xxx_i2c_probe(struct platform_device *pd) goto exit_clk; } if (drv_data->irq < 0) { - rc = -ENXIO; + rc = drv_data->irq; goto exit_reset; } diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c index dbe7e44c9321..6ba6c83ca8f1 100644 --- a/drivers/i2c/busses/i2c-xgene-slimpro.c +++ b/drivers/i2c/busses/i2c-xgene-slimpro.c @@ -416,6 +416,7 @@ static int xgene_slimpro_i2c_probe(struct platform_device *pdev) adapter->class = I2C_CLASS_HWMON; adapter->dev.parent = &pdev->dev; adapter->dev.of_node = pdev->dev.of_node; + ACPI_COMPANION_SET(&adapter->dev, ACPI_COMPANION(&pdev->dev)); i2c_set_adapdata(adapter, ctx); rc = i2c_add_adapter(adapter); if (rc) { diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 26f7237558ba..9669ca4937b8 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -395,18 +395,20 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, if (force_nr) { priv->adap.nr = force_nr; ret = i2c_add_numbered_adapter(&priv->adap); - dev_err(&parent->dev, - "failed to add mux-adapter %u as bus %u (error=%d)\n", - chan_id, force_nr, ret); + if (ret < 0) { + dev_err(&parent->dev, + "failed to add mux-adapter %u as bus %u (error=%d)\n", + chan_id, force_nr, ret); + goto err_free_priv; + } } else { ret = i2c_add_adapter(&priv->adap); - dev_err(&parent->dev, - "failed to add mux-adapter %u (error=%d)\n", - chan_id, ret); - } - if (ret < 0) { - kfree(priv); - return ret; + if (ret < 0) { + dev_err(&parent->dev, + "failed to add mux-adapter %u (error=%d)\n", + chan_id, ret); + goto err_free_priv; + } } WARN(sysfs_create_link(&priv->adap.dev.kobj, &muxc->dev->kobj, @@ -422,6 +424,10 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, muxc->adapter[muxc->num_adapters++] = &priv->adap; return 0; + +err_free_priv: + kfree(priv); + return ret; } EXPORT_SYMBOL_GPL(i2c_mux_add_adapter); diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c index 406d5059072c..d97031804de8 100644 --- a/drivers/i2c/muxes/i2c-mux-reg.c +++ b/drivers/i2c/muxes/i2c-mux-reg.c @@ -196,20 +196,25 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); mux->data.reg_size = resource_size(res); mux->data.reg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(mux->data.reg)) - return PTR_ERR(mux->data.reg); + if (IS_ERR(mux->data.reg)) { + ret = PTR_ERR(mux->data.reg); + goto err_put_parent; + } } if (mux->data.reg_size != 4 && mux->data.reg_size != 2 && mux->data.reg_size != 1) { dev_err(&pdev->dev, "Invalid register size\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_parent; } muxc = i2c_mux_alloc(parent, &pdev->dev, mux->data.n_values, 0, 0, i2c_mux_reg_select, NULL); - if (!muxc) - return -ENOMEM; + if (!muxc) { + ret = -ENOMEM; + goto err_put_parent; + } muxc->priv = mux; platform_set_drvdata(pdev, muxc); @@ -223,7 +228,7 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class); if (ret) - goto add_adapter_failed; + goto err_del_mux_adapters; } dev_dbg(&pdev->dev, "%d port mux on %s adapter\n", @@ -231,8 +236,10 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) return 0; -add_adapter_failed: +err_del_mux_adapters: i2c_mux_del_adapters(muxc); +err_put_parent: + i2c_put_adapter(parent); return ret; } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 8348f366ddd1..62618e77bedc 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -396,13 +396,13 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie, dma_addr_t iova, size_t size) { struct iova_domain *iovad = &cookie->iovad; - unsigned long shift = iova_shift(iovad); /* The MSI case is only ever cleaning up its most recent allocation */ if (cookie->type == IOMMU_DMA_MSI_COOKIE) cookie->msi_iova -= size; else - free_iova_fast(iovad, iova >> shift, size >> shift); + free_iova_fast(iovad, iova_pfn(iovad, iova), + size >> iova_shift(iovad)); } static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr, @@ -617,11 +617,14 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, { struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; - struct iova_domain *iovad = &cookie->iovad; - size_t iova_off = iova_offset(iovad, phys); + size_t iova_off = 0; dma_addr_t iova; - size = iova_align(iovad, size + iova_off); + if (cookie->type == IOMMU_DMA_IOVA_COOKIE) { + iova_off = iova_offset(&cookie->iovad, phys); + size = iova_align(&cookie->iovad, size + iova_off); + } + iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev); if (!iova) return DMA_ERROR_CODE; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 90ab0115d78e..fc2765ccdb57 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2055,11 +2055,14 @@ static int domain_context_mapping_one(struct dmar_domain *domain, if (context_copied(context)) { u16 did_old = context_domain_id(context); - if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) + if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) { iommu->flush.flush_context(iommu, did_old, (((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL); + iommu->flush.flush_iotlb(iommu, did_old, 0, 0, + DMA_TLB_DSI_FLUSH); + } } pgd = domain->pgd; diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index a27ef570c328..bc1efbfb9ddf 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -18,6 +18,7 @@ #include <linux/clk.h> #include <linux/component.h> #include <linux/device.h> +#include <linux/dma-mapping.h> #include <linux/dma-iommu.h> #include <linux/err.h> #include <linux/interrupt.h> diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index d2306c821ebb..31d6b5a582d2 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -106,10 +106,7 @@ static inline void get_mbigen_type_reg(irq_hw_number_t hwirq, static inline void get_mbigen_clear_reg(irq_hw_number_t hwirq, u32 *mask, u32 *addr) { - unsigned int ofst; - - hwirq -= RESERVED_IRQ_PER_MBIGEN_CHIP; - ofst = hwirq / 32 * 4; + unsigned int ofst = (hwirq / 32) * 4; *mask = 1 << (hwirq % 32); *addr = ofst + REG_MBIGEN_CLEAR_OFFSET; @@ -337,9 +334,15 @@ static int mbigen_device_probe(struct platform_device *pdev) mgn_chip->pdev = pdev; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mgn_chip->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(mgn_chip->base)) - return PTR_ERR(mgn_chip->base); + if (!res) + return -EINVAL; + + mgn_chip->base = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!mgn_chip->base) { + dev_err(&pdev->dev, "failed to ioremap %pR\n", res); + return -ENOMEM; + } if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node) err = mbigen_of_create_domain(pdev, mgn_chip); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 5db11a405129..cd8139593ccd 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -218,7 +218,7 @@ static DEFINE_SPINLOCK(param_spinlock); * Buffers are freed after this timeout */ static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS; -static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; +static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES; static unsigned long dm_bufio_peak_allocated; static unsigned long dm_bufio_allocated_kmem_cache; @@ -1558,10 +1558,10 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) return true; } -static unsigned get_retain_buffers(struct dm_bufio_client *c) +static unsigned long get_retain_buffers(struct dm_bufio_client *c) { - unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); - return retain_bytes / c->block_size; + unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes); + return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT); } static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, @@ -1571,7 +1571,7 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, struct dm_buffer *b, *tmp; unsigned long freed = 0; unsigned long count = nr_to_scan; - unsigned retain_target = get_retain_buffers(c); + unsigned long retain_target = get_retain_buffers(c); for (l = 0; l < LIST_SIZE; l++) { list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) { @@ -1794,8 +1794,8 @@ static bool older_than(struct dm_buffer *b, unsigned long age_hz) static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz) { struct dm_buffer *b, *tmp; - unsigned retain_target = get_retain_buffers(c); - unsigned count; + unsigned long retain_target = get_retain_buffers(c); + unsigned long count; LIST_HEAD(write_list); dm_bufio_lock(c); @@ -1955,7 +1955,7 @@ MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache"); module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds"); -module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR); +module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory"); module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR); diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c index 9b1afdfb13f0..707233891291 100644 --- a/drivers/md/dm-cache-background-tracker.c +++ b/drivers/md/dm-cache-background-tracker.c @@ -33,6 +33,11 @@ struct background_tracker *btracker_create(unsigned max_work) { struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL); + if (!b) { + DMERR("couldn't create background_tracker"); + return NULL; + } + b->max_work = max_work; atomic_set(&b->pending_promotes, 0); atomic_set(&b->pending_writebacks, 0); diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index 72479bd61e11..e5eb9c9b4bc8 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1120,8 +1120,6 @@ static bool clean_target_met(struct smq_policy *mq, bool idle) * Cache entries may not be populated. So we cannot rely on the * size of the clean queue. */ - unsigned nr_clean; - if (idle) { /* * We'd like to clean everything. @@ -1129,18 +1127,16 @@ static bool clean_target_met(struct smq_policy *mq, bool idle) return q_size(&mq->dirty) == 0u; } - nr_clean = from_cblock(mq->cache_size) - q_size(&mq->dirty); - return (nr_clean + btracker_nr_writebacks_queued(mq->bg_work)) >= - percent_to_target(mq, CLEAN_TARGET); + /* + * If we're busy we don't worry about cleaning at all. + */ + return true; } -static bool free_target_met(struct smq_policy *mq, bool idle) +static bool free_target_met(struct smq_policy *mq) { unsigned nr_free; - if (!idle) - return true; - nr_free = from_cblock(mq->cache_size) - mq->cache_alloc.nr_allocated; return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >= percent_to_target(mq, FREE_TARGET); @@ -1190,9 +1186,9 @@ static void queue_demotion(struct smq_policy *mq) if (unlikely(WARN_ON_ONCE(!mq->migrations_allowed))) return; - e = q_peek(&mq->clean, mq->clean.nr_levels, true); + e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true); if (!e) { - if (!clean_target_met(mq, false)) + if (!clean_target_met(mq, true)) queue_writeback(mq); return; } @@ -1220,7 +1216,7 @@ static void queue_promotion(struct smq_policy *mq, dm_oblock_t oblock, * We always claim to be 'idle' to ensure some demotions happen * with continuous loads. */ - if (!free_target_met(mq, true)) + if (!free_target_met(mq)) queue_demotion(mq); return; } @@ -1421,14 +1417,10 @@ static int smq_get_background_work(struct dm_cache_policy *p, bool idle, spin_lock_irqsave(&mq->lock, flags); r = btracker_issue(mq->bg_work, result); if (r == -ENODATA) { - /* find some writeback work to do */ - if (mq->migrations_allowed && !free_target_met(mq, idle)) - queue_demotion(mq); - - else if (!clean_target_met(mq, idle)) + if (!clean_target_met(mq, idle)) { queue_writeback(mq); - - r = btracker_issue(mq->bg_work, result); + r = btracker_issue(mq->bg_work, result); + } } spin_unlock_irqrestore(&mq->lock, flags); @@ -1452,6 +1444,7 @@ static void __complete_background_work(struct smq_policy *mq, clear_pending(mq, e); if (success) { e->oblock = work->oblock; + e->level = NR_CACHE_LEVELS - 1; push(mq, e); // h, q, a } else { diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 1db375f50a13..d682a0511381 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -94,6 +94,9 @@ static void iot_io_begin(struct io_tracker *iot, sector_t len) static void __iot_io_end(struct io_tracker *iot, sector_t len) { + if (!len) + return; + iot->in_flight -= len; if (!iot->in_flight) iot->idle_time = jiffies; @@ -474,7 +477,7 @@ struct cache { spinlock_t invalidation_lock; struct list_head invalidation_requests; - struct io_tracker origin_tracker; + struct io_tracker tracker; struct work_struct commit_ws; struct batcher committer; @@ -901,8 +904,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio) static bool accountable_bio(struct cache *cache, struct bio *bio) { - return ((bio->bi_bdev == cache->origin_dev->bdev) && - bio_op(bio) != REQ_OP_DISCARD); + return bio_op(bio) != REQ_OP_DISCARD; } static void accounted_begin(struct cache *cache, struct bio *bio) @@ -912,7 +914,7 @@ static void accounted_begin(struct cache *cache, struct bio *bio) if (accountable_bio(cache, bio)) { pb->len = bio_sectors(bio); - iot_io_begin(&cache->origin_tracker, pb->len); + iot_io_begin(&cache->tracker, pb->len); } } @@ -921,7 +923,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio) size_t pb_data_size = get_per_bio_data_size(cache); struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); - iot_io_end(&cache->origin_tracker, pb->len); + iot_io_end(&cache->tracker, pb->len); } static void accounted_request(struct cache *cache, struct bio *bio) @@ -1716,20 +1718,19 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock, enum busy { IDLE, - MODERATE, BUSY }; static enum busy spare_migration_bandwidth(struct cache *cache) { - bool idle = iot_idle_for(&cache->origin_tracker, HZ); + bool idle = iot_idle_for(&cache->tracker, HZ); sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) * cache->sectors_per_block; - if (current_volume <= cache->migration_threshold) - return idle ? IDLE : MODERATE; + if (idle && current_volume <= cache->migration_threshold) + return IDLE; else - return idle ? MODERATE : BUSY; + return BUSY; } static void inc_hit_counter(struct cache *cache, struct bio *bio) @@ -2045,8 +2046,6 @@ static void check_migrations(struct work_struct *ws) for (;;) { b = spare_migration_bandwidth(cache); - if (b == BUSY) - break; r = policy_get_background_work(cache->policy, b == IDLE, &op); if (r == -ENODATA) @@ -2717,7 +2716,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) batcher_init(&cache->committer, commit_op, cache, issue_op, cache, cache->wq); - iot_init(&cache->origin_tracker); + iot_init(&cache->tracker); init_rwsem(&cache->background_work_lock); prevent_background_work(cache); @@ -2941,7 +2940,7 @@ static void cache_postsuspend(struct dm_target *ti) cancel_delayed_work(&cache->waker); flush_workqueue(cache->wq); - WARN_ON(cache->origin_tracker.in_flight); + WARN_ON(cache->tracker.in_flight); /* * If it's a flush suspend there won't be any deferred bios, so this diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 926a6bcb32c8..3df056b73b66 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -447,7 +447,7 @@ failed: * it has been invoked. */ #define dm_report_EIO(m) \ -({ \ +do { \ struct mapped_device *md = dm_table_get_md((m)->ti->table); \ \ pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \ @@ -455,8 +455,7 @@ failed: test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags), \ test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags), \ dm_noflush_suspending((m)->ti)); \ - -EIO; \ -}) +} while (0) /* * Map cloned requests (request-based multipath) @@ -481,7 +480,8 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, if (!pgpath) { if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) return DM_MAPIO_DELAY_REQUEUE; - return dm_report_EIO(m); /* Failed */ + dm_report_EIO(m); /* Failed */ + return DM_MAPIO_KILL; } else if (test_bit(MPATHF_QUEUE_IO, &m->flags) || test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) { if (pg_init_all_paths(m)) @@ -558,7 +558,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m if (!pgpath) { if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) return DM_MAPIO_REQUEUE; - return dm_report_EIO(m); + dm_report_EIO(m); + return -EIO; } mpio->pgpath = pgpath; @@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone, if (atomic_read(&m->nr_valid_paths) == 0 && !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { if (error == -EIO) - error = dm_report_EIO(m); + dm_report_EIO(m); /* complete with the original error */ r = DM_ENDIO_DONE; } @@ -1524,8 +1525,10 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone, fail_path(mpio->pgpath); if (atomic_read(&m->nr_valid_paths) == 0 && - !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) - return dm_report_EIO(m); + !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { + dm_report_EIO(m); + return -EIO; + } /* Queue for the daemon to resubmit */ dm_bio_restore(get_bio_details_from_bio(clone), clone); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 2af27026aa2e..b639fa7246ee 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -507,6 +507,7 @@ static int map_request(struct dm_rq_target_io *tio) case DM_MAPIO_KILL: /* The target wants to complete the I/O */ dm_kill_unmapped_request(rq, -EIO); + break; default: DMWARN("unimplemented target map return value: %d", r); BUG(); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 0f0251d0d337..d31d18d9727c 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -484,11 +484,11 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) if (r < 0) return r; - r = save_sm_roots(pmd); + r = dm_tm_pre_commit(pmd->tm); if (r < 0) return r; - r = dm_tm_pre_commit(pmd->tm); + r = save_sm_roots(pmd); if (r < 0) return r; diff --git a/drivers/md/md.c b/drivers/md/md.c index 82f798be964f..10367ffe92e3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8022,18 +8022,15 @@ EXPORT_SYMBOL(md_write_end); * may proceed without blocking. It is important to call this before * attempting a GFP_KERNEL allocation while holding the mddev lock. * Must be called with mddev_lock held. - * - * In the ->external case MD_SB_CHANGE_PENDING can not be cleared until mddev->lock - * is dropped, so return -EAGAIN after notifying userspace. */ -int md_allow_write(struct mddev *mddev) +void md_allow_write(struct mddev *mddev) { if (!mddev->pers) - return 0; + return; if (mddev->ro) - return 0; + return; if (!mddev->pers->sync_request) - return 0; + return; spin_lock(&mddev->lock); if (mddev->in_sync) { @@ -8046,13 +8043,12 @@ int md_allow_write(struct mddev *mddev) spin_unlock(&mddev->lock); md_update_sb(mddev, 0); sysfs_notify_dirent_safe(mddev->sysfs_state); + /* wait for the dirty state to be recorded in the metadata */ + wait_event(mddev->sb_wait, + !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) && + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); } else spin_unlock(&mddev->lock); - - if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) - return -EAGAIN; - else - return 0; } EXPORT_SYMBOL_GPL(md_allow_write); diff --git a/drivers/md/md.h b/drivers/md/md.h index 4e75d121bfcc..11f15146ce51 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -665,7 +665,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, bool metadata_op); extern void md_do_sync(struct md_thread *thread); extern void md_new_event(struct mddev *mddev); -extern int md_allow_write(struct mddev *mddev); +extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index ebb280a14325..32adf6b4a9c7 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -142,10 +142,23 @@ static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b) static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b) { + int r; + uint32_t old_count; enum allocation_event ev; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); - return sm_ll_dec(&smd->ll, b, &ev); + r = sm_ll_dec(&smd->ll, b, &ev); + if (!r && (ev == SM_FREE)) { + /* + * It's only free if it's also free in the last + * transaction. + */ + r = sm_ll_lookup(&smd->old_ll, b, &old_count); + if (!r && !old_count) + smd->nr_allocated_this_transaction--; + } + + return r; } static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 84e58596594d..d6c0bc76e837 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -385,7 +385,7 @@ static int raid0_run(struct mddev *mddev) blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_discard_sectors(mddev->queue, UINT_MAX); blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); blk_queue_io_opt(mddev->queue, @@ -459,6 +459,95 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev, } } +static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) +{ + struct r0conf *conf = mddev->private; + struct strip_zone *zone; + sector_t start = bio->bi_iter.bi_sector; + sector_t end; + unsigned int stripe_size; + sector_t first_stripe_index, last_stripe_index; + sector_t start_disk_offset; + unsigned int start_disk_index; + sector_t end_disk_offset; + unsigned int end_disk_index; + unsigned int disk; + + zone = find_zone(conf, &start); + + if (bio_end_sector(bio) > zone->zone_end) { + struct bio *split = bio_split(bio, + zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO, + mddev->bio_set); + bio_chain(split, bio); + generic_make_request(bio); + bio = split; + end = zone->zone_end; + } else + end = bio_end_sector(bio); + + if (zone != conf->strip_zone) + end = end - zone[-1].zone_end; + + /* Now start and end is the offset in zone */ + stripe_size = zone->nb_dev * mddev->chunk_sectors; + + first_stripe_index = start; + sector_div(first_stripe_index, stripe_size); + last_stripe_index = end; + sector_div(last_stripe_index, stripe_size); + + start_disk_index = (int)(start - first_stripe_index * stripe_size) / + mddev->chunk_sectors; + start_disk_offset = ((int)(start - first_stripe_index * stripe_size) % + mddev->chunk_sectors) + + first_stripe_index * mddev->chunk_sectors; + end_disk_index = (int)(end - last_stripe_index * stripe_size) / + mddev->chunk_sectors; + end_disk_offset = ((int)(end - last_stripe_index * stripe_size) % + mddev->chunk_sectors) + + last_stripe_index * mddev->chunk_sectors; + + for (disk = 0; disk < zone->nb_dev; disk++) { + sector_t dev_start, dev_end; + struct bio *discard_bio = NULL; + struct md_rdev *rdev; + + if (disk < start_disk_index) + dev_start = (first_stripe_index + 1) * + mddev->chunk_sectors; + else if (disk > start_disk_index) + dev_start = first_stripe_index * mddev->chunk_sectors; + else + dev_start = start_disk_offset; + + if (disk < end_disk_index) + dev_end = (last_stripe_index + 1) * mddev->chunk_sectors; + else if (disk > end_disk_index) + dev_end = last_stripe_index * mddev->chunk_sectors; + else + dev_end = end_disk_offset; + + if (dev_end <= dev_start) + continue; + + rdev = conf->devlist[(zone - conf->strip_zone) * + conf->strip_zone[0].nb_dev + disk]; + if (__blkdev_issue_discard(rdev->bdev, + dev_start + zone->dev_start + rdev->data_offset, + dev_end - dev_start, GFP_NOIO, 0, &discard_bio) || + !discard_bio) + continue; + bio_chain(discard_bio, bio); + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(rdev->bdev), + discard_bio, disk_devt(mddev->gendisk), + bio->bi_iter.bi_sector); + generic_make_request(discard_bio); + } + bio_endio(bio); +} + static void raid0_make_request(struct mddev *mddev, struct bio *bio) { struct strip_zone *zone; @@ -473,6 +562,11 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) return; } + if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) { + raid0_handle_discard(mddev, bio); + return; + } + bio_sector = bio->bi_iter.bi_sector; sector = bio_sector; chunk_sects = mddev->chunk_sectors; @@ -498,19 +592,13 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) bio->bi_iter.bi_sector = sector + zone->dev_start + tmp_dev->data_offset; - if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) { - /* Just ignore it */ - bio_endio(bio); - } else { - if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), - bio, disk_devt(mddev->gendisk), - bio_sector); - mddev_check_writesame(mddev, bio); - mddev_check_write_zeroes(mddev, bio); - generic_make_request(bio); - } + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), + bio, disk_devt(mddev->gendisk), + bio_sector); + mddev_check_writesame(mddev, bio); + mddev_check_write_zeroes(mddev, bio); + generic_make_request(bio); } static void raid0_status(struct seq_file *seq, struct mddev *mddev) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7ed59351fe97..af5056d56878 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -666,8 +666,11 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect break; } continue; - } else + } else { + if ((sectors > best_good_sectors) && (best_disk >= 0)) + best_disk = -1; best_good_sectors = sectors; + } if (best_disk >= 0) /* At least two disks to choose from so failfast is OK */ @@ -1529,17 +1532,16 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, plug = container_of(cb, struct raid1_plug_cb, cb); else plug = NULL; - spin_lock_irqsave(&conf->device_lock, flags); if (plug) { bio_list_add(&plug->pending, mbio); plug->pending_cnt++; } else { + spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; - } - spin_unlock_irqrestore(&conf->device_lock, flags); - if (!plug) + spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); + } } r1_bio_write_done(r1_bio); @@ -3197,7 +3199,7 @@ static int raid1_reshape(struct mddev *mddev) struct r1conf *conf = mddev->private; int cnt, raid_disks; unsigned long flags; - int d, d2, err; + int d, d2; /* Cannot change chunk_size, layout, or level */ if (mddev->chunk_sectors != mddev->new_chunk_sectors || @@ -3209,11 +3211,8 @@ static int raid1_reshape(struct mddev *mddev) return -EINVAL; } - if (!mddev_is_clustered(mddev)) { - err = md_allow_write(mddev); - if (err) - return err; - } + if (!mddev_is_clustered(mddev)) + md_allow_write(mddev); raid_disks = mddev->raid_disks + mddev->delta_disks; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 6b86a0032cf8..4343d7ff9916 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1282,17 +1282,16 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, plug = container_of(cb, struct raid10_plug_cb, cb); else plug = NULL; - spin_lock_irqsave(&conf->device_lock, flags); if (plug) { bio_list_add(&plug->pending, mbio); plug->pending_cnt++; } else { + spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; - } - spin_unlock_irqrestore(&conf->device_lock, flags); - if (!plug) + spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); + } } static void raid10_write_request(struct mddev *mddev, struct bio *bio, diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 26ba09282e7c..4c00bc248287 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -24,6 +24,7 @@ #include "md.h" #include "raid5.h" #include "bitmap.h" +#include "raid5-log.h" /* * metadata/data stored in disk with 4k size unit (a block) regardless @@ -622,20 +623,30 @@ static void r5l_do_submit_io(struct r5l_log *log, struct r5l_io_unit *io) __r5l_set_io_unit_state(io, IO_UNIT_IO_START); spin_unlock_irqrestore(&log->io_list_lock, flags); + /* + * In case of journal device failures, submit_bio will get error + * and calls endio, then active stripes will continue write + * process. Therefore, it is not necessary to check Faulty bit + * of journal device here. + * + * We can't check split_bio after current_bio is submitted. If + * io->split_bio is null, after current_bio is submitted, current_bio + * might already be completed and the io_unit is freed. We submit + * split_bio first to avoid the issue. + */ + if (io->split_bio) { + if (io->has_flush) + io->split_bio->bi_opf |= REQ_PREFLUSH; + if (io->has_fua) + io->split_bio->bi_opf |= REQ_FUA; + submit_bio(io->split_bio); + } + if (io->has_flush) io->current_bio->bi_opf |= REQ_PREFLUSH; if (io->has_fua) io->current_bio->bi_opf |= REQ_FUA; submit_bio(io->current_bio); - - if (!io->split_bio) - return; - - if (io->has_flush) - io->split_bio->bi_opf |= REQ_PREFLUSH; - if (io->has_fua) - io->split_bio->bi_opf |= REQ_FUA; - submit_bio(io->split_bio); } /* deferred io_unit will be dispatched here */ @@ -670,6 +681,11 @@ static void r5c_disable_writeback_async(struct work_struct *work) return; pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n", mdname(mddev)); + + /* wait superblock change before suspend */ + wait_event(mddev->sb_wait, + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); + mddev_suspend(mddev); log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; mddev_resume(mddev); @@ -2621,8 +2637,11 @@ int r5c_try_caching_write(struct r5conf *conf, * When run in degraded mode, array is set to write-through mode. * This check helps drain pending write safely in the transition to * write-through mode. + * + * When a stripe is syncing, the write is also handled in write + * through mode. */ - if (s->failed) { + if (s->failed || test_bit(STRIPE_SYNCING, &sh->state)) { r5c_make_stripe_write_out(sh); return -EAGAIN; } @@ -2825,6 +2844,9 @@ void r5c_finish_stripe_write_out(struct r5conf *conf, } r5l_append_flush_payload(log, sh->sector); + /* stripe is flused to raid disks, we can do resync now */ + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) + set_bit(STRIPE_HANDLE, &sh->state); } int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh) @@ -2973,7 +2995,7 @@ ioerr: return ret; } -void r5c_update_on_rdev_error(struct mddev *mddev) +void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev) { struct r5conf *conf = mddev->private; struct r5l_log *log = conf->log; @@ -2981,7 +3003,8 @@ void r5c_update_on_rdev_error(struct mddev *mddev) if (!log) return; - if (raid5_calc_degraded(conf) > 0 && + if ((raid5_calc_degraded(conf) > 0 || + test_bit(Journal, &rdev->flags)) && conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK) schedule_work(&log->disable_writeback_work); } diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index 27097101ccca..328d67aedda4 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -28,7 +28,8 @@ extern void r5c_flush_cache(struct r5conf *conf, int num); extern void r5c_check_stripe_cache_usage(struct r5conf *conf); extern void r5c_check_cached_full_stripe(struct r5conf *conf); extern struct md_sysfs_entry r5c_journal_mode; -extern void r5c_update_on_rdev_error(struct mddev *mddev); +extern void r5c_update_on_rdev_error(struct mddev *mddev, + struct md_rdev *rdev); extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect); extern struct dma_async_tx_descriptor * diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2e38cfac5b1d..9c4f7659f8b1 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -103,8 +103,7 @@ static inline void unlock_device_hash_lock(struct r5conf *conf, int hash) static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) { int i; - local_irq_disable(); - spin_lock(conf->hash_locks); + spin_lock_irq(conf->hash_locks); for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++) spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks); spin_lock(&conf->device_lock); @@ -114,9 +113,9 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf) { int i; spin_unlock(&conf->device_lock); - for (i = NR_STRIPE_HASH_LOCKS; i; i--) - spin_unlock(conf->hash_locks + i - 1); - local_irq_enable(); + for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--) + spin_unlock(conf->hash_locks + i); + spin_unlock_irq(conf->hash_locks); } /* Find first data disk in a raid6 stripe */ @@ -234,11 +233,15 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, if (test_bit(R5_InJournal, &sh->dev[i].flags)) injournal++; /* - * When quiesce in r5c write back, set STRIPE_HANDLE for stripes with - * data in journal, so they are not released to cached lists + * In the following cases, the stripe cannot be released to cached + * lists. Therefore, we make the stripe write out and set + * STRIPE_HANDLE: + * 1. when quiesce in r5c write back; + * 2. when resync is requested fot the stripe. */ - if (conf->quiesce && r5c_is_writeback(conf->log) && - !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) { + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) || + (conf->quiesce && r5c_is_writeback(conf->log) && + !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0)) { if (test_bit(STRIPE_R5C_CACHING, &sh->state)) r5c_make_stripe_write_out(sh); set_bit(STRIPE_HANDLE, &sh->state); @@ -714,12 +717,11 @@ static bool is_full_stripe_write(struct stripe_head *sh) static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) { - local_irq_disable(); if (sh1 > sh2) { - spin_lock(&sh2->stripe_lock); + spin_lock_irq(&sh2->stripe_lock); spin_lock_nested(&sh1->stripe_lock, 1); } else { - spin_lock(&sh1->stripe_lock); + spin_lock_irq(&sh1->stripe_lock); spin_lock_nested(&sh2->stripe_lock, 1); } } @@ -727,8 +729,7 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) { spin_unlock(&sh1->stripe_lock); - spin_unlock(&sh2->stripe_lock); - local_irq_enable(); + spin_unlock_irq(&sh2->stripe_lock); } /* Only freshly new full stripe normal write stripe can be added to a batch list */ @@ -2312,14 +2313,12 @@ static int resize_stripes(struct r5conf *conf, int newsize) struct stripe_head *osh, *nsh; LIST_HEAD(newstripes); struct disk_info *ndisks; - int err; + int err = 0; struct kmem_cache *sc; int i; int hash, cnt; - err = md_allow_write(conf->mddev); - if (err) - return err; + md_allow_write(conf->mddev); /* Step 1 */ sc = kmem_cache_create(conf->cache_name[1-conf->active_name], @@ -2694,7 +2693,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) bdevname(rdev->bdev, b), mdname(mddev), conf->raid_disks - mddev->degraded); - r5c_update_on_rdev_error(mddev); + r5c_update_on_rdev_error(mddev, rdev); } /* @@ -3055,6 +3054,11 @@ sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous) * When LOG_CRITICAL, stripes with injournal == 0 will be sent to * no_space_stripes list. * + * 3. during journal failure + * In journal failure, we try to flush all cached data to raid disks + * based on data in stripe cache. The array is read-only to upper + * layers, so we would skip all pending writes. + * */ static inline bool delay_towrite(struct r5conf *conf, struct r5dev *dev, @@ -3068,6 +3072,9 @@ static inline bool delay_towrite(struct r5conf *conf, if (test_bit(R5C_LOG_CRITICAL, &conf->cache_state) && s->injournal > 0) return true; + /* case 3 above */ + if (s->log_failed && s->injournal) + return true; return false; } @@ -4653,8 +4660,13 @@ static void handle_stripe(struct stripe_head *sh) if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) { spin_lock(&sh->stripe_lock); - /* Cannot process 'sync' concurrently with 'discard' */ - if (!test_bit(STRIPE_DISCARD, &sh->state) && + /* + * Cannot process 'sync' concurrently with 'discard'. + * Flush data in r5cache before 'sync'. + */ + if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state) && + !test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) && + !test_bit(STRIPE_DISCARD, &sh->state) && test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { set_bit(STRIPE_SYNCING, &sh->state); clear_bit(STRIPE_INSYNC, &sh->state); @@ -4701,10 +4713,15 @@ static void handle_stripe(struct stripe_head *sh) " to_write=%d failed=%d failed_num=%d,%d\n", s.locked, s.uptodate, s.to_read, s.to_write, s.failed, s.failed_num[0], s.failed_num[1]); - /* check if the array has lost more than max_degraded devices and, + /* + * check if the array has lost more than max_degraded devices and, * if so, some requests might need to be failed. + * + * When journal device failed (log_failed), we will only process + * the stripe if there is data need write to raid disks */ - if (s.failed > conf->max_degraded || s.log_failed) { + if (s.failed > conf->max_degraded || + (s.log_failed && s.injournal == 0)) { sh->check_state = 0; sh->reconstruct_state = 0; break_stripe_batch_list(sh, 0); @@ -5277,8 +5294,10 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group) struct stripe_head *sh, *tmp; struct list_head *handle_list = NULL; struct r5worker_group *wg; - bool second_try = !r5c_is_writeback(conf->log); - bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state); + bool second_try = !r5c_is_writeback(conf->log) && + !r5l_log_disk_error(conf); + bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state) || + r5l_log_disk_error(conf); again: wg = NULL; @@ -6313,7 +6332,6 @@ int raid5_set_cache_size(struct mddev *mddev, int size) { struct r5conf *conf = mddev->private; - int err; if (size <= 16 || size > 32768) return -EINVAL; @@ -6325,10 +6343,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) ; mutex_unlock(&conf->cache_size_mutex); - - err = md_allow_write(mddev); - if (err) - return err; + md_allow_write(mddev); mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) @@ -7530,7 +7545,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) * neilb: there is no locking about new writes here, * so this cannot be safe. */ - if (atomic_read(&conf->active_stripes)) { + if (atomic_read(&conf->active_stripes) || + atomic_read(&conf->r5c_cached_full_stripes) || + atomic_read(&conf->r5c_cached_partial_stripes)) { return -EBUSY; } log_exit(conf); diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index bf0fe0137dfe..6d1b4b707cc2 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -512,7 +512,7 @@ static void gpmc_cs_show_timings(int cs, const char *desc) pr_info("gpmc cs%i access configuration:\n", cs); GPMC_GET_RAW_BOOL(GPMC_CS_CONFIG1, 4, 4, "time-para-granularity"); GPMC_GET_RAW(GPMC_CS_CONFIG1, 8, 9, "mux-add-data"); - GPMC_GET_RAW_MAX(GPMC_CS_CONFIG1, 12, 13, + GPMC_GET_RAW_SHIFT_MAX(GPMC_CS_CONFIG1, 12, 13, 1, GPMC_CONFIG1_DEVICESIZE_MAX, "device-width"); GPMC_GET_RAW(GPMC_CS_CONFIG1, 16, 17, "wait-pin"); GPMC_GET_RAW_BOOL(GPMC_CS_CONFIG1, 21, 21, "wait-on-write"); diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 2cba76e6fa3c..07bbd4cc1852 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -492,6 +492,7 @@ config ASPEED_LPC_CTRL config PCI_ENDPOINT_TEST depends on PCI + select CRC32 tristate "PCI Endpoint Test driver" ---help--- Enable this configuration option to enable the host side test driver diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 19581d783d8e..d034d8cd7d22 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -849,6 +849,9 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, mv88e6xxx_g1_stats_read(chip, reg, &low); if (s->sizeof_stat == 8) mv88e6xxx_g1_stats_read(chip, reg + 1, &high); + break; + default: + return UINT64_MAX; } value = (((u64)high) << 16) | low; return value; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 4ee15ff06a44..faeb4935ef3e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -200,29 +200,18 @@ err_exit: static int hw_atl_a0_hw_offload_set(struct aq_hw_s *self, struct aq_nic_cfg_s *aq_nic_cfg) { - int err = 0; - /* TX checksums offloads*/ tpo_ipv4header_crc_offload_en_set(self, 1); tpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* RX checksums offloads*/ rpo_ipv4header_crc_offload_en_set(self, 1); rpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* LSO offloads*/ tdm_large_send_offload_en_set(self, 0xFFFFFFFFU); - if (err < 0) - goto err_exit; - - err = aq_hw_err_from_flags(self); -err_exit: - return err; + return aq_hw_err_from_flags(self); } static int hw_atl_a0_hw_init_tx_path(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 42150708191d..1bceb7358e5c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -200,25 +200,18 @@ err_exit: static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, struct aq_nic_cfg_s *aq_nic_cfg) { - int err = 0; unsigned int i; /* TX checksums offloads*/ tpo_ipv4header_crc_offload_en_set(self, 1); tpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* RX checksums offloads*/ rpo_ipv4header_crc_offload_en_set(self, 1); rpo_tcp_udp_crc_offload_en_set(self, 1); - if (err < 0) - goto err_exit; /* LSO offloads*/ tdm_large_send_offload_en_set(self, 0xFFFFFFFFU); - if (err < 0) - goto err_exit; /* LRO offloads */ { @@ -245,10 +238,7 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, rpo_lro_en_set(self, aq_nic_cfg->is_lro ? 0xFFFFFFFFU : 0U); } - err = aq_hw_err_from_flags(self); - -err_exit: - return err; + return aq_hw_err_from_flags(self); } static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b56c54d68d5e..03f55daecb20 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7630,8 +7630,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->min_mtu = ETH_ZLEN; dev->max_mtu = BNXT_MAX_MTU; - bnxt_dcb_init(bp); - #ifdef CONFIG_BNXT_SRIOV init_waitqueue_head(&bp->sriov_cfg_wait); #endif @@ -7669,6 +7667,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_hwrm_func_qcfg(bp); bnxt_hwrm_port_led_qcaps(bp); bnxt_ethtool_init(bp); + bnxt_dcb_init(bp); bnxt_set_rx_skb_mode(bp, false); bnxt_set_tpa_flags(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 46de2f8ff024..5c6dd0ce209f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -553,8 +553,10 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode) if ((mode & DCB_CAP_DCBX_VER_CEE) || !(mode & DCB_CAP_DCBX_VER_IEEE)) return 1; - if ((mode & DCB_CAP_DCBX_HOST) && BNXT_VF(bp)) - return 1; + if (mode & DCB_CAP_DCBX_HOST) { + if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT)) + return 1; + } if (mode == bp->dcbx_cap) return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index fa376444e57c..3549d3876278 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -37,7 +37,7 @@ #define T4FW_VERSION_MAJOR 0x01 #define T4FW_VERSION_MINOR 0x10 -#define T4FW_VERSION_MICRO 0x21 +#define T4FW_VERSION_MICRO 0x2B #define T4FW_VERSION_BUILD 0x00 #define T4FW_MIN_VERSION_MAJOR 0x01 @@ -46,7 +46,7 @@ #define T5FW_VERSION_MAJOR 0x01 #define T5FW_VERSION_MINOR 0x10 -#define T5FW_VERSION_MICRO 0x21 +#define T5FW_VERSION_MICRO 0x2B #define T5FW_VERSION_BUILD 0x00 #define T5FW_MIN_VERSION_MAJOR 0x00 @@ -55,7 +55,7 @@ #define T6FW_VERSION_MAJOR 0x01 #define T6FW_VERSION_MINOR 0x10 -#define T6FW_VERSION_MICRO 0x21 +#define T6FW_VERSION_MICRO 0x2B #define T6FW_VERSION_BUILD 0x00 #define T6FW_MIN_VERSION_MAJOR 0x00 diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c index 6ac336b546e6..1536356e2ea8 100644 --- a/drivers/net/ethernet/faraday/ftmac100.c +++ b/drivers/net/ethernet/faraday/ftmac100.c @@ -1174,11 +1174,17 @@ static int ftmac100_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id ftmac100_of_ids[] = { + { .compatible = "andestech,atmac100" }, + { } +}; + static struct platform_driver ftmac100_driver = { .probe = ftmac100_probe, .remove = ftmac100_remove, .driver = { .name = DRV_NAME, + .of_match_table = ftmac100_of_ids }, }; @@ -1202,3 +1208,4 @@ module_exit(ftmac100_exit); MODULE_AUTHOR("Po-Yu Chuang <ratbert@faraday-tech.com>"); MODULE_DESCRIPTION("FTMAC100 driver"); MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(of, ftmac100_of_ids); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 703205475524..83aab1e4c8c8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2862,12 +2862,10 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) int port = 0; if (msi_x) { - int nreq = dev->caps.num_ports * num_online_cpus() + 1; - - nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, - nreq); - if (nreq > MAX_MSIX) - nreq = MAX_MSIX; + int nreq = min3(dev->caps.num_ports * + (int)num_online_cpus() + 1, + dev->caps.num_eqs - dev->caps.reserved_eqs, + MAX_MSIX); entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); if (!entries) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index fc52d742b7f7..27251a78075c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -13,7 +13,7 @@ config MLX5_CORE config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" - depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE + depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE depends on IPV6=y || IPV6=n || MLX5_CORE=m imply PTP_1588_CLOCK default n diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0099a3e397bc..2fd044b23875 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1003,7 +1003,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv); void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv); void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); -int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn); +int mlx5e_create_ttc_table(struct mlx5e_priv *priv); void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv); int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index ce7b09d72ff6..8209affa75c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -794,7 +794,6 @@ static void get_supported(u32 eth_proto_cap, ptys2ethtool_supported_port(link_ksettings, eth_proto_cap); ptys2ethtool_supported_link(supported, eth_proto_cap); ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause); - ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause); } static void get_advertising(u32 eth_proto_cap, u8 tx_pause, @@ -804,7 +803,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause, unsigned long *advertising = link_ksettings->link_modes.advertising; ptys2ethtool_adver_link(advertising, eth_proto_cap); - if (tx_pause) + if (rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause); if (tx_pause ^ rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause); @@ -849,6 +848,8 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0}; + u32 rx_pause = 0; + u32 tx_pause = 0; u32 eth_proto_cap; u32 eth_proto_admin; u32 eth_proto_lp; @@ -871,11 +872,13 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev, an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); an_status = MLX5_GET(ptys_reg, out, an_status); + mlx5_query_port_pause(mdev, &rx_pause, &tx_pause); + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); get_supported(eth_proto_cap, link_ksettings); - get_advertising(eth_proto_admin, 0, 0, link_ksettings); + get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings); get_speed_duplex(netdev, eth_proto_oper, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 576d6787b484..53ed58320a24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -800,7 +800,7 @@ void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) mlx5e_destroy_flow_table(&ttc->ft); } -int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn) +int mlx5e_create_ttc_table(struct mlx5e_priv *priv) { struct mlx5e_ttc_table *ttc = &priv->fs.ttc; struct mlx5_flow_table_attr ft_attr = {}; @@ -810,7 +810,6 @@ int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn) ft_attr.max_fte = MLX5E_TTC_TABLE_SIZE; ft_attr.level = MLX5E_TTC_FT_LEVEL; ft_attr.prio = MLX5E_NIC_PRIO; - ft_attr.underlay_qpn = underlay_qpn; ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); if (IS_ERR(ft->t)) { @@ -1147,7 +1146,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } - err = mlx5e_create_ttc_table(priv, 0); + err = mlx5e_create_ttc_table(priv); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a61b71b6fff3..41cd22a223dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2976,7 +2976,7 @@ static int mlx5e_setup_tc(struct net_device *netdev, u8 tc) new_channels.params = priv->channels.params; new_channels.params.num_tc = tc ? tc : 1; - if (test_bit(MLX5E_STATE_OPENED, &priv->state)) { + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 19e3d2fc2099..fcec7bedd3cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -40,28 +40,25 @@ #include "eswitch.h" int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft) + struct mlx5_flow_table *ft, u32 underlay_qpn) { u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0}; u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0}; if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && - ft->underlay_qpn == 0) + underlay_qpn == 0) return 0; MLX5_SET(set_flow_table_root_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); MLX5_SET(set_flow_table_root_in, in, table_type, ft->type); MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn); if (ft->vport) { MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); MLX5_SET(set_flow_table_root_in, in, other_vport, 1); } - if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && - ft->underlay_qpn != 0) - MLX5_SET(set_flow_table_root_in, in, underlay_qpn, ft->underlay_qpn); - return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 8fad80688536..0f98a7cf4877 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -71,7 +71,8 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, unsigned int index); int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft); + struct mlx5_flow_table *ft, + u32 underlay_qpn); int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u16 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u16 id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b8a176503d38..0e487e8ca634 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -650,7 +650,7 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio if (ft->level >= min_level) return 0; - err = mlx5_cmd_update_root_ft(root->dev, ft); + err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn); if (err) mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", ft->id); @@ -818,8 +818,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa goto unlock_root; } - ft->underlay_qpn = ft_attr->underlay_qpn; - tree_init_node(&ft->node, 1, del_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); @@ -1489,7 +1487,8 @@ static int update_root_ft_destroy(struct mlx5_flow_table *ft) new_root_ft = find_next_ft(ft); if (new_root_ft) { - int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft); + int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, + root->underlay_qpn); if (err) { mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", @@ -2062,3 +2061,21 @@ err: mlx5_cleanup_fs(dev); return err; } + +int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) +{ + struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + + root->underlay_qpn = underlay_qpn; + return 0; +} +EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn); + +int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) +{ + struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + + root->underlay_qpn = 0; + return 0; +} +EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 81eafc7b9dd9..990acee6fb09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -118,7 +118,6 @@ struct mlx5_flow_table { /* FWD rules that point on this flow table */ struct list_head fwd_rules; u32 flags; - u32 underlay_qpn; }; struct mlx5_fc_cache { @@ -195,6 +194,7 @@ struct mlx5_flow_root_namespace { struct mlx5_flow_table *root_ft; /* Should be held when chaining flow tables */ struct mutex chain_lock; + u32 underlay_qpn; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c index 019c230da498..cc1858752e70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c @@ -66,6 +66,10 @@ static void mlx5i_init(struct mlx5_core_dev *mdev, mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev)); + /* Override RQ params as IPoIB supports only LINKED LIST RQ for now */ + mlx5e_set_rq_type_params(mdev, &priv->channels.params, MLX5_WQ_TYPE_LINKED_LIST); + priv->channels.params.lro_en = false; + mutex_init(&priv->state_lock); netdev->hw_features |= NETIF_F_SG; @@ -156,6 +160,8 @@ out: static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { + mlx5_fs_remove_rx_underlay_qpn(mdev, qp->qpn); + mlx5_core_destroy_qp(mdev, qp); } @@ -170,6 +176,8 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) return err; } + mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); + err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); @@ -189,7 +197,6 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; int err; priv->fs.ns = mlx5_get_flow_namespace(priv->mdev, @@ -205,7 +212,7 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } - err = mlx5e_create_ttc_table(priv, ipriv->qp.qpn); + err = mlx5e_create_ttc_table(priv); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index ea56f6ade6b4..5f0a7bc692a4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -199,10 +199,11 @@ static int mlxsw_sp_erif_entry_get(struct mlxsw_sp *mlxsw_sp, entry->counter_valid = false; entry->counter = 0; + entry->index = mlxsw_sp_rif_index(rif); + if (!counters_enabled) return 0; - entry->index = mlxsw_sp_rif_index(rif); err = mlxsw_sp_rif_counter_value_get(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS, &cnt); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 33cec1cc1642..9f89c4137d21 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -206,6 +206,9 @@ void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp, { unsigned int *p_counter_index; + if (!mlxsw_sp_rif_counter_valid_get(rif, dir)) + return; + p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir); if (WARN_ON(!p_counter_index)) return; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 0d8411f1f954..f4bb0c0b7c1d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1497,8 +1497,7 @@ do_fdb_op: err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, adding, true); if (err) { - if (net_ratelimit()) - netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n"); return; } @@ -1558,8 +1557,7 @@ do_fdb_op: err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid, adding, true); if (err) { - if (net_ratelimit()) - netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n"); return; } diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c index b8d5270359cd..e30676515529 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c @@ -247,7 +247,7 @@ nx_fw_cmd_set_mtu(struct netxen_adapter *adapter, int mtu) cmd.req.arg3 = 0; if (recv_ctx->state == NX_HOST_CTX_STATE_ACTIVE) - netxen_issue_cmd(adapter, &cmd); + rcode = netxen_issue_cmd(adapter, &cmd); if (rcode != NX_RCODE_SUCCESS) return -EIO; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index 67200c5498ab..0a8fde629991 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -983,7 +983,7 @@ void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn, memset(&camline, 0, sizeof(union gft_cam_line_union)); qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id, camline.cam_line_mapped.camline); - memset(&ramline, 0, sizeof(union gft_cam_line_union)); + memset(&ramline, 0, sizeof(ramline)); for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) { u32 hw_addr = PRS_REG_GFT_PROFILE_MASK_RAM; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 49bad00a0f8f..7245b1072518 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -37,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 65 -#define QLCNIC_LINUX_VERSIONID "5.3.65" +#define _QLCNIC_LINUX_SUBVERSION 66 +#define QLCNIC_LINUX_VERSIONID "5.3.66" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 718bf58a7da6..4fb68797630e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -3168,6 +3168,40 @@ int qlcnic_83xx_flash_read32(struct qlcnic_adapter *adapter, u32 flash_addr, return 0; } +void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_cmd_args cmd; + u32 config; + int err; + + err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_LINK_STATUS); + if (err) + return; + + err = qlcnic_issue_cmd(adapter, &cmd); + if (err) { + dev_info(&adapter->pdev->dev, + "Get Link Status Command failed: 0x%x\n", err); + goto out; + } else { + config = cmd.rsp.arg[3]; + + switch (QLC_83XX_SFP_MODULE_TYPE(config)) { + case QLC_83XX_MODULE_FIBRE_1000BASE_SX: + case QLC_83XX_MODULE_FIBRE_1000BASE_LX: + case QLC_83XX_MODULE_FIBRE_1000BASE_CX: + case QLC_83XX_MODULE_TP_1000BASE_T: + ahw->port_type = QLCNIC_GBE; + break; + default: + ahw->port_type = QLCNIC_XGBE; + } + } +out: + qlcnic_free_mbx_args(&cmd); +} + int qlcnic_83xx_test_link(struct qlcnic_adapter *adapter) { u8 pci_func; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index 3dfe8e27b51c..b75a81246856 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -637,6 +637,7 @@ void qlcnic_83xx_get_pauseparam(struct qlcnic_adapter *, int qlcnic_83xx_set_pauseparam(struct qlcnic_adapter *, struct ethtool_pauseparam *); int qlcnic_83xx_test_link(struct qlcnic_adapter *); +void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter); int qlcnic_83xx_reg_test(struct qlcnic_adapter *); int qlcnic_83xx_get_regs_len(struct qlcnic_adapter *); int qlcnic_83xx_get_registers(struct qlcnic_adapter *, u32 *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 9a869c15d8bf..7f7deeaf1cf0 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -486,6 +486,9 @@ static int qlcnic_set_link_ksettings(struct net_device *dev, u32 ret = 0; struct qlcnic_adapter *adapter = netdev_priv(dev); + if (qlcnic_83xx_check(adapter)) + qlcnic_83xx_get_port_type(adapter); + if (adapter->ahw->port_type != QLCNIC_GBE) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 513e6c74e199..24ca7df15d07 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -296,8 +296,9 @@ qcaspi_receive(struct qcaspi *qca) /* Allocate rx SKB if we don't have one available. */ if (!qca->rx_skb) { - qca->rx_skb = netdev_alloc_skb(net_dev, - net_dev->mtu + VLAN_ETH_HLEN); + qca->rx_skb = netdev_alloc_skb_ip_align(net_dev, + net_dev->mtu + + VLAN_ETH_HLEN); if (!qca->rx_skb) { netdev_dbg(net_dev, "out of RX resources\n"); qca->stats.out_of_mem++; @@ -377,7 +378,7 @@ qcaspi_receive(struct qcaspi *qca) qca->rx_skb, qca->rx_skb->dev); qca->rx_skb->ip_summed = CHECKSUM_UNNECESSARY; netif_rx_ni(qca->rx_skb); - qca->rx_skb = netdev_alloc_skb(net_dev, + qca->rx_skb = netdev_alloc_skb_ip_align(net_dev, net_dev->mtu + VLAN_ETH_HLEN); if (!qca->rx_skb) { netdev_dbg(net_dev, "out of RX resources\n"); @@ -759,7 +760,8 @@ qcaspi_netdev_init(struct net_device *dev) if (!qca->rx_buffer) return -ENOBUFS; - qca->rx_skb = netdev_alloc_skb(dev, qca->net_dev->mtu + VLAN_ETH_HLEN); + qca->rx_skb = netdev_alloc_skb_ip_align(dev, qca->net_dev->mtu + + VLAN_ETH_HLEN); if (!qca->rx_skb) { kfree(qca->rx_buffer); netdev_info(qca->net_dev, "Failed to allocate RX sk_buff.\n"); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index f68c4db656ed..2d686ccf971b 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3220,7 +3220,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev) /* MDIO bus init */ ret = sh_mdio_init(mdp, pd); if (ret) { - dev_err(&ndev->dev, "failed to initialise MDIO\n"); + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "MDIO init failed: %d\n", ret); goto out_release; } diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 7b916aa21bde..4d7fb8af880d 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -18,8 +18,12 @@ #include "mcdi.h" enum { - EFX_REV_SIENA_A0 = 0, - EFX_REV_HUNT_A0 = 1, + /* Revisions 0-2 were Falcon A0, A1 and B0 respectively. + * They are not supported by this driver but these revision numbers + * form part of the ethtool API for register dumping. + */ + EFX_REV_SIENA_A0 = 3, + EFX_REV_HUNT_A0 = 4, }; static inline int efx_nic_rev(struct efx_nic *efx) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index cd8c60132390..a74c481401c4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3725,7 +3725,7 @@ static void sysfs_display_ring(void *head, int size, int extend_desc, ep++; } else { seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n", - i, (unsigned int)virt_to_phys(ep), + i, (unsigned int)virt_to_phys(p), le32_to_cpu(p->des0), le32_to_cpu(p->des1), le32_to_cpu(p->des2), le32_to_cpu(p->des3)); p++; diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 5a90fed06260..5b56c24b6ed2 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -411,13 +411,14 @@ static int vsw_port_remove(struct vio_dev *vdev) if (port) { del_timer_sync(&port->vio.timer); + del_timer_sync(&port->clean_timer); napi_disable(&port->napi); + unregister_netdev(port->dev); list_del_rcu(&port->list); synchronize_rcu(); - del_timer_sync(&port->clean_timer); spin_lock_irqsave(&port->vp->lock, flags); sunvnet_port_rm_txq_common(port); spin_unlock_irqrestore(&port->vp->lock, flags); @@ -427,7 +428,6 @@ static int vsw_port_remove(struct vio_dev *vdev) dev_set_drvdata(&vdev->dev, NULL); - unregister_netdev(port->dev); free_netdev(port->dev); } diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 729a7da90b5b..e6222e535019 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1353,9 +1353,10 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe) tx_pipe->dma_channel = knav_dma_open_channel(dev, tx_pipe->dma_chan_name, &config); - if (IS_ERR_OR_NULL(tx_pipe->dma_channel)) { + if (IS_ERR(tx_pipe->dma_channel)) { dev_err(dev, "failed opening tx chan(%s)\n", tx_pipe->dma_chan_name); + ret = PTR_ERR(tx_pipe->dma_channel); goto err; } @@ -1673,9 +1674,10 @@ static int netcp_setup_navigator_resources(struct net_device *ndev) netcp->rx_channel = knav_dma_open_channel(netcp->netcp_device->device, netcp->dma_chan_name, &config); - if (IS_ERR_OR_NULL(netcp->rx_channel)) { + if (IS_ERR(netcp->rx_channel)) { dev_err(netcp->ndev_dev, "failed opening rx chan(%s\n", netcp->dma_chan_name); + ret = PTR_ERR(netcp->rx_channel); goto fail; } diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 897176fc5043..dd92950a4615 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2651,7 +2651,6 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) case HWTSTAMP_FILTER_NONE: cpts_rx_enable(cpts, 0); break; - case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index 8716b8c07feb..6f3c805f7211 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -1077,7 +1077,7 @@ static int stir421x_patch_device(struct irda_usb_cb *self) * are "42101001.sb" or "42101002.sb" */ sprintf(stir421x_fw_name, "4210%4X.sb", - self->usbdev->descriptor.bcdDevice); + le16_to_cpu(self->usbdev->descriptor.bcdDevice)); ret = request_firmware(&fw, stir421x_fw_name, &self->usbdev->dev); if (ret < 0) return ret; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index b34eaaae03fd..346ad2ff3998 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -789,10 +789,12 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu) */ static struct lock_class_key macvlan_netdev_addr_lock_key; -#define ALWAYS_ON_FEATURES \ - (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \ +#define ALWAYS_ON_OFFLOADS \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST) +#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX) + #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \ @@ -827,6 +829,7 @@ static int macvlan_init(struct net_device *dev) dev->features |= ALWAYS_ON_FEATURES; dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; + dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->gso_max_size = lowerdev->gso_max_size; dev->gso_max_segs = lowerdev->gso_max_segs; dev->hard_header_len = lowerdev->hard_header_len; diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 963838d4fac1..599ce24c514f 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -122,10 +122,9 @@ int mdio_mux_init(struct device *dev, pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL); if (pb == NULL) { ret_val = -ENOMEM; - goto err_parent_bus; + goto err_pb_kz; } - pb->switch_data = data; pb->switch_fn = switch_fn; pb->current_child = -1; @@ -154,6 +153,7 @@ int mdio_mux_init(struct device *dev, cb->mii_bus = mdiobus_alloc(); if (!cb->mii_bus) { ret_val = -ENOMEM; + devm_kfree(dev, cb); of_node_put(child_bus_node); break; } @@ -170,7 +170,6 @@ int mdio_mux_init(struct device *dev, mdiobus_free(cb->mii_bus); devm_kfree(dev, cb); } else { - of_node_get(child_bus_node); cb->next = pb->children; pb->children = cb; } @@ -181,9 +180,11 @@ int mdio_mux_init(struct device *dev, return 0; } + devm_kfree(dev, pb); +err_pb_kz: /* balance the reference of_mdio_find_bus() took */ - put_device(&pb->mii_bus->dev); - + if (!mux_bus) + put_device(&parent_bus->dev); err_parent_bus: of_node_put(parent_bus_node); return ret_val; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index a898e5c4ef1b..8e73f5f36e71 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -364,9 +364,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) mutex_init(&bus->mdio_lock); - if (bus->reset) - bus->reset(bus); - /* de-assert bus level PHY GPIO resets */ if (bus->num_reset_gpios > 0) { bus->reset_gpiod = devm_kcalloc(&bus->dev, @@ -396,6 +393,9 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) } } + if (bus->reset) + bus->reset(bus); + for (i = 0; i < PHY_MAX_ADDR; i++) { if ((bus->phy_mask & (1 << i)) == 0) { struct phy_device *phydev; diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c index c4f1c363e24b..9df3c1ffff35 100644 --- a/drivers/net/usb/ch9200.c +++ b/drivers/net/usb/ch9200.c @@ -310,8 +310,8 @@ static int get_mac_address(struct usbnet *dev, unsigned char *data) int rd_mac_len = 0; netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n", - dev->udev->descriptor.idVendor, - dev->udev->descriptor.idProduct); + le16_to_cpu(dev->udev->descriptor.idVendor), + le16_to_cpu(dev->udev->descriptor.idProduct)); memset(mac_addr, 0, sizeof(mac_addr)); rd_mac_len = control_read(dev, REQUEST_READ, 0, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index d7165767ca9d..8f923a147fa9 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1196,6 +1196,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 25bc764ae7dc..d1c7029ded7c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2962,6 +2962,11 @@ vmxnet3_force_close(struct vmxnet3_adapter *adapter) /* we need to enable NAPI, otherwise dev_close will deadlock */ for (i = 0; i < adapter->num_rx_queues; i++) napi_enable(&adapter->rx_queue[i].napi); + /* + * Need to clear the quiesce bit to ensure that vmxnet3_close + * can quiesce the device properly + */ + clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); dev_close(adapter->netdev); } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index ceda5861da78..db882493875c 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -989,6 +989,7 @@ static u32 vrf_fib_table(const struct net_device *dev) static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + kfree_skb(skb); return 0; } @@ -998,7 +999,7 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, { struct net *net = dev_net(dev); - if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0) + if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1) skb = NULL; /* kfree_skb(skb) handled by nf code */ return skb; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 6ffc482550c1..7b61adb6270c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1934,8 +1934,7 @@ abort_transaction_no_dev_fatal: xennet_disconnect_backend(info); xennet_destroy_queues(info); out: - unregister_netdev(info->netdev); - xennet_free_netdev(info->netdev); + device_unregister(&dev->dev); return err; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 70e689bf1cad..dca7165fabcf 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1754,6 +1754,10 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) dev_info(ctrl->ctrl.device, "NVME-FC{%d}: resetting controller\n", ctrl->cnum); + /* stop the queues on error, cleanup is in reset thread */ + if (ctrl->queue_count > 1) + nvme_stop_queues(&ctrl->ctrl); + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: error_recovery: Couldn't change state " @@ -2720,6 +2724,12 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, unsigned long flags; int ret, idx; + if (!(rport->remoteport.port_role & + (FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) { + ret = -EBADR; + goto out_fail; + } + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); if (!ctrl) { ret = -ENOMEM; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fed803232edc..4c2ff2bb26bc 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1506,6 +1506,11 @@ static inline void nvme_release_cmb(struct nvme_dev *dev) if (dev->cmb) { iounmap(dev->cmb); dev->cmb = NULL; + if (dev->cmbsz) { + sysfs_remove_file_from_group(&dev->ctrl.device->kobj, + &dev_attr_cmb.attr, NULL); + dev->cmbsz = 0; + } } } @@ -1779,6 +1784,7 @@ static void nvme_pci_disable(struct nvme_dev *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); + nvme_release_cmb(dev); pci_free_irq_vectors(pdev); if (pci_is_enabled(pdev)) { @@ -2184,7 +2190,6 @@ static void nvme_remove(struct pci_dev *pdev) nvme_dev_disable(dev, true); nvme_dev_remove_admin(dev); nvme_free_queues(dev, 0); - nvme_release_cmb(dev); nvme_release_prp_pools(dev); nvme_dev_unmap(dev); nvme_put_ctrl(&dev->ctrl); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index cf90713043da..eb9399ac97cf 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -529,6 +529,12 @@ fail: } EXPORT_SYMBOL_GPL(nvmet_req_init); +void nvmet_req_uninit(struct nvmet_req *req) +{ + percpu_ref_put(&req->sq->ref); +} +EXPORT_SYMBOL_GPL(nvmet_req_uninit); + static inline bool nvmet_cc_en(u32 cc) { return cc & 0x1; diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 62eba29c85fb..2006fae61980 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -517,9 +517,7 @@ nvmet_fc_queue_to_cpu(struct nvmet_fc_tgtport *tgtport, int qid) { int cpu, idx, cnt; - if (!(tgtport->ops->target_features & - NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED) || - tgtport->ops->max_hw_queues == 1) + if (tgtport->ops->max_hw_queues == 1) return WORK_CPU_UNBOUND; /* Simple cpu selection based on qid modulo active cpu count */ diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 15551ef79c8c..294a6611fb24 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -698,7 +698,6 @@ static struct nvmet_fc_target_template tgttemplate = { .dma_boundary = FCLOOP_DMABOUND_4G, /* optional features */ .target_features = NVMET_FCTGTFEAT_CMD_IN_ISR | - NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED | NVMET_FCTGTFEAT_OPDONE_IN_ISR, /* sizes of additional private data for data structures */ .target_priv_sz = sizeof(struct fcloop_tport), diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7cb77ba5993b..cfc5c7fb0ab7 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -261,6 +261,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req); bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops); +void nvmet_req_uninit(struct nvmet_req *req); void nvmet_req_complete(struct nvmet_req *req, u16 status); void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid, diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 99c69018a35f..9e45cde63376 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -567,6 +567,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc) rsp->n_rdma = 0; if (unlikely(wc->status != IB_WC_SUCCESS)) { + nvmet_req_uninit(&rsp->req); nvmet_rdma_release_rsp(rsp); if (wc->status != IB_WC_WR_FLUSH_ERR) { pr_info("RDMA READ for CQE 0x%p failed with status %s (%d).\n", diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 3080d9dd031d..43bd69dceabf 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -507,6 +507,9 @@ void *__unflatten_device_tree(const void *blob, /* Allocate memory for the expanded device tree */ mem = dt_alloc(size + 4, __alignof__(struct device_node)); + if (!mem) + return NULL; + memset(mem, 0, size); *(__be32 *)(mem + size) = cpu_to_be32(0xdeadbeef); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 4dec07ea510f..d507c3569a88 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -197,7 +197,7 @@ static int __init __reserved_mem_init_node(struct reserved_mem *rmem) const struct of_device_id *i; for (i = __reservedmem_of_table; i < &__rmem_of_table_sentinel; i++) { - int const (*initfn)(struct reserved_mem *rmem) = i->data; + reservedmem_of_init_fn initfn = i->data; const char *compat = i->compatible; if (!of_flat_dt_is_compatible(rmem->fdt_node, compat)) diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index e443b0d0b236..34b9ad6b3143 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -35,7 +35,7 @@ static struct bus_type ccwgroup_bus_type; static void __ccwgroup_remove_symlinks(struct ccwgroup_device *gdev) { int i; - char str[8]; + char str[16]; for (i = 0; i < gdev->count; i++) { sprintf(str, "cdev%d", i); @@ -238,7 +238,7 @@ static void ccwgroup_release(struct device *dev) static int __ccwgroup_create_symlinks(struct ccwgroup_device *gdev) { - char str[8]; + char str[16]; int i, rc; for (i = 0; i < gdev->count; i++) { diff --git a/drivers/s390/cio/qdio_debug.h b/drivers/s390/cio/qdio_debug.h index f33ce8577619..1d595d17bf11 100644 --- a/drivers/s390/cio/qdio_debug.h +++ b/drivers/s390/cio/qdio_debug.h @@ -11,7 +11,7 @@ #include "qdio.h" /* that gives us 15 characters in the text event views */ -#define QDIO_DBF_LEN 16 +#define QDIO_DBF_LEN 32 extern debug_info_t *qdio_dbf_setup; extern debug_info_t *qdio_dbf_error; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index f6aa21176d89..30bc6105aac3 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -701,6 +701,7 @@ enum qeth_discipline_id { }; struct qeth_discipline { + const struct device_type *devtype; void (*start_poll)(struct ccw_device *, int, unsigned long); qdio_handler_t *input_handler; qdio_handler_t *output_handler; @@ -875,6 +876,9 @@ extern struct qeth_discipline qeth_l2_discipline; extern struct qeth_discipline qeth_l3_discipline; extern const struct attribute_group *qeth_generic_attr_groups[]; 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 *); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 38114a8d56e0..fc6d85f2b38d 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5530,10 +5530,12 @@ void qeth_core_free_discipline(struct qeth_card *card) card->discipline = NULL; } -static const struct device_type qeth_generic_devtype = { +const struct device_type qeth_generic_devtype = { .name = "qeth_generic", .groups = qeth_generic_attr_groups, }; +EXPORT_SYMBOL_GPL(qeth_generic_devtype); + static const struct device_type qeth_osn_devtype = { .name = "qeth_osn", .groups = qeth_osn_attr_groups, @@ -5659,23 +5661,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) goto err_card; } - if (card->info.type == QETH_CARD_TYPE_OSN) - gdev->dev.type = &qeth_osn_devtype; - else - gdev->dev.type = &qeth_generic_devtype; - switch (card->info.type) { case QETH_CARD_TYPE_OSN: case QETH_CARD_TYPE_OSM: rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2); if (rc) goto err_card; + + gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN) + ? card->discipline->devtype + : &qeth_osn_devtype; rc = card->discipline->setup(card->gdev); if (rc) goto err_disc; - case QETH_CARD_TYPE_OSD: - case QETH_CARD_TYPE_OSX: + break; default: + gdev->dev.type = &qeth_generic_devtype; break; } @@ -5731,8 +5732,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev) if (rc) goto err; rc = card->discipline->setup(card->gdev); - if (rc) + if (rc) { + qeth_core_free_discipline(card); goto err; + } } rc = card->discipline->set_online(gdev); err: diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 75b29fd2fcf4..db6a285d41e0 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -413,12 +413,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev, if (card->options.layer2 == newdis) goto out; - else { - card->info.mac_bits = 0; - if (card->discipline) { - card->discipline->remove(card->gdev); - qeth_core_free_discipline(card); - } + if (card->info.type == QETH_CARD_TYPE_OSM) { + /* fixed layer, can't switch */ + rc = -EOPNOTSUPP; + goto out; + } + + card->info.mac_bits = 0; + if (card->discipline) { + card->discipline->remove(card->gdev); + qeth_core_free_discipline(card); } rc = qeth_core_load_discipline(card, newdis); @@ -426,6 +430,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev, goto out; rc = card->discipline->setup(card->gdev); + if (rc) + qeth_core_free_discipline(card); out: mutex_unlock(&card->discipline_mutex); return rc ? rc : count; @@ -703,10 +709,11 @@ static struct attribute *qeth_blkt_device_attrs[] = { &dev_attr_inter_jumbo.attr, NULL, }; -static struct attribute_group qeth_device_blkt_group = { +const struct attribute_group qeth_device_blkt_group = { .name = "blkt", .attrs = qeth_blkt_device_attrs, }; +EXPORT_SYMBOL_GPL(qeth_device_blkt_group); static struct attribute *qeth_device_attrs[] = { &dev_attr_state.attr, @@ -726,9 +733,10 @@ static struct attribute *qeth_device_attrs[] = { &dev_attr_switch_attrs.attr, NULL, }; -static struct attribute_group qeth_device_attr_group = { +const struct attribute_group qeth_device_attr_group = { .attrs = qeth_device_attrs, }; +EXPORT_SYMBOL_GPL(qeth_device_attr_group); const struct attribute_group *qeth_generic_attr_groups[] = { &qeth_device_attr_group, diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h index 29d9fb3890ad..0d59f9a45ea9 100644 --- a/drivers/s390/net/qeth_l2.h +++ b/drivers/s390/net/qeth_l2.h @@ -8,6 +8,8 @@ #include "qeth_core.h" +extern const struct attribute_group *qeth_l2_attr_groups[]; + int qeth_l2_create_device_attributes(struct device *); void qeth_l2_remove_device_attributes(struct device *); void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 1b07f382d74c..bd2df62a5cdf 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -880,11 +880,21 @@ static int qeth_l2_stop(struct net_device *dev) return 0; } +static const struct device_type qeth_l2_devtype = { + .name = "qeth_layer2", + .groups = qeth_l2_attr_groups, +}; + static int qeth_l2_probe_device(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); + int rc; - qeth_l2_create_device_attributes(&gdev->dev); + if (gdev->dev.type == &qeth_generic_devtype) { + rc = qeth_l2_create_device_attributes(&gdev->dev); + if (rc) + return rc; + } INIT_LIST_HEAD(&card->vid_list); hash_init(card->mac_htable); card->options.layer2 = 1; @@ -896,7 +906,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) { struct qeth_card *card = dev_get_drvdata(&cgdev->dev); - qeth_l2_remove_device_attributes(&cgdev->dev); + if (cgdev->dev.type == &qeth_generic_devtype) + qeth_l2_remove_device_attributes(&cgdev->dev); qeth_set_allowed_threads(card, 0, 1); wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0); @@ -954,7 +965,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) case QETH_CARD_TYPE_OSN: card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup); - card->dev->flags |= IFF_NOARP; break; default: card->dev = alloc_etherdev(0); @@ -969,9 +979,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) card->dev->min_mtu = 64; card->dev->max_mtu = ETH_MAX_MTU; card->dev->netdev_ops = &qeth_l2_netdev_ops; - card->dev->ethtool_ops = - (card->info.type != QETH_CARD_TYPE_OSN) ? - &qeth_l2_ethtool_ops : &qeth_l2_osn_ops; + if (card->info.type == QETH_CARD_TYPE_OSN) { + card->dev->ethtool_ops = &qeth_l2_osn_ops; + card->dev->flags |= IFF_NOARP; + } else { + card->dev->ethtool_ops = &qeth_l2_ethtool_ops; + } card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { card->dev->hw_features = NETIF_F_SG; @@ -1269,6 +1282,7 @@ static int qeth_l2_control_event(struct qeth_card *card, } struct qeth_discipline qeth_l2_discipline = { + .devtype = &qeth_l2_devtype, .start_poll = qeth_qdio_start_poll, .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 687972356d6b..9696baa49e2d 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -269,3 +269,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) } else qeth_bridgeport_an_set(card, 0); } + +const struct attribute_group *qeth_l2_attr_groups[] = { + &qeth_device_attr_group, + &qeth_device_blkt_group, + /* l2 specific, see l2_{create,remove}_device_attributes(): */ + &qeth_l2_bridgeport_attr_group, + NULL, +}; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 6e0354ef4b86..d8df1e635163 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3039,8 +3039,13 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) static int qeth_l3_probe_device(struct ccwgroup_device *gdev) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); + int rc; - qeth_l3_create_device_attributes(&gdev->dev); + rc = qeth_l3_create_device_attributes(&gdev->dev); + if (rc) + return rc; + hash_init(card->ip_htable); + hash_init(card->ip_mc_htable); card->options.layer2 = 0; card->info.hwtrap = 0; return 0; @@ -3306,6 +3311,7 @@ static int qeth_l3_control_event(struct qeth_card *card, } struct qeth_discipline qeth_l3_discipline = { + .devtype = &qeth_generic_devtype, .start_poll = qeth_qdio_start_poll, .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 2a76ea78a0bf..b18fe2014cf2 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -87,7 +87,7 @@ struct vq_info_block { } __packed; struct virtio_feature_desc { - __u32 features; + __le32 features; __u8 index; } __packed; diff --git a/drivers/scsi/cxlflash/Kconfig b/drivers/scsi/cxlflash/Kconfig index c052104e523e..a011c5dbf214 100644 --- a/drivers/scsi/cxlflash/Kconfig +++ b/drivers/scsi/cxlflash/Kconfig @@ -5,6 +5,7 @@ config CXLFLASH tristate "Support for IBM CAPI Flash" depends on PCI && SCSI && CXL && EEH + select IRQ_POLL default m help Allows CAPI Accelerated IO to Flash diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index a808e8ef1d08..234352da5c3c 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -407,11 +407,12 @@ unlock: * can_queue. Eventually we will hit the point where we run * on all reserved structs. */ -static void fc_fcp_can_queue_ramp_down(struct fc_lport *lport) +static bool fc_fcp_can_queue_ramp_down(struct fc_lport *lport) { struct fc_fcp_internal *si = fc_get_scsi_internal(lport); unsigned long flags; int can_queue; + bool changed = false; spin_lock_irqsave(lport->host->host_lock, flags); @@ -427,9 +428,11 @@ static void fc_fcp_can_queue_ramp_down(struct fc_lport *lport) if (!can_queue) can_queue = 1; lport->host->can_queue = can_queue; + changed = true; unlock: spin_unlock_irqrestore(lport->host->host_lock, flags); + return changed; } /* @@ -1896,11 +1899,11 @@ int fc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc_cmd) if (!fc_fcp_lport_queue_ready(lport)) { if (lport->qfull) { - fc_fcp_can_queue_ramp_down(lport); - shost_printk(KERN_ERR, lport->host, - "libfc: queue full, " - "reducing can_queue to %d.\n", - lport->host->can_queue); + if (fc_fcp_can_queue_ramp_down(lport)) + shost_printk(KERN_ERR, lport->host, + "libfc: queue full, " + "reducing can_queue to %d.\n", + lport->host->can_queue); } rc = SCSI_MLQUEUE_HOST_BUSY; goto out; diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 944b32ca4931..1c55408ac718 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -294,6 +294,7 @@ int lpfc_selective_reset(struct lpfc_hba *); void lpfc_reset_barrier(struct lpfc_hba *); int lpfc_sli_brdready(struct lpfc_hba *, uint32_t); int lpfc_sli_brdkill(struct lpfc_hba *); +int lpfc_sli_chipset_init(struct lpfc_hba *phba); int lpfc_sli_brdreset(struct lpfc_hba *); int lpfc_sli_brdrestart(struct lpfc_hba *); int lpfc_sli_hba_setup(struct lpfc_hba *); diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 1487406aea77..c7962dae4dab 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -630,7 +630,7 @@ lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type, NLP_EVT_DEVICE_RECOVERY); spin_lock_irq(shost->host_lock); ndlp->nlp_flag &= ~NLP_NVMET_RECOV; - spin_lock_irq(shost->host_lock); + spin_unlock_irq(shost->host_lock); } } diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 90ae354a9c45..4b1eb98c228d 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -3602,6 +3602,13 @@ lpfc_get_wwpn(struct lpfc_hba *phba) LPFC_MBOXQ_t *mboxq; MAILBOX_t *mb; + if (phba->sli_rev < LPFC_SLI_REV4) { + /* Reset the port first */ + lpfc_sli_brdrestart(phba); + rc = lpfc_sli_chipset_init(phba); + if (rc) + return (uint64_t)-1; + } mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); @@ -8847,7 +8854,7 @@ lpfc_sli4_queue_unset(struct lpfc_hba *phba) lpfc_wq_destroy(phba, phba->sli4_hba.nvmels_wq); /* Unset ELS work queue */ - if (phba->sli4_hba.els_cq) + if (phba->sli4_hba.els_wq) lpfc_wq_destroy(phba, phba->sli4_hba.els_wq); /* Unset unsolicited receive queue */ diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index 94434e621c33..0488580eea12 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -764,7 +764,6 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba) lpfc_tgttemplate.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1; lpfc_tgttemplate.max_hw_queues = phba->cfg_nvme_io_channel; lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP | - NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED | NVMET_FCTGTFEAT_CMD_IN_ISR | NVMET_FCTGTFEAT_OPDONE_IN_ISR; diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index cf19f4976f5f..2a4fc00dfa9b 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -4204,13 +4204,16 @@ lpfc_sli_brdreset(struct lpfc_hba *phba) /* Reset HBA */ lpfc_printf_log(phba, KERN_INFO, LOG_SLI, "0325 Reset HBA Data: x%x x%x\n", - phba->pport->port_state, psli->sli_flag); + (phba->pport) ? phba->pport->port_state : 0, + psli->sli_flag); /* perform board reset */ phba->fc_eventTag = 0; phba->link_events = 0; - phba->pport->fc_myDID = 0; - phba->pport->fc_prevDID = 0; + if (phba->pport) { + phba->pport->fc_myDID = 0; + phba->pport->fc_prevDID = 0; + } /* Turn off parity checking and serr during the physical reset */ pci_read_config_word(phba->pcidev, PCI_COMMAND, &cfg_value); @@ -4336,7 +4339,8 @@ lpfc_sli_brdrestart_s3(struct lpfc_hba *phba) /* Restart HBA */ lpfc_printf_log(phba, KERN_INFO, LOG_SLI, "0337 Restart HBA Data: x%x x%x\n", - phba->pport->port_state, psli->sli_flag); + (phba->pport) ? phba->pport->port_state : 0, + psli->sli_flag); word0 = 0; mb = (MAILBOX_t *) &word0; @@ -4350,7 +4354,7 @@ lpfc_sli_brdrestart_s3(struct lpfc_hba *phba) readl(to_slim); /* flush */ /* Only skip post after fc_ffinit is completed */ - if (phba->pport->port_state) + if (phba->pport && phba->pport->port_state) word0 = 1; /* This is really setting up word1 */ else word0 = 0; /* This is really setting up word1 */ @@ -4359,7 +4363,8 @@ lpfc_sli_brdrestart_s3(struct lpfc_hba *phba) readl(to_slim); /* flush */ lpfc_sli_brdreset(phba); - phba->pport->stopped = 0; + if (phba->pport) + phba->pport->stopped = 0; phba->link_state = LPFC_INIT_START; phba->hba_flag = 0; spin_unlock_irq(&phba->hbalock); @@ -4446,7 +4451,7 @@ lpfc_sli_brdrestart(struct lpfc_hba *phba) * iteration, the function will restart the HBA again. The function returns * zero if HBA successfully restarted else returns negative error code. **/ -static int +int lpfc_sli_chipset_init(struct lpfc_hba *phba) { uint32_t status, i = 0; diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index a4aadf5f4dc6..1cc814f1505a 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -3770,9 +3770,6 @@ static long pmcraid_ioctl_passthrough( pmcraid_err("couldn't build passthrough ioadls\n"); goto out_free_cmd; } - } else if (request_size < 0) { - rc = -EINVAL; - goto out_free_cmd; } /* If data is being written into the device, copy the data from user diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h index 40aeb6bb96a2..07ee88200e91 100644 --- a/drivers/scsi/qedf/qedf.h +++ b/drivers/scsi/qedf/qedf.h @@ -259,7 +259,7 @@ struct qedf_io_log { uint16_t task_id; uint32_t port_id; /* Remote port fabric ID */ int lun; - char op; /* SCSI CDB */ + unsigned char op; /* SCSI CDB */ uint8_t lba[4]; unsigned int bufflen; /* SCSI buffer length */ unsigned int sg_count; /* Number of SG elements */ diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c index c505d41f6dc8..90627033bde6 100644 --- a/drivers/scsi/qedf/qedf_els.c +++ b/drivers/scsi/qedf/qedf_els.c @@ -109,7 +109,7 @@ retry_els: did = fcport->rdata->ids.port_id; sid = fcport->sid; - __fc_fill_fc_hdr(fc_hdr, FC_RCTL_ELS_REQ, sid, did, + __fc_fill_fc_hdr(fc_hdr, FC_RCTL_ELS_REQ, did, sid, FC_TYPE_ELS, FC_FC_FIRST_SEQ | FC_FC_END_SEQ | FC_FC_SEQ_INIT, 0); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index cceddd995a4b..a5c97342fd5d 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -2895,7 +2895,7 @@ static int __qedf_probe(struct pci_dev *pdev, int mode) slowpath_params.drv_minor = QEDF_DRIVER_MINOR_VER; slowpath_params.drv_rev = QEDF_DRIVER_REV_VER; slowpath_params.drv_eng = QEDF_DRIVER_ENG_VER; - memcpy(slowpath_params.name, "qedf", QED_DRV_VER_STR_SIZE); + strncpy(slowpath_params.name, "qedf", QED_DRV_VER_STR_SIZE); rc = qed_ops->common->slowpath_start(qedf->cdev, &slowpath_params); if (rc) { QEDF_ERR(&(qedf->dbg_ctx), "Cannot start slowpath.\n"); diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 7bfbcfa7af40..61cdd99ae41e 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -763,6 +763,8 @@ struct scsi_device *__scsi_device_lookup(struct Scsi_Host *shost, struct scsi_device *sdev; list_for_each_entry(sdev, &shost->__devices, siblings) { + if (sdev->sdev_state == SDEV_DEL) + continue; if (sdev->channel == channel && sdev->id == id && sdev->lun ==lun) return sdev; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 814a4bd8405d..e31f1cc90b81 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -30,6 +30,7 @@ #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> +#include <scsi/scsi_transport.h> /* __scsi_init_queue() */ #include <scsi/scsi_dh.h> #include <trace/events/scsi.h> diff --git a/drivers/soc/bcm/brcmstb/common.c b/drivers/soc/bcm/brcmstb/common.c index b6195fdf0d00..22e98a90468c 100644 --- a/drivers/soc/bcm/brcmstb/common.c +++ b/drivers/soc/bcm/brcmstb/common.c @@ -49,7 +49,7 @@ static const struct of_device_id sun_top_ctrl_match[] = { { .compatible = "brcm,bcm7420-sun-top-ctrl", }, { .compatible = "brcm,bcm7425-sun-top-ctrl", }, { .compatible = "brcm,bcm7429-sun-top-ctrl", }, - { .compatible = "brcm,bcm7425-sun-top-ctrl", }, + { .compatible = "brcm,bcm7435-sun-top-ctrl", }, { .compatible = "brcm,brcmstb-sun-top-ctrl", }, { } }; diff --git a/drivers/soc/imx/Kconfig b/drivers/soc/imx/Kconfig index 357a5d8f8da0..a5b86a28f343 100644 --- a/drivers/soc/imx/Kconfig +++ b/drivers/soc/imx/Kconfig @@ -2,8 +2,9 @@ menu "i.MX SoC drivers" config IMX7_PM_DOMAINS bool "i.MX7 PM domains" - select PM_GENERIC_DOMAINS depends on SOC_IMX7D || (COMPILE_TEST && OF) + depends on PM + select PM_GENERIC_DOMAINS default y if SOC_IMX7D endmenu diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c index ecebe2eecc3a..026182d3b27c 100644 --- a/drivers/soc/ti/knav_dma.c +++ b/drivers/soc/ti/knav_dma.c @@ -413,7 +413,7 @@ static int of_channel_match_helper(struct device_node *np, const char *name, * @name: slave channel name * @config: dma configuration parameters * - * Returns pointer to appropriate DMA channel on success or NULL. + * Returns pointer to appropriate DMA channel on success or error. */ void *knav_dma_open_channel(struct device *dev, const char *name, struct knav_dma_cfg *config) diff --git a/drivers/staging/android/ion/devicetree.txt b/drivers/staging/android/ion/devicetree.txt deleted file mode 100644 index 168715271f06..000000000000 --- a/drivers/staging/android/ion/devicetree.txt +++ /dev/null @@ -1,51 +0,0 @@ -Ion Memory Manager - -Ion is a memory manager that allows for sharing of buffers via dma-buf. -Ion allows for different types of allocation via an abstraction called -a 'heap'. A heap represents a specific type of memory. Each heap has -a different type. There can be multiple instances of the same heap -type. - -Specific heap instances are tied to heap IDs. Heap IDs are not to be specified -in the devicetree. - -Required properties for Ion - -- compatible: "linux,ion" PLUS a compatible property for the device - -All child nodes of a linux,ion node are interpreted as heaps - -required properties for heaps - -- compatible: compatible string for a heap type PLUS a compatible property -for the specific instance of the heap. Current heap types --- linux,ion-heap-system --- linux,ion-heap-system-contig --- linux,ion-heap-carveout --- linux,ion-heap-chunk --- linux,ion-heap-dma --- linux,ion-heap-custom - -Optional properties -- memory-region: A phandle to a memory region. Required for DMA heap type -(see reserved-memory.txt for details on the reservation) - -Example: - - ion { - compatbile = "hisilicon,ion", "linux,ion"; - - ion-system-heap { - compatbile = "hisilicon,system-heap", "linux,ion-heap-system" - }; - - ion-camera-region { - compatible = "hisilicon,camera-heap", "linux,ion-heap-dma" - memory-region = <&camera_region>; - }; - - ion-fb-region { - compatbile = "hisilicon,fb-heap", "linux,ion-heap-dma" - memory-region = <&fb_region>; - }; - } diff --git a/drivers/staging/ccree/ssi_request_mgr.c b/drivers/staging/ccree/ssi_request_mgr.c index 522bd62c102e..8611adf3bb2e 100644 --- a/drivers/staging/ccree/ssi_request_mgr.c +++ b/drivers/staging/ccree/ssi_request_mgr.c @@ -376,7 +376,6 @@ int send_request( rc = ssi_power_mgr_runtime_get(&drvdata->plat_dev->dev); if (rc != 0) { SSI_LOG_ERR("ssi_power_mgr_runtime_get returned %x\n",rc); - spin_unlock_bh(&req_mgr_h->hw_lock); return rc; } #endif diff --git a/drivers/staging/fsl-dpaa2/Kconfig b/drivers/staging/fsl-dpaa2/Kconfig index 2e325cb747ae..730fd6d4db33 100644 --- a/drivers/staging/fsl-dpaa2/Kconfig +++ b/drivers/staging/fsl-dpaa2/Kconfig @@ -12,6 +12,7 @@ config FSL_DPAA2 config FSL_DPAA2_ETH tristate "Freescale DPAA2 Ethernet" depends on FSL_DPAA2 && FSL_MC_DPIO + depends on NETDEVICES && ETHERNET ---help--- Ethernet driver for Freescale DPAA2 SoCs, using the Freescale MC bus driver diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 4723a0bd5067..1c6ed5b2a6f9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -97,8 +97,9 @@ void rtl92e_set_reg(struct net_device *dev, u8 variable, u8 *val) switch (variable) { case HW_VAR_BSSID: - rtl92e_writel(dev, BSSIDR, ((u32 *)(val))[0]); - rtl92e_writew(dev, BSSIDR+2, ((u16 *)(val+2))[0]); + /* BSSIDR 2 byte alignment */ + rtl92e_writew(dev, BSSIDR, *(u16 *)val); + rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(val + 2)); break; case HW_VAR_MEDIA_STATUS: @@ -624,7 +625,7 @@ void rtl92e_get_eeprom_size(struct net_device *dev) struct r8192_priv *priv = rtllib_priv(dev); RT_TRACE(COMP_INIT, "===========>%s()\n", __func__); - curCR = rtl92e_readl(dev, EPROM_CMD); + curCR = rtl92e_readw(dev, EPROM_CMD); RT_TRACE(COMP_INIT, "read from Reg Cmd9346CR(%x):%x\n", EPROM_CMD, curCR); priv->epromtype = (curCR & EPROM_CMD_9356SEL) ? EEPROM_93C56 : @@ -961,8 +962,8 @@ static void _rtl92e_net_update(struct net_device *dev) rtl92e_config_rate(dev, &rate_config); priv->dot11CurrentPreambleMode = PREAMBLE_AUTO; priv->basic_rate = rate_config &= 0x15f; - rtl92e_writel(dev, BSSIDR, ((u32 *)net->bssid)[0]); - rtl92e_writew(dev, BSSIDR+4, ((u16 *)net->bssid)[2]); + rtl92e_writew(dev, BSSIDR, *(u16 *)net->bssid); + rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(net->bssid + 2)); if (priv->rtllib->iw_mode == IW_MODE_ADHOC) { rtl92e_writew(dev, ATIMWND, 2); @@ -1182,8 +1183,7 @@ void rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc, struct cb_desc *cb_desc, struct sk_buff *skb) { struct r8192_priv *priv = rtllib_priv(dev); - dma_addr_t mapping = pci_map_single(priv->pdev, skb->data, skb->len, - PCI_DMA_TODEVICE); + dma_addr_t mapping; struct tx_fwinfo_8190pci *pTxFwInfo; pTxFwInfo = (struct tx_fwinfo_8190pci *)skb->data; @@ -1194,8 +1194,6 @@ void rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc, pTxFwInfo->Short = _rtl92e_query_is_short(pTxFwInfo->TxHT, pTxFwInfo->TxRate, cb_desc); - if (pci_dma_mapping_error(priv->pdev, mapping)) - netdev_err(dev, "%s(): DMA Mapping error\n", __func__); if (cb_desc->bAMPDUEnable) { pTxFwInfo->AllowAggregation = 1; pTxFwInfo->RxMF = cb_desc->ampdu_factor; @@ -1230,6 +1228,14 @@ void rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc, } memset((u8 *)pdesc, 0, 12); + + mapping = pci_map_single(priv->pdev, skb->data, skb->len, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(priv->pdev, mapping)) { + netdev_err(dev, "%s(): DMA Mapping error\n", __func__); + return; + } + pdesc->LINIP = 0; pdesc->CmdInit = 1; pdesc->Offset = sizeof(struct tx_fwinfo_8190pci) + 8; diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c index 48bbd9e8a52f..dcc4eb691889 100644 --- a/drivers/staging/rtl8192e/rtl819x_TSProc.c +++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c @@ -306,11 +306,6 @@ static void MakeTSEntry(struct ts_common_info *pTsCommonInfo, u8 *Addr, pTsCommonInfo->TClasNum = TCLAS_Num; } -static bool IsACValid(unsigned int tid) -{ - return tid < 7; -} - bool GetTs(struct rtllib_device *ieee, struct ts_common_info **ppTS, u8 *Addr, u8 TID, enum tr_select TxRxSelect, bool bAddNewTs) { @@ -328,12 +323,6 @@ bool GetTs(struct rtllib_device *ieee, struct ts_common_info **ppTS, if (ieee->current_network.qos_data.supported == 0) { UP = 0; } else { - if (!IsACValid(TID)) { - netdev_warn(ieee->dev, "%s(): TID(%d) is not valid\n", - __func__, TID); - return false; - } - switch (TID) { case 0: case 3: @@ -351,6 +340,10 @@ bool GetTs(struct rtllib_device *ieee, struct ts_common_info **ppTS, case 7: UP = 7; break; + default: + netdev_warn(ieee->dev, "%s(): TID(%d) is not valid\n", + __func__, TID); + return false; } } diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index 5e7a61f24f8d..36c3189fc4b7 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -3531,7 +3531,6 @@ int rtw_wdev_alloc(struct adapter *padapter, struct device *dev) pwdev_priv->power_mgmt = true; else pwdev_priv->power_mgmt = false; - kfree((u8 *)wdev); return ret; diff --git a/drivers/staging/typec/fusb302/fusb302.c b/drivers/staging/typec/fusb302/fusb302.c index 2cee9a952c9b..4a356e509fe4 100644 --- a/drivers/staging/typec/fusb302/fusb302.c +++ b/drivers/staging/typec/fusb302/fusb302.c @@ -264,22 +264,36 @@ static void fusb302_debugfs_exit(const struct fusb302_chip *chip) { } #define FUSB302_RESUME_RETRY 10 #define FUSB302_RESUME_RETRY_SLEEP 50 -static int fusb302_i2c_write(struct fusb302_chip *chip, - u8 address, u8 data) + +static bool fusb302_is_suspended(struct fusb302_chip *chip) { int retry_cnt; - int ret = 0; - atomic_set(&chip->i2c_busy, 1); for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) { if (atomic_read(&chip->pm_suspend)) { - pr_err("fusb302_i2c: pm suspend, retry %d/%d\n", - retry_cnt + 1, FUSB302_RESUME_RETRY); + dev_err(chip->dev, "i2c: pm suspend, retry %d/%d\n", + retry_cnt + 1, FUSB302_RESUME_RETRY); msleep(FUSB302_RESUME_RETRY_SLEEP); } else { - break; + return false; } } + + return true; +} + +static int fusb302_i2c_write(struct fusb302_chip *chip, + u8 address, u8 data) +{ + int ret = 0; + + atomic_set(&chip->i2c_busy, 1); + + if (fusb302_is_suspended(chip)) { + atomic_set(&chip->i2c_busy, 0); + return -ETIMEDOUT; + } + ret = i2c_smbus_write_byte_data(chip->i2c_client, address, data); if (ret < 0) fusb302_log(chip, "cannot write 0x%02x to 0x%02x, ret=%d", @@ -292,21 +306,17 @@ static int fusb302_i2c_write(struct fusb302_chip *chip, static int fusb302_i2c_block_write(struct fusb302_chip *chip, u8 address, u8 length, const u8 *data) { - int retry_cnt; int ret = 0; if (length <= 0) return ret; atomic_set(&chip->i2c_busy, 1); - for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) { - if (atomic_read(&chip->pm_suspend)) { - pr_err("fusb302_i2c: pm suspend, retry %d/%d\n", - retry_cnt + 1, FUSB302_RESUME_RETRY); - msleep(FUSB302_RESUME_RETRY_SLEEP); - } else { - break; - } + + if (fusb302_is_suspended(chip)) { + atomic_set(&chip->i2c_busy, 0); + return -ETIMEDOUT; } + ret = i2c_smbus_write_i2c_block_data(chip->i2c_client, address, length, data); if (ret < 0) @@ -320,19 +330,15 @@ static int fusb302_i2c_block_write(struct fusb302_chip *chip, u8 address, static int fusb302_i2c_read(struct fusb302_chip *chip, u8 address, u8 *data) { - int retry_cnt; int ret = 0; atomic_set(&chip->i2c_busy, 1); - for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) { - if (atomic_read(&chip->pm_suspend)) { - pr_err("fusb302_i2c: pm suspend, retry %d/%d\n", - retry_cnt + 1, FUSB302_RESUME_RETRY); - msleep(FUSB302_RESUME_RETRY_SLEEP); - } else { - break; - } + + if (fusb302_is_suspended(chip)) { + atomic_set(&chip->i2c_busy, 0); + return -ETIMEDOUT; } + ret = i2c_smbus_read_byte_data(chip->i2c_client, address); *data = (u8)ret; if (ret < 0) @@ -345,33 +351,31 @@ static int fusb302_i2c_read(struct fusb302_chip *chip, static int fusb302_i2c_block_read(struct fusb302_chip *chip, u8 address, u8 length, u8 *data) { - int retry_cnt; int ret = 0; if (length <= 0) return ret; atomic_set(&chip->i2c_busy, 1); - for (retry_cnt = 0; retry_cnt < FUSB302_RESUME_RETRY; retry_cnt++) { - if (atomic_read(&chip->pm_suspend)) { - pr_err("fusb302_i2c: pm suspend, retry %d/%d\n", - retry_cnt + 1, FUSB302_RESUME_RETRY); - msleep(FUSB302_RESUME_RETRY_SLEEP); - } else { - break; - } + + if (fusb302_is_suspended(chip)) { + atomic_set(&chip->i2c_busy, 0); + return -ETIMEDOUT; } + ret = i2c_smbus_read_i2c_block_data(chip->i2c_client, address, length, data); if (ret < 0) { fusb302_log(chip, "cannot block read 0x%02x, len=%d, ret=%d", address, length, ret); - return ret; + goto done; } if (ret != length) { fusb302_log(chip, "only read %d/%d bytes from 0x%02x", ret, length, address); - return -EIO; + ret = -EIO; } + +done: atomic_set(&chip->i2c_busy, 0); return ret; @@ -489,7 +493,7 @@ static int tcpm_init(struct tcpc_dev *dev) ret = fusb302_i2c_read(chip, FUSB_REG_STATUS0, &data); if (ret < 0) return ret; - chip->vbus_present = !!(FUSB_REG_STATUS0 & FUSB_REG_STATUS0_VBUSOK); + chip->vbus_present = !!(data & FUSB_REG_STATUS0_VBUSOK); ret = fusb302_i2c_read(chip, FUSB_REG_DEVICE_ID, &data); if (ret < 0) return ret; @@ -1025,7 +1029,7 @@ static int fusb302_pd_send_message(struct fusb302_chip *chip, buf[pos++] = FUSB302_TKN_SYNC1; buf[pos++] = FUSB302_TKN_SYNC2; - len = pd_header_cnt(msg->header) * 4; + len = pd_header_cnt_le(msg->header) * 4; /* plug 2 for header */ len += 2; if (len > 0x1F) { @@ -1481,7 +1485,7 @@ static int fusb302_pd_read_message(struct fusb302_chip *chip, (u8 *)&msg->header); if (ret < 0) return ret; - len = pd_header_cnt(msg->header) * 4; + len = pd_header_cnt_le(msg->header) * 4; /* add 4 to length to include the CRC */ if (len > PD_MAX_PAYLOAD * 4) { fusb302_log(chip, "PD message too long %d", len); @@ -1663,14 +1667,12 @@ static int init_gpio(struct fusb302_chip *chip) if (ret < 0) { fusb302_log(chip, "cannot set GPIO Int_N to input, ret=%d", ret); - gpio_free(chip->gpio_int_n); return ret; } ret = gpio_to_irq(chip->gpio_int_n); if (ret < 0) { fusb302_log(chip, "cannot request IRQ for GPIO Int_N, ret=%d", ret); - gpio_free(chip->gpio_int_n); return ret; } chip->gpio_int_n_irq = ret; @@ -1787,11 +1789,13 @@ static const struct of_device_id fusb302_dt_match[] = { {.compatible = "fcs,fusb302"}, {}, }; +MODULE_DEVICE_TABLE(of, fusb302_dt_match); static const struct i2c_device_id fusb302_i2c_device_id[] = { {"typec_fusb302", 0}, {}, }; +MODULE_DEVICE_TABLE(i2c, fusb302_i2c_device_id); static const struct dev_pm_ops fusb302_pm_ops = { .suspend = fusb302_pm_suspend, diff --git a/drivers/staging/typec/pd.h b/drivers/staging/typec/pd.h index 8d97bdb95f23..510ef7279900 100644 --- a/drivers/staging/typec/pd.h +++ b/drivers/staging/typec/pd.h @@ -92,6 +92,16 @@ static inline unsigned int pd_header_type_le(__le16 header) return pd_header_type(le16_to_cpu(header)); } +static inline unsigned int pd_header_msgid(u16 header) +{ + return (header >> PD_HEADER_ID_SHIFT) & PD_HEADER_ID_MASK; +} + +static inline unsigned int pd_header_msgid_le(__le16 header) +{ + return pd_header_msgid(le16_to_cpu(header)); +} + #define PD_MAX_PAYLOAD 7 struct pd_message { diff --git a/drivers/staging/typec/pd_vdo.h b/drivers/staging/typec/pd_vdo.h index dba172e0e0d1..d92259f8de0a 100644 --- a/drivers/staging/typec/pd_vdo.h +++ b/drivers/staging/typec/pd_vdo.h @@ -22,6 +22,9 @@ * VDM object is minimum of VDM header + 6 additional data objects. */ +#define VDO_MAX_OBJECTS 6 +#define VDO_MAX_SIZE (VDO_MAX_OBJECTS + 1) + /* * VDM header * ---------- @@ -34,7 +37,6 @@ * <5> :: reserved (SVDM), command type (UVDM) * <4:0> :: command */ -#define VDO_MAX_SIZE 7 #define VDO(vid, type, custom) \ (((vid) << 16) | \ ((type) << 15) | \ diff --git a/drivers/staging/typec/tcpci.c b/drivers/staging/typec/tcpci.c index 5e5be74c7850..df72d8b01e73 100644 --- a/drivers/staging/typec/tcpci.c +++ b/drivers/staging/typec/tcpci.c @@ -425,7 +425,7 @@ static const struct regmap_config tcpci_regmap_config = { .max_register = 0x7F, /* 0x80 .. 0xFF are vendor defined */ }; -const struct tcpc_config tcpci_tcpc_config = { +static const struct tcpc_config tcpci_tcpc_config = { .type = TYPEC_PORT_DFP, .default_role = TYPEC_SINK, }; diff --git a/drivers/staging/typec/tcpm.c b/drivers/staging/typec/tcpm.c index abba655ba00a..20eb4ebcf8c3 100644 --- a/drivers/staging/typec/tcpm.c +++ b/drivers/staging/typec/tcpm.c @@ -238,6 +238,7 @@ struct tcpm_port { unsigned int hard_reset_count; bool pd_capable; bool explicit_contract; + unsigned int rx_msgid; /* Partner capabilities/requests */ u32 sink_request; @@ -251,6 +252,8 @@ struct tcpm_port { unsigned int nr_src_pdo; u32 snk_pdo[PDO_MAX_OBJECTS]; unsigned int nr_snk_pdo; + u32 snk_vdo[VDO_MAX_OBJECTS]; + unsigned int nr_snk_vdo; unsigned int max_snk_mv; unsigned int max_snk_ma; @@ -997,6 +1000,7 @@ static int tcpm_pd_svdm(struct tcpm_port *port, const __le32 *payload, int cnt, struct pd_mode_data *modep; int rlen = 0; u16 svid; + int i; tcpm_log(port, "Rx VDM cmd 0x%x type %d cmd %d len %d", p0, cmd_type, cmd, cnt); @@ -1007,6 +1011,14 @@ static int tcpm_pd_svdm(struct tcpm_port *port, const __le32 *payload, int cnt, case CMDT_INIT: switch (cmd) { case CMD_DISCOVER_IDENT: + /* 6.4.4.3.1: Only respond as UFP (device) */ + if (port->data_role == TYPEC_DEVICE && + port->nr_snk_vdo) { + for (i = 0; i < port->nr_snk_vdo; i++) + response[i + 1] + = cpu_to_le32(port->snk_vdo[i]); + rlen = port->nr_snk_vdo + 1; + } break; case CMD_DISCOVER_SVID: break; @@ -1415,6 +1427,7 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port, break; case SOFT_RESET_SEND: port->message_id = 0; + port->rx_msgid = -1; if (port->pwr_role == TYPEC_SOURCE) next_state = SRC_SEND_CAPABILITIES; else @@ -1503,6 +1516,22 @@ static void tcpm_pd_rx_handler(struct work_struct *work) port->attached); if (port->attached) { + enum pd_ctrl_msg_type type = pd_header_type_le(msg->header); + unsigned int msgid = pd_header_msgid_le(msg->header); + + /* + * USB PD standard, 6.6.1.2: + * "... if MessageID value in a received Message is the + * same as the stored value, the receiver shall return a + * GoodCRC Message with that MessageID value and drop + * the Message (this is a retry of an already received + * Message). Note: this shall not apply to the Soft_Reset + * Message which always has a MessageID value of zero." + */ + if (msgid == port->rx_msgid && type != PD_CTRL_SOFT_RESET) + goto done; + port->rx_msgid = msgid; + /* * If both ends believe to be DFP/host, we have a data role * mismatch. @@ -1520,6 +1549,7 @@ static void tcpm_pd_rx_handler(struct work_struct *work) } } +done: mutex_unlock(&port->lock); kfree(event); } @@ -1719,8 +1749,7 @@ static int tcpm_pd_build_request(struct tcpm_port *port, u32 *rdo) } ma = min(ma, port->max_snk_ma); - /* XXX: Any other flags need to be set? */ - flags = 0; + flags = RDO_USB_COMM | RDO_NO_SUSPEND; /* Set mismatch bit if offered power is less than operating power */ mw = ma * mv / 1000; @@ -1957,6 +1986,12 @@ static void tcpm_reset_port(struct tcpm_port *port) port->attached = false; port->pd_capable = false; + /* + * First Rx ID should be 0; set this to a sentinel of -1 so that + * we can check tcpm_pd_rx_handler() if we had seen it before. + */ + port->rx_msgid = -1; + port->tcpc->set_pd_rx(port->tcpc, false); tcpm_init_vbus(port); /* also disables charging */ tcpm_init_vconn(port); @@ -2170,6 +2205,7 @@ static void run_state_machine(struct tcpm_port *port) port->pwr_opmode = TYPEC_PWR_MODE_USB; port->caps_count = 0; port->message_id = 0; + port->rx_msgid = -1; port->explicit_contract = false; tcpm_set_state(port, SRC_SEND_CAPABILITIES, 0); break; @@ -2329,6 +2365,7 @@ static void run_state_machine(struct tcpm_port *port) typec_set_pwr_opmode(port->typec_port, TYPEC_PWR_MODE_USB); port->pwr_opmode = TYPEC_PWR_MODE_USB; port->message_id = 0; + port->rx_msgid = -1; port->explicit_contract = false; tcpm_set_state(port, SNK_DISCOVERY, 0); break; @@ -2496,6 +2533,7 @@ static void run_state_machine(struct tcpm_port *port) /* Soft_Reset states */ case SOFT_RESET: port->message_id = 0; + port->rx_msgid = -1; tcpm_pd_send_control(port, PD_CTRL_ACCEPT); if (port->pwr_role == TYPEC_SOURCE) tcpm_set_state(port, SRC_SEND_CAPABILITIES, 0); @@ -2504,6 +2542,7 @@ static void run_state_machine(struct tcpm_port *port) break; case SOFT_RESET_SEND: port->message_id = 0; + port->rx_msgid = -1; if (tcpm_pd_send_control(port, PD_CTRL_SOFT_RESET)) tcpm_set_state_cond(port, hard_reset_state(port), 0); else @@ -2568,6 +2607,14 @@ static void run_state_machine(struct tcpm_port *port) break; case PR_SWAP_SRC_SNK_SOURCE_OFF: tcpm_set_cc(port, TYPEC_CC_RD); + /* + * USB-PD standard, 6.2.1.4, Port Power Role: + * "During the Power Role Swap Sequence, for the initial Source + * Port, the Port Power Role field shall be set to Sink in the + * PS_RDY Message indicating that the initial Source’s power + * supply is turned off" + */ + tcpm_set_pwr_role(port, TYPEC_SINK); if (tcpm_pd_send_control(port, PD_CTRL_PS_RDY)) { tcpm_set_state(port, ERROR_RECOVERY, 0); break; @@ -2575,7 +2622,6 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state_cond(port, SNK_UNATTACHED, PD_T_PS_SOURCE_ON); break; case PR_SWAP_SRC_SNK_SINK_ON: - tcpm_set_pwr_role(port, TYPEC_SINK); tcpm_swap_complete(port, 0); tcpm_set_state(port, SNK_STARTUP, 0); break; @@ -2587,8 +2633,15 @@ static void run_state_machine(struct tcpm_port *port) case PR_SWAP_SNK_SRC_SOURCE_ON: tcpm_set_cc(port, tcpm_rp_cc(port)); tcpm_set_vbus(port, true); - tcpm_pd_send_control(port, PD_CTRL_PS_RDY); + /* + * USB PD standard, 6.2.1.4: + * "Subsequent Messages initiated by the Policy Engine, + * such as the PS_RDY Message sent to indicate that Vbus + * is ready, will have the Port Power Role field set to + * Source." + */ tcpm_set_pwr_role(port, TYPEC_SOURCE); + tcpm_pd_send_control(port, PD_CTRL_PS_RDY); tcpm_swap_complete(port, 0); tcpm_set_state(port, SRC_STARTUP, 0); break; @@ -3292,6 +3345,20 @@ static int tcpm_copy_pdos(u32 *dest_pdo, const u32 *src_pdo, return nr_pdo; } +static int tcpm_copy_vdos(u32 *dest_vdo, const u32 *src_vdo, + unsigned int nr_vdo) +{ + unsigned int i; + + if (nr_vdo > VDO_MAX_OBJECTS) + nr_vdo = VDO_MAX_OBJECTS; + + for (i = 0; i < nr_vdo; i++) + dest_vdo[i] = src_vdo[i]; + + return nr_vdo; +} + void tcpm_update_source_capabilities(struct tcpm_port *port, const u32 *pdo, unsigned int nr_pdo) { @@ -3382,6 +3449,8 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) tcpc->config->nr_src_pdo); port->nr_snk_pdo = tcpm_copy_pdos(port->snk_pdo, tcpc->config->snk_pdo, tcpc->config->nr_snk_pdo); + port->nr_snk_vdo = tcpm_copy_vdos(port->snk_vdo, tcpc->config->snk_vdo, + tcpc->config->nr_snk_vdo); port->max_snk_mv = tcpc->config->max_snk_mv; port->max_snk_ma = tcpc->config->max_snk_ma; diff --git a/drivers/staging/typec/tcpm.h b/drivers/staging/typec/tcpm.h index 969b365e6549..19c307d31a5a 100644 --- a/drivers/staging/typec/tcpm.h +++ b/drivers/staging/typec/tcpm.h @@ -60,6 +60,9 @@ struct tcpc_config { const u32 *snk_pdo; unsigned int nr_snk_pdo; + const u32 *snk_vdo; + unsigned int nr_snk_vdo; + unsigned int max_snk_mv; unsigned int max_snk_ma; unsigned int max_snk_mw; diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c index 988ee61fb4a7..d04db3f55519 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c @@ -502,8 +502,15 @@ create_pagelist(char __user *buf, size_t count, unsigned short type, */ sg_init_table(scatterlist, num_pages); /* Now set the pages for each scatterlist */ - for (i = 0; i < num_pages; i++) - sg_set_page(scatterlist + i, pages[i], PAGE_SIZE, 0); + for (i = 0; i < num_pages; i++) { + unsigned int len = PAGE_SIZE - offset; + + if (len > count) + len = count; + sg_set_page(scatterlist + i, pages[i], len, offset); + offset = 0; + count -= len; + } dma_buffers = dma_map_sg(g_dev, scatterlist, @@ -524,20 +531,20 @@ create_pagelist(char __user *buf, size_t count, unsigned short type, u32 addr = sg_dma_address(sg); /* Note: addrs is the address + page_count - 1 - * The firmware expects the block to be page + * The firmware expects blocks after the first to be page- * aligned and a multiple of the page size */ WARN_ON(len == 0); - WARN_ON(len & ~PAGE_MASK); - WARN_ON(addr & ~PAGE_MASK); + WARN_ON(i && (i != (dma_buffers - 1)) && (len & ~PAGE_MASK)); + WARN_ON(i && (addr & ~PAGE_MASK)); if (k > 0 && - ((addrs[k - 1] & PAGE_MASK) | - ((addrs[k - 1] & ~PAGE_MASK) + 1) << PAGE_SHIFT) - == addr) { - addrs[k - 1] += (len >> PAGE_SHIFT); - } else { - addrs[k++] = addr | ((len >> PAGE_SHIFT) - 1); - } + ((addrs[k - 1] & PAGE_MASK) + + (((addrs[k - 1] & ~PAGE_MASK) + 1) << PAGE_SHIFT)) + == (addr & PAGE_MASK)) + addrs[k - 1] += ((len + PAGE_SIZE - 1) >> PAGE_SHIFT); + else + addrs[k++] = (addr & PAGE_MASK) | + (((len + PAGE_SIZE - 1) >> PAGE_SHIFT) - 1); } /* Partial cache lines (fragments) require special measures */ diff --git a/drivers/tee/Kconfig b/drivers/tee/Kconfig index 2330a4eb4e8b..a6df12d88f90 100644 --- a/drivers/tee/Kconfig +++ b/drivers/tee/Kconfig @@ -1,6 +1,7 @@ # Generic Trusted Execution Environment Configuration config TEE tristate "Trusted Execution Environment support" + depends on HAVE_ARM_SMCCC || COMPILE_TEST select DMA_SHARED_BUFFER select GENERIC_ALLOCATOR help diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 1c196f87e9d9..ff04b7f8549f 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -279,7 +279,7 @@ static int uio_dev_add_attributes(struct uio_device *idev) map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) { ret = -ENOMEM; - goto err_map_kobj; + goto err_map; } kobject_init(&map->kobj, &map_attr_type); map->mem = mem; @@ -289,7 +289,7 @@ static int uio_dev_add_attributes(struct uio_device *idev) goto err_map_kobj; ret = kobject_uevent(&map->kobj, KOBJ_ADD); if (ret) - goto err_map; + goto err_map_kobj; } for (pi = 0; pi < MAX_UIO_PORT_REGIONS; pi++) { @@ -308,7 +308,7 @@ static int uio_dev_add_attributes(struct uio_device *idev) portio = kzalloc(sizeof(*portio), GFP_KERNEL); if (!portio) { ret = -ENOMEM; - goto err_portio_kobj; + goto err_portio; } kobject_init(&portio->kobj, &portio_attr_type); portio->port = port; @@ -319,7 +319,7 @@ static int uio_dev_add_attributes(struct uio_device *idev) goto err_portio_kobj; ret = kobject_uevent(&portio->kobj, KOBJ_ADD); if (ret) - goto err_portio; + goto err_portio_kobj; } return 0; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index cfc3cff6e8d5..8e6ef671be9b 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -475,11 +475,11 @@ static void snoop_urb(struct usb_device *udev, if (userurb) { /* Async */ if (when == SUBMIT) - dev_info(&udev->dev, "userurb %p, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " "length %u\n", userurb, ep, t, d, length); else - dev_info(&udev->dev, "userurb %p, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " "actual_length %u status %d\n", userurb, ep, t, d, length, timeout_or_status); @@ -1895,7 +1895,7 @@ static int proc_reapurb(struct usb_dev_state *ps, void __user *arg) if (as) { int retval; - snoop(&ps->dev->dev, "reap %p\n", as->userurb); + snoop(&ps->dev->dev, "reap %pK\n", as->userurb); retval = processcompl(as, (void __user * __user *)arg); free_async(as); return retval; @@ -1912,7 +1912,7 @@ static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg) as = async_getcompleted(ps); if (as) { - snoop(&ps->dev->dev, "reap %p\n", as->userurb); + snoop(&ps->dev->dev, "reap %pK\n", as->userurb); retval = processcompl(as, (void __user * __user *)arg); free_async(as); } else { @@ -2043,7 +2043,7 @@ static int proc_reapurb_compat(struct usb_dev_state *ps, void __user *arg) if (as) { int retval; - snoop(&ps->dev->dev, "reap %p\n", as->userurb); + snoop(&ps->dev->dev, "reap %pK\n", as->userurb); retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); return retval; @@ -2060,7 +2060,7 @@ static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *ar as = async_getcompleted(ps); if (as) { - snoop(&ps->dev->dev, "reap %p\n", as->userurb); + snoop(&ps->dev->dev, "reap %pK\n", as->userurb); retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); } else { @@ -2489,7 +2489,7 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, #endif case USBDEVFS_DISCARDURB: - snoop(&dev->dev, "%s: DISCARDURB %p\n", __func__, p); + snoop(&dev->dev, "%s: DISCARDURB %pK\n", __func__, p); ret = proc_unlinkurb(ps, p); break; diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 49550790a3cb..5dea98358c05 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1723,7 +1723,7 @@ int usb_hcd_unlink_urb (struct urb *urb, int status) if (retval == 0) retval = -EINPROGRESS; else if (retval != -EIDRM && retval != -EBUSY) - dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n", + dev_dbg(&udev->dev, "hcd_unlink_urb %pK fail %d\n", urb, retval); usb_put_dev(udev); } @@ -1890,7 +1890,7 @@ rescan: /* kick hcd */ unlink1(hcd, urb, -ESHUTDOWN); dev_dbg (hcd->self.controller, - "shutdown urb %p ep%d%s%s\n", + "shutdown urb %pK ep%d%s%s\n", urb, usb_endpoint_num(&ep->desc), is_in ? "in" : "out", ({ char *s; @@ -2520,6 +2520,7 @@ struct usb_hcd *__usb_create_hcd(const struct hc_driver *driver, hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex), GFP_KERNEL); if (!hcd->bandwidth_mutex) { + kfree(hcd->address0_mutex); kfree(hcd); dev_dbg(dev, "hcd bandwidth mutex alloc failed\n"); return NULL; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 9dca59ef18b3..b8bb20d7acdb 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -362,7 +362,8 @@ static void usb_set_lpm_parameters(struct usb_device *udev) } /* USB 2.0 spec Section 11.24.4.5 */ -static int get_hub_descriptor(struct usb_device *hdev, void *data) +static int get_hub_descriptor(struct usb_device *hdev, + struct usb_hub_descriptor *desc) { int i, ret, size; unsigned dtype; @@ -378,10 +379,18 @@ static int get_hub_descriptor(struct usb_device *hdev, void *data) for (i = 0; i < 3; i++) { ret = usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0), USB_REQ_GET_DESCRIPTOR, USB_DIR_IN | USB_RT_HUB, - dtype << 8, 0, data, size, + dtype << 8, 0, desc, size, USB_CTRL_GET_TIMEOUT); - if (ret >= (USB_DT_HUB_NONVAR_SIZE + 2)) + if (hub_is_superspeed(hdev)) { + if (ret == size) + return ret; + } else if (ret >= USB_DT_HUB_NONVAR_SIZE + 2) { + /* Make sure we have the DeviceRemovable field. */ + size = USB_DT_HUB_NONVAR_SIZE + desc->bNbrPorts / 8 + 1; + if (ret < size) + return -EMSGSIZE; return ret; + } } return -EINVAL; } @@ -1313,7 +1322,7 @@ static int hub_configure(struct usb_hub *hub, } mutex_init(&hub->status_mutex); - hub->descriptor = kmalloc(sizeof(*hub->descriptor), GFP_KERNEL); + hub->descriptor = kzalloc(sizeof(*hub->descriptor), GFP_KERNEL); if (!hub->descriptor) { ret = -ENOMEM; goto fail; @@ -1321,13 +1330,19 @@ static int hub_configure(struct usb_hub *hub, /* Request the entire hub descriptor. * hub->descriptor can handle USB_MAXCHILDREN ports, - * but the hub can/will return fewer bytes here. + * but a (non-SS) hub can/will return fewer bytes here. */ ret = get_hub_descriptor(hdev, hub->descriptor); if (ret < 0) { message = "can't read hub descriptor"; goto fail; - } else if (hub->descriptor->bNbrPorts > USB_MAXCHILDREN) { + } + + maxchild = USB_MAXCHILDREN; + if (hub_is_superspeed(hdev)) + maxchild = min_t(unsigned, maxchild, USB_SS_MAXPORTS); + + if (hub->descriptor->bNbrPorts > maxchild) { message = "hub has too many ports!"; ret = -ENODEV; goto fail; diff --git a/drivers/usb/core/of.c b/drivers/usb/core/of.c index d787f195a9a6..d563cbcf76cf 100644 --- a/drivers/usb/core/of.c +++ b/drivers/usb/core/of.c @@ -53,6 +53,9 @@ EXPORT_SYMBOL_GPL(usb_of_get_child_node); * * Find the companion device from platform bus. * + * Takes a reference to the returned struct device which needs to be dropped + * after use. + * * Return: On success, a pointer to the companion device, %NULL on failure. */ struct device *usb_of_get_companion_dev(struct device *dev) diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index d75cb8c0f7df..47903d510955 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -338,7 +338,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags) if (!urb || !urb->complete) return -EINVAL; if (urb->hcpriv) { - WARN_ONCE(1, "URB %p submitted while active\n", urb); + WARN_ONCE(1, "URB %pK submitted while active\n", urb); return -EBUSY; } diff --git a/drivers/usb/dwc3/dwc3-keystone.c b/drivers/usb/dwc3/dwc3-keystone.c index 72664700b8a2..12ee23f53cdd 100644 --- a/drivers/usb/dwc3/dwc3-keystone.c +++ b/drivers/usb/dwc3/dwc3-keystone.c @@ -107,6 +107,10 @@ static int kdwc3_probe(struct platform_device *pdev) return PTR_ERR(kdwc->usbss); kdwc->clk = devm_clk_get(kdwc->dev, "usb"); + if (IS_ERR(kdwc->clk)) { + dev_err(kdwc->dev, "unable to get usb clock\n"); + return PTR_ERR(kdwc->clk); + } error = clk_prepare_enable(kdwc->clk); if (error < 0) { diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index a15ec71d0423..84a2cebfc712 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -39,6 +39,8 @@ #define PCI_DEVICE_ID_INTEL_APL 0x5aaa #define PCI_DEVICE_ID_INTEL_KBP 0xa2b0 #define PCI_DEVICE_ID_INTEL_GLK 0x31aa +#define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee +#define PCI_DEVICE_ID_INTEL_CNPH 0xa36e #define PCI_INTEL_BXT_DSM_UUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511" #define PCI_INTEL_BXT_FUNC_PMU_PWR 4 @@ -270,6 +272,8 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBP), }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_GLK), }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPLP), }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CNPH), }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), }, { } /* Terminating Entry */ }; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 6f6f0b3be3ad..aea9a5b948b4 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1261,14 +1261,24 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req) __dwc3_gadget_start_isoc(dwc, dep, cur_uf); dep->flags &= ~DWC3_EP_PENDING_REQUEST; } + return 0; } - return 0; + + if ((dep->flags & DWC3_EP_BUSY) && + !(dep->flags & DWC3_EP_MISSED_ISOC)) { + WARN_ON_ONCE(!dep->resource_index); + ret = __dwc3_gadget_kick_transfer(dep, + dep->resource_index); + } + + goto out; } if (!dwc3_calc_trbs_left(dep)) return 0; ret = __dwc3_gadget_kick_transfer(dep, 0); +out: if (ret == -EBUSY) ret = 0; @@ -3026,6 +3036,15 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) return IRQ_HANDLED; } + /* + * With PCIe legacy interrupt, test shows that top-half irq handler can + * be called again after HW interrupt deassertion. Check if bottom-half + * irq event handler completes before caching new event to prevent + * losing events. + */ + if (evt->flags & DWC3_EVENT_PENDING) + return IRQ_HANDLED; + count = dwc3_readl(dwc->regs, DWC3_GEVNTCOUNT(0)); count &= DWC3_GEVNTCOUNT_MASK; if (!count) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 71dd27c0d7f2..47dda3450abd 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1858,12 +1858,12 @@ static int ffs_func_eps_enable(struct ffs_function *func) ep->ep->driver_data = ep; ep->ep->desc = ds; - comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds + - USB_DT_ENDPOINT_SIZE); - ep->ep->maxburst = comp_desc->bMaxBurst + 1; - - if (needs_comp_desc) + if (needs_comp_desc) { + comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds + + USB_DT_ENDPOINT_SIZE); + ep->ep->maxburst = comp_desc->bMaxBurst + 1; ep->ep->comp_desc = comp_desc; + } ret = usb_ep_enable(ep->ep); if (likely(!ret)) { diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 000677c991b0..9b0805f55ad7 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1256,7 +1256,7 @@ static void gserial_console_exit(void) struct gscons_info *info = &gscons_info; unregister_console(&gserial_cons); - if (info->console_thread != NULL) + if (!IS_ERR_OR_NULL(info->console_thread)) kthread_stop(info->console_thread); gs_buf_free(&info->con_buf); } diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index c79081952ea0..ccabb51cb98d 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -2008,7 +2008,7 @@ ss_hub_descriptor(struct usb_hub_descriptor *desc) HUB_CHAR_COMMON_OCPM); desc->bNbrPorts = 1; desc->u.ss.bHubHdrDecLat = 0x04; /* Worst case: 0.4 micro sec*/ - desc->u.ss.DeviceRemovable = 0xffff; + desc->u.ss.DeviceRemovable = 0; } static inline void hub_descriptor(struct usb_hub_descriptor *desc) @@ -2020,8 +2020,8 @@ static inline void hub_descriptor(struct usb_hub_descriptor *desc) HUB_CHAR_INDV_PORT_LPSM | HUB_CHAR_COMMON_OCPM); desc->bNbrPorts = 1; - desc->u.hs.DeviceRemovable[0] = 0xff; - desc->u.hs.DeviceRemovable[1] = 0xff; + desc->u.hs.DeviceRemovable[0] = 0; + desc->u.hs.DeviceRemovable[1] = 0xff; /* PortPwrCtrlMask */ } static int dummy_hub_control( diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c index bc7b9be12f54..f1908ea9fbd8 100644 --- a/drivers/usb/host/ehci-platform.c +++ b/drivers/usb/host/ehci-platform.c @@ -384,8 +384,10 @@ static int ehci_platform_resume(struct device *dev) } companion_dev = usb_of_get_companion_dev(hcd->self.controller); - if (companion_dev) + if (companion_dev) { device_pm_wait_for_dev(hcd->self.controller, companion_dev); + put_device(companion_dev); + } ehci_resume(hcd, priv->reset_on_resume); return 0; diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c index bfa7fa3d2eea..7bf78be1fd32 100644 --- a/drivers/usb/host/r8a66597-hcd.c +++ b/drivers/usb/host/r8a66597-hcd.c @@ -1269,7 +1269,7 @@ static void set_td_timer(struct r8a66597 *r8a66597, struct r8a66597_td *td) time = 30; break; default: - time = 300; + time = 50; break; } @@ -1785,6 +1785,7 @@ static void r8a66597_td_timer(unsigned long _r8a66597) pipe = td->pipe; pipe_stop(r8a66597, pipe); + /* Select a different address or endpoint */ new_td = td; do { list_move_tail(&new_td->queue, @@ -1794,7 +1795,8 @@ static void r8a66597_td_timer(unsigned long _r8a66597) new_td = td; break; } - } while (td != new_td && td->address == new_td->address); + } while (td != new_td && td->address == new_td->address && + td->pipe->info.epnum == new_td->pipe->info.epnum); start_transfer(r8a66597, new_td); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 5e3e9d4c6956..0dde49c35dd2 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -419,7 +419,7 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend) wait_for_completion(cmd->completion); if (cmd->status == COMP_COMMAND_ABORTED || - cmd->status == COMP_STOPPED) { + cmd->status == COMP_COMMAND_RING_STOPPED) { xhci_warn(xhci, "Timeout while waiting for stop endpoint command\n"); ret = -ETIME; } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index bbe22bcc550a..1f1687e888d6 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -56,7 +56,7 @@ static struct xhci_segment *xhci_segment_alloc(struct xhci_hcd *xhci, } if (max_packet) { - seg->bounce_buf = kzalloc(max_packet, flags | GFP_DMA); + seg->bounce_buf = kzalloc(max_packet, flags); if (!seg->bounce_buf) { dma_pool_free(xhci->segment_pool, seg->trbs, dma); kfree(seg); @@ -1724,7 +1724,7 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags) xhci->dcbaa->dev_context_ptrs[0] = cpu_to_le64(xhci->scratchpad->sp_dma); for (i = 0; i < num_sp; i++) { dma_addr_t dma; - void *buf = dma_alloc_coherent(dev, xhci->page_size, &dma, + void *buf = dma_zalloc_coherent(dev, xhci->page_size, &dma, flags); if (!buf) goto fail_sp4; @@ -2307,10 +2307,11 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags) /* Place limits on the number of roothub ports so that the hub * descriptors aren't longer than the USB core will allocate. */ - if (xhci->num_usb3_ports > 15) { + if (xhci->num_usb3_ports > USB_SS_MAXPORTS) { xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "Limiting USB 3.0 roothub ports to 15."); - xhci->num_usb3_ports = 15; + "Limiting USB 3.0 roothub ports to %u.", + USB_SS_MAXPORTS); + xhci->num_usb3_ports = USB_SS_MAXPORTS; } if (xhci->num_usb2_ports > USB_MAXCHILDREN) { xhci_dbg_trace(xhci, trace_xhci_dbg_init, diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 7b86508ac8cf..fcf1f3f63e7a 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -52,6 +52,7 @@ #define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI 0x0aa8 #define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI 0x1aa8 #define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8 +#define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0 static const char hcd_name[] = "xhci_hcd"; @@ -166,7 +167,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI)) { + pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) { xhci->quirks |= XHCI_PME_STUCK_QUIRK; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && @@ -175,7 +177,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) xhci->quirks |= XHCI_MISSING_CAS; if (pdev->vendor == PCI_VENDOR_ID_ETRON && diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 7c2a9e7c8e0f..c04144b25a67 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -177,7 +177,7 @@ static int xhci_plat_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENODEV; + return irq; /* * sysdev must point to a device that is known to the system firmware diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 74bf5c60a260..03f63f50afb6 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -323,7 +323,7 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci, if (i_cmd->status != COMP_COMMAND_ABORTED) continue; - i_cmd->status = COMP_STOPPED; + i_cmd->status = COMP_COMMAND_RING_STOPPED; xhci_dbg(xhci, "Turn aborted command %p to no-op\n", i_cmd->command_trb); @@ -641,8 +641,8 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci, xhci_urb_free_priv(urb_priv); usb_hcd_unlink_urb_from_ep(hcd, urb); spin_unlock(&xhci->lock); - usb_hcd_giveback_urb(hcd, urb, status); trace_xhci_urb_giveback(urb); + usb_hcd_giveback_urb(hcd, urb, status); spin_lock(&xhci->lock); } @@ -1380,7 +1380,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, cmd_comp_code = GET_COMP_CODE(le32_to_cpu(event->status)); /* If CMD ring stopped we own the trbs between enqueue and dequeue */ - if (cmd_comp_code == COMP_STOPPED) { + if (cmd_comp_code == COMP_COMMAND_RING_STOPPED) { complete_all(&xhci->cmd_ring_stop_completion); return; } @@ -1436,8 +1436,8 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, break; case TRB_CMD_NOOP: /* Is this an aborted command turned to NO-OP? */ - if (cmd->status == COMP_STOPPED) - cmd_comp_code = COMP_STOPPED; + if (cmd->status == COMP_COMMAND_RING_STOPPED) + cmd_comp_code = COMP_COMMAND_RING_STOPPED; break; case TRB_RESET_EP: WARN_ON(slot_id != TRB_TO_SLOT_ID( @@ -2677,11 +2677,12 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) struct xhci_hcd *xhci = hcd_to_xhci(hcd); union xhci_trb *event_ring_deq; irqreturn_t ret = IRQ_NONE; + unsigned long flags; dma_addr_t deq; u64 temp_64; u32 status; - spin_lock(&xhci->lock); + spin_lock_irqsave(&xhci->lock, flags); /* Check if the xHC generated the interrupt, or the irq is shared */ status = readl(&xhci->op_regs->status); if (status == ~(u32)0) { @@ -2707,12 +2708,9 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) */ status |= STS_EINT; writel(status, &xhci->op_regs->status); - /* FIXME when MSI-X is supported and there are multiple vectors */ - /* Clear the MSI-X event interrupt status */ - if (hcd->irq) { + if (!hcd->msi_enabled) { u32 irq_pending; - /* Acknowledge the PCI interrupt */ irq_pending = readl(&xhci->ir_set->irq_pending); irq_pending |= IMAN_IP; writel(irq_pending, &xhci->ir_set->irq_pending); @@ -2757,7 +2755,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) ret = IRQ_HANDLED; out: - spin_unlock(&xhci->lock); + spin_unlock_irqrestore(&xhci->lock, flags); return ret; } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 2d1310220832..30f47d92a610 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -359,9 +359,10 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd) /* fall back to msi*/ ret = xhci_setup_msi(xhci); - if (!ret) - /* hcd->irq is 0, we have MSI */ + if (!ret) { + hcd->msi_enabled = 1; return 0; + } if (!pdev->irq) { xhci_err(xhci, "No msi-x/msi found and no IRQ in BIOS\n"); @@ -1763,7 +1764,7 @@ static int xhci_configure_endpoint_result(struct xhci_hcd *xhci, switch (*cmd_status) { case COMP_COMMAND_ABORTED: - case COMP_STOPPED: + case COMP_COMMAND_RING_STOPPED: xhci_warn(xhci, "Timeout while waiting for configure endpoint command\n"); ret = -ETIME; break; @@ -1813,7 +1814,7 @@ static int xhci_evaluate_context_result(struct xhci_hcd *xhci, switch (*cmd_status) { case COMP_COMMAND_ABORTED: - case COMP_STOPPED: + case COMP_COMMAND_RING_STOPPED: xhci_warn(xhci, "Timeout while waiting for evaluate context command\n"); ret = -ETIME; break; @@ -3432,7 +3433,7 @@ static int xhci_discover_or_reset_device(struct usb_hcd *hcd, ret = reset_device_cmd->status; switch (ret) { case COMP_COMMAND_ABORTED: - case COMP_STOPPED: + case COMP_COMMAND_RING_STOPPED: xhci_warn(xhci, "Timeout waiting for reset device command\n"); ret = -ETIME; goto command_cleanup; @@ -3817,7 +3818,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, */ switch (command->status) { case COMP_COMMAND_ABORTED: - case COMP_STOPPED: + case COMP_COMMAND_RING_STOPPED: xhci_warn(xhci, "Timeout while waiting for setup device command\n"); ret = -ETIME; break; diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c index e9cae4d82af2..15d4e64d3b65 100644 --- a/drivers/usb/misc/chaoskey.c +++ b/drivers/usb/misc/chaoskey.c @@ -192,7 +192,7 @@ static int chaoskey_probe(struct usb_interface *interface, dev->in_ep = in_ep; - if (udev->descriptor.idVendor != ALEA_VENDOR_ID) + if (le16_to_cpu(udev->descriptor.idVendor) != ALEA_VENDOR_ID) dev->reads_started = 1; dev->size = size; diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index 77569531b78a..83b05a287b0c 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -554,7 +554,7 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd, info.revision = le16_to_cpu(dev->udev->descriptor.bcdDevice); /* 0==UNKNOWN, 1==LOW(usb1.1) ,2=FULL(usb1.1), 3=HIGH(usb2.0) */ - info.speed = le16_to_cpu(dev->udev->speed); + info.speed = dev->udev->speed; info.if_num = dev->interface->cur_altsetting->desc.bInterfaceNumber; info.report_size = dev->report_size; diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c index aa3c280fdf8d..0782ac6f5edf 100644 --- a/drivers/usb/misc/legousbtower.c +++ b/drivers/usb/misc/legousbtower.c @@ -926,6 +926,7 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device USB_MAJOR, dev->minor); exit: + kfree(get_version_reply); return retval; error: diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c index 3c6948af726a..f019d80ca9e4 100644 --- a/drivers/usb/misc/sisusbvga/sisusb_con.c +++ b/drivers/usb/misc/sisusbvga/sisusb_con.c @@ -973,7 +973,7 @@ sisusbcon_set_origin(struct vc_data *c) mutex_unlock(&sisusb->lock); - return 1; + return true; } /* Interface routine */ diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index ac3a4952abb4..dbe617a735d8 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2780,10 +2780,11 @@ int musb_host_setup(struct musb *musb, int power_budget) int ret; struct usb_hcd *hcd = musb->hcd; - MUSB_HST_MODE(musb); - musb->xceiv->otg->default_a = 1; - musb->xceiv->otg->state = OTG_STATE_A_IDLE; - + if (musb->port_mode == MUSB_PORT_MODE_HOST) { + MUSB_HST_MODE(musb); + musb->xceiv->otg->default_a = 1; + musb->xceiv->otg->state = OTG_STATE_A_IDLE; + } otg_set_host(musb->xceiv->otg, &hcd->self); hcd->self.otg_port = 1; musb->xceiv->otg->host = &hcd->self; diff --git a/drivers/usb/musb/tusb6010_omap.c b/drivers/usb/musb/tusb6010_omap.c index 8b43c4b99f04..7870b37e0ea5 100644 --- a/drivers/usb/musb/tusb6010_omap.c +++ b/drivers/usb/musb/tusb6010_omap.c @@ -219,6 +219,7 @@ static int tusb_omap_dma_program(struct dma_channel *channel, u16 packet_sz, u32 dma_remaining; int src_burst, dst_burst; u16 csr; + u32 psize; int ch; s8 dmareq; s8 sync_dev; @@ -390,15 +391,19 @@ static int tusb_omap_dma_program(struct dma_channel *channel, u16 packet_sz, if (chdat->tx) { /* Send transfer_packet_sz packets at a time */ - musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, - chdat->transfer_packet_sz); + psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET); + psize &= ~0x7ff; + psize |= chdat->transfer_packet_sz; + musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize); musb_writel(ep_conf, TUSB_EP_TX_OFFSET, TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len)); } else { /* Receive transfer_packet_sz packets at a time */ - musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, - chdat->transfer_packet_sz << 16); + psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET); + psize &= ~(0x7ff << 16); + psize |= (chdat->transfer_packet_sz << 16); + musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize); musb_writel(ep_conf, TUSB_EP_RX_OFFSET, TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len)); diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index d38780fa8788..aba74f817dc6 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -809,10 +809,10 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) }, { USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_H_PID, 1) }, { USB_DEVICE(FIC_VID, FIC_NEO1973_DEBUG_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_OOCDLINK_PID), @@ -1527,9 +1527,9 @@ static int set_serial_info(struct tty_struct *tty, (new_serial.flags & ASYNC_FLAGS)); priv->custom_divisor = new_serial.custom_divisor; +check_and_exit: write_latency_timer(port); -check_and_exit: if ((old_priv.flags & ASYNC_SPD_MASK) != (priv->flags & ASYNC_SPD_MASK)) { if ((priv->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI) diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 71fb9e59db71..4fcf1cecb6d7 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -882,6 +882,8 @@ /* Olimex */ #define OLIMEX_VID 0x15BA #define OLIMEX_ARM_USB_OCD_PID 0x0003 +#define OLIMEX_ARM_USB_TINY_PID 0x0004 +#define OLIMEX_ARM_USB_TINY_H_PID 0x002a #define OLIMEX_ARM_USB_OCD_H_PID 0x002b /* diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c index 87798e625d6c..6cefb9cb133d 100644 --- a/drivers/usb/serial/io_ti.c +++ b/drivers/usb/serial/io_ti.c @@ -2336,8 +2336,11 @@ static void change_port_settings(struct tty_struct *tty, if (!baud) { /* pick a default, any default... */ baud = 9600; - } else + } else { + /* Avoid a zero divisor. */ + baud = min(baud, 461550); tty_encode_baud_rate(tty, baud, baud); + } edge_port->baud_rate = baud; config->wBaudRate = (__u16)((461550L + baud/2) / baud); diff --git a/drivers/usb/serial/ir-usb.c b/drivers/usb/serial/ir-usb.c index 73956d48a0c5..f9734a96d516 100644 --- a/drivers/usb/serial/ir-usb.c +++ b/drivers/usb/serial/ir-usb.c @@ -197,6 +197,7 @@ static u8 ir_xbof_change(u8 xbof) static int ir_startup(struct usb_serial *serial) { struct usb_irda_cs_descriptor *irda_desc; + int rates; irda_desc = irda_usb_find_class_desc(serial, 0); if (!irda_desc) { @@ -205,18 +206,20 @@ static int ir_startup(struct usb_serial *serial) return -ENODEV; } + rates = le16_to_cpu(irda_desc->wBaudRate); + dev_dbg(&serial->dev->dev, "%s - Baud rates supported:%s%s%s%s%s%s%s%s%s\n", __func__, - (irda_desc->wBaudRate & USB_IRDA_BR_2400) ? " 2400" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_9600) ? " 9600" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_19200) ? " 19200" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_38400) ? " 38400" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_57600) ? " 57600" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_115200) ? " 115200" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_576000) ? " 576000" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_1152000) ? " 1152000" : "", - (irda_desc->wBaudRate & USB_IRDA_BR_4000000) ? " 4000000" : ""); + (rates & USB_IRDA_BR_2400) ? " 2400" : "", + (rates & USB_IRDA_BR_9600) ? " 9600" : "", + (rates & USB_IRDA_BR_19200) ? " 19200" : "", + (rates & USB_IRDA_BR_38400) ? " 38400" : "", + (rates & USB_IRDA_BR_57600) ? " 57600" : "", + (rates & USB_IRDA_BR_115200) ? " 115200" : "", + (rates & USB_IRDA_BR_576000) ? " 576000" : "", + (rates & USB_IRDA_BR_1152000) ? " 1152000" : "", + (rates & USB_IRDA_BR_4000000) ? " 4000000" : ""); switch (irda_desc->bmAdditionalBOFs) { case USB_IRDA_AB_48: diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c index edbc81f205c2..70f346f1aa86 100644 --- a/drivers/usb/serial/mct_u232.c +++ b/drivers/usb/serial/mct_u232.c @@ -189,7 +189,7 @@ static int mct_u232_set_baud_rate(struct tty_struct *tty, return -ENOMEM; divisor = mct_u232_calculate_baud_rate(serial, value, &speed); - put_unaligned_le32(cpu_to_le32(divisor), buf); + put_unaligned_le32(divisor, buf); rc = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), MCT_U232_SET_BAUD_RATE_REQUEST, MCT_U232_SET_REQUEST_TYPE, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index af67a0de6b5d..3bf61acfc26b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -281,6 +281,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_LE922_USBCFG0 0x1042 #define TELIT_PRODUCT_LE922_USBCFG3 0x1043 #define TELIT_PRODUCT_LE922_USBCFG5 0x1045 +#define TELIT_PRODUCT_ME910 0x1100 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 #define TELIT_PRODUCT_LE910_USBCFG4 0x1206 @@ -640,6 +641,11 @@ static const struct option_blacklist_info simcom_sim7100e_blacklist = { .reserved = BIT(5) | BIT(6), }; +static const struct option_blacklist_info telit_me910_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(3), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -1235,6 +1241,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff), .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), + .driver_info = (kernel_ulong_t)&telit_me910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 38b3f0d8cd58..fd509ed6cf70 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -162,6 +162,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */ {DEVICE_SWI(0x1199, 0x9078)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */ + {DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c index 369f3c24815a..44af719194b2 100644 --- a/drivers/usb/storage/ene_ub6250.c +++ b/drivers/usb/storage/ene_ub6250.c @@ -446,6 +446,10 @@ struct ms_lib_ctrl { #define SD_BLOCK_LEN 9 struct ene_ub6250_info { + + /* I/O bounce buffer */ + u8 *bbuf; + /* for 6250 code */ struct SD_STATUS SD_Status; struct MS_STATUS MS_Status; @@ -493,8 +497,11 @@ static int ene_load_bincode(struct us_data *us, unsigned char flag); static void ene_ub6250_info_destructor(void *extra) { + struct ene_ub6250_info *info = (struct ene_ub6250_info *) extra; + if (!extra) return; + kfree(info->bbuf); } static int ene_send_scsi_cmd(struct us_data *us, u8 fDir, void *buf, int use_sg) @@ -860,8 +867,9 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr, u8 PageNum, u32 *PageBuf, struct ms_lib_type_extdat *ExtraDat) { struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; + struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; int result; - u8 ExtBuf[4]; u32 bn = PhyBlockAddr * 0x20 + PageNum; result = ene_load_bincode(us, MS_RW_PATTERN); @@ -901,7 +909,7 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr, bcb->CDB[2] = (unsigned char)(PhyBlockAddr>>16); bcb->CDB[6] = 0x01; - result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; @@ -910,9 +918,9 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr, ExtraDat->status0 = 0x10; /* Not yet,fireware support */ ExtraDat->status1 = 0x00; /* Not yet,fireware support */ - ExtraDat->ovrflg = ExtBuf[0]; - ExtraDat->mngflg = ExtBuf[1]; - ExtraDat->logadr = memstick_logaddr(ExtBuf[2], ExtBuf[3]); + ExtraDat->ovrflg = bbuf[0]; + ExtraDat->mngflg = bbuf[1]; + ExtraDat->logadr = memstick_logaddr(bbuf[2], bbuf[3]); return USB_STOR_TRANSPORT_GOOD; } @@ -1332,8 +1340,9 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock, u8 PageNum, struct ms_lib_type_extdat *ExtraDat) { struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; + struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; int result; - u8 ExtBuf[4]; memset(bcb, 0, sizeof(struct bulk_cb_wrap)); bcb->Signature = cpu_to_le32(US_BULK_CB_SIGN); @@ -1347,7 +1356,7 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock, bcb->CDB[2] = (unsigned char)(PhyBlock>>16); bcb->CDB[6] = 0x01; - result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; @@ -1355,9 +1364,9 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock, ExtraDat->intr = 0x80; /* Not yet, waiting for fireware support */ ExtraDat->status0 = 0x10; /* Not yet, waiting for fireware support */ ExtraDat->status1 = 0x00; /* Not yet, waiting for fireware support */ - ExtraDat->ovrflg = ExtBuf[0]; - ExtraDat->mngflg = ExtBuf[1]; - ExtraDat->logadr = memstick_logaddr(ExtBuf[2], ExtBuf[3]); + ExtraDat->ovrflg = bbuf[0]; + ExtraDat->mngflg = bbuf[1]; + ExtraDat->logadr = memstick_logaddr(bbuf[2], bbuf[3]); return USB_STOR_TRANSPORT_GOOD; } @@ -1556,9 +1565,9 @@ static int ms_lib_scan_logicalblocknumber(struct us_data *us, u16 btBlk1st) u16 PhyBlock, newblk, i; u16 LogStart, LogEnde; struct ms_lib_type_extdat extdat; - u8 buf[0x200]; u32 count = 0, index = 0; struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; for (PhyBlock = 0; PhyBlock < info->MS_Lib.NumberOfPhyBlock;) { ms_lib_phy_to_log_range(PhyBlock, &LogStart, &LogEnde); @@ -1572,14 +1581,16 @@ static int ms_lib_scan_logicalblocknumber(struct us_data *us, u16 btBlk1st) } if (count == PhyBlock) { - ms_lib_read_extrablock(us, PhyBlock, 0, 0x80, &buf); + ms_lib_read_extrablock(us, PhyBlock, 0, 0x80, + bbuf); count += 0x80; } index = (PhyBlock % 0x80) * 4; - extdat.ovrflg = buf[index]; - extdat.mngflg = buf[index+1]; - extdat.logadr = memstick_logaddr(buf[index+2], buf[index+3]); + extdat.ovrflg = bbuf[index]; + extdat.mngflg = bbuf[index+1]; + extdat.logadr = memstick_logaddr(bbuf[index+2], + bbuf[index+3]); if ((extdat.ovrflg & MS_REG_OVR_BKST) != MS_REG_OVR_BKST_OK) { ms_lib_setacquired_errorblock(us, PhyBlock); @@ -2062,9 +2073,9 @@ static int ene_ms_init(struct us_data *us) { struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; int result; - u8 buf[0x200]; u16 MSP_BlockSize, MSP_UserAreaBlocks; struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; printk(KERN_INFO "transport --- ENE_MSInit\n"); @@ -2083,13 +2094,13 @@ static int ene_ms_init(struct us_data *us) bcb->CDB[0] = 0xF1; bcb->CDB[1] = 0x01; - result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) { printk(KERN_ERR "Execution MS Init Code Fail !!\n"); return USB_STOR_TRANSPORT_ERROR; } /* the same part to test ENE */ - info->MS_Status = *(struct MS_STATUS *)&buf[0]; + info->MS_Status = *(struct MS_STATUS *) bbuf; if (info->MS_Status.Insert && info->MS_Status.Ready) { printk(KERN_INFO "Insert = %x\n", info->MS_Status.Insert); @@ -2098,15 +2109,15 @@ static int ene_ms_init(struct us_data *us) printk(KERN_INFO "IsMSPHG = %x\n", info->MS_Status.IsMSPHG); printk(KERN_INFO "WtP= %x\n", info->MS_Status.WtP); if (info->MS_Status.IsMSPro) { - MSP_BlockSize = (buf[6] << 8) | buf[7]; - MSP_UserAreaBlocks = (buf[10] << 8) | buf[11]; + MSP_BlockSize = (bbuf[6] << 8) | bbuf[7]; + MSP_UserAreaBlocks = (bbuf[10] << 8) | bbuf[11]; info->MSP_TotalBlock = MSP_BlockSize * MSP_UserAreaBlocks; } else { ms_card_init(us); /* Card is MS (to ms.c)*/ } usb_stor_dbg(us, "MS Init Code OK !!\n"); } else { - usb_stor_dbg(us, "MS Card Not Ready --- %x\n", buf[0]); + usb_stor_dbg(us, "MS Card Not Ready --- %x\n", bbuf[0]); return USB_STOR_TRANSPORT_ERROR; } @@ -2116,9 +2127,9 @@ static int ene_ms_init(struct us_data *us) static int ene_sd_init(struct us_data *us) { int result; - u8 buf[0x200]; struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf; struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; + u8 *bbuf = info->bbuf; usb_stor_dbg(us, "transport --- ENE_SDInit\n"); /* SD Init Part-1 */ @@ -2152,17 +2163,17 @@ static int ene_sd_init(struct us_data *us) bcb->Flags = US_BULK_FLAG_IN; bcb->CDB[0] = 0xF1; - result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0); + result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0); if (result != USB_STOR_XFER_GOOD) { usb_stor_dbg(us, "Execution SD Init Code Fail !!\n"); return USB_STOR_TRANSPORT_ERROR; } - info->SD_Status = *(struct SD_STATUS *)&buf[0]; + info->SD_Status = *(struct SD_STATUS *) bbuf; if (info->SD_Status.Insert && info->SD_Status.Ready) { struct SD_STATUS *s = &info->SD_Status; - ene_get_card_status(us, (unsigned char *)&buf); + ene_get_card_status(us, bbuf); usb_stor_dbg(us, "Insert = %x\n", s->Insert); usb_stor_dbg(us, "Ready = %x\n", s->Ready); usb_stor_dbg(us, "IsMMC = %x\n", s->IsMMC); @@ -2170,7 +2181,7 @@ static int ene_sd_init(struct us_data *us) usb_stor_dbg(us, "HiSpeed = %x\n", s->HiSpeed); usb_stor_dbg(us, "WtP = %x\n", s->WtP); } else { - usb_stor_dbg(us, "SD Card Not Ready --- %x\n", buf[0]); + usb_stor_dbg(us, "SD Card Not Ready --- %x\n", bbuf[0]); return USB_STOR_TRANSPORT_ERROR; } return USB_STOR_TRANSPORT_GOOD; @@ -2180,13 +2191,15 @@ static int ene_sd_init(struct us_data *us) static int ene_init(struct us_data *us) { int result; - u8 misc_reg03 = 0; + u8 misc_reg03; struct ene_ub6250_info *info = (struct ene_ub6250_info *)(us->extra); + u8 *bbuf = info->bbuf; - result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03); + result = ene_get_card_type(us, REG_CARD_STATUS, bbuf); if (result != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; + misc_reg03 = bbuf[0]; if (misc_reg03 & 0x01) { if (!info->SD_Status.Ready) { result = ene_sd_init(us); @@ -2303,8 +2316,9 @@ static int ene_ub6250_probe(struct usb_interface *intf, const struct usb_device_id *id) { int result; - u8 misc_reg03 = 0; + u8 misc_reg03; struct us_data *us; + struct ene_ub6250_info *info; result = usb_stor_probe1(&us, intf, id, (id - ene_ub6250_usb_ids) + ene_ub6250_unusual_dev_list, @@ -2313,11 +2327,16 @@ static int ene_ub6250_probe(struct usb_interface *intf, return result; /* FIXME: where should the code alloc extra buf ? */ - if (!us->extra) { - us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL); - if (!us->extra) - return -ENOMEM; - us->extra_destructor = ene_ub6250_info_destructor; + us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL); + if (!us->extra) + return -ENOMEM; + us->extra_destructor = ene_ub6250_info_destructor; + + info = (struct ene_ub6250_info *)(us->extra); + info->bbuf = kmalloc(512, GFP_KERNEL); + if (!info->bbuf) { + kfree(us->extra); + return -ENOMEM; } us->transport_name = "ene_ub6250"; @@ -2329,12 +2348,13 @@ static int ene_ub6250_probe(struct usb_interface *intf, return result; /* probe card type */ - result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03); + result = ene_get_card_type(us, REG_CARD_STATUS, info->bbuf); if (result != USB_STOR_XFER_GOOD) { usb_stor_disconnect(intf); return USB_STOR_TRANSPORT_ERROR; } + misc_reg03 = info->bbuf[0]; if (!(misc_reg03 & 0x01)) { pr_info("ums_eneub6250: This driver only supports SD/MS cards. " "It does not support SM cards.\n"); diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 5d8b2c261940..0585078638db 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -235,14 +235,19 @@ done: static inline void hub_descriptor(struct usb_hub_descriptor *desc) { + int width; + memset(desc, 0, sizeof(*desc)); desc->bDescriptorType = USB_DT_HUB; - desc->bDescLength = 9; desc->wHubCharacteristics = cpu_to_le16( HUB_CHAR_INDV_PORT_LPSM | HUB_CHAR_COMMON_OCPM); + desc->bNbrPorts = VHCI_HC_PORTS; - desc->u.hs.DeviceRemovable[0] = 0xff; - desc->u.hs.DeviceRemovable[1] = 0xff; + BUILD_BUG_ON(VHCI_HC_PORTS > USB_MAXCHILDREN); + width = desc->bNbrPorts / 8 + 1; + desc->bDescLength = USB_DT_HUB_NONVAR_SIZE + 2 * width; + memset(&desc->u.hs.DeviceRemovable[0], 0, width); + memset(&desc->u.hs.DeviceRemovable[width], 0xff, width); } static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, diff --git a/drivers/uwb/i1480/dfu/usb.c b/drivers/uwb/i1480/dfu/usb.c index 6345e85822a4..a50cf45e530f 100644 --- a/drivers/uwb/i1480/dfu/usb.c +++ b/drivers/uwb/i1480/dfu/usb.c @@ -341,6 +341,7 @@ error_submit_ep1: static int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id) { + struct usb_device *udev = interface_to_usbdev(iface); struct i1480_usb *i1480_usb; struct i1480 *i1480; struct device *dev = &iface->dev; @@ -352,8 +353,8 @@ int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id) iface->cur_altsetting->desc.bInterfaceNumber); goto error; } - if (iface->num_altsetting > 1 - && interface_to_usbdev(iface)->descriptor.idProduct == 0xbabe) { + if (iface->num_altsetting > 1 && + le16_to_cpu(udev->descriptor.idProduct) == 0xbabe) { /* Need altsetting #1 [HW QUIRK] or EP1 won't work */ result = usb_set_interface(interface_to_usbdev(iface), 0, 1); if (result < 0) diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 52a70ee6014f..8b9049dac094 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -452,7 +452,7 @@ config DAVINCI_WATCHDOG config ORION_WATCHDOG tristate "Orion watchdog" - depends on ARCH_ORION5X || ARCH_DOVE || MACH_DOVE || ARCH_MVEBU || COMPILE_TEST + depends on ARCH_ORION5X || ARCH_DOVE || MACH_DOVE || ARCH_MVEBU || (COMPILE_TEST && !ARCH_EBSA110) depends on ARM select WATCHDOG_CORE help diff --git a/drivers/watchdog/bcm_kona_wdt.c b/drivers/watchdog/bcm_kona_wdt.c index 6fce17d5b9f1..a5775dfd8d5f 100644 --- a/drivers/watchdog/bcm_kona_wdt.c +++ b/drivers/watchdog/bcm_kona_wdt.c @@ -304,6 +304,8 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev) if (!wdt) return -ENOMEM; + spin_lock_init(&wdt->lock); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); wdt->base = devm_ioremap_resource(dev, res); if (IS_ERR(wdt->base)) @@ -316,7 +318,6 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev) return ret; } - spin_lock_init(&wdt->lock); platform_set_drvdata(pdev, wdt); watchdog_set_drvdata(&bcm_kona_wdt_wdd, wdt); bcm_kona_wdt_wdd.parent = &pdev->dev; diff --git a/drivers/watchdog/cadence_wdt.c b/drivers/watchdog/cadence_wdt.c index 8d61e8bfe60b..86e0b5d2e761 100644 --- a/drivers/watchdog/cadence_wdt.c +++ b/drivers/watchdog/cadence_wdt.c @@ -49,7 +49,7 @@ /* Counter maximum value */ #define CDNS_WDT_COUNTER_MAX 0xFFF -static int wdt_timeout = CDNS_WDT_DEFAULT_TIMEOUT; +static int wdt_timeout; static int nowayout = WATCHDOG_NOWAYOUT; module_param(wdt_timeout, int, 0); diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index 347f0389b089..c4f65873bfa4 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -306,16 +306,15 @@ static int iTCO_wdt_ping(struct watchdog_device *wd_dev) iTCO_vendor_pre_keepalive(p->smi_res, wd_dev->timeout); + /* Reset the timeout status bit so that the timer + * needs to count down twice again before rebooting */ + outw(0x0008, TCO1_STS(p)); /* write 1 to clear bit */ + /* Reload the timer by writing to the TCO Timer Counter register */ - if (p->iTCO_version >= 2) { + if (p->iTCO_version >= 2) outw(0x01, TCO_RLD(p)); - } else if (p->iTCO_version == 1) { - /* Reset the timeout status bit so that the timer - * needs to count down twice again before rebooting */ - outw(0x0008, TCO1_STS(p)); /* write 1 to clear bit */ - + else if (p->iTCO_version == 1) outb(0x01, TCO_RLD(p)); - } spin_unlock(&p->io_lock); return 0; @@ -328,11 +327,8 @@ static int iTCO_wdt_set_timeout(struct watchdog_device *wd_dev, unsigned int t) unsigned char val8; unsigned int tmrval; - tmrval = seconds_to_ticks(p, t); - - /* For TCO v1 the timer counts down twice before rebooting */ - if (p->iTCO_version == 1) - tmrval /= 2; + /* The timer counts down twice before rebooting */ + tmrval = seconds_to_ticks(p, t) / 2; /* from the specs: */ /* "Values of 0h-3h are ignored and should not be attempted" */ @@ -385,6 +381,8 @@ static unsigned int iTCO_wdt_get_timeleft(struct watchdog_device *wd_dev) spin_lock(&p->io_lock); val16 = inw(TCO_RLD(p)); val16 &= 0x3ff; + if (!(inw(TCO1_STS(p)) & 0x0008)) + val16 += (inw(TCOv2_TMR(p)) & 0x3ff); spin_unlock(&p->io_lock); time_left = ticks_to_seconds(p, val16); diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c index 99ebf6ea3de6..5615f4013924 100644 --- a/drivers/watchdog/pcwd_usb.c +++ b/drivers/watchdog/pcwd_usb.c @@ -630,6 +630,9 @@ static int usb_pcwd_probe(struct usb_interface *interface, return -ENODEV; } + if (iface_desc->desc.bNumEndpoints < 1) + return -ENODEV; + /* check out the endpoint: it has to be Interrupt & IN */ endpoint = &iface_desc->endpoint[0].desc; diff --git a/drivers/watchdog/sama5d4_wdt.c b/drivers/watchdog/sama5d4_wdt.c index f709962018ac..362fd229786d 100644 --- a/drivers/watchdog/sama5d4_wdt.c +++ b/drivers/watchdog/sama5d4_wdt.c @@ -6,6 +6,7 @@ * Licensed under GPLv2. */ +#include <linux/delay.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> @@ -29,6 +30,7 @@ struct sama5d4_wdt { struct watchdog_device wdd; void __iomem *reg_base; u32 mr; + unsigned long last_ping; }; static int wdt_timeout = WDT_DEFAULT_TIMEOUT; @@ -44,11 +46,34 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); +#define wdt_enabled (!(wdt->mr & AT91_WDT_WDDIS)) + #define wdt_read(wdt, field) \ readl_relaxed((wdt)->reg_base + (field)) -#define wdt_write(wtd, field, val) \ - writel_relaxed((val), (wdt)->reg_base + (field)) +/* 4 slow clock periods is 4/32768 = 122.07µs*/ +#define WDT_DELAY usecs_to_jiffies(123) + +static void wdt_write(struct sama5d4_wdt *wdt, u32 field, u32 val) +{ + /* + * WDT_CR and WDT_MR must not be modified within three slow clock + * periods following a restart of the watchdog performed by a write + * access in WDT_CR. + */ + while (time_before(jiffies, wdt->last_ping + WDT_DELAY)) + usleep_range(30, 125); + writel_relaxed(val, wdt->reg_base + field); + wdt->last_ping = jiffies; +} + +static void wdt_write_nosleep(struct sama5d4_wdt *wdt, u32 field, u32 val) +{ + if (time_before(jiffies, wdt->last_ping + WDT_DELAY)) + udelay(123); + writel_relaxed(val, wdt->reg_base + field); + wdt->last_ping = jiffies; +} static int sama5d4_wdt_start(struct watchdog_device *wdd) { @@ -89,7 +114,16 @@ static int sama5d4_wdt_set_timeout(struct watchdog_device *wdd, wdt->mr &= ~AT91_WDT_WDD; wdt->mr |= AT91_WDT_SET_WDV(value); wdt->mr |= AT91_WDT_SET_WDD(value); - wdt_write(wdt, AT91_WDT_MR, wdt->mr); + + /* + * WDDIS has to be 0 when updating WDD/WDV. The datasheet states: When + * setting the WDDIS bit, and while it is set, the fields WDV and WDD + * must not be modified. + * If the watchdog is enabled, then the timeout can be updated. Else, + * wait that the user enables it. + */ + if (wdt_enabled) + wdt_write(wdt, AT91_WDT_MR, wdt->mr & ~AT91_WDT_WDDIS); wdd->timeout = timeout; @@ -145,23 +179,21 @@ static int of_sama5d4_wdt_init(struct device_node *np, struct sama5d4_wdt *wdt) static int sama5d4_wdt_init(struct sama5d4_wdt *wdt) { - struct watchdog_device *wdd = &wdt->wdd; - u32 value = WDT_SEC2TICKS(wdd->timeout); u32 reg; - /* - * Because the fields WDV and WDD must not be modified when the WDDIS - * bit is set, so clear the WDDIS bit before writing the WDT_MR. + * When booting and resuming, the bootloader may have changed the + * watchdog configuration. + * If the watchdog is already running, we can safely update it. + * Else, we have to disable it properly. */ - reg = wdt_read(wdt, AT91_WDT_MR); - reg &= ~AT91_WDT_WDDIS; - wdt_write(wdt, AT91_WDT_MR, reg); - - wdt->mr |= AT91_WDT_SET_WDD(value); - wdt->mr |= AT91_WDT_SET_WDV(value); - - wdt_write(wdt, AT91_WDT_MR, wdt->mr); - + if (wdt_enabled) { + wdt_write_nosleep(wdt, AT91_WDT_MR, wdt->mr); + } else { + reg = wdt_read(wdt, AT91_WDT_MR); + if (!(reg & AT91_WDT_WDDIS)) + wdt_write_nosleep(wdt, AT91_WDT_MR, + reg | AT91_WDT_WDDIS); + } return 0; } @@ -172,6 +204,7 @@ static int sama5d4_wdt_probe(struct platform_device *pdev) struct resource *res; void __iomem *regs; u32 irq = 0; + u32 timeout; int ret; wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL); @@ -184,6 +217,7 @@ static int sama5d4_wdt_probe(struct platform_device *pdev) wdd->ops = &sama5d4_wdt_ops; wdd->min_timeout = MIN_WDT_TIMEOUT; wdd->max_timeout = MAX_WDT_TIMEOUT; + wdt->last_ping = jiffies; watchdog_set_drvdata(wdd, wdt); @@ -221,6 +255,11 @@ static int sama5d4_wdt_probe(struct platform_device *pdev) return ret; } + timeout = WDT_SEC2TICKS(wdd->timeout); + + wdt->mr |= AT91_WDT_SET_WDD(timeout); + wdt->mr |= AT91_WDT_SET_WDV(timeout); + ret = sama5d4_wdt_init(wdt); if (ret) return ret; @@ -263,9 +302,7 @@ static int sama5d4_wdt_resume(struct device *dev) { struct sama5d4_wdt *wdt = dev_get_drvdata(dev); - wdt_write(wdt, AT91_WDT_MR, wdt->mr & ~AT91_WDT_WDDIS); - if (wdt->mr & AT91_WDT_WDDIS) - wdt_write(wdt, AT91_WDT_MR, wdt->mr); + sama5d4_wdt_init(wdt); return 0; } diff --git a/drivers/watchdog/wdt_pci.c b/drivers/watchdog/wdt_pci.c index 48b2c058b009..bc7addc2dc06 100644 --- a/drivers/watchdog/wdt_pci.c +++ b/drivers/watchdog/wdt_pci.c @@ -332,7 +332,7 @@ static irqreturn_t wdtpci_interrupt(int irq, void *dev_id) pr_crit("Would Reboot\n"); #else pr_crit("Initiating system reboot\n"); - emergency_restart(NULL); + emergency_restart(); #endif #else pr_crit("Reset in 5ms\n"); diff --git a/drivers/watchdog/zx2967_wdt.c b/drivers/watchdog/zx2967_wdt.c index e290d5a13a6d..c98252733c30 100644 --- a/drivers/watchdog/zx2967_wdt.c +++ b/drivers/watchdog/zx2967_wdt.c @@ -211,10 +211,8 @@ static int zx2967_wdt_probe(struct platform_device *pdev) base = platform_get_resource(pdev, IORESOURCE_MEM, 0); wdt->reg_base = devm_ioremap_resource(dev, base); - if (IS_ERR(wdt->reg_base)) { - dev_err(dev, "ioremap failed\n"); + if (IS_ERR(wdt->reg_base)) return PTR_ERR(wdt->reg_base); - } zx2967_wdt_reset_sysctrl(dev); diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 15bac390dff9..b98436f5c7c7 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1135,20 +1135,19 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, u32 acllen = 0; int rc = 0; struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); - struct cifs_tcon *tcon; + struct smb_version_operations *ops; cifs_dbg(NOISY, "converting ACL to mode for %s\n", path); if (IS_ERR(tlink)) return PTR_ERR(tlink); - tcon = tlink_tcon(tlink); - if (pfid && (tcon->ses->server->ops->get_acl_by_fid)) - pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid, - &acllen); - else if (tcon->ses->server->ops->get_acl) - pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, - &acllen); + ops = tlink_tcon(tlink)->ses->server->ops; + + if (pfid && (ops->get_acl_by_fid)) + pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen); + else if (ops->get_acl) + pntsd = ops->get_acl(cifs_sb, inode, path, &acllen); else { cifs_put_tlink(tlink); return -EOPNOTSUPP; @@ -1181,23 +1180,23 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); - struct cifs_tcon *tcon; + struct smb_version_operations *ops; if (IS_ERR(tlink)) return PTR_ERR(tlink); - tcon = tlink_tcon(tlink); + + ops = tlink_tcon(tlink)->ses->server->ops; cifs_dbg(NOISY, "set ACL from mode for %s\n", path); /* Get the security descriptor */ - if (tcon->ses->server->ops->get_acl == NULL) { + if (ops->get_acl == NULL) { cifs_put_tlink(tlink); return -EOPNOTSUPP; } - pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, - &secdesclen); + pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen); if (IS_ERR(pntsd)) { rc = PTR_ERR(pntsd); cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); @@ -1224,13 +1223,12 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc); - if (tcon->ses->server->ops->set_acl == NULL) + if (ops->set_acl == NULL) rc = -EOPNOTSUPP; if (!rc) { /* Set the security descriptor */ - rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode, - path, aclflag); + rc = ops->set_acl(pnntsd, secdesclen, inode, path, aclflag); cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); } cifs_put_tlink(tlink); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 8be55be70faf..bcc7d9acad64 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -418,7 +418,7 @@ struct smb_version_operations { int (*validate_negotiate)(const unsigned int, struct cifs_tcon *); ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *, const unsigned char *, const unsigned char *, char *, - size_t, const struct nls_table *, int); + size_t, struct cifs_sb_info *); int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *, const char *, const void *, const __u16, const struct nls_table *, int); diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index e49958c3f8bb..6eb3147132e3 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -480,8 +480,7 @@ extern int CIFSSMBCopy(unsigned int xid, extern ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, const unsigned char *ea_name, char *EAData, - size_t bufsize, const struct nls_table *nls_codepage, - int remap_special_chars); + size_t bufsize, struct cifs_sb_info *cifs_sb); extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, const char *fileName, const char *ea_name, const void *ea_value, const __u16 ea_value_len, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 4c01b3f9abf0..fbb0d4cbda41 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -697,9 +697,7 @@ cifs_echo_callback(struct mid_q_entry *mid) { struct TCP_Server_Info *server = mid->callback_data; - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, 1, CIFS_ECHO_OP); } @@ -1599,9 +1597,7 @@ cifs_readv_callback(struct mid_q_entry *mid) } queue_work(cifsiod_wq, &rdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, 1, 0); } @@ -2058,7 +2054,6 @@ cifs_writev_callback(struct mid_q_entry *mid) { struct cifs_writedata *wdata = mid->callback_data; struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; unsigned int written; WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf; @@ -2095,9 +2090,7 @@ cifs_writev_callback(struct mid_q_entry *mid) } queue_work(cifsiod_wq, &wdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(tcon->ses->server, 1, 0); } @@ -6076,11 +6069,13 @@ ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, const unsigned char *ea_name, char *EAData, size_t buf_size, - const struct nls_table *nls_codepage, int remap) + struct cifs_sb_info *cifs_sb) { /* BB assumes one setup word */ TRANSACTION2_QPI_REQ *pSMB = NULL; TRANSACTION2_QPI_RSP *pSMBr = NULL; + int remap = cifs_remap(cifs_sb); + struct nls_table *nls_codepage = cifs_sb->local_nls; int rc = 0; int bytes_returned; int list_len; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 6ef78ad838e6..0fd081bd2a2f 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -582,7 +582,7 @@ cifs_relock_file(struct cifsFileInfo *cfile) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; - down_read(&cinode->lock_sem); + down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING); if (cinode->can_cache_brlcks) { /* can cache locks - no need to relock */ up_read(&cinode->lock_sem); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index c3b2fa0b2ec8..4d1fcd76d022 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -563,8 +563,7 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path, rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path, "SETFILEBITS", ea_value, 4 /* size of buf */, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); + cifs_sb); cifs_put_tlink(tlink); if (rc < 0) return (int)rc; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 48ff7703b919..e4afdaae743f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1240,15 +1240,19 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, goto tcon_exit; } - if (rsp->ShareType & SMB2_SHARE_TYPE_DISK) + switch (rsp->ShareType) { + case SMB2_SHARE_TYPE_DISK: cifs_dbg(FYI, "connection to disk share\n"); - else if (rsp->ShareType & SMB2_SHARE_TYPE_PIPE) { + break; + case SMB2_SHARE_TYPE_PIPE: tcon->ipc = true; cifs_dbg(FYI, "connection to pipe share\n"); - } else if (rsp->ShareType & SMB2_SHARE_TYPE_PRINT) { - tcon->print = true; + break; + case SMB2_SHARE_TYPE_PRINT: + tcon->ipc = true; cifs_dbg(FYI, "connection to printer\n"); - } else { + break; + default: cifs_dbg(VFS, "unknown share type %d\n", rsp->ShareType); rc = -EOPNOTSUPP; goto tcon_error_exit; @@ -2173,9 +2177,7 @@ smb2_echo_callback(struct mid_q_entry *mid) if (mid->mid_state == MID_RESPONSE_RECEIVED) credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, credits_received, CIFS_ECHO_OP); } @@ -2433,9 +2435,7 @@ smb2_readv_callback(struct mid_q_entry *mid) cifs_stats_fail_inc(tcon, SMB2_READ_HE); queue_work(cifsiod_wq, &rdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(server, credits_received, 0); } @@ -2594,7 +2594,6 @@ smb2_writev_callback(struct mid_q_entry *mid) { struct cifs_writedata *wdata = mid->callback_data; struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; unsigned int written; struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf; unsigned int credits_received = 1; @@ -2634,9 +2633,7 @@ smb2_writev_callback(struct mid_q_entry *mid) cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); queue_work(cifsiod_wq, &wdata->work); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); add_credits(tcon->ses->server, credits_received, 0); } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 4d64b5b8fc9c..47a125ece11e 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -94,7 +94,7 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) now = jiffies; /* commands taking longer than one second are indications that something is wrong, unless it is quite a slow link or server */ - if ((now - midEntry->when_alloc) > HZ) { + if (time_after(now, midEntry->when_alloc + HZ)) { if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) { pr_debug(" CIFS slow rsp: cmd %d mid %llu", midEntry->command, midEntry->mid); @@ -613,9 +613,7 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) } spin_unlock(&GlobalMid_Lock); - mutex_lock(&server->srv_mutex); DeleteMidQEntry(mid); - mutex_unlock(&server->srv_mutex); return rc; } diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 20af5187ba63..3cb5c9e2d4e7 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -235,8 +235,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler, if (pTcon->ses->server->ops->query_all_EAs) rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, - full_path, name, value, size, - cifs_sb->local_nls, cifs_remap(cifs_sb)); + full_path, name, value, size, cifs_sb); break; case XATTR_CIFS_ACL: { @@ -336,8 +335,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) if (pTcon->ses->server->ops->query_all_EAs) rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, - full_path, NULL, data, buf_size, - cifs_sb->local_nls, cifs_remap(cifs_sb)); + full_path, NULL, data, buf_size, cifs_sb); list_ea_exit: kfree(full_path); free_xid(xid); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 26d77f9f8c12..2dcbd5698884 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -817,7 +817,7 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->bdev = bdev; iomap->offset = (u64)first_block << blkbits; if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); + iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); else iomap->dax_dev = NULL; @@ -841,7 +841,7 @@ static int ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { - put_dax(iomap->dax_dev); + fs_put_dax(iomap->dax_dev); if (iomap->type == IOMAP_MAPPED && written < length && (flags & IOMAP_WRITE)) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5834c4d76be8..1bd0bfa547f6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3412,7 +3412,7 @@ retry: bdev = inode->i_sb->s_bdev; iomap->bdev = bdev; if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); + iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); else iomap->dax_dev = NULL; iomap->offset = first_block << blkbits; @@ -3447,7 +3447,7 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, int blkbits = inode->i_blkbits; bool truncate = false; - put_dax(iomap->dax_dev); + fs_put_dax(iomap->dax_dev); if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT)) return 0; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 5a1b58f8fef4..65c88379a3a1 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -975,8 +975,15 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) int err; char *suffix = ""; - if (sb->s_bdev) + if (sb->s_bdev) { suffix = "-fuseblk"; + /* + * sb->s_bdi points to blkdev's bdi however we want to redirect + * it to our private bdi... + */ + bdi_put(sb->s_bdi); + sb->s_bdi = &noop_backing_dev_info; + } err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev), MINOR(fc->dev), suffix); if (err) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index a63f61c256bd..94e5bdf7304c 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1068,7 +1068,7 @@ xfs_file_iomap_begin( /* optionally associate a dax device with the iomap bdev */ bdev = iomap->bdev; if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); + iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); else iomap->dax_dev = NULL; @@ -1149,7 +1149,7 @@ xfs_file_iomap_end( unsigned flags, struct iomap *iomap) { - put_dax(iomap->dax_dev); + fs_put_dax(iomap->dax_dev); if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC) return xfs_file_iomap_end_delalloc(XFS_I(inode), offset, length, written, iomap); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5efb4db44e1e..d5093b52b485 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -40,6 +40,9 @@ struct bpf_reg_state { */ s64 min_value; u64 max_value; + u32 min_align; + u32 aux_off; + u32 aux_off_align; }; enum bpf_stack_slot_type { @@ -87,6 +90,7 @@ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ + bool strict_alignment; /* perform strict pointer alignment checks */ struct bpf_verifier_state cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ diff --git a/include/linux/dax.h b/include/linux/dax.h index 00ebac854bb7..5ec1f6c47716 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -18,6 +18,20 @@ struct dax_operations { void **, pfn_t *); }; +#if IS_ENABLED(CONFIG_DAX) +struct dax_device *dax_get_by_host(const char *host); +void put_dax(struct dax_device *dax_dev); +#else +static inline struct dax_device *dax_get_by_host(const char *host) +{ + return NULL; +} + +static inline void put_dax(struct dax_device *dax_dev) +{ +} +#endif + int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) int __bdev_dax_supported(struct super_block *sb, int blocksize); @@ -25,23 +39,29 @@ static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { return __bdev_dax_supported(sb, blocksize); } + +static inline struct dax_device *fs_dax_get_by_host(const char *host) +{ + return dax_get_by_host(host); +} + +static inline void fs_put_dax(struct dax_device *dax_dev) +{ + put_dax(dax_dev); +} + #else static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { return -EOPNOTSUPP; } -#endif -#if IS_ENABLED(CONFIG_DAX) -struct dax_device *dax_get_by_host(const char *host); -void put_dax(struct dax_device *dax_dev); -#else -static inline struct dax_device *dax_get_by_host(const char *host) +static inline struct dax_device *fs_dax_get_by_host(const char *host) { return NULL; } -static inline void put_dax(struct dax_device *dax_dev) +static inline void fs_put_dax(struct dax_device *dax_dev) { } #endif diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 30f90c1a0aaf..541df0b5b815 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -349,6 +349,9 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif +extern void wait_for_kprobe_optimizer(void); +#else +static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1b166d2e19c5..b25e7baa273e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -109,7 +109,6 @@ struct mlx5_flow_table_attr { int max_fte; u32 level; u32 flags; - u32 underlay_qpn; }; struct mlx5_flow_table * @@ -167,4 +166,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); +int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); +int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); + #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9c23bd2efb56..3f39d27decf4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3296,11 +3296,15 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); + +typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp); +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, u32 flags); +bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 0db37158a61d..6c8c5d8041b7 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -27,8 +27,8 @@ /* FC Port role bitmask - can merge with FC Port Roles in fc transport */ #define FC_PORT_ROLE_NVME_INITIATOR 0x10 -#define FC_PORT_ROLE_NVME_TARGET 0x11 -#define FC_PORT_ROLE_NVME_DISCOVERY 0x12 +#define FC_PORT_ROLE_NVME_TARGET 0x20 +#define FC_PORT_ROLE_NVME_DISCOVERY 0x40 /** @@ -642,15 +642,7 @@ enum { * sequence in one LLDD operation. Errors during Data * sequence transmit must not allow RSP sequence to be sent. */ - NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED = (1 << 1), - /* Bit 1: When 0, the LLDD will deliver FCP CMD - * on the CPU it should be affinitized to. Thus work will - * be scheduled on the cpu received on. When 1, the LLDD - * may not deliver the CMD on the CPU it should be worked - * on. The transport should pick a cpu to schedule the work - * on. - */ - NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 2), + NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 1), /* Bit 2: When 0, the LLDD is calling the cmd rcv handler * in a non-isr context, allowing the transport to finish * op completion in the calling context. When 1, the LLDD @@ -658,7 +650,7 @@ enum { * requiring the transport to transition to a workqueue * for op completion. */ - NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 3), + NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 2), /* Bit 3: When 0, the LLDD is calling the op done handler * in a non-isr context, allowing the transport to finish * op completion in the calling context. When 1, the LLDD diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index ec6b11deb773..1e0deb8e8494 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -8,7 +8,7 @@ #include <linux/ioport.h> #include <linux/of.h> -typedef int const (*of_irq_init_cb_t)(struct device_node *, struct device_node *); +typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *); /* * Workarounds only applied to 32bit powermac machines diff --git a/include/linux/soc/renesas/rcar-rst.h b/include/linux/soc/renesas/rcar-rst.h index a18e0783946b..787e7ad53d45 100644 --- a/include/linux/soc/renesas/rcar-rst.h +++ b/include/linux/soc/renesas/rcar-rst.h @@ -1,6 +1,11 @@ #ifndef __LINUX_SOC_RENESAS_RCAR_RST_H__ #define __LINUX_SOC_RENESAS_RCAR_RST_H__ +#if defined(CONFIG_ARCH_RCAR_GEN1) || defined(CONFIG_ARCH_RCAR_GEN2) || \ + defined(CONFIG_ARCH_R8A7795) || defined(CONFIG_ARCH_R8A7796) int rcar_rst_read_mode_pins(u32 *mode); +#else +static inline int rcar_rst_read_mode_pins(u32 *mode) { return -ENODEV; } +#endif #endif /* __LINUX_SOC_RENESAS_RCAR_RST_H__ */ diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index a469999a106d..50398b69ca44 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -148,6 +148,7 @@ struct usb_hcd { unsigned rh_registered:1;/* is root hub registered? */ unsigned rh_pollable:1; /* may we poll the root hub? */ unsigned msix_enabled:1; /* driver has MSI-X enabled? */ + unsigned msi_enabled:1; /* driver has MSI enabled? */ unsigned remove_phy:1; /* auto-remove USB phy */ /* The next flag is a stopgap, to be removed when all the HCDs diff --git a/include/net/x25.h b/include/net/x25.h index c383aa4edbf0..6d30a01d281d 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -298,10 +298,10 @@ void x25_check_rbuf(struct sock *); /* sysctl_net_x25.c */ #ifdef CONFIG_SYSCTL -void x25_register_sysctl(void); +int x25_register_sysctl(void); void x25_unregister_sysctl(void); #else -static inline void x25_register_sysctl(void) {}; +static inline int x25_register_sysctl(void) { return 0; }; static inline void x25_unregister_sysctl(void) {}; #endif /* CONFIG_SYSCTL */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 945a1f5f63c5..94dfa9def355 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -132,6 +132,13 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ @@ -177,6 +184,7 @@ union bpf_attr { __u32 log_size; /* size of user buffer */ __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ + __u32 prog_flags; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8e56ac70e0d1..15ac20382aba 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -888,9 +888,18 @@ enum { /* XDP section */ #define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) -#define XDP_FLAGS_SKB_MODE (2U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) #define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ - XDP_FLAGS_SKB_MODE) + XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, +}; enum { IFLA_XDP_UNSPEC, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 577429a95ad8..2b8dc1ca18d4 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -155,6 +155,35 @@ struct kvm_s390_skeys { __u32 reserved[9]; }; +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 @@ -895,6 +924,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SPAPR_TCE_VFIO 142 #define KVM_CAP_X86_GUEST_MWAIT 143 #define KVM_CAP_ARM_USER_IRQ 144 +#define KVM_CAP_S390_CMMA_MIGRATION 145 #ifdef KVM_CAP_IRQ_ROUTING @@ -1318,6 +1348,9 @@ struct kvm_s390_ucas_mapping { #define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state) /* Available with KVM_CAP_X86_SMM */ #define KVM_SMI _IO(KVMIO, 0xb7) +/* Available with KVM_CAP_S390_CMMA_MIGRATION */ +#define KVM_S390_GET_CMMA_BITS _IOW(KVMIO, 0xb8, struct kvm_s390_cmma_log) +#define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) diff --git a/include/uapi/linux/usb/ch11.h b/include/uapi/linux/usb/ch11.h index 361297e96f58..576c704e3fb8 100644 --- a/include/uapi/linux/usb/ch11.h +++ b/include/uapi/linux/usb/ch11.h @@ -22,6 +22,9 @@ */ #define USB_MAXCHILDREN 31 +/* See USB 3.1 spec Table 10-5 */ +#define USB_SS_MAXPORTS 15 + /* * Hub request types */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fd2411fd6914..265a0d854e33 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -783,7 +783,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD kern_version +#define BPF_PROG_LOAD_LAST_FIELD prog_flags static int bpf_prog_load(union bpf_attr *attr) { @@ -796,6 +796,9 @@ static int bpf_prog_load(union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; + if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT) + return -EINVAL; + /* copy eBPF program license from user space */ if (strncpy_from_user(license, u64_to_user_ptr(attr->license), sizeof(license) - 1) < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c5b56c92f8e2..1eddb713b815 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -140,7 +140,7 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_INSNS 65536 +#define BPF_COMPLEXITY_LIMIT_INSNS 98304 #define BPF_COMPLEXITY_LIMIT_STACK 1024 #define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA) @@ -241,6 +241,12 @@ static void print_verifier_state(struct bpf_verifier_state *state) if (reg->max_value != BPF_REGISTER_MAX_RANGE) verbose(",max_value=%llu", (unsigned long long)reg->max_value); + if (reg->min_align) + verbose(",min_align=%u", reg->min_align); + if (reg->aux_off) + verbose(",aux_off=%u", reg->aux_off); + if (reg->aux_off_align) + verbose(",aux_off_align=%u", reg->aux_off_align); } for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] == STACK_SPILL) @@ -466,6 +472,9 @@ static void init_reg_state(struct bpf_reg_state *regs) regs[i].imm = 0; regs[i].min_value = BPF_REGISTER_MIN_RANGE; regs[i].max_value = BPF_REGISTER_MAX_RANGE; + regs[i].min_align = 0; + regs[i].aux_off = 0; + regs[i].aux_off_align = 0; } /* frame pointer */ @@ -492,6 +501,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno) { regs[regno].min_value = BPF_REGISTER_MIN_RANGE; regs[regno].max_value = BPF_REGISTER_MAX_RANGE; + regs[regno].min_align = 0; } static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs, @@ -779,17 +789,33 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) } static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, - int off, int size) + int off, int size, bool strict) { - if (reg->id && size != 1) { - verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n"); - return -EACCES; + int ip_align; + int reg_off; + + /* Byte size accesses are always allowed. */ + if (!strict || size == 1) + return 0; + + reg_off = reg->off; + if (reg->id) { + if (reg->aux_off_align % size) { + verbose("Packet access is only %u byte aligned, %d byte access not allowed\n", + reg->aux_off_align, size); + return -EACCES; + } + reg_off += reg->aux_off; } - /* skb->data is NET_IP_ALIGN-ed */ - if ((NET_IP_ALIGN + reg->off + off) % size != 0) { + /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking + * we force this to 2 which is universally what architectures use + * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. + */ + ip_align = strict ? 2 : NET_IP_ALIGN; + if ((ip_align + reg_off + off) % size != 0) { verbose("misaligned packet access off %d+%d+%d size %d\n", - NET_IP_ALIGN, reg->off, off, size); + ip_align, reg_off, off, size); return -EACCES; } @@ -797,9 +823,9 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, } static int check_val_ptr_alignment(const struct bpf_reg_state *reg, - int size) + int size, bool strict) { - if (size != 1) { + if (strict && size != 1) { verbose("Unknown alignment. Only byte-sized access allowed in value access.\n"); return -EACCES; } @@ -807,16 +833,20 @@ static int check_val_ptr_alignment(const struct bpf_reg_state *reg, return 0; } -static int check_ptr_alignment(const struct bpf_reg_state *reg, +static int check_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int off, int size) { + bool strict = env->strict_alignment; + + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) + strict = true; + switch (reg->type) { case PTR_TO_PACKET: - return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : - check_pkt_ptr_alignment(reg, off, size); + return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE_ADJ: - return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 : - check_val_ptr_alignment(reg, size); + return check_val_ptr_alignment(reg, size, strict); default: if (off % size != 0) { verbose("misaligned access off %d size %d\n", @@ -849,7 +879,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, if (size < 0) return size; - err = check_ptr_alignment(reg, off, size); + err = check_ptr_alignment(env, reg, off, size); if (err) return err; @@ -883,6 +913,8 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, value_regno); /* note that reg.[id|off|range] == 0 */ state->regs[value_regno].type = reg_type; + state->regs[value_regno].aux_off = 0; + state->regs[value_regno].aux_off_align = 0; } } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) { @@ -1455,6 +1487,8 @@ add_imm: */ dst_reg->off += imm; } else { + bool had_id; + if (src_reg->type == PTR_TO_PACKET) { /* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */ tmp_reg = *dst_reg; /* save r7 state */ @@ -1488,14 +1522,23 @@ add_imm: src_reg->imm); return -EACCES; } + + had_id = (dst_reg->id != 0); + /* dst_reg stays as pkt_ptr type and since some positive * integer value was added to the pointer, increment its 'id' */ dst_reg->id = ++env->id_gen; - /* something was added to pkt_ptr, set range and off to zero */ + /* something was added to pkt_ptr, set range to zero */ + dst_reg->aux_off += dst_reg->off; dst_reg->off = 0; dst_reg->range = 0; + if (had_id) + dst_reg->aux_off_align = min(dst_reg->aux_off_align, + src_reg->min_align); + else + dst_reg->aux_off_align = src_reg->min_align; } return 0; } @@ -1669,6 +1712,13 @@ static void check_reg_overflow(struct bpf_reg_state *reg) reg->min_value = BPF_REGISTER_MIN_RANGE; } +static u32 calc_align(u32 imm) +{ + if (!imm) + return 1U << 31; + return imm - ((imm - 1) & imm); +} + static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { @@ -1676,8 +1726,10 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, s64 min_val = BPF_REGISTER_MIN_RANGE; u64 max_val = BPF_REGISTER_MAX_RANGE; u8 opcode = BPF_OP(insn->code); + u32 dst_align, src_align; dst_reg = ®s[insn->dst_reg]; + src_align = 0; if (BPF_SRC(insn->code) == BPF_X) { check_reg_overflow(®s[insn->src_reg]); min_val = regs[insn->src_reg].min_value; @@ -1693,12 +1745,18 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, regs[insn->src_reg].type != UNKNOWN_VALUE) { min_val = BPF_REGISTER_MIN_RANGE; max_val = BPF_REGISTER_MAX_RANGE; + src_align = 0; + } else { + src_align = regs[insn->src_reg].min_align; } } else if (insn->imm < BPF_REGISTER_MAX_RANGE && (s64)insn->imm > BPF_REGISTER_MIN_RANGE) { min_val = max_val = insn->imm; + src_align = calc_align(insn->imm); } + dst_align = dst_reg->min_align; + /* We don't know anything about what was done to this register, mark it * as unknown. */ @@ -1723,18 +1781,21 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, dst_reg->min_value += min_val; if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value += max_val; + dst_reg->min_align = min(src_align, dst_align); break; case BPF_SUB: if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value -= min_val; if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value -= max_val; + dst_reg->min_align = min(src_align, dst_align); break; case BPF_MUL: if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value *= min_val; if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value *= max_val; + dst_reg->min_align = max(src_align, dst_align); break; case BPF_AND: /* Disallow AND'ing of negative numbers, ain't nobody got time @@ -1746,17 +1807,23 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, else dst_reg->min_value = 0; dst_reg->max_value = max_val; + dst_reg->min_align = max(src_align, dst_align); break; case BPF_LSH: /* Gotta have special overflow logic here, if we're shifting * more than MAX_RANGE then just assume we have an invalid * range. */ - if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) + if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) { dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) - dst_reg->min_value <<= min_val; - + dst_reg->min_align = 1; + } else { + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value <<= min_val; + if (!dst_reg->min_align) + dst_reg->min_align = 1; + dst_reg->min_align <<= min_val; + } if (max_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->max_value = BPF_REGISTER_MAX_RANGE; else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) @@ -1766,11 +1833,19 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* RSH by a negative number is undefined, and the BPF_RSH is an * unsigned shift, so make the appropriate casts. */ - if (min_val < 0 || dst_reg->min_value < 0) + if (min_val < 0 || dst_reg->min_value < 0) { dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else + } else { dst_reg->min_value = (u64)(dst_reg->min_value) >> min_val; + } + if (min_val < 0) { + dst_reg->min_align = 1; + } else { + dst_reg->min_align >>= (u64) min_val; + if (!dst_reg->min_align) + dst_reg->min_align = 1; + } if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value >>= max_val; break; @@ -1872,6 +1947,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) regs[insn->dst_reg].imm = insn->imm; regs[insn->dst_reg].max_value = insn->imm; regs[insn->dst_reg].min_value = insn->imm; + regs[insn->dst_reg].min_align = calc_align(insn->imm); } } else if (opcode > BPF_END) { @@ -2564,6 +2640,7 @@ peek_stack: env->explored_states[t + 1] = STATE_LIST_MARK; } else { /* conditional jump with two edges */ + env->explored_states[t] = STATE_LIST_MARK; ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret == 1) goto peek_stack; @@ -2722,6 +2799,12 @@ static bool states_equal(struct bpf_verifier_env *env, rcur->type != NOT_INIT)) continue; + /* Don't care about the reg->id in this case. */ + if (rold->type == PTR_TO_MAP_VALUE_OR_NULL && + rcur->type == PTR_TO_MAP_VALUE_OR_NULL && + rold->map_ptr == rcur->map_ptr) + continue; + if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && compare_ptrs_to_packet(rold, rcur)) continue; @@ -2856,8 +2939,15 @@ static int do_check(struct bpf_verifier_env *env) goto process_bpf_exit; } - if (log_level && do_print_state) { - verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx); + if (need_resched()) + cond_resched(); + + if (log_level > 1 || (log_level && do_print_state)) { + if (log_level > 1) + verbose("%d:", insn_idx); + else + verbose("\nfrom %d to %d:", + prev_insn_idx, insn_idx); print_verifier_state(&env->cur_state); do_print_state = false; } @@ -3494,6 +3584,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) } else { log_level = 0; } + if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT) + env->strict_alignment = true; + else + env->strict_alignment = false; ret = replace_map_fd_with_map_ptr(env); if (ret < 0) @@ -3599,6 +3693,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, mutex_lock(&bpf_verifier_lock); log_level = 0; + env->strict_alignment = false; env->explored_states = kcalloc(env->prog->len, sizeof(struct bpf_verifier_state_list *), diff --git a/kernel/fork.c b/kernel/fork.c index 06d759ab4c62..aa1076c5e4a9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1845,11 +1845,13 @@ static __latent_entropy struct task_struct *copy_process( */ recalc_sigpending(); if (signal_pending(current)) { - spin_unlock(¤t->sighand->siglock); - write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; goto bad_fork_cancel_cgroup; } + if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) { + retval = -ENOMEM; + goto bad_fork_cancel_cgroup; + } if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); @@ -1907,6 +1909,8 @@ static __latent_entropy struct task_struct *copy_process( return p; bad_fork_cancel_cgroup: + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p); bad_fork_free_pid: cgroup_threadgroup_change_end(current); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 686be4b73018..c94da688ee9b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -880,8 +880,8 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, if (!desc) return; - __irq_do_set_handler(desc, handle, 1, NULL); desc->irq_common_data.handler_data = data; + __irq_do_set_handler(desc, handle, 1, NULL); irq_put_desc_busunlock(desc, flags); } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 7367e0ec6f81..2d2d3a568e4e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -595,7 +595,7 @@ static void kprobe_optimizer(struct work_struct *work) } /* Wait for completing optimization and unoptimization */ -static void wait_for_kprobe_optimizer(void) +void wait_for_kprobe_optimizer(void) { mutex_lock(&kprobe_mutex); @@ -2183,6 +2183,12 @@ static int kprobes_module_callback(struct notifier_block *nb, * The vaddr this probe is installed will soon * be vfreed buy not synced to disk. Hence, * disarming the breakpoint isn't needed. + * + * Note, this will also move any optimized probes + * that are pending to be removed from their + * corresponding lists to the freeing_list and + * will not be touched by the delayed + * kprobe_optimizer work handler. */ kill_kprobe(p); } diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index d1f3e9f558b8..74a5a7255b4d 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -277,7 +277,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) * if reparented. */ for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->nr_hashed == init_pids) break; schedule(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 759f4bd52cd6..803c3bc274c4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3502,6 +3502,31 @@ asmlinkage __visible void __sched schedule(void) } EXPORT_SYMBOL(schedule); +/* + * synchronize_rcu_tasks() makes sure that no task is stuck in preempted + * state (have scheduled out non-voluntarily) by making sure that all + * tasks have either left the run queue or have gone into user space. + * As idle tasks do not do either, they must not ever be preempted + * (schedule out non-voluntarily). + * + * schedule_idle() is similar to schedule_preempt_disable() except that it + * never enables preemption because it does not call sched_submit_work(). + */ +void __sched schedule_idle(void) +{ + /* + * As this skips calling sched_submit_work(), which the idle task does + * regardless because that function is a nop when the task is in a + * TASK_RUNNING state, make sure this isn't used someplace that the + * current task can be in any other state. Note, idle is always in the + * TASK_RUNNING state. + */ + WARN_ON_ONCE(current->state); + do { + __schedule(false); + } while (need_resched()); +} + #ifdef CONFIG_CONTEXT_TRACKING asmlinkage __visible void __sched schedule_user(void) { diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 2a25a9ec2c6e..ef63adce0c9c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -265,7 +265,7 @@ static void do_idle(void) smp_mb__after_atomic(); sched_ttwu_pending(); - schedule_preempt_disabled(); + schedule_idle(); if (unlikely(klp_patch_pending(current))) klp_update_patch_state(current); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7808ab050599..6dda2aab731e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1467,6 +1467,8 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq) } #endif +extern void schedule_idle(void); + extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index bd8ae8d5ae9c..193c5f5e3f79 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1662,14 +1662,14 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, goto out; if (attr == &dev_attr_act_mask) { - if (sscanf(buf, "%llx", &value) != 1) { + if (kstrtoull(buf, 0, &value)) { /* Assume it is a list of trace category names */ ret = blk_trace_str2mask(buf); if (ret < 0) goto out; value = ret; } - } else if (sscanf(buf, "%llu", &value) != 1) + } else if (kstrtoull(buf, 0, &value)) goto out; ret = -ENXIO; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 39dca4e86a94..74fdfe9ed3db 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4144,9 +4144,9 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, int i, ret = -ENODEV; int size; - if (glob && (strcmp(glob, "*") == 0 || !strlen(glob))) + if (!glob || !strlen(glob) || !strcmp(glob, "*")) func_g.search = NULL; - else if (glob) { + else { int not; func_g.type = filter_parse_regex(glob, strlen(glob), @@ -4256,6 +4256,14 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, return ret; } +void clear_ftrace_function_probes(struct trace_array *tr) +{ + struct ftrace_func_probe *probe, *n; + + list_for_each_entry_safe(probe, n, &tr->func_probes, list) + unregister_ftrace_function_probe_func(NULL, tr, probe->probe_ops); +} + static LIST_HEAD(ftrace_commands); static DEFINE_MUTEX(ftrace_cmd_mutex); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c4536c449021..1122f151466f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1558,7 +1558,7 @@ static __init int init_trace_selftests(void) return 0; } -early_initcall(init_trace_selftests); +core_initcall(init_trace_selftests); #else static inline int run_tracer_selftest(struct tracer *type) { @@ -2568,7 +2568,36 @@ static inline void ftrace_trace_stack(struct trace_array *tr, void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { - __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL); + struct ring_buffer *buffer = tr->trace_buffer.buffer; + + if (rcu_is_watching()) { + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + return; + } + + /* + * When an NMI triggers, RCU is enabled via rcu_nmi_enter(), + * but if the above rcu_is_watching() failed, then the NMI + * triggered someplace critical, and rcu_irq_enter() should + * not be called from NMI. + */ + if (unlikely(in_nmi())) + return; + + /* + * It is possible that a function is being traced in a + * location that RCU is not watching. A call to + * rcu_irq_enter() will make sure that it is, but there's + * a few internal rcu functions that could be traced + * where that wont work either. In those cases, we just + * do nothing. + */ + if (unlikely(rcu_irq_enter_disabled())) + return; + + rcu_irq_enter_irqson(); + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); + rcu_irq_exit_irqson(); } /** @@ -7550,6 +7579,7 @@ static int instance_rmdir(const char *name) } tracing_set_nop(tr); + clear_ftrace_function_probes(tr); event_trace_del_tracer(tr); ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 291a1bca5748..39fd77330aab 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -980,6 +980,7 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, extern int unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, struct ftrace_probe_ops *ops); +extern void clear_ftrace_function_probes(struct trace_array *tr); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); @@ -998,6 +999,10 @@ static inline __init int unregister_ftrace_command(char *cmd_name) { return -EINVAL; } +static inline void clear_ftrace_function_probes(struct trace_array *tr) +{ +} + /* * The ops parameter passed in is usually undefined. * This must be a macro. diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 8485f6738a87..c129fca6ec99 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1535,6 +1535,11 @@ static __init int kprobe_trace_self_tests_init(void) end: release_all_trace_kprobes(); + /* + * Wait for the optimizer work to finish. Otherwise it might fiddle + * with probes in already freed __init text. + */ + wait_for_kprobe_optimizer(); if (warn) pr_cont("NG: Some tests are failed. Please check them.\n"); else diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 71e85643b3f9..6ad3e043c617 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -454,8 +454,8 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, goto error_xenbus; } priv->tag = xenbus_read(xbt, dev->nodename, "tag", NULL); - if (!priv->tag) { - ret = -EINVAL; + if (IS_ERR(priv->tag)) { + ret = PTR_ERR(priv->tag); goto error_xenbus; } ret = xenbus_transaction_end(xbt, 0); @@ -525,7 +525,7 @@ static struct xenbus_driver xen_9pfs_front_driver = { .otherend_changed = xen_9pfs_front_changed, }; -int p9_trans_xen_init(void) +static int p9_trans_xen_init(void) { if (!xen_domain()) return -ENODEV; @@ -537,7 +537,7 @@ int p9_trans_xen_init(void) } module_init(p9_trans_xen_init); -void p9_trans_xen_exit(void) +static void p9_trans_xen_exit(void) { v9fs_unregister_trans(&p9_xen_trans); return xenbus_unregister_driver(&xen_9pfs_front_driver); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index c5ce7745b230..574f78824d8a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -835,6 +835,13 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return -EPROTONOSUPPORT; } } + + if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { + __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); + + if (defpvid >= VLAN_VID_MASK) + return -EINVAL; + } #endif return 0; diff --git a/net/core/dev.c b/net/core/dev.c index 96cf83da0d66..fca407b4a6ea 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6852,6 +6852,32 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down); +bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op) +{ + struct netdev_xdp xdp; + + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG; + + /* Query must always succeed. */ + WARN_ON(xdp_op(dev, &xdp) < 0); + return xdp.prog_attached; +} + +static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op, + struct netlink_ext_ack *extack, + struct bpf_prog *prog) +{ + struct netdev_xdp xdp; + + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_SETUP_PROG; + xdp.extack = extack; + xdp.prog = prog; + + return xdp_op(dev, &xdp); +} + /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device @@ -6864,41 +6890,34 @@ EXPORT_SYMBOL(dev_change_proto_down); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags) { - int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp); const struct net_device_ops *ops = dev->netdev_ops; struct bpf_prog *prog = NULL; - struct netdev_xdp xdp; + xdp_op_t xdp_op, xdp_chk; int err; ASSERT_RTNL(); - xdp_op = ops->ndo_xdp; + xdp_op = xdp_chk = ops->ndo_xdp; + if (!xdp_op && (flags & XDP_FLAGS_DRV_MODE)) + return -EOPNOTSUPP; if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE)) xdp_op = generic_xdp_install; + if (xdp_op == xdp_chk) + xdp_chk = generic_xdp_install; if (fd >= 0) { - if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) { - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_QUERY_PROG; - - err = xdp_op(dev, &xdp); - if (err < 0) - return err; - if (xdp.prog_attached) - return -EBUSY; - } + if (xdp_chk && __dev_xdp_attached(dev, xdp_chk)) + return -EEXIST; + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && + __dev_xdp_attached(dev, xdp_op)) + return -EBUSY; prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); if (IS_ERR(prog)) return PTR_ERR(prog); } - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_SETUP_PROG; - xdp.extack = extack; - xdp.prog = prog; - - err = xdp_op(dev, &xdp); + err = dev_xdp_install(dev, xdp_op, extack, prog); if (err < 0 && prog) bpf_prog_put(prog); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 58b0bcc125b5..d274f81fcc2c 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1132,10 +1132,6 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, lladdr = neigh->ha; } - if (new & NUD_CONNECTED) - neigh->confirmed = jiffies; - neigh->updated = jiffies; - /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ @@ -1157,6 +1153,16 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } } + /* Update timestamps only once we know we will make a change to the + * neighbour entry. Otherwise we risk to move the locktime window with + * noop updates and ignore relevant ARP updates. + */ + if (new != old || lladdr != neigh->ha) { + if (new & NUD_CONNECTED) + neigh->confirmed = jiffies; + neigh->updated = jiffies; + } + if (new != old) { neigh_del_timer(neigh); if (new & NUD_PROBE) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bcb0f610ee42..49a279a7cc15 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -899,8 +899,7 @@ static size_t rtnl_port_size(const struct net_device *dev, static size_t rtnl_xdp_size(void) { size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ - nla_total_size(1) + /* XDP_ATTACHED */ - nla_total_size(4); /* XDP_FLAGS */ + nla_total_size(1); /* XDP_ATTACHED */ return xdp_size; } @@ -1247,37 +1246,34 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) return 0; } +static u8 rtnl_xdp_attached_mode(struct net_device *dev) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + ASSERT_RTNL(); + + if (rcu_access_pointer(dev->xdp_prog)) + return XDP_ATTACHED_SKB; + if (ops->ndo_xdp && __dev_xdp_attached(dev, ops->ndo_xdp)) + return XDP_ATTACHED_DRV; + + return XDP_ATTACHED_NONE; +} + static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) { struct nlattr *xdp; - u32 xdp_flags = 0; - u8 val = 0; int err; xdp = nla_nest_start(skb, IFLA_XDP); if (!xdp) return -EMSGSIZE; - if (rcu_access_pointer(dev->xdp_prog)) { - xdp_flags = XDP_FLAGS_SKB_MODE; - val = 1; - } else if (dev->netdev_ops->ndo_xdp) { - struct netdev_xdp xdp_op = {}; - - xdp_op.command = XDP_QUERY_PROG; - err = dev->netdev_ops->ndo_xdp(dev, &xdp_op); - if (err) - goto err_cancel; - val = xdp_op.prog_attached; - } - err = nla_put_u8(skb, IFLA_XDP_ATTACHED, val); + + err = nla_put_u8(skb, IFLA_XDP_ATTACHED, + rtnl_xdp_attached_mode(dev)); if (err) goto err_cancel; - if (xdp_flags) { - err = nla_put_u32(skb, IFLA_XDP_FLAGS, xdp_flags); - if (err) - goto err_cancel; - } nla_nest_end(skb, xdp); return 0; @@ -1631,13 +1627,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, 0, flags, ext_filter_mask); - /* If we ran out of room on the first message, - * we're in trouble - */ - WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); - if (err < 0) - goto out; + if (err < 0) { + if (likely(skb->len)) + goto out; + + goto out_err; + } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: @@ -1645,10 +1641,12 @@ cont: } } out: + err = skb->len; +out_err: cb->args[1] = idx; cb->args[0] = h; - return skb->len; + return err; } int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, @@ -2199,6 +2197,11 @@ static int do_setlink(const struct sk_buff *skb, err = -EINVAL; goto errout; } + if ((xdp_flags & XDP_FLAGS_SKB_MODE) && + (xdp_flags & XDP_FLAGS_DRV_MODE)) { + err = -EINVAL; + goto errout; + } } if (xdp[IFLA_XDP_FD]) { @@ -3452,8 +3455,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) err = br_dev->netdev_ops->ndo_bridge_getlink( skb, portid, seq, dev, filter_mask, NLM_F_MULTI); - if (err < 0 && err != -EOPNOTSUPP) - break; + if (err < 0 && err != -EOPNOTSUPP) { + if (likely(skb->len)) + break; + + goto out_err; + } } idx++; } @@ -3464,16 +3471,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) seq, dev, filter_mask, NLM_F_MULTI); - if (err < 0 && err != -EOPNOTSUPP) - break; + if (err < 0 && err != -EOPNOTSUPP) { + if (likely(skb->len)) + break; + + goto out_err; + } } idx++; } } + err = skb->len; +out_err: rcu_read_unlock(); cb->args[0] = idx; - return skb->len; + return err; } static inline size_t bridge_nlmsg_size(void) diff --git a/net/core/sock.c b/net/core/sock.c index 79c6aee6af9b..727f924b7f91 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,10 +139,7 @@ #include <trace/events/sock.h> -#ifdef CONFIG_INET #include <net/tcp.h> -#endif - #include <net/busy_poll.h> static DEFINE_MUTEX(proto_list_mutex); @@ -1803,28 +1800,24 @@ EXPORT_SYMBOL(skb_set_owner_w); * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. * But we also want to keep skb->sk set because some packet schedulers - * rely on it (sch_fq for example). So we set skb->truesize to a small - * amount (1) and decrease sk_wmem_alloc accordingly. + * rely on it (sch_fq for example). */ void skb_orphan_partial(struct sk_buff *skb) { - /* If this skb is a TCP pure ACK or already went here, - * we have nothing to do. 2 is already a very small truesize. - */ - if (skb->truesize <= 2) + if (skb_is_tcp_pure_ack(skb)) return; - /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, - * so we do not completely orphan skb, but transfert all - * accounted bytes but one, to avoid unexpected reorders. - */ if (skb->destructor == sock_wfree #ifdef CONFIG_INET || skb->destructor == tcp_wfree #endif ) { - atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); - skb->truesize = 1; + struct sock *sk = skb->sk; + + if (atomic_inc_not_zero(&sk->sk_refcnt)) { + atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + skb->destructor = sock_efree; + } } else { skb_orphan(skb); } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 840f14aaa016..992621172220 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -426,6 +426,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, newsk->sk_backlog_rcv = dccp_v4_do_rcv; newnp->pktoptions = NULL; newnp->opt = NULL; + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; @@ -490,6 +493,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 0937b34c27ca..d54345a06f72 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -653,6 +653,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) unsigned char *arp_ptr; struct rtable *rt; unsigned char *sha; + unsigned char *tha = NULL; __be32 sip, tip; u16 dev_type = dev->type; int addr_type; @@ -724,6 +725,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) break; #endif default: + tha = arp_ptr; arp_ptr += dev->addr_len; } memcpy(&tip, arp_ptr, 4); @@ -842,8 +844,18 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) It is possible, that this option should be enabled for some devices (strip is candidate) */ - is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && - addr_type == RTN_UNICAST; + is_garp = tip == sip && addr_type == RTN_UNICAST; + + /* Unsolicited ARP _replies_ also require target hwaddr to be + * the same as source. + */ + if (is_garp && arp->ar_op == htons(ARPOP_REPLY)) + is_garp = + /* IPv4 over IEEE 1394 doesn't provide target + * hardware address field in its ARP payload. + */ + tha && + !memcmp(tha, sha, dev->addr_len); if (!n && ((arp->ar_op == htons(ARPOP_REPLY) && diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 39bd1edee676..83e3ed258467 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -763,7 +763,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; - int dumped = 0; + int dumped = 0, err; if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) @@ -783,20 +783,27 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); - if (fib_table_dump(tb, skb, cb) < 0) - goto out; + err = fib_table_dump(tb, skb, cb); + if (err < 0) { + if (likely(skb->len)) + goto out; + + goto out_err; + } dumped = 1; next: e++; } } out: + err = skb->len; +out_err: rcu_read_unlock(); cb->args[1] = e; cb->args[0] = h; - return skb->len; + return err; } /* Prepare and feed intra-kernel routing request. diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1201409ba1dc..51182ff2b441 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1983,6 +1983,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + int err; + if (i < s_i) { i++; continue; @@ -1993,17 +1995,14 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, continue; } - if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->tb_id, - fa->fa_type, - xkey, - KEYLENGTH - fa->fa_slen, - fa->fa_tos, - fa->fa_info, NLM_F_MULTI) < 0) { + err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE, + tb->tb_id, fa->fa_type, + xkey, KEYLENGTH - fa->fa_slen, + fa->fa_tos, fa->fa_info, NLM_F_MULTI); + if (err < 0) { cb->args[4] = i; - return -1; + return err; } i++; } @@ -2025,10 +2024,13 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, t_key key = cb->args[3]; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) { + int err; + + err = fn_trie_dump_leaf(l, tb, skb, cb); + if (err < 0) { cb->args[3] = key; cb->args[2] = count; - return -1; + return err; } ++count; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3a02d52ed50e..551de4d023a8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1980,6 +1980,20 @@ int ip_mr_input(struct sk_buff *skb) struct net *net = dev_net(skb->dev); int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; struct mr_table *mrt; + struct net_device *dev; + + /* skb->dev passed in is the loX master dev for vrfs. + * As there are no vifs associated with loopback devices, + * get the proper interface that does have a vif associated with it. + */ + dev = skb->dev; + if (netif_is_l3_master(skb->dev)) { + dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); + if (!dev) { + kfree_skb(skb); + return -ENODEV; + } + } /* Packet is looped back after forward, it should not be * forwarded second time, but still can be delivered locally. @@ -2017,7 +2031,7 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); if (!cache) { - int vif = ipmr_find_vif(mrt, skb->dev); + int vif = ipmr_find_vif(mrt, dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, @@ -2037,7 +2051,7 @@ int ip_mr_input(struct sk_buff *skb) } read_lock(&mrt_lock); - vif = ipmr_find_vif(mrt, skb->dev); + vif = ipmr_find_vif(mrt, dev); if (vif >= 0) { int err2 = ipmr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5a3ad09e2786..174d4376baa5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1179,13 +1179,14 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, */ if (pkt_len > mss) { unsigned int new_len = (pkt_len / mss) * mss; - if (!in_sack && new_len < pkt_len) { + if (!in_sack && new_len < pkt_len) new_len += mss; - if (new_len >= skb->len) - return 0; - } pkt_len = new_len; } + + if (pkt_len >= skb->len && !in_sack) + return 0; + err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; @@ -3189,7 +3190,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, int delta; /* Non-retransmitted hole got filled? That's reordering */ - if (reord < prior_fackets) + if (reord < prior_fackets && reord <= tp->fackets_out) tcp_update_reordering(sk, tp->fackets_out - reord, 0); delta = tcp_is_fack(tp) ? pkts_acked : diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ea6e4cff9faf..1d6219bf2d6b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1612,7 +1612,7 @@ static void udp_v4_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash); } -int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1657,7 +1657,7 @@ EXPORT_SYMBOL(udp_encap_enable); * Note that in the success and error cases, the skb is assumed to * have either been requeued or freed. */ -int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index feb50a16398d..a8cf8c6fb60c 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -25,7 +25,6 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udp_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8d297a79b568..6a4fb1e629fb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1022,7 +1022,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; ifa->prefix_len = pfxlen; - ifa->flags = flags | IFA_F_TENTATIVE; + ifa->flags = flags; + /* No need to add the TENTATIVE flag for addresses with NODAD */ + if (!(flags & IFA_F_NODAD)) + ifa->flags |= IFA_F_TENTATIVE; ifa->valid_lft = valid_lft; ifa->prefered_lft = prefered_lft; ifa->cstamp = ifa->tstamp = jiffies; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 93e58a5e1837..280268f1dd7b 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -63,7 +63,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, const struct net_offload *ops; int proto; struct frag_hdr *fptr; - unsigned int unfrag_ip6hlen; unsigned int payload_len; u8 *prevhdr; int offset = 0; @@ -116,8 +115,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, skb->network_header = (u8 *)ipv6h - skb->head; if (udpfrag) { - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); + int err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + return ERR_PTR(err); + fptr = (struct frag_hdr *)((u8 *)ipv6h + err); fptr->frag_off = htons(offset); if (skb->next) fptr->frag_off |= htons(IP6_MF); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 58f6288e9ba5..d4a31becbd25 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -597,7 +597,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; - hlen = ip6_find_1stfragopt(skb, &prevhdr); + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + goto fail; + hlen = err; nexthdr = *prevhdr; mtu = ip6_skb_dst_mtu(skb); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index cd4252346a32..e9065b8d3af8 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -79,14 +79,13 @@ EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; - while (offset + 1 <= packet_len) { + while (offset <= packet_len) { + struct ipv6_opt_hdr *exthdr; switch (**nexthdr) { @@ -107,13 +106,16 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; + if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) + return -EINVAL; + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; } - return offset; + return -EINVAL; } EXPORT_SYMBOL(ip6_find_1stfragopt); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7a8237acd210..4f4310a36a04 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1062,6 +1062,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; @@ -1131,6 +1132,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * First: no IPv4 options. */ newinet->inet_opt = NULL; + newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 04862abfe4ec..06ec39b79609 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -526,7 +526,7 @@ out: return; } -int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -569,7 +569,7 @@ void udpv6_encap_enable(void) } EXPORT_SYMBOL(udpv6_encap_enable); -int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index e78bdc76dcc3..f180b3d85e31 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -26,7 +26,6 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); -int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udpv6_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ac858c480f2f..a2267f80febb 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; + int err; mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) @@ -90,7 +91,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + return ERR_PTR(err); + unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f4001763134d..e3eeed19cc7a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2658,13 +2658,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); } - sockc.tsflags = po->sk.sk_tsflags; - if (msg->msg_controllen) { - err = sock_cmsg_send(&po->sk, msg, &sockc); - if (unlikely(err)) - goto out; - } - err = -ENXIO; if (unlikely(dev == NULL)) goto out; @@ -2672,6 +2665,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; + sockc.tsflags = po->sk.sk_tsflags; + if (msg->msg_controllen) { + err = sock_cmsg_send(&po->sk, msg, &sockc); + if (unlikely(err)) + goto out_put; + } + if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bbe57d57b67f..e88342fde1bc 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1831,6 +1831,12 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, if (!qdisc_dev(root)) return 0; + if (tcm->tcm_parent) { + q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent)); + if (q && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) + return -1; + return 0; + } hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 961ee59f696a..f5b45b8b8b16 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -240,12 +240,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct sctp_bind_addr *bp; struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; - union sctp_addr *baddr = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; struct in6_addr *final_p, final; __u8 matchlen = 0; - __u8 bmatchlen; sctp_scope_t scope; memset(fl6, 0, sizeof(struct flowi6)); @@ -312,23 +310,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid) + struct dst_entry *bdst; + __u8 bmatchlen; + + if (!laddr->valid || + laddr->state != SCTP_ADDR_SRC || + laddr->a.sa.sa_family != AF_INET6 || + scope > sctp_scope(&laddr->a)) continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (laddr->a.sa.sa_family == AF_INET6) && - (scope <= sctp_scope(&laddr->a))) { - bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); - if (!baddr || (matchlen < bmatchlen)) { - baddr = &laddr->a; - matchlen = bmatchlen; - } - } - } - if (baddr) { - fl6->saddr = baddr->v6.sin6_addr; - fl6->fl6_sport = baddr->v6.sin6_port; + + fl6->saddr = laddr->a.v6.sin6_addr; + fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + + if (!IS_ERR(bdst) && + ipv6_chk_addr(dev_net(bdst->dev), + &laddr->a.v6.sin6_addr, bdst->dev, 1)) { + if (!IS_ERR_OR_NULL(dst)) + dst_release(dst); + dst = bdst; + break; + } + + bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); + if (matchlen > bmatchlen) + continue; + + if (!IS_ERR_OR_NULL(dst)) + dst_release(dst); + dst = bdst; + matchlen = bmatchlen; } rcu_read_unlock(); @@ -665,6 +677,9 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; rcu_read_lock(); opt = rcu_dereference(np->opt); diff --git a/net/smc/Kconfig b/net/smc/Kconfig index c717ef0896aa..33954852f3f8 100644 --- a/net/smc/Kconfig +++ b/net/smc/Kconfig @@ -8,6 +8,10 @@ config SMC The Linux implementation of the SMC-R solution is designed as a separate socket family SMC. + Warning: SMC will expose all memory for remote reads and writes + once a connection is established. Don't enable this option except + for tightly controlled lab environment. + Select this option if you want to run SMC socket applications config SMC_DIAG diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index e41f594a1e1d..03ec058d18df 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -204,7 +204,7 @@ int smc_clc_send_confirm(struct smc_sock *smc) memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN); hton24(cclc.qpn, link->roce_qp->qp_num); cclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); + htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]); cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */ cclc.rmbe_alert_token = htonl(conn->alert_token_local); cclc.qp_mtu = min(link->path_mtu, link->peer_mtu); @@ -256,7 +256,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact) memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN); hton24(aclc.qpn, link->roce_qp->qp_num); aclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); + htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]); aclc.conn_idx = 1; /* as long as 1 RMB = 1 RMBE */ aclc.rmbe_alert_token = htonl(conn->alert_token_local); aclc.qp_mtu = link->path_mtu; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 65020e93ff21..3ac09a629ea1 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -613,19 +613,8 @@ int smc_rmb_create(struct smc_sock *smc) rmb_desc = NULL; continue; /* if mapping failed, try smaller one */ } - rc = smc_ib_get_memory_region(lgr->lnk[SMC_SINGLE_LINK].roce_pd, - IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_LOCAL_WRITE, - &rmb_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) { - smc_ib_buf_unmap(lgr->lnk[SMC_SINGLE_LINK].smcibdev, - tmp_bufsize, rmb_desc, - DMA_FROM_DEVICE); - kfree(rmb_desc->cpu_addr); - kfree(rmb_desc); - rmb_desc = NULL; - continue; - } + rmb_desc->rkey[SMC_SINGLE_LINK] = + lgr->lnk[SMC_SINGLE_LINK].roce_pd->unsafe_global_rkey; rmb_desc->used = 1; write_lock_bh(&lgr->rmbs_lock); list_add(&rmb_desc->list, @@ -668,6 +657,7 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn, for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) && + (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) && test_bit(i, lgr->rtokens_used_mask)) { conn->rtoken_idx = i; return 0; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 27eb38056a27..b013cb43a327 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -93,7 +93,7 @@ struct smc_buf_desc { u64 dma_addr[SMC_LINKS_PER_LGR_MAX]; /* mapped address of buffer */ void *cpu_addr; /* virtual address of buffer */ - struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; + u32 rkey[SMC_LINKS_PER_LGR_MAX]; /* for rmb only: * rkey provided to peer */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index cb69ab977cd7..b31715505a35 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -37,24 +37,6 @@ u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET; /* unique system * identifier */ -int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags, - struct ib_mr **mr) -{ - int rc; - - if (*mr) - return 0; /* already done */ - - /* obtain unique key - - * next invocation of get_dma_mr returns a different key! - */ - *mr = pd->device->get_dma_mr(pd, access_flags); - rc = PTR_ERR_OR_ZERO(*mr); - if (IS_ERR(*mr)) - *mr = NULL; - return rc; -} - static int smc_ib_modify_qp_init(struct smc_link *lnk) { struct ib_qp_attr qp_attr; @@ -210,7 +192,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) { int rc; - lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0); + lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, + IB_PD_UNSAFE_GLOBAL_RKEY); rc = PTR_ERR_OR_ZERO(lnk->roce_pd); if (IS_ERR(lnk->roce_pd)) lnk->roce_pd = NULL; diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 7e1f0e24d177..b567152a526d 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -61,8 +61,6 @@ void smc_ib_dealloc_protection_domain(struct smc_link *lnk); int smc_ib_create_protection_domain(struct smc_link *lnk); void smc_ib_destroy_queue_pair(struct smc_link *lnk); int smc_ib_create_queue_pair(struct smc_link *lnk); -int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags, - struct ib_mr **mr); int smc_ib_ready_link(struct smc_link *lnk); int smc_ib_modify_qp_rts(struct smc_link *lnk); int smc_ib_modify_qp_reset(struct smc_link *lnk); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 0d4f2f455a7c..1b92b72e812f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -362,25 +362,25 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) return 0; } -#define tipc_wait_for_cond(sock_, timeout_, condition_) \ -({ \ - int rc_ = 0; \ - int done_ = 0; \ - \ - while (!(condition_) && !done_) { \ - struct sock *sk_ = sock->sk; \ - DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ - \ - rc_ = tipc_sk_sock_err(sock_, timeout_); \ - if (rc_) \ - break; \ - prepare_to_wait(sk_sleep(sk_), &wait_, \ - TASK_INTERRUPTIBLE); \ - done_ = sk_wait_event(sk_, timeout_, \ - (condition_), &wait_); \ - remove_wait_queue(sk_sleep(sk_), &wait_); \ - } \ - rc_; \ +#define tipc_wait_for_cond(sock_, timeo_, condition_) \ +({ \ + struct sock *sk_; \ + int rc_; \ + \ + while ((rc_ = !(condition_))) { \ + DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ + sk_ = (sock_)->sk; \ + rc_ = tipc_sk_sock_err((sock_), timeo_); \ + if (rc_) \ + break; \ + prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \ + release_sock(sk_); \ + *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \ + sched_annotate_sleep(); \ + lock_sock(sk_); \ + remove_wait_queue(sk_sleep(sk_), &wait_); \ + } \ + rc_; \ }) /** diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 8b911c29860e..5a1a98df3499 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1791,32 +1791,40 @@ void x25_kill_by_neigh(struct x25_neigh *nb) static int __init x25_init(void) { - int rc = proto_register(&x25_proto, 0); + int rc; - if (rc != 0) + rc = proto_register(&x25_proto, 0); + if (rc) goto out; rc = sock_register(&x25_family_ops); - if (rc != 0) + if (rc) goto out_proto; dev_add_pack(&x25_packet_type); rc = register_netdevice_notifier(&x25_dev_notifier); - if (rc != 0) + if (rc) goto out_sock; - pr_info("Linux Version 0.2\n"); + rc = x25_register_sysctl(); + if (rc) + goto out_dev; - x25_register_sysctl(); rc = x25_proc_init(); - if (rc != 0) - goto out_dev; + if (rc) + goto out_sysctl; + + pr_info("Linux Version 0.2\n"); + out: return rc; +out_sysctl: + x25_unregister_sysctl(); out_dev: unregister_netdevice_notifier(&x25_dev_notifier); out_sock: + dev_remove_pack(&x25_packet_type); sock_unregister(AF_X25); out_proto: proto_unregister(&x25_proto); diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c index a06dfe143c67..ba078c85f0a1 100644 --- a/net/x25/sysctl_net_x25.c +++ b/net/x25/sysctl_net_x25.c @@ -73,9 +73,12 @@ static struct ctl_table x25_table[] = { { }, }; -void __init x25_register_sysctl(void) +int __init x25_register_sysctl(void) { x25_table_header = register_net_sysctl(&init_net, "net/x25", x25_table); + if (!x25_table_header) + return -ENOMEM; + return 0; } void x25_unregister_sysctl(void) diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c index b08ab4e88929..9d751e209f31 100644 --- a/samples/bpf/cookie_uid_helper_example.c +++ b/samples/bpf/cookie_uid_helper_example.c @@ -306,7 +306,9 @@ int main(int argc, char *argv[]) prog_attach_iptables(argv[2]); if (cfg_test_traffic) { if (signal(SIGINT, finish) == SIG_ERR) - error(1, errno, "register handler failed"); + error(1, errno, "register SIGINT handler failed"); + if (signal(SIGTERM, finish) == SIG_ERR) + error(1, errno, "register SIGTERM handler failed"); while (!test_finish) { print_table(); printf("\n"); diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 9cce2a66bd66..512f87a5fd20 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -100,6 +100,7 @@ int main(int argc, char **argv) setrlimit(RLIMIT_MEMLOCK, &r); signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c index be59d7dcbdde..4ed690b907ff 100644 --- a/samples/bpf/sampleip_user.c +++ b/samples/bpf/sampleip_user.c @@ -180,6 +180,7 @@ int main(int argc, char **argv) return 1; } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); /* do sampling */ printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n", diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 0c5561d193a4..fa4336423da5 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -192,6 +192,7 @@ int main(int argc, char **argv) setrlimit(RLIMIT_MEMLOCK, &r); signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 7fee0f1ba9a3..7321a3f253c9 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -127,6 +127,7 @@ int main(int ac, char **argv) } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); /* start 'ping' in the background to have some kfree_skb events */ f = popen("ping -c5 localhost", "r"); diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index 378850c70eb8..2431c0321b71 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -62,13 +62,14 @@ static void usage(const char *prog) fprintf(stderr, "usage: %s [OPTS] IFINDEX\n\n" "OPTS:\n" - " -S use skb-mode\n", + " -S use skb-mode\n" + " -N enforce native mode\n", prog); } int main(int argc, char **argv) { - const char *optstr = "S"; + const char *optstr = "SN"; char filename[256]; int opt; @@ -77,6 +78,9 @@ int main(int argc, char **argv) case 'S': xdp_flags |= XDP_FLAGS_SKB_MODE; break; + case 'N': + xdp_flags |= XDP_FLAGS_DRV_MODE; + break; default: usage(basename(argv[0])); return 1; @@ -102,6 +106,7 @@ int main(int argc, char **argv) } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { printf("link set xdp fd failed\n"); diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index 92b8bde9337c..715cd12eaca5 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -79,6 +79,8 @@ static void usage(const char *cmd) printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt\n"); printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n"); printf(" -P <IP-Protocol> Default is TCP\n"); + printf(" -S use skb-mode\n"); + printf(" -N enforce native mode\n"); printf(" -h Display this help\n"); } @@ -138,7 +140,7 @@ int main(int argc, char **argv) { unsigned char opt_flags[256] = {}; unsigned int kill_after_s = 0; - const char *optstr = "i:a:p:s:d:m:T:P:Sh"; + const char *optstr = "i:a:p:s:d:m:T:P:SNh"; int min_port = 0, max_port = 0; struct iptnl_info tnl = {}; struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; @@ -206,6 +208,9 @@ int main(int argc, char **argv) case 'S': xdp_flags |= XDP_FLAGS_SKB_MODE; break; + case 'N': + xdp_flags |= XDP_FLAGS_DRV_MODE; + break; default: usage(argv[0]); return 1; @@ -239,6 +244,7 @@ int main(int argc, char **argv) } signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); while (min_port <= max_port) { vip.dport = htons(min_port++); diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index 6ba97a1f9c5a..ce753a408c56 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -8,6 +8,29 @@ # # ========================================================================== +PHONY := __headers +__headers: + +include scripts/Kbuild.include + +srcdir := $(srctree)/$(obj) +subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.)) +# caller may set destination dir (when installing to asm/) +_dst := $(if $(dst),$(dst),$(obj)) + +# Recursion +__headers: $(subdirs) + +.PHONY: $(subdirs) +$(subdirs): + $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@ + +# Skip header install/check for include/uapi and arch/$(hdr-arch)/include/uapi. +# We have only sub-directories there. +skip-inst := $(if $(filter %/uapi,$(obj)),1) + +ifeq ($(skip-inst),) + # generated header directory gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj))) @@ -15,21 +38,14 @@ gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj))) kbuild-file := $(srctree)/$(obj)/Kbuild -include $(kbuild-file) -# called may set destination dir (when installing to asm/) -_dst := $(if $(dst),$(dst),$(obj)) - old-kbuild-file := $(srctree)/$(subst uapi/,,$(obj))/Kbuild ifneq ($(wildcard $(old-kbuild-file)),) include $(old-kbuild-file) endif -include scripts/Kbuild.include - installdir := $(INSTALL_HDR_PATH)/$(subst uapi/,,$(_dst)) -srcdir := $(srctree)/$(obj) gendir := $(objtree)/$(gen) -subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.)) header-files := $(notdir $(wildcard $(srcdir)/*.h)) header-files += $(notdir $(wildcard $(srcdir)/*.agh)) header-files := $(filter-out $(no-export-headers), $(header-files)) @@ -88,11 +104,9 @@ quiet_cmd_check = CHECK $(printdir) ($(words $(all-files)) files) $(PERL) $< $(INSTALL_HDR_PATH)/include $(SRCARCH); \ touch $@ -PHONY += __headersinst __headerscheck - ifndef HDRCHECK # Rules for installing headers -__headersinst: $(subdirs) $(install-file) +__headers: $(install-file) @: targets += $(install-file) @@ -104,7 +118,7 @@ $(install-file): scripts/headers_install.sh \ $(call if_changed,install) else -__headerscheck: $(subdirs) $(check-file) +__headers: $(check-file) @: targets += $(check-file) @@ -113,11 +127,6 @@ $(check-file): scripts/headers_check.pl $(output-files) FORCE endif -# Recursion -.PHONY: $(subdirs) -$(subdirs): - $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@ - targets := $(wildcard $(sort $(targets))) cmd_files := $(wildcard \ $(foreach f,$(targets),$(dir $(f)).$(notdir $(f)).cmd)) @@ -126,6 +135,8 @@ ifneq ($(cmd_files),) include $(cmd_files) endif +endif # skip-inst + .PHONY: $(PHONY) PHONY += FORCE FORCE: ; diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 6dc1eda13b8e..58c05e5d9870 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -175,7 +175,7 @@ ld_flags = $(LDFLAGS) $(ldflags-y) dtc_cpp_flags = -Wp,-MD,$(depfile).pre.tmp -nostdinc \ -I$(srctree)/arch/$(SRCARCH)/boot/dts \ - -I$(srctree)/arch/$(SRCARCH)/boot/dts/include \ + -I$(srctree)/scripts/dtc/include-prefixes \ -I$(srctree)/drivers/of/testcase-data \ -undef -D__DTS__ diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c index 5adfc8f52b4f..4b72b530c84f 100644 --- a/scripts/dtc/checks.c +++ b/scripts/dtc/checks.c @@ -873,7 +873,7 @@ static void check_simple_bus_reg(struct check *c, struct dt_info *dti, struct no while (size--) reg = (reg << 32) | fdt32_to_cpu(*(cells++)); - snprintf(unit_addr, sizeof(unit_addr), "%lx", reg); + snprintf(unit_addr, sizeof(unit_addr), "%zx", reg); if (!streq(unitname, unit_addr)) FAIL(c, dti, "Node %s simple-bus unit address format error, expected \"%s\"", node->fullpath, unit_addr); diff --git a/scripts/dtc/include-prefixes/arc b/scripts/dtc/include-prefixes/arc new file mode 120000 index 000000000000..5d21b5a69a11 --- /dev/null +++ b/scripts/dtc/include-prefixes/arc @@ -0,0 +1 @@ +../../../arch/arc/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/arm b/scripts/dtc/include-prefixes/arm new file mode 120000 index 000000000000..eb14d4515a57 --- /dev/null +++ b/scripts/dtc/include-prefixes/arm @@ -0,0 +1 @@ +../../../arch/arm/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/arm64 b/scripts/dtc/include-prefixes/arm64 new file mode 120000 index 000000000000..275c42c21d71 --- /dev/null +++ b/scripts/dtc/include-prefixes/arm64 @@ -0,0 +1 @@ +../../../arch/arm64/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/c6x b/scripts/dtc/include-prefixes/c6x new file mode 120000 index 000000000000..49ded4cae2be --- /dev/null +++ b/scripts/dtc/include-prefixes/c6x @@ -0,0 +1 @@ +../../../arch/c6x/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/cris b/scripts/dtc/include-prefixes/cris new file mode 120000 index 000000000000..736d998ba506 --- /dev/null +++ b/scripts/dtc/include-prefixes/cris @@ -0,0 +1 @@ +../../../arch/cris/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/dt-bindings b/scripts/dtc/include-prefixes/dt-bindings new file mode 120000 index 000000000000..04fdbb3af016 --- /dev/null +++ b/scripts/dtc/include-prefixes/dt-bindings @@ -0,0 +1 @@ +../../../include/dt-bindings
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/h8300 b/scripts/dtc/include-prefixes/h8300 new file mode 120000 index 000000000000..3bdaa332c54c --- /dev/null +++ b/scripts/dtc/include-prefixes/h8300 @@ -0,0 +1 @@ +../../../arch/h8300/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/metag b/scripts/dtc/include-prefixes/metag new file mode 120000 index 000000000000..87a3c847db8f --- /dev/null +++ b/scripts/dtc/include-prefixes/metag @@ -0,0 +1 @@ +../../../arch/metag/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/microblaze b/scripts/dtc/include-prefixes/microblaze new file mode 120000 index 000000000000..d9830330a21d --- /dev/null +++ b/scripts/dtc/include-prefixes/microblaze @@ -0,0 +1 @@ +../../../arch/microblaze/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/mips b/scripts/dtc/include-prefixes/mips new file mode 120000 index 000000000000..ae8d4948dc8d --- /dev/null +++ b/scripts/dtc/include-prefixes/mips @@ -0,0 +1 @@ +../../../arch/mips/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/nios2 b/scripts/dtc/include-prefixes/nios2 new file mode 120000 index 000000000000..51772336d13f --- /dev/null +++ b/scripts/dtc/include-prefixes/nios2 @@ -0,0 +1 @@ +../../../arch/nios2/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/openrisc b/scripts/dtc/include-prefixes/openrisc new file mode 120000 index 000000000000..71c3bc75c560 --- /dev/null +++ b/scripts/dtc/include-prefixes/openrisc @@ -0,0 +1 @@ +../../../arch/openrisc/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/powerpc b/scripts/dtc/include-prefixes/powerpc new file mode 120000 index 000000000000..7cd6ec16e899 --- /dev/null +++ b/scripts/dtc/include-prefixes/powerpc @@ -0,0 +1 @@ +../../../arch/powerpc/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/sh b/scripts/dtc/include-prefixes/sh new file mode 120000 index 000000000000..67d37808c599 --- /dev/null +++ b/scripts/dtc/include-prefixes/sh @@ -0,0 +1 @@ +../../../arch/sh/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/xtensa b/scripts/dtc/include-prefixes/xtensa new file mode 120000 index 000000000000..d1eaf6ec7a2b --- /dev/null +++ b/scripts/dtc/include-prefixes/xtensa @@ -0,0 +1 @@ +../../../arch/xtensa/boot/dts
\ No newline at end of file diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index 664b7fe206d6..b11d3920b9a5 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -1809,10 +1809,6 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) pdata->notify_pending = false; spin_unlock_irq(&pdata->lpe_audio_slock); - /* runtime PM isn't enabled as default, since it won't save much on - * BYT/CHT devices; user who want the runtime PM should adjust the - * power/ontrol and power/autosuspend_delay_ms sysfs entries instead - */ pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_mark_last_busy(&pdev->dev); pm_runtime_set_active(&pdev->dev); diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index ebc6dceddb58..7598361ef1f1 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -29,6 +29,7 @@ int main(void) attr.log_size = 0; attr.log_level = 0; attr.kern_version = 0; + attr.prog_flags = 0; /* * Test existence of __NR_bpf and BPF_PROG_LOAD. diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e553529929f6..94dfa9def355 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -132,6 +132,13 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ @@ -177,6 +184,7 @@ union bpf_attr { __u32 log_size; /* size of user buffer */ __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ + __u32 prog_flags; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -481,8 +489,7 @@ union bpf_attr { * u32 bpf_get_socket_uid(skb) * Get the owner uid of the socket stored inside sk_buff. * @skb: pointer to skb - * Return: uid of the socket owner on success or 0 if the socket pointer - * inside sk_buff is NULL + * Return: uid of the socket owner on success or overflowuid if failed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 8f74ed8e7237..dd8f00cfb8b4 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -295,114 +295,6 @@ class ArchS390(Arch): ARCH = Arch.get_arch() -def walkdir(path): - """Returns os.walk() data for specified directory. - - As it is only a wrapper it returns the same 3-tuple of (dirpath, - dirnames, filenames). - """ - return next(os.walk(path)) - - -def parse_int_list(list_string): - """Returns an int list from a string of comma separated integers and - integer ranges.""" - integers = [] - members = list_string.split(',') - - for member in members: - if '-' not in member: - integers.append(int(member)) - else: - int_range = member.split('-') - integers.extend(range(int(int_range[0]), - int(int_range[1]) + 1)) - - return integers - - -def get_pid_from_gname(gname): - """Fuzzy function to convert guest name to QEMU process pid. - - Returns a list of potential pids, can be empty if no match found. - Throws an exception on processing errors. - - """ - pids = [] - try: - child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'], - stdout=subprocess.PIPE) - except: - raise Exception - for line in child.stdout: - line = line.lstrip().split(' ', 1) - # perform a sanity check before calling the more expensive - # function to possibly extract the guest name - if ' -name ' in line[1] and gname == get_gname_from_pid(line[0]): - pids.append(int(line[0])) - child.stdout.close() - - return pids - - -def get_gname_from_pid(pid): - """Returns the guest name for a QEMU process pid. - - Extracts the guest name from the QEMU comma line by processing the '-name' - option. Will also handle names specified out of sequence. - - """ - name = '' - try: - line = open('/proc/{}/cmdline'.format(pid), 'rb').read().split('\0') - parms = line[line.index('-name') + 1].split(',') - while '' in parms: - # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results in - # ['foo', '', 'bar'], which we revert here - idx = parms.index('') - parms[idx - 1] += ',' + parms[idx + 1] - del parms[idx:idx+2] - # the '-name' switch allows for two ways to specify the guest name, - # where the plain name overrides the name specified via 'guest=' - for arg in parms: - if '=' not in arg: - name = arg - break - if arg[:6] == 'guest=': - name = arg[6:] - except (ValueError, IOError, IndexError): - pass - - return name - - -def get_online_cpus(): - """Returns a list of cpu id integers.""" - with open('/sys/devices/system/cpu/online') as cpu_list: - cpu_string = cpu_list.readline() - return parse_int_list(cpu_string) - - -def get_filters(): - """Returns a dict of trace events, their filter ids and - the values that can be filtered. - - Trace events can be filtered for special values by setting a - filter string via an ioctl. The string normally has the format - identifier==value. For each filter a new event will be created, to - be able to distinguish the events. - - """ - filters = {} - filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS) - if ARCH.exit_reasons: - filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) - return filters - -libc = ctypes.CDLL('libc.so.6', use_errno=True) -syscall = libc.syscall - - class perf_event_attr(ctypes.Structure): """Struct that holds the necessary data to set up a trace event. @@ -432,25 +324,6 @@ class perf_event_attr(ctypes.Structure): self.read_format = PERF_FORMAT_GROUP -def perf_event_open(attr, pid, cpu, group_fd, flags): - """Wrapper for the sys_perf_evt_open() syscall. - - Used to set up performance events, returns a file descriptor or -1 - on error. - - Attributes are: - - syscall number - - struct perf_event_attr * - - pid or -1 to monitor all pids - - cpu number or -1 to monitor all cpus - - The file descriptor of the group leader or -1 to create a group. - - flags - - """ - return syscall(ARCH.sc_perf_evt_open, ctypes.pointer(attr), - ctypes.c_int(pid), ctypes.c_int(cpu), - ctypes.c_int(group_fd), ctypes.c_long(flags)) - PERF_TYPE_TRACEPOINT = 2 PERF_FORMAT_GROUP = 1 << 3 @@ -495,6 +368,8 @@ class Event(object): """Represents a performance event and manages its life cycle.""" def __init__(self, name, group, trace_cpu, trace_pid, trace_point, trace_filter, trace_set='kvm'): + self.libc = ctypes.CDLL('libc.so.6', use_errno=True) + self.syscall = self.libc.syscall self.name = name self.fd = None self.setup_event(group, trace_cpu, trace_pid, trace_point, @@ -511,6 +386,25 @@ class Event(object): if self.fd: os.close(self.fd) + def perf_event_open(self, attr, pid, cpu, group_fd, flags): + """Wrapper for the sys_perf_evt_open() syscall. + + Used to set up performance events, returns a file descriptor or -1 + on error. + + Attributes are: + - syscall number + - struct perf_event_attr * + - pid or -1 to monitor all pids + - cpu number or -1 to monitor all cpus + - The file descriptor of the group leader or -1 to create a group. + - flags + + """ + return self.syscall(ARCH.sc_perf_evt_open, ctypes.pointer(attr), + ctypes.c_int(pid), ctypes.c_int(cpu), + ctypes.c_int(group_fd), ctypes.c_long(flags)) + def setup_event_attribute(self, trace_set, trace_point): """Returns an initialized ctype perf_event_attr struct.""" @@ -539,8 +433,8 @@ class Event(object): if group.events: group_leader = group.events[0].fd - fd = perf_event_open(event_attr, trace_pid, - trace_cpu, group_leader, 0) + fd = self.perf_event_open(event_attr, trace_pid, + trace_cpu, group_leader, 0) if fd == -1: err = ctypes.get_errno() raise OSError(err, os.strerror(err), @@ -575,17 +469,53 @@ class Event(object): fcntl.ioctl(self.fd, ARCH.ioctl_numbers['RESET'], 0) -class TracepointProvider(object): +class Provider(object): + """Encapsulates functionalities used by all providers.""" + @staticmethod + def is_field_wanted(fields_filter, field): + """Indicate whether field is valid according to fields_filter.""" + if not fields_filter: + return True + return re.match(fields_filter, field) is not None + + @staticmethod + def walkdir(path): + """Returns os.walk() data for specified directory. + + As it is only a wrapper it returns the same 3-tuple of (dirpath, + dirnames, filenames). + """ + return next(os.walk(path)) + + +class TracepointProvider(Provider): """Data provider for the stats class. Manages the events/groups from which it acquires its data. """ - def __init__(self): + def __init__(self, pid, fields_filter): self.group_leaders = [] - self.filters = get_filters() - self._fields = self.get_available_fields() - self._pid = 0 + self.filters = self.get_filters() + self.update_fields(fields_filter) + self.pid = pid + + @staticmethod + def get_filters(): + """Returns a dict of trace events, their filter ids and + the values that can be filtered. + + Trace events can be filtered for special values by setting a + filter string via an ioctl. The string normally has the format + identifier==value. For each filter a new event will be created, to + be able to distinguish the events. + + """ + filters = {} + filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS) + if ARCH.exit_reasons: + filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) + return filters def get_available_fields(self): """Returns a list of available event's of format 'event name(filter @@ -603,7 +533,7 @@ class TracepointProvider(object): """ path = os.path.join(PATH_DEBUGFS_TRACING, 'events', 'kvm') - fields = walkdir(path)[1] + fields = self.walkdir(path)[1] extra = [] for field in fields: if field in self.filters: @@ -613,6 +543,34 @@ class TracepointProvider(object): fields += extra return fields + def update_fields(self, fields_filter): + """Refresh fields, applying fields_filter""" + self._fields = [field for field in self.get_available_fields() + if self.is_field_wanted(fields_filter, field)] + + @staticmethod + def get_online_cpus(): + """Returns a list of cpu id integers.""" + def parse_int_list(list_string): + """Returns an int list from a string of comma separated integers and + integer ranges.""" + integers = [] + members = list_string.split(',') + + for member in members: + if '-' not in member: + integers.append(int(member)) + else: + int_range = member.split('-') + integers.extend(range(int(int_range[0]), + int(int_range[1]) + 1)) + + return integers + + with open('/sys/devices/system/cpu/online') as cpu_list: + cpu_string = cpu_list.readline() + return parse_int_list(cpu_string) + def setup_traces(self): """Creates all event and group objects needed to be able to retrieve data.""" @@ -621,9 +579,9 @@ class TracepointProvider(object): # Fetch list of all threads of the monitored pid, as qemu # starts a thread for each vcpu. path = os.path.join('/proc', str(self._pid), 'task') - groupids = walkdir(path)[1] + groupids = self.walkdir(path)[1] else: - groupids = get_online_cpus() + groupids = self.get_online_cpus() # The constant is needed as a buffer for python libs, std # streams and other files that the script opens. @@ -671,9 +629,6 @@ class TracepointProvider(object): self.group_leaders.append(group) - def available_fields(self): - return self.get_available_fields() - @property def fields(self): return self._fields @@ -707,7 +662,7 @@ class TracepointProvider(object): self.setup_traces() self.fields = self._fields - def read(self): + def read(self, by_guest=0): """Returns 'event name: current value' for all enabled events.""" ret = defaultdict(int) for group in self.group_leaders: @@ -723,16 +678,17 @@ class TracepointProvider(object): event.reset() -class DebugfsProvider(object): +class DebugfsProvider(Provider): """Provides data from the files that KVM creates in the kvm debugfs folder.""" - def __init__(self): - self._fields = self.get_available_fields() + def __init__(self, pid, fields_filter, include_past): + self.update_fields(fields_filter) self._baseline = {} - self._pid = 0 self.do_read = True self.paths = [] - self.reset() + self.pid = pid + if include_past: + self.restore() def get_available_fields(self): """"Returns a list of available fields. @@ -740,7 +696,12 @@ class DebugfsProvider(object): The fields are all available KVM debugfs files """ - return walkdir(PATH_DEBUGFS_KVM)[2] + return self.walkdir(PATH_DEBUGFS_KVM)[2] + + def update_fields(self, fields_filter): + """Refresh fields, applying fields_filter""" + self._fields = [field for field in self.get_available_fields() + if self.is_field_wanted(fields_filter, field)] @property def fields(self): @@ -757,10 +718,9 @@ class DebugfsProvider(object): @pid.setter def pid(self, pid): + self._pid = pid if pid != 0: - self._pid = pid - - vms = walkdir(PATH_DEBUGFS_KVM)[1] + vms = self.walkdir(PATH_DEBUGFS_KVM)[1] if len(vms) == 0: self.do_read = False @@ -771,8 +731,15 @@ class DebugfsProvider(object): self.do_read = True self.reset() - def read(self, reset=0): - """Returns a dict with format:'file name / field -> current value'.""" + def read(self, reset=0, by_guest=0): + """Returns a dict with format:'file name / field -> current value'. + + Parameter 'reset': + 0 plain read + 1 reset field counts to 0 + 2 restore the original field counts + + """ results = {} # If no debugfs filtering support is available, then don't read. @@ -789,12 +756,22 @@ class DebugfsProvider(object): for field in self._fields: value = self.read_field(field, path) key = path + field - if reset: + if reset == 1: self._baseline[key] = value + if reset == 2: + self._baseline[key] = 0 if self._baseline.get(key, -1) == -1: self._baseline[key] = value - results[field] = (results.get(field, 0) + value - - self._baseline.get(key, 0)) + increment = (results.get(field, 0) + value - + self._baseline.get(key, 0)) + if by_guest: + pid = key.split('-')[0] + if pid in results: + results[pid] += increment + else: + results[pid] = increment + else: + results[field] = increment return results @@ -813,6 +790,11 @@ class DebugfsProvider(object): self._baseline = {} self.read(1) + def restore(self): + """Reset field counters""" + self._baseline = {} + self.read(2) + class Stats(object): """Manages the data providers and the data they provide. @@ -821,33 +803,32 @@ class Stats(object): provider data. """ - def __init__(self, providers, pid, fields=None): - self.providers = providers - self._pid_filter = pid - self._fields_filter = fields + def __init__(self, options): + self.providers = self.get_providers(options) + self._pid_filter = options.pid + self._fields_filter = options.fields self.values = {} - self.update_provider_pid() - self.update_provider_filters() + + @staticmethod + def get_providers(options): + """Returns a list of data providers depending on the passed options.""" + providers = [] + + if options.debugfs: + providers.append(DebugfsProvider(options.pid, options.fields, + options.dbgfs_include_past)) + if options.tracepoints or not providers: + providers.append(TracepointProvider(options.pid, options.fields)) + + return providers def update_provider_filters(self): """Propagates fields filters to providers.""" - def wanted(key): - if not self._fields_filter: - return True - return re.match(self._fields_filter, key) is not None - # As we reset the counters when updating the fields we can # also clear the cache of old values. self.values = {} for provider in self.providers: - provider_fields = [key for key in provider.get_available_fields() - if wanted(key)] - provider.fields = provider_fields - - def update_provider_pid(self): - """Propagates pid filters to providers.""" - for provider in self.providers: - provider.pid = self._pid_filter + provider.update_fields(self._fields_filter) def reset(self): self.values = {} @@ -873,27 +854,52 @@ class Stats(object): if pid != self._pid_filter: self._pid_filter = pid self.values = {} - self.update_provider_pid() + for provider in self.providers: + provider.pid = self._pid_filter - def get(self): + def get(self, by_guest=0): """Returns a dict with field -> (value, delta to last value) of all provider data.""" for provider in self.providers: - new = provider.read() - for key in provider.fields: + new = provider.read(by_guest=by_guest) + for key in new if by_guest else provider.fields: oldval = self.values.get(key, (0, 0))[0] newval = new.get(key, 0) newdelta = newval - oldval self.values[key] = (newval, newdelta) return self.values -LABEL_WIDTH = 40 -NUMBER_WIDTH = 10 -DELAY_INITIAL = 0.25 -DELAY_REGULAR = 3.0 + def toggle_display_guests(self, to_pid): + """Toggle between collection of stats by individual event and by + guest pid + + Events reported by DebugfsProvider change when switching to/from + reading by guest values. Hence we have to remove the excess event + names from self.values. + + """ + if any(isinstance(ins, TracepointProvider) for ins in self.providers): + return 1 + if to_pid: + for provider in self.providers: + if isinstance(provider, DebugfsProvider): + for key in provider.fields: + if key in self.values.keys(): + del self.values[key] + else: + oldvals = self.values.copy() + for key in oldvals: + if key.isdigit(): + del self.values[key] + # Update oldval (see get()) + self.get(to_pid) + return 0 + +DELAY_DEFAULT = 3.0 MAX_GUEST_NAME_LEN = 48 MAX_REGEX_LEN = 44 DEFAULT_REGEX = r'^[^\(]*$' +SORT_DEFAULT = 0 class Tui(object): @@ -901,7 +907,10 @@ class Tui(object): def __init__(self, stats): self.stats = stats self.screen = None - self.update_drilldown() + self._delay_initial = 0.25 + self._delay_regular = DELAY_DEFAULT + self._sorting = SORT_DEFAULT + self._display_guests = 0 def __enter__(self): """Initialises curses for later use. Based on curses.wrapper @@ -929,7 +938,7 @@ class Tui(object): return self def __exit__(self, *exception): - """Resets the terminal to its normal state. Based on curses.wrappre + """Resets the terminal to its normal state. Based on curses.wrapper implementation from the Python standard library.""" if self.screen: self.screen.keypad(0) @@ -937,6 +946,86 @@ class Tui(object): curses.nocbreak() curses.endwin() + def get_all_gnames(self): + """Returns a list of (pid, gname) tuples of all running guests""" + res = [] + try: + child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'], + stdout=subprocess.PIPE) + except: + raise Exception + for line in child.stdout: + line = line.lstrip().split(' ', 1) + # perform a sanity check before calling the more expensive + # function to possibly extract the guest name + if ' -name ' in line[1]: + res.append((line[0], self.get_gname_from_pid(line[0]))) + child.stdout.close() + + return res + + def print_all_gnames(self, row): + """Print a list of all running guests along with their pids.""" + self.screen.addstr(row, 2, '%8s %-60s' % + ('Pid', 'Guest Name (fuzzy list, might be ' + 'inaccurate!)'), + curses.A_UNDERLINE) + row += 1 + try: + for line in self.get_all_gnames(): + self.screen.addstr(row, 2, '%8s %-60s' % (line[0], line[1])) + row += 1 + if row >= self.screen.getmaxyx()[0]: + break + except Exception: + self.screen.addstr(row + 1, 2, 'Not available') + + def get_pid_from_gname(self, gname): + """Fuzzy function to convert guest name to QEMU process pid. + + Returns a list of potential pids, can be empty if no match found. + Throws an exception on processing errors. + + """ + pids = [] + for line in self.get_all_gnames(): + if gname == line[1]: + pids.append(int(line[0])) + + return pids + + @staticmethod + def get_gname_from_pid(pid): + """Returns the guest name for a QEMU process pid. + + Extracts the guest name from the QEMU comma line by processing the + '-name' option. Will also handle names specified out of sequence. + + """ + name = '' + try: + line = open('/proc/{}/cmdline' + .format(pid), 'rb').read().split('\0') + parms = line[line.index('-name') + 1].split(',') + while '' in parms: + # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results + # in # ['foo', '', 'bar'], which we revert here + idx = parms.index('') + parms[idx - 1] += ',' + parms[idx + 1] + del parms[idx:idx+2] + # the '-name' switch allows for two ways to specify the guest name, + # where the plain name overrides the name specified via 'guest=' + for arg in parms: + if '=' not in arg: + name = arg + break + if arg[:6] == 'guest=': + name = arg[6:] + except (ValueError, IOError, IndexError): + pass + + return name + def update_drilldown(self): """Sets or removes a filter that only allows fields without braces.""" if not self.stats.fields_filter: @@ -954,7 +1043,7 @@ class Tui(object): if pid is None: pid = self.stats.pid_filter self.screen.erase() - gname = get_gname_from_pid(pid) + gname = self.get_gname_from_pid(pid) if gname: gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...' if len(gname) > MAX_GUEST_NAME_LEN @@ -970,13 +1059,13 @@ class Tui(object): if len(regex) > MAX_REGEX_LEN: regex = regex[:MAX_REGEX_LEN] + '...' self.screen.addstr(1, 17, 'regex filter: {0}'.format(regex)) - self.screen.addstr(2, 1, 'Event') - self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH - - len('Total'), 'Total') - self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 - - len('%Total'), '%Total') - self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 + 8 - - len('Current'), 'Current') + if self._display_guests: + col_name = 'Guest Name' + else: + col_name = 'Event' + self.screen.addstr(2, 1, '%-40s %10s%7s %8s' % + (col_name, 'Total', '%Total', 'CurAvg/s'), + curses.A_STANDOUT) self.screen.addstr(4, 1, 'Collecting data...') self.screen.refresh() @@ -984,16 +1073,25 @@ class Tui(object): row = 3 self.screen.move(row, 0) self.screen.clrtobot() - stats = self.stats.get() + stats = self.stats.get(self._display_guests) - def sortkey(x): + def sortCurAvg(x): + # sort by current events if available if stats[x][1]: return (-stats[x][1], -stats[x][0]) else: return (0, -stats[x][0]) + + def sortTotal(x): + # sort by totals + return (0, -stats[x][0]) total = 0. for val in stats.values(): total += val[0] + if self._sorting == SORT_DEFAULT: + sortkey = sortCurAvg + else: + sortkey = sortTotal for key in sorted(stats.keys(), key=sortkey): if row >= self.screen.getmaxyx()[0]: @@ -1001,18 +1099,61 @@ class Tui(object): values = stats[key] if not values[0] and not values[1]: break - col = 1 - self.screen.addstr(row, col, key) - col += LABEL_WIDTH - self.screen.addstr(row, col, '%10d' % (values[0],)) - col += NUMBER_WIDTH - self.screen.addstr(row, col, '%7.1f' % (values[0] * 100 / total,)) - col += 7 - if values[1] is not None: - self.screen.addstr(row, col, '%8d' % (values[1] / sleeptime,)) + if values[0] is not None: + cur = int(round(values[1] / sleeptime)) if values[1] else '' + if self._display_guests: + key = self.get_gname_from_pid(key) + self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % + (key, values[0], values[0] * 100 / total, + cur)) row += 1 + if row == 3: + self.screen.addstr(4, 1, 'No matching events reported yet') self.screen.refresh() + def show_msg(self, text): + """Display message centered text and exit on key press""" + hint = 'Press any key to continue' + curses.cbreak() + self.screen.erase() + (x, term_width) = self.screen.getmaxyx() + row = 2 + for line in text: + start = (term_width - len(line)) / 2 + self.screen.addstr(row, start, line) + row += 1 + self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint, + curses.A_STANDOUT) + self.screen.getkey() + + def show_help_interactive(self): + """Display help with list of interactive commands""" + msg = (' b toggle events by guests (debugfs only, honors' + ' filters)', + ' c clear filter', + ' f filter by regular expression', + ' g filter by guest name', + ' h display interactive commands reference', + ' o toggle sorting order (Total vs CurAvg/s)', + ' p filter by PID', + ' q quit', + ' r reset stats', + ' s set update interval', + ' x toggle reporting of stats for individual child trace' + ' events', + 'Any other key refreshes statistics immediately') + curses.cbreak() + self.screen.erase() + self.screen.addstr(0, 0, "Interactive commands reference", + curses.A_BOLD) + self.screen.addstr(2, 0, "Press any key to exit", curses.A_STANDOUT) + row = 4 + for line in msg: + self.screen.addstr(row, 0, line) + row += 1 + self.screen.getkey() + self.refresh_header() + def show_filter_selection(self): """Draws filter selection mask. @@ -1059,6 +1200,7 @@ class Tui(object): 'This might limit the shown data to the trace ' 'statistics.') self.screen.addstr(5, 0, msg) + self.print_all_gnames(7) curses.echo() self.screen.addstr(3, 0, "Pid [0 or pid]: ") @@ -1077,10 +1219,40 @@ class Tui(object): self.refresh_header(pid) self.update_pid(pid) break - except ValueError: msg = '"' + str(pid) + '": Not a valid pid' - continue + + def show_set_update_interval(self): + """Draws update interval selection mask.""" + msg = '' + while True: + self.screen.erase() + self.screen.addstr(0, 0, 'Set update interval (defaults to %fs).' % + DELAY_DEFAULT, curses.A_BOLD) + self.screen.addstr(4, 0, msg) + self.screen.addstr(2, 0, 'Change delay from %.1fs to ' % + self._delay_regular) + curses.echo() + val = self.screen.getstr() + curses.noecho() + + try: + if len(val) > 0: + delay = float(val) + if delay < 0.1: + msg = '"' + str(val) + '": Value must be >=0.1' + continue + if delay > 25.5: + msg = '"' + str(val) + '": Value must be <=25.5' + continue + else: + delay = DELAY_DEFAULT + self._delay_regular = delay + break + + except ValueError: + msg = '"' + str(val) + '": Invalid value' + self.refresh_header() def show_vm_selection_by_guest_name(self): """Draws guest selection mask. @@ -1098,6 +1270,7 @@ class Tui(object): 'This might limit the shown data to the trace ' 'statistics.') self.screen.addstr(5, 0, msg) + self.print_all_gnames(7) curses.echo() self.screen.addstr(3, 0, "Guest [ENTER or guest]: ") gname = self.screen.getstr() @@ -1110,7 +1283,7 @@ class Tui(object): else: pids = [] try: - pids = get_pid_from_gname(gname) + pids = self.get_pid_from_gname(gname) except: msg = '"' + gname + '": Internal error while searching, ' \ 'use pid filter instead' @@ -1128,38 +1301,60 @@ class Tui(object): def show_stats(self): """Refreshes the screen and processes user input.""" - sleeptime = DELAY_INITIAL + sleeptime = self._delay_initial self.refresh_header() + start = 0.0 # result based on init value never appears on screen while True: - self.refresh_body(sleeptime) + self.refresh_body(time.time() - start) curses.halfdelay(int(sleeptime * 10)) - sleeptime = DELAY_REGULAR + start = time.time() + sleeptime = self._delay_regular try: char = self.screen.getkey() - if char == 'x': + if char == 'b': + self._display_guests = not self._display_guests + if self.stats.toggle_display_guests(self._display_guests): + self.show_msg(['Command not available with tracepoints' + ' enabled', 'Restart with debugfs only ' + '(see option \'-d\') and try again!']) + self._display_guests = not self._display_guests self.refresh_header() - self.update_drilldown() - sleeptime = DELAY_INITIAL - if char == 'q': - break if char == 'c': self.stats.fields_filter = DEFAULT_REGEX self.refresh_header(0) self.update_pid(0) - sleeptime = DELAY_INITIAL if char == 'f': + curses.curs_set(1) self.show_filter_selection() - sleeptime = DELAY_INITIAL + curses.curs_set(0) + sleeptime = self._delay_initial if char == 'g': + curses.curs_set(1) self.show_vm_selection_by_guest_name() - sleeptime = DELAY_INITIAL + curses.curs_set(0) + sleeptime = self._delay_initial + if char == 'h': + self.show_help_interactive() + if char == 'o': + self._sorting = not self._sorting if char == 'p': + curses.curs_set(1) self.show_vm_selection_by_pid() - sleeptime = DELAY_INITIAL + curses.curs_set(0) + sleeptime = self._delay_initial + if char == 'q': + break if char == 'r': - self.refresh_header() self.stats.reset() - sleeptime = DELAY_INITIAL + if char == 's': + curses.curs_set(1) + self.show_set_update_interval() + curses.curs_set(0) + sleeptime = self._delay_initial + if char == 'x': + self.update_drilldown() + # prevents display of current values on next refresh + self.stats.get() except KeyboardInterrupt: break except curses.error: @@ -1227,13 +1422,17 @@ Requirements: the large number of files that are possibly opened. Interactive Commands: + b toggle events by guests (debugfs only, honors filters) c clear filter f filter by regular expression g filter by guest name + h display interactive commands reference + o toggle sorting order (Total vs CurAvg/s) p filter by PID q quit - x toggle reporting of stats for individual child trace events r reset stats + s set update interval + x toggle reporting of stats for individual child trace events Press any other key to refresh statistics immediately. """ @@ -1246,7 +1445,7 @@ Press any other key to refresh statistics immediately. def cb_guest_to_pid(option, opt, val, parser): try: - pids = get_pid_from_gname(val) + pids = Tui.get_pid_from_gname(val) except: raise optparse.OptionValueError('Error while searching for guest ' '"{}", use "-p" to specify a pid ' @@ -1268,6 +1467,13 @@ Press any other key to refresh statistics immediately. dest='once', help='run in batch mode for one second', ) + optparser.add_option('-i', '--debugfs-include-past', + action='store_true', + default=False, + dest='dbgfs_include_past', + help='include all available data on past events for ' + 'debugfs', + ) optparser.add_option('-l', '--log', action='store_true', default=False, @@ -1288,7 +1494,7 @@ Press any other key to refresh statistics immediately. ) optparser.add_option('-f', '--fields', action='store', - default=None, + default=DEFAULT_REGEX, dest='fields', help='fields to display (regex)', ) @@ -1311,20 +1517,6 @@ Press any other key to refresh statistics immediately. return options -def get_providers(options): - """Returns a list of data providers depending on the passed options.""" - providers = [] - - if options.tracepoints: - providers.append(TracepointProvider()) - if options.debugfs: - providers.append(DebugfsProvider()) - if len(providers) == 0: - providers.append(TracepointProvider()) - - return providers - - def check_access(options): """Exits if the current user can't access all needed directories.""" if not os.path.exists('/sys/kernel/debug'): @@ -1365,8 +1557,7 @@ def main(): sys.stderr.write('Did you use a (unsupported) tid instead of a pid?\n') sys.exit('Specified pid does not exist.') - providers = get_providers(options) - stats = Stats(providers, options.pid, fields=options.fields) + stats = Stats(options) if options.log: log(stats) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index 109431bdc63c..e5cf836be8a1 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -29,18 +29,26 @@ meaning of events. INTERACTIVE COMMANDS -------------------- [horizontal] +*b*:: toggle events by guests (debugfs only, honors filters) + *c*:: clear filter *f*:: filter by regular expression *g*:: filter by guest name +*h*:: display interactive commands reference + +*o*:: toggle sorting order (Total vs CurAvg/s) + *p*:: filter by PID *q*:: quit *r*:: reset stats +*s*:: set update interval + *x*:: toggle reporting of stats for child trace events Press any other key to refresh statistics immediately. @@ -64,6 +72,10 @@ OPTIONS --debugfs:: retrieve statistics from debugfs +-i:: +--debugfs-include-past:: + include all available data on past events for debugfs + -p<pid>:: --pid=<pid>:: limit statistics to one virtual machine (pid) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 4fe444b8092e..6e178987af8e 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -117,6 +117,28 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } +int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, int strict_alignment, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.prog_type = type; + attr.insn_cnt = (__u32)insns_cnt; + attr.insns = ptr_to_u64(insns); + attr.license = ptr_to_u64(license); + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_buf_sz; + attr.log_level = 2; + log_buf[0] = 0; + attr.kern_version = kern_version; + attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0; + + return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); +} + int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags) { diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index edb4daeff7a5..972bd8333eb7 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -35,6 +35,10 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, size_t log_buf_sz); +int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, int strict_alignment, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz); int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 91edd0566237..f389b02d43a0 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -11,7 +11,8 @@ endif CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf -TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs +TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ + test_align TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o @@ -34,6 +35,7 @@ $(BPFOBJ): force CLANG ?= clang %.o: %.c - $(CLANG) -I. -I../../../include/uapi -I../../../../samples/bpf/ \ + $(CLANG) -I. -I./include/uapi -I../../../include/uapi \ + -I../../../../samples/bpf/ \ -Wno-compare-distinct-pointer-types \ -O2 -target bpf -c $< -o $@ diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/testing/selftests/bpf/include/uapi/linux/types.h new file mode 100644 index 000000000000..51841848fbfe --- /dev/null +++ b/tools/testing/selftests/bpf/include/uapi/linux/types.h @@ -0,0 +1,22 @@ +#ifndef _UAPI_LINUX_TYPES_H +#define _UAPI_LINUX_TYPES_H + +#include <asm-generic/int-ll64.h> + +/* copied from linux:include/uapi/linux/types.h */ +#define __bitwise +typedef __u16 __bitwise __le16; +typedef __u16 __bitwise __be16; +typedef __u32 __bitwise __le32; +typedef __u32 __bitwise __be32; +typedef __u64 __bitwise __le64; +typedef __u64 __bitwise __be64; + +typedef __u16 __bitwise __sum16; +typedef __u32 __bitwise __wsum; + +#define __aligned_u64 __u64 __attribute__((aligned(8))) +#define __aligned_be64 __be64 __attribute__((aligned(8))) +#define __aligned_le64 __le64 __attribute__((aligned(8))) + +#endif /* _UAPI_LINUX_TYPES_H */ diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c new file mode 100644 index 000000000000..9644d4e069de --- /dev/null +++ b/tools/testing/selftests/bpf/test_align.c @@ -0,0 +1,453 @@ +#include <asm/types.h> +#include <linux/types.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <stddef.h> +#include <stdbool.h> + +#include <linux/unistd.h> +#include <linux/filter.h> +#include <linux/bpf_perf_event.h> +#include <linux/bpf.h> + +#include <bpf/bpf.h> + +#include "../../../include/linux/filter.h" + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +#define MAX_INSNS 512 +#define MAX_MATCHES 16 + +struct bpf_align_test { + const char *descr; + struct bpf_insn insns[MAX_INSNS]; + enum { + UNDEF, + ACCEPT, + REJECT + } result; + enum bpf_prog_type prog_type; + const char *matches[MAX_MATCHES]; +}; + +static struct bpf_align_test tests[] = { + { + .descr = "mov", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_3, 8), + BPF_MOV64_IMM(BPF_REG_3, 16), + BPF_MOV64_IMM(BPF_REG_3, 32), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + "2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", + "5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp", + }, + }, + { + .descr = "shift", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_4, 32), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", + "2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + "3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", + "6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", + "7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp", + "8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp", + "9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + }, + }, + { + .descr = "addsub", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", + "2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp", + "3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp", + "4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", + "5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp", + "6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp", + }, + }, + { + .descr = "mul", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 7), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 2), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", + "2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", + "3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp", + "4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp", + }, + }, + +#define PREP_PKT_POINTERS \ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \ + offsetof(struct __sk_buff, data)), \ + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, \ + offsetof(struct __sk_buff, data_end)) + +#define LOAD_UNKNOWN(DST_REG) \ + PREP_PKT_POINTERS, \ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), \ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), \ + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 1), \ + BPF_EXIT_INSN(), \ + BPF_LDX_MEM(BPF_B, DST_REG, BPF_REG_2, 0) + + { + .descr = "unknown shift", + .insns = { + LOAD_UNKNOWN(BPF_REG_3), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1), + LOAD_UNKNOWN(BPF_REG_4), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 5), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", + "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp", + "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp", + "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp", + "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp", + "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp", + "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp", + "20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp", + "21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp", + "22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp", + "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp", + }, + }, + { + .descr = "unknown mul", + .insns = { + LOAD_UNKNOWN(BPF_REG_3), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 1), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 4), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_3), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 8), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", + "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp", + "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp", + "12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp", + "14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", + "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp", + "16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp" + }, + }, + { + .descr = "packet const offset", + .insns = { + PREP_PKT_POINTERS, + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + + BPF_MOV64_IMM(BPF_REG_0, 0), + + /* Skip over ethernet header. */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 2), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 3), + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 0), + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + "4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp", + "5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp", + "6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp", + "10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp", + "14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", + "15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", + }, + }, + { + .descr = "packet variable offset", + .insns = { + LOAD_UNKNOWN(BPF_REG_6), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + + /* First, add a constant to the R5 packet pointer, + * then a variable with a known alignment. + */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + /* Now, test in the other direction. Adding first + * the variable offset to R5, then the constant. + */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + /* Test multiple accumulations of unknown values + * into a packet pointer. + */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp", + + /* Offset is added to packet pointer R5, resulting in known + * auxiliary alignment and offset. + */ + "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* At the time the word size load is performed from R5, + * it's total offset is NET_IP_ALIGN + reg->off (0) + + * reg->aux_off (14) which is 16. Then the variable + * offset is considered using reg->aux_off_align which + * is 4 and meets the load's requirements. + */ + "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + + /* Variable offset is added to R5 packet pointer, + * resulting in auxiliary alignment of 4. + */ + "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* Constant offset is added to R5, resulting in + * reg->off of 14. + */ + "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* At the time the word size load is performed from R5, + * it's total offset is NET_IP_ALIGN + reg->off (14) which + * is 16. Then the variable offset is considered using + * reg->aux_off_align which is 4 and meets the load's + * requirements. + */ + "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp", + + /* Constant offset is added to R5 packet pointer, + * resulting in reg->off value of 14. + */ + "26: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=0,off=14,r=8) R6=inv54,min_align=4 R10=fp", + /* Variable offset is added to R5, resulting in an + * auxiliary offset of 14, and an auxiliary alignment of 4. + */ + "27: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + /* Constant is added to R5 again, setting reg->off to 4. */ + "28: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=4,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + /* And once more we add a variable, which causes an accumulation + * of reg->off into reg->aux_off_align, with resulting value of + * 18. The auxiliary alignment stays at 4. + */ + "29: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=4,off=0,r=0),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + /* At the time the word size load is performed from R5, + * it's total offset is NET_IP_ALIGN + reg->off (0) + + * reg->aux_off (18) which is 20. Then the variable offset + * is considered using reg->aux_off_align which is 4 and meets + * the load's requirements. + */ + "33: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=4,off=4,r=4),aux_off=18,aux_off_align=4 R5=pkt(id=4,off=0,r=4),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + }, + }, +}; + +static int probe_filter_length(const struct bpf_insn *fp) +{ + int len; + + for (len = MAX_INSNS - 1; len > 0; --len) + if (fp[len].code != 0 || fp[len].imm != 0) + break; + return len + 1; +} + +static char bpf_vlog[32768]; + +static int do_test_single(struct bpf_align_test *test) +{ + struct bpf_insn *prog = test->insns; + int prog_type = test->prog_type; + int prog_len, i; + int fd_prog; + int ret; + + prog_len = probe_filter_length(prog); + fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, + prog, prog_len, 1, "GPL", 0, + bpf_vlog, sizeof(bpf_vlog)); + if (fd_prog < 0) { + printf("Failed to load program.\n"); + printf("%s", bpf_vlog); + ret = 1; + } else { + ret = 0; + for (i = 0; i < MAX_MATCHES; i++) { + const char *t, *m = test->matches[i]; + + if (!m) + break; + t = strstr(bpf_vlog, m); + if (!t) { + printf("Failed to find match: %s\n", m); + ret = 1; + printf("%s", bpf_vlog); + break; + } + } + close(fd_prog); + } + return ret; +} + +static int do_test(unsigned int from, unsigned int to) +{ + int all_pass = 0; + int all_fail = 0; + unsigned int i; + + for (i = from; i < to; i++) { + struct bpf_align_test *test = &tests[i]; + int fail; + + printf("Test %3d: %s ... ", + i, test->descr); + fail = do_test_single(test); + if (fail) { + all_fail++; + printf("FAIL\n"); + } else { + all_pass++; + printf("PASS\n"); + } + } + printf("Results: %d pass %d fail\n", + all_pass, all_fail); + return 0; +} + +int main(int argc, char **argv) +{ + unsigned int from = 0, to = ARRAY_SIZE(tests); + + if (argc == 3) { + unsigned int l = atoi(argv[argc - 2]); + unsigned int u = atoi(argv[argc - 1]); + + if (l < to && u < to) { + from = l; + to = u + 1; + } + } else if (argc == 2) { + unsigned int t = atoi(argv[argc - 1]); + + if (t < to) { + from = t; + to = t + 1; + } + } + return do_test(from, to); +} diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/test_pkt_access.c index 39387bb7e08c..6e11ba11709e 100644 --- a/tools/testing/selftests/bpf/test_pkt_access.c +++ b/tools/testing/selftests/bpf/test_pkt_access.c @@ -5,6 +5,7 @@ * License as published by the Free Software Foundation. */ #include <stddef.h> +#include <string.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 32e6211e1c6e..717581145cfc 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -58,7 +58,7 @@ parse_opts() { # opts ;; --verbose|-v|-vv) VERBOSE=$((VERBOSE + 1)) - [ $1 == '-vv' ] && VERBOSE=$((VERBOSE + 1)) + [ $1 = '-vv' ] && VERBOSE=$((VERBOSE + 1)) shift 1 ;; --debug|-d) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc index 07bb3e5930b4..aa31368851c9 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc @@ -48,7 +48,7 @@ test_event_enabled() { e=`cat $EVENT_ENABLE` if [ "$e" != $val ]; then echo "Expected $val but found $e" - exit -1 + exit 1 fi } diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 9aec6fcb7729..f2019b37370d 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -34,10 +34,10 @@ reset_ftrace_filter() { # reset all triggers in set_ftrace_filter echo > set_ftrace_filter grep -v '^#' set_ftrace_filter | while read t; do tr=`echo $t | cut -d: -f2` - if [ "$tr" == "" ]; then + if [ "$tr" = "" ]; then continue fi - if [ $tr == "enable_event" -o $tr == "disable_event" ]; then + if [ $tr = "enable_event" -o $tr = "disable_event" ]; then tr=`echo $t | cut -d: -f1-4` limit=`echo $t | cut -d: -f5` else diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc index 4c5a061a5b4e..c73db7863adb 100644 --- a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc +++ b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc @@ -75,9 +75,13 @@ rmdir foo if [ -d foo ]; then fail "foo still exists" fi -exit 0 - +mkdir foo +echo "schedule:enable_event:sched:sched_switch" > foo/set_ftrace_filter +rmdir foo +if [ -d foo ]; then + fail "foo still exists" +fi instance_slam() { diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index 427621792229..2f1f7b013293 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -11,3 +11,4 @@ tm-signal-context-chk-fpu tm-signal-context-chk-gpr tm-signal-context-chk-vmx tm-signal-context-chk-vsx +tm-vmx-unavail diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 5576ee6a51f2..958c11c14acd 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -2,7 +2,8 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu tm-signal-context-chk-vmx tm-signal-context-chk-vsx TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ - tm-vmxcopy tm-fork tm-tar tm-tmspr $(SIGNAL_CONTEXT_CHK_TESTS) + tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail \ + $(SIGNAL_CONTEXT_CHK_TESTS) include ../../lib.mk @@ -13,6 +14,7 @@ CFLAGS += -mhtm $(OUTPUT)/tm-syscall: tm-syscall-asm.S $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include $(OUTPUT)/tm-tmspr: CFLAGS += -pthread +$(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS)) $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S diff --git a/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c new file mode 100644 index 000000000000..137185ba4937 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-vmx-unavail.c @@ -0,0 +1,118 @@ +/* + * Copyright 2017, Michael Neuling, IBM Corp. + * Licensed under GPLv2. + * Original: Breno Leitao <brenohl@br.ibm.com> & + * Gustavo Bueno Romero <gromero@br.ibm.com> + * Edited: Michael Neuling + * + * Force VMX unavailable during a transaction and see if it corrupts + * the checkpointed VMX register state after the abort. + */ + +#include <inttypes.h> +#include <htmintrin.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <pthread.h> +#include <sys/mman.h> +#include <unistd.h> +#include <pthread.h> + +#include "tm.h" +#include "utils.h" + +int passed; + +void *worker(void *unused) +{ + __int128 vmx0; + uint64_t texasr; + + asm goto ( + "li 3, 1;" /* Stick non-zero value in VMX0 */ + "std 3, 0(%[vmx0_ptr]);" + "lvx 0, 0, %[vmx0_ptr];" + + /* Wait here a bit so we get scheduled out 255 times */ + "lis 3, 0x3fff;" + "1: ;" + "addi 3, 3, -1;" + "cmpdi 3, 0;" + "bne 1b;" + + /* Kernel will hopefully turn VMX off now */ + + "tbegin. ;" + "beq failure;" + + /* Cause VMX unavail. Any VMX instruction */ + "vaddcuw 0,0,0;" + + "tend. ;" + "b %l[success];" + + /* Check VMX0 sanity after abort */ + "failure: ;" + "lvx 1, 0, %[vmx0_ptr];" + "vcmpequb. 2, 0, 1;" + "bc 4, 24, %l[value_mismatch];" + "b %l[value_match];" + : + : [vmx0_ptr] "r"(&vmx0) + : "r3" + : success, value_match, value_mismatch + ); + + /* HTM aborted and VMX0 is corrupted */ +value_mismatch: + texasr = __builtin_get_texasr(); + + printf("\n\n==============\n\n"); + printf("Failure with error: %lx\n", _TEXASR_FAILURE_CODE(texasr)); + printf("Summary error : %lx\n", _TEXASR_FAILURE_SUMMARY(texasr)); + printf("TFIAR exact : %lx\n\n", _TEXASR_TFIAR_EXACT(texasr)); + + passed = 0; + return NULL; + + /* HTM aborted but VMX0 is correct */ +value_match: +// printf("!"); + return NULL; + +success: +// printf("."); + return NULL; +} + +int tm_vmx_unavail_test() +{ + int threads; + pthread_t *thread; + + SKIP_IF(!have_htm()); + + passed = 1; + + threads = sysconf(_SC_NPROCESSORS_ONLN) * 4; + thread = malloc(sizeof(pthread_t)*threads); + if (!thread) + return EXIT_FAILURE; + + for (uint64_t i = 0; i < threads; i++) + pthread_create(&thread[i], NULL, &worker, NULL); + + for (uint64_t i = 0; i < threads; i++) + pthread_join(thread[i], NULL); + + free(thread); + + return passed ? EXIT_SUCCESS : EXIT_FAILURE; +} + + +int main(int argc, char **argv) +{ + return test_harness(tm_vmx_unavail_test, "tm_vmx_unavail_test"); +} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f0fe9d02f6bb..19f0ecb9b93e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -73,17 +73,17 @@ MODULE_LICENSE("GPL"); /* Architectures should define their poll value according to the halt latency */ unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT; -module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR); +module_param(halt_poll_ns, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns); /* Default doubles per-vcpu halt_poll_ns. */ unsigned int halt_poll_ns_grow = 2; -module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR); +module_param(halt_poll_ns_grow, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow); /* Default resets per-vcpu halt_poll_ns . */ unsigned int halt_poll_ns_shrink; -module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR); +module_param(halt_poll_ns_shrink, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); /* @@ -3191,6 +3191,12 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) return PTR_ERR(file); } + /* + * Don't call kvm_put_kvm anymore at this point; file->f_op is + * already set, with ->release() being kvm_vm_release(). In error + * cases it will be called by the final fput(file) and will take + * care of doing kvm_put_kvm(kvm). + */ if (kvm_create_vm_debugfs(kvm, r) < 0) { put_unused_fd(r); fput(file); |