diff options
438 files changed, 4883 insertions, 2679 deletions
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 17ea3fecddaa..ab7ed2fd072f 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -107,6 +107,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX2 SMMUv3| #126 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +| Cavium | ThunderX2 Core | #219 | CAVIUM_TX2_ERRATUM_219 | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index b72d07d70239..525296121d89 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -41,6 +41,9 @@ smaller binary while the latter is 1.1 - 2 times faster. Both KASAN modes work with both SLUB and SLAB memory allocators. For better bug detection and nicer reporting, enable CONFIG_STACKTRACE. +To augment reports with last allocation and freeing stack of the physical page, +it is recommended to enable also CONFIG_PAGE_OWNER and boot with page_owner=on. + To disable instrumentation for specific files or directories, add a line similar to the following to the respective kernel Makefile: diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt index f4c5d34c4111..7079d44bf3ba 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt @@ -1,8 +1,11 @@ * Advanced Interrupt Controller (AIC) Required properties: -- compatible: Should be "atmel,<chip>-aic" - <chip> can be "at91rm9200", "sama5d2", "sama5d3" or "sama5d4" +- compatible: Should be: + - "atmel,<chip>-aic" where <chip> can be "at91rm9200", "sama5d2", + "sama5d3" or "sama5d4" + - "microchip,<chip>-aic" where <chip> can be "sam9x60" + - interrupt-controller: Identifies the node as an interrupt controller. - #interrupt-cells: The number of cells to define the interrupts. It should be 3. The first cell is the IRQ number (aka "Peripheral IDentifier" on datasheet). diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml index f83d888176cc..064b7dfc4252 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml @@ -33,13 +33,13 @@ patternProperties: allOf: - $ref: "/schemas/types.yaml#/definitions/string" - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, - ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI, - ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, - GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, - GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, I2C12, - I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, - I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC, - LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, + ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMC, + ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, + GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, + GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, + I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, + I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, + LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1, @@ -48,47 +48,45 @@ patternProperties: PWM8, PWM9, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3, RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10, SALT11, SALT12, SALT13, SALT14, SALT15, SALT16, SALT2, SALT3, SALT4, SALT5, - SALT6, SALT7, SALT8, SALT9, SD1, SD2, SD3, SD3DAT4, SD3DAT5, - SD3DAT6, SD3DAT7, SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO, - SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1, - SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11, - TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, TACH4, TACH5, - TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, THRU3, TXD1, - TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13, UART6, UART7, - UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, - WDTRST4, ] + SALT6, SALT7, SALT8, SALT9, SD1, SD2, SGPM1, SGPS1, SIOONCTRL, + SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, + SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, + TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, + TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, + THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13, + UART6, UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, + WDTRST3, WDTRST4, ] groups: allOf: - $ref: "/schemas/types.yaml#/definitions/string" - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, - ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI, - ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWQSPID, FWSPIWP, GPIT0, - GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, - GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, HVI3C3, HVI3C4, I2C1, - I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, - I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, - JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, - MACLINK1, MACLINK2, MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3, - MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4, - NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1, - NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4, OSCCLK, PEWAKE, - PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1, PWM12G0, PWM12G1, - PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0, PWM15G1, PWM2, PWM3, - PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1, PWM9G0, PWM9G1, QSPI1, - QSPI2, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3, - RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10G0, SALT10G1, - SALT11G0, SALT11G1, SALT12G0, SALT12G1, SALT13G0, SALT13G1, - SALT14G0, SALT14G1, SALT15G0, SALT15G1, SALT16G0, SALT16G1, - SALT2, SALT3, SALT4, SALT5, SALT6, SALT7, SALT8, SALT9G0, - SALT9G1, SD1, SD2, SD3, SD3DAT4, SD3DAT5, SD3DAT6, SD3DAT7, - SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, - SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1, SPI1WP, SPI2, - SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11, TACH12, TACH13, - TACH14, TACH15, TACH2, TACH3, TACH4, TACH5, TACH6, TACH7, TACH8, - TACH9, THRU0, THRU1, THRU2, THRU3, TXD1, TXD2, TXD3, TXD4, - UART10, UART11, UART12G0, UART12G1, UART13G0, UART13G1, UART6, - UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, - WDTRST4, ] + ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1, + EMMCG4, EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, + FWQSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, + GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, + GPIU7, HVI3C3, HVI3C4, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14, + I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, + I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD, + LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, MACLINK3, MACLINK4, + MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, + NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, + NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4, + OSCCLK, PEWAKE, PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1, + PWM12G0, PWM12G1, PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0, + PWM15G1, PWM2, PWM3, PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1, + PWM9G0, PWM9G1, QSPI1, QSPI2, RGMII1, RGMII2, RGMII3, RGMII4, + RMII1, RMII2, RMII3, RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, + SALT10G0, SALT10G1, SALT11G0, SALT11G1, SALT12G0, SALT12G1, + SALT13G0, SALT13G1, SALT14G0, SALT14G1, SALT15G0, SALT15G1, + SALT16G0, SALT16G1, SALT2, SALT3, SALT4, SALT5, SALT6, SALT7, + SALT8, SALT9G0, SALT9G1, SD1, SD2, SD3, SGPM1, SGPS1, SIOONCTRL, + SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, + SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, + TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, + TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, + THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12G0, + UART12G1, UART13G0, UART13G1, UART6, UART7, UART8, UART9, VB, + VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, WDTRST4, ] required: - compatible diff --git a/Documentation/networking/device_drivers/pensando/ionic.rst b/Documentation/networking/device_drivers/pensando/ionic.rst index 67b6839d516b..13935896bee6 100644 --- a/Documentation/networking/device_drivers/pensando/ionic.rst +++ b/Documentation/networking/device_drivers/pensando/ionic.rst @@ -36,8 +36,10 @@ Support ======= For general Linux networking support, please use the netdev mailing list, which is monitored by Pensando personnel:: + netdev@vger.kernel.org For more specific support needs, please use the Pensando driver support email:: - drivers@pensando.io + + drivers@pensando.io diff --git a/Documentation/networking/net_dim.txt b/Documentation/networking/net_dim.txt index 9cb31c5e2dcd..9bdb7d5a3ba3 100644 --- a/Documentation/networking/net_dim.txt +++ b/Documentation/networking/net_dim.txt @@ -92,16 +92,16 @@ under some conditions. Part III: Registering a Network Device to DIM ============================================== -Net DIM API exposes the main function net_dim(struct net_dim *dim, -struct net_dim_sample end_sample). This function is the entry point to the Net +Net DIM API exposes the main function net_dim(struct dim *dim, +struct dim_sample end_sample). This function is the entry point to the Net DIM algorithm and has to be called every time the driver would like to check if it should change interrupt moderation parameters. The driver should provide two -data structures: struct net_dim and struct net_dim_sample. Struct net_dim +data structures: struct dim and struct dim_sample. Struct dim describes the state of DIM for a specific object (RX queue, TX queue, other queues, etc.). This includes the current selected profile, previous data samples, the callback function provided by the driver and more. -Struct net_dim_sample describes a data sample, which will be compared to the -data sample stored in struct net_dim in order to decide on the algorithm's next +Struct dim_sample describes a data sample, which will be compared to the +data sample stored in struct dim in order to decide on the algorithm's next step. The sample should include bytes, packets and interrupts, measured by the driver. @@ -110,9 +110,9 @@ main net_dim() function. The recommended method is to call net_dim() on each interrupt. Since Net DIM has a built-in moderation and it might decide to skip iterations under certain conditions, there is no need to moderate the net_dim() calls as well. As mentioned above, the driver needs to provide an object of type -struct net_dim to the net_dim() function call. It is advised for each entity -using Net DIM to hold a struct net_dim as part of its data structure and use it -as the main Net DIM API object. The struct net_dim_sample should hold the latest +struct dim to the net_dim() function call. It is advised for each entity +using Net DIM to hold a struct dim as part of its data structure and use it +as the main Net DIM API object. The struct dim_sample should hold the latest bytes, packets and interrupts count. No need to perform any calculations, just include the raw data. @@ -132,19 +132,19 @@ usage is not complete but it should make the outline of the usage clear. my_driver.c: -#include <linux/net_dim.h> +#include <linux/dim.h> /* Callback for net DIM to schedule on a decision to change moderation */ void my_driver_do_dim_work(struct work_struct *work) { - /* Get struct net_dim from struct work_struct */ - struct net_dim *dim = container_of(work, struct net_dim, - work); + /* Get struct dim from struct work_struct */ + struct dim *dim = container_of(work, struct dim, + work); /* Do interrupt moderation related stuff */ ... /* Signal net DIM work is done and it should move to next iteration */ - dim->state = NET_DIM_START_MEASURE; + dim->state = DIM_START_MEASURE; } /* My driver's interrupt handler */ @@ -152,13 +152,13 @@ int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...) { ... /* A struct to hold current measured data */ - struct net_dim_sample dim_sample; + struct dim_sample dim_sample; ... /* Initiate data sample struct with current data */ - net_dim_sample(my_entity->events, - my_entity->packets, - my_entity->bytes, - &dim_sample); + dim_update_sample(my_entity->events, + my_entity->packets, + my_entity->bytes, + &dim_sample); /* Call net DIM */ net_dim(&my_entity->dim, dim_sample); ... diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt index bd29d44af32b..49183add44e7 100644 --- a/Documentation/virt/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -3002,6 +3002,9 @@ can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number indicating the number of supported registers. +For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP capability indicates whether +the single-step debug event (KVM_GUESTDBG_SINGLESTEP) is supported. + When debug events exit the main run loop with the reason KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run structure containing architecture specific debug information. diff --git a/Documentation/virt/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.txt index 42864935ac5d..423332dda7bc 100644 --- a/Documentation/virt/kvm/devices/xics.txt +++ b/Documentation/virt/kvm/devices/xics.txt @@ -3,9 +3,19 @@ XICS interrupt controller Device type supported: KVM_DEV_TYPE_XICS Groups: - KVM_DEV_XICS_SOURCES + 1. KVM_DEV_XICS_GRP_SOURCES Attributes: One per interrupt source, indexed by the source number. + 2. KVM_DEV_XICS_GRP_CTRL + Attributes: + 2.1 KVM_DEV_XICS_NR_SERVERS (write only) + The kvm_device_attr.addr points to a __u32 value which is the number of + interrupt server numbers (ie, highest possible vcpu id plus one). + Errors: + -EINVAL: Value greater than KVM_MAX_VCPU_ID. + -EFAULT: Invalid user pointer for attr->addr. + -EBUSY: A vcpu is already connected to the device. + This device emulates the XICS (eXternal Interrupt Controller Specification) defined in PAPR. The XICS has a set of interrupt sources, each identified by a 20-bit source number, and a set of @@ -38,7 +48,7 @@ least-significant end of the word: Each source has 64 bits of state that can be read and written using the KVM_GET_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls, specifying the -KVM_DEV_XICS_SOURCES attribute group, with the attribute number being +KVM_DEV_XICS_GRP_SOURCES attribute group, with the attribute number being the interrupt source number. The 64 bit state word has the following bitfields, starting from the least-significant end of the word: diff --git a/Documentation/virt/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.txt index 9a24a4525253..f5d1d6b5af61 100644 --- a/Documentation/virt/kvm/devices/xive.txt +++ b/Documentation/virt/kvm/devices/xive.txt @@ -78,6 +78,14 @@ the legacy interrupt mode, referred as XICS (POWER7/8). migrating the VM. Errors: none + 1.3 KVM_DEV_XIVE_NR_SERVERS (write only) + The kvm_device_attr.addr points to a __u32 value which is the number of + interrupt server numbers (ie, highest possible vcpu id plus one). + Errors: + -EINVAL: Value greater than KVM_MAX_VCPU_ID. + -EFAULT: Invalid user pointer for attr->addr. + -EBUSY: A vCPU is already connected to the device. + 2. KVM_DEV_XIVE_GRP_SOURCE (write only) Initializes a new source in the XIVE device and mask it. Attributes: diff --git a/MAINTAINERS b/MAINTAINERS index a69e6db80c79..e51a68bf8ca8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9122,7 +9122,7 @@ F: drivers/auxdisplay/ks0108.c F: include/linux/ks0108.h L3MDEV -M: David Ahern <dsa@cumulusnetworks.com> +M: David Ahern <dsahern@kernel.org> L: netdev@vger.kernel.org S: Maintained F: net/l3mdev @@ -10255,7 +10255,7 @@ MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@openwrt.org> M: John Crispin <john@phrozen.org> M: Sean Wang <sean.wang@mediatek.com> -M: Nelson Chang <nelson.chang@mediatek.com> +M: Mark Lee <Mark-MC.Lee@mediatek.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/mediatek/ @@ -12312,12 +12312,15 @@ F: arch/parisc/ F: Documentation/parisc/ F: drivers/parisc/ F: drivers/char/agp/parisc-agp.c +F: drivers/input/misc/hp_sdc_rtc.c F: drivers/input/serio/gscps2.c +F: drivers/input/serio/hp_sdc* F: drivers/parport/parport_gsc.* F: drivers/tty/serial/8250/8250_gsc.c F: drivers/video/fbdev/sti* F: drivers/video/console/sti* F: drivers/video/logo/logo_parisc* +F: include/linux/hp_sdc.h PARMAN M: Jiri Pirko <jiri@mellanox.com> @@ -13361,7 +13364,7 @@ S: Maintained F: drivers/scsi/qla1280.[ch] QLOGIC QLA2XXX FC-SCSI DRIVER -M: qla2xxx-upstream@qlogic.com +M: hmadhani@marvell.com L: linux-scsi@vger.kernel.org S: Supported F: Documentation/scsi/LICENSE.qla2xxx @@ -17430,7 +17433,7 @@ F: include/linux/regulator/ K: regulator_get_optional VRF -M: David Ahern <dsa@cumulusnetworks.com> +M: David Ahern <dsahern@kernel.org> M: Shrijeet Mukherjee <shrijeet@gmail.com> L: netdev@vger.kernel.org S: Maintained @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Nesting Opossum # *DOCUMENTATION* @@ -1037,7 +1037,7 @@ export KBUILD_VMLINUX_OBJS := $(head-y) $(init-y) $(core-y) $(libs-y2) \ export KBUILD_VMLINUX_LIBS := $(libs-y1) export KBUILD_LDS := arch/$(SRCARCH)/kernel/vmlinux.lds export LDFLAGS_vmlinux -# used by scripts/package/Makefile +# used by scripts/Makefile.package export KBUILD_ALLDIRS := $(sort $(filter-out arch/%,$(vmlinux-alldirs)) LICENSES arch include scripts tools) vmlinux-deps := $(KBUILD_LDS) $(KBUILD_VMLINUX_OBJS) $(KBUILD_VMLINUX_LIBS) diff --git a/arch/arm/boot/dts/mt7629-rfb.dts b/arch/arm/boot/dts/mt7629-rfb.dts index 3621b7d2b22a..9980c10c6e29 100644 --- a/arch/arm/boot/dts/mt7629-rfb.dts +++ b/arch/arm/boot/dts/mt7629-rfb.dts @@ -66,9 +66,21 @@ pinctrl-1 = <&ephy_leds_pins>; status = "okay"; + gmac0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "2500base-x"; + fixed-link { + speed = <2500>; + full-duplex; + pause; + }; + }; + gmac1: mac@1 { compatible = "mediatek,eth-mac"; reg = <1>; + phy-mode = "gmii"; phy-handle = <&phy0>; }; @@ -78,7 +90,6 @@ phy0: ethernet-phy@0 { reg = <0>; - phy-mode = "gmii"; }; }; }; diff --git a/arch/arm/boot/dts/mt7629.dtsi b/arch/arm/boot/dts/mt7629.dtsi index 9608bc2ccb3f..867b88103b9d 100644 --- a/arch/arm/boot/dts/mt7629.dtsi +++ b/arch/arm/boot/dts/mt7629.dtsi @@ -468,14 +468,12 @@ compatible = "mediatek,mt7629-sgmiisys", "syscon"; reg = <0x1b128000 0x3000>; #clock-cells = <1>; - mediatek,physpeed = "2500"; }; sgmiisys1: syscon@1b130000 { compatible = "mediatek,mt7629-sgmiisys", "syscon"; reg = <0x1b130000 0x3000>; #clock-cells = <1>; - mediatek,physpeed = "2500"; }; }; }; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 950a56b71ff0..3f047afb982c 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -616,6 +616,23 @@ config CAVIUM_ERRATUM_30115 If unsure, say Y. +config CAVIUM_TX2_ERRATUM_219 + bool "Cavium ThunderX2 erratum 219: PRFM between TTBR change and ISB fails" + default y + help + On Cavium ThunderX2, a load, store or prefetch instruction between a + TTBR update and the corresponding context synchronizing operation can + cause a spurious Data Abort to be delivered to any hardware thread in + the CPU core. + + Work around the issue by avoiding the problematic code sequence and + trapping KVM guest TTBRx_EL1 writes to EL2 when SMT is enabled. The + trap handler performs the corresponding register access, skips the + instruction and ensures context synchronization by virtue of the + exception return. + + If unsure, say Y. + config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" default y diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index f74909ba29bd..5bf963830b17 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -78,10 +78,9 @@ alternative_else_nop_endif /* * Remove the address tag from a virtual address, if present. */ - .macro clear_address_tag, dst, addr - tst \addr, #(1 << 55) - bic \dst, \addr, #(0xff << 56) - csel \dst, \dst, \addr, eq + .macro untagged_addr, dst, addr + sbfx \dst, \addr, #0, #56 + and \dst, \dst, \addr .endm #endif diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index f19fe4b9acc4..ac1dbca3d0cd 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -52,7 +52,9 @@ #define ARM64_HAS_IRQ_PRIO_MASKING 42 #define ARM64_HAS_DCPODP 43 #define ARM64_WORKAROUND_1463225 44 +#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 +#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 -#define ARM64_NCAPS 45 +#define ARM64_NCAPS 47 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b61b50bf68b1..c23c47360664 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -215,12 +215,18 @@ static inline unsigned long kaslr_offset(void) * up with a tagged userland pointer. Clear the tag to get a sane pointer to * pass on to access_ok(), for instance. */ -#define untagged_addr(addr) \ +#define __untagged_addr(addr) \ ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) +#define untagged_addr(addr) ({ \ + u64 __addr = (__force u64)addr; \ + __addr &= __untagged_addr(__addr); \ + (__force __typeof__(addr))__addr; \ +}) + #ifdef CONFIG_KASAN_SW_TAGS #define __tag_shifted(tag) ((u64)(tag) << 56) -#define __tag_reset(addr) untagged_addr(addr) +#define __tag_reset(addr) __untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else #define __tag_shifted(tag) 0UL diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7576df00eb50..8330810f699e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -876,9 +876,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) -#define kc_vaddr_to_offset(v) ((v) & ~PAGE_END) -#define kc_offset_to_vaddr(o) ((o) | PAGE_END) - #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) #else diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 972d196c7714..6e919fafb43d 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -212,7 +212,7 @@ #define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0) #define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0) -#define SYS_PAR_EL1_F BIT(1) +#define SYS_PAR_EL1_F BIT(0) #define SYS_PAR_EL1_FST GENMASK(6, 1) /*** Statistical Profiling Extension ***/ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 401246e095e7..df9465120e2f 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/cpufeature.h> +#include <asm/smp_plat.h> static bool __maybe_unused is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) @@ -587,6 +588,30 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope) return (need_wa > 0); } +static const __maybe_unused struct midr_range tx2_family_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), + MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), + {}, +}; + +static bool __maybe_unused +needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry, + int scope) +{ + int i; + + if (!is_affected_midr_range_list(entry, scope) || + !is_hyp_mode_available()) + return false; + + for_each_possible_cpu(i) { + if (MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0) != 0) + return true; + } + + return false; +} + #ifdef CONFIG_HARDEN_EL2_VECTORS static const struct midr_range arm64_harden_el2_vectors[] = { @@ -816,6 +841,19 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_cortex_a76_erratum_1463225, }, #endif +#ifdef CONFIG_CAVIUM_TX2_ERRATUM_219 + { + .desc = "Cavium ThunderX2 erratum 219 (KVM guest sysreg trapping)", + .capability = ARM64_WORKAROUND_CAVIUM_TX2_219_TVM, + ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), + .matches = needs_tx2_tvm_workaround, + }, + { + .desc = "Cavium ThunderX2 erratum 219 (PRFM removal)", + .capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM, + ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index cabebf1a7976..80f459ad0190 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -176,11 +176,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0), ARM64_FTR_END, }; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index e304fe04b098..cf3bd2976e57 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -604,7 +604,7 @@ el1_da: */ mrs x3, far_el1 inherit_daif pstate=x23, tmp=x2 - clear_address_tag x0, x3 + untagged_addr x0, x3 mov x2, sp // struct pt_regs bl do_mem_abort @@ -680,7 +680,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING orr x24, x24, x0 alternative_else_nop_endif cbnz x24, 1f // preempt count != 0 || NMI return path - bl preempt_schedule_irq // irq en/disable is done inside + bl arm64_preempt_schedule_irq // irq en/disable is done inside 1: #endif @@ -808,7 +808,7 @@ el0_da: mrs x26, far_el1 ct_user_exit_irqoff enable_daif - clear_address_tag x0, x26 + untagged_addr x0, x26 mov x1, x25 mov x2, sp bl do_mem_abort @@ -1071,7 +1071,9 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 #else ldr x30, =vectors #endif +alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM prfm plil1strm, [x30, #(1b - tramp_vectors)] +alternative_else_nop_endif msr vbar_el1, x30 add x30, x30, #(1b - tramp_vectors) isb diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index e0a7fce0e01c..a96b2921d22c 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -201,6 +201,7 @@ static int create_safe_exec_page(void *src_start, size_t length, gfp_t mask) { int rc = 0; + pgd_t *trans_pgd; pgd_t *pgdp; pud_t *pudp; pmd_t *pmdp; @@ -215,7 +216,13 @@ static int create_safe_exec_page(void *src_start, size_t length, memcpy((void *)dst, src_start, length); __flush_icache_range(dst, dst + length); - pgdp = pgd_offset_raw(allocator(mask), dst_addr); + trans_pgd = allocator(mask); + if (!trans_pgd) { + rc = -ENOMEM; + goto out; + } + + pgdp = pgd_offset_raw(trans_pgd, dst_addr); if (pgd_none(READ_ONCE(*pgdp))) { pudp = allocator(mask); if (!pudp) { diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 1fb2819fc048..71f788cd2b18 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -17,6 +17,7 @@ #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/kernel.h> +#include <linux/lockdep.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/sysctl.h> @@ -44,6 +45,7 @@ #include <asm/alternative.h> #include <asm/arch_gicv3.h> #include <asm/compat.h> +#include <asm/cpufeature.h> #include <asm/cacheflush.h> #include <asm/exec.h> #include <asm/fpsimd.h> @@ -631,3 +633,19 @@ static int __init tagged_addr_init(void) core_initcall(tagged_addr_init); #endif /* CONFIG_ARM64_TAGGED_ADDR_ABI */ + +asmlinkage void __sched arm64_preempt_schedule_irq(void) +{ + lockdep_assert_irqs_disabled(); + + /* + * Preempting a task from an IRQ means we leave copies of PSTATE + * on the stack. cpufeature's enable calls may modify PSTATE, but + * resuming one of these preempted tasks would undo those changes. + * + * Only allow a task to be preempted once cpufeatures have been + * enabled. + */ + if (static_branch_likely(&arm64_const_caps_ready)) + preempt_schedule_irq(); +} diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 3d3815020e36..799e84a40335 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -124,6 +124,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) { u64 hcr = vcpu->arch.hcr_el2; + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) + hcr |= HCR_TVM; + write_sysreg(hcr, hcr_el2); if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) @@ -174,8 +177,10 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) * the crucial bit is "On taking a vSError interrupt, * HCR_EL2.VSE is cleared to 0." */ - if (vcpu->arch.hcr_el2 & HCR_VSE) - vcpu->arch.hcr_el2 = read_sysreg(hcr_el2); + if (vcpu->arch.hcr_el2 & HCR_VSE) { + vcpu->arch.hcr_el2 &= ~HCR_VSE; + vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE; + } if (has_vhe()) deactivate_traps_vhe(); @@ -380,6 +385,61 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) return true; } +static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu)); + int rt = kvm_vcpu_sys_get_rt(vcpu); + u64 val = vcpu_get_reg(vcpu, rt); + + /* + * The normal sysreg handling code expects to see the traps, + * let's not do anything here. + */ + if (vcpu->arch.hcr_el2 & HCR_TVM) + return false; + + switch (sysreg) { + case SYS_SCTLR_EL1: + write_sysreg_el1(val, SYS_SCTLR); + break; + case SYS_TTBR0_EL1: + write_sysreg_el1(val, SYS_TTBR0); + break; + case SYS_TTBR1_EL1: + write_sysreg_el1(val, SYS_TTBR1); + break; + case SYS_TCR_EL1: + write_sysreg_el1(val, SYS_TCR); + break; + case SYS_ESR_EL1: + write_sysreg_el1(val, SYS_ESR); + break; + case SYS_FAR_EL1: + write_sysreg_el1(val, SYS_FAR); + break; + case SYS_AFSR0_EL1: + write_sysreg_el1(val, SYS_AFSR0); + break; + case SYS_AFSR1_EL1: + write_sysreg_el1(val, SYS_AFSR1); + break; + case SYS_MAIR_EL1: + write_sysreg_el1(val, SYS_MAIR); + break; + case SYS_AMAIR_EL1: + write_sysreg_el1(val, SYS_AMAIR); + break; + case SYS_CONTEXTIDR_EL1: + write_sysreg_el1(val, SYS_CONTEXTIDR); + break; + default: + return false; + } + + __kvm_skip_instr(vcpu); + return true; +} + /* * Return true when we were able to fixup the guest exit and should return to * the guest, false when we should restore the host state and return to the @@ -399,6 +459,11 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (*exit_code != ARM_EXCEPTION_TRAP) goto exit; + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && + kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 && + handle_tx2_tvm(vcpu)) + return true; + /* * We trap the first access to the FP/SIMD to save the host context * and restore the guest context lazily. diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 2071260a275b..46822afc57e0 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -632,6 +632,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); + if (!system_supports_32bit_el0()) + val |= ARMV8_PMU_PMCR_LC; __vcpu_sys_reg(vcpu, r->reg) = val; } @@ -682,6 +684,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, val = __vcpu_sys_reg(vcpu, PMCR_EL0); val &= ~ARMV8_PMU_PMCR_MASK; val |= p->regval & ARMV8_PMU_PMCR_MASK; + if (!system_supports_32bit_el0()) + val |= ARMV8_PMU_PMCR_LC; __vcpu_sys_reg(vcpu, PMCR_EL0) = val; kvm_pmu_handle_pmcr(vcpu, val); kvm_vcpu_pmu_restore_guest(vcpu); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 855f2a7954e6..9fc6db0bcbad 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -268,8 +268,12 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, par = read_sysreg(par_el1); local_irq_restore(flags); + /* + * If we now have a valid translation, treat the translation fault as + * spurious. + */ if (!(par & SYS_PAR_EL1_F)) - return false; + return true; /* * If we got a different type of fault from the AT instruction, diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h index 73ca89a47f49..e5de3f897633 100644 --- a/arch/parisc/include/asm/cache.h +++ b/arch/parisc/include/asm/cache.h @@ -22,7 +22,7 @@ #define ARCH_DMA_MINALIGN L1_CACHE_BYTES -#define __read_mostly __attribute__((__section__(".data..read_mostly"))) +#define __read_mostly __section(.data..read_mostly) void parisc_cache_init(void); /* initializes cache-flushing */ void disable_sr_hashing_asm(int); /* low level support for above */ diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index 3eb4bfc1fb36..e080143e79a3 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -52,7 +52,7 @@ }) #ifdef CONFIG_SMP -# define __lock_aligned __attribute__((__section__(".data..lock_aligned"))) +# define __lock_aligned __section(.data..lock_aligned) #endif #endif /* __PARISC_LDCW_H */ diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 92a9b5f12f98..f29f682352f0 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -3,7 +3,7 @@ * arch/parisc/mm/ioremap.c * * (C) Copyright 1995 1996 Linus Torvalds - * (C) Copyright 2001-2006 Helge Deller <deller@gmx.de> + * (C) Copyright 2001-2019 Helge Deller <deller@gmx.de> * (C) Copyright 2005 Kyle McMartin <kyle@parisc-linux.org> */ @@ -84,7 +84,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l addr = (void __iomem *) area->addr; if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, phys_addr, pgprot)) { - vfree(addr); + vunmap(addr); return NULL; } @@ -92,9 +92,11 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l } EXPORT_SYMBOL(__ioremap); -void iounmap(const volatile void __iomem *addr) +void iounmap(const volatile void __iomem *io_addr) { - if (addr > high_memory) - return vfree((void *) (PAGE_MASK & (unsigned long __force) addr)); + unsigned long addr = (unsigned long)io_addr & PAGE_MASK; + + if (is_vmalloc_addr((void *)addr)) + vunmap((void *)addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 6fe6ad64cba5..4273e799203d 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -401,7 +401,6 @@ struct kvmppc_mmu { u32 (*mfsrin)(struct kvm_vcpu *vcpu, u32 srnum); int (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data, bool iswrite); - void (*reset_msr)(struct kvm_vcpu *vcpu); void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large); int (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid); u64 (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data); diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index ee62776e5433..d63f649fe713 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -271,6 +271,7 @@ struct kvmppc_ops { union kvmppc_one_reg *val); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); + void (*inject_interrupt)(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr); int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index b3cbb1136bce..75c7e95a321b 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -748,6 +748,18 @@ #define SPRN_USPRG7 0x107 /* SPRG7 userspace read */ #define SPRN_SRR0 0x01A /* Save/Restore Register 0 */ #define SPRN_SRR1 0x01B /* Save/Restore Register 1 */ + +#ifdef CONFIG_PPC_BOOK3S +/* + * Bits loaded from MSR upon interrupt. + * PPC (64-bit) bits 33-36,42-47 are interrupt dependent, the others are + * loaded from MSR. The exception is that SRESET and MCE do not always load + * bit 62 (RI) from MSR. Don't use PPC_BITMASK for this because 32-bit uses + * it. + */ +#define SRR1_MSR_BITS (~0x783f0000UL) +#endif + #define SRR1_ISI_NOPT 0x40000000 /* ISI: Not found in hash */ #define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index b0f72dea8b11..264e266a85bf 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char { /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ +#define KVM_DEV_XICS_GRP_CTRL 2 +#define KVM_DEV_XICS_NR_SERVERS 1 /* Layout of 64-bit source attribute values */ #define KVM_XICS_DESTINATION_SHIFT 0 @@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char { #define KVM_DEV_XIVE_GRP_CTRL 1 #define KVM_DEV_XIVE_RESET 1 #define KVM_DEV_XIVE_EQ_SYNC 2 +#define KVM_DEV_XIVE_NR_SERVERS 3 #define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG 3 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_EQ_CONFIG 4 /* 64-bit EQ identifier */ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index ec2547cc5ecb..58a59ee998e2 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -74,27 +74,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) { - ulong pc = kvmppc_get_pc(vcpu); - ulong lr = kvmppc_get_lr(vcpu); - if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) - kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK); - if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) - kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK); - vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK; - } -} -EXPORT_SYMBOL_GPL(kvmppc_unfixup_split_real); - -static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) -{ - if (!is_kvmppc_hv_enabled(vcpu->kvm)) - return to_book3s(vcpu)->hior; - return 0; -} - static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, unsigned long pending_now, unsigned long old_pending) { @@ -134,11 +113,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) { - kvmppc_unfixup_split_real(vcpu); - kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu)); - kvmppc_set_srr1(vcpu, (kvmppc_get_msr(vcpu) & ~0x783f0000ul) | flags); - kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec); - vcpu->arch.mmu.reset_msr(vcpu); + vcpu->kvm->arch.kvm_ops->inject_interrupt(vcpu, vec, flags); } static int kvmppc_book3s_vec2irqprio(unsigned int vec) diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h index 2ef1311a2a13..3a4613985949 100644 --- a/arch/powerpc/kvm/book3s.h +++ b/arch/powerpc/kvm/book3s.h @@ -32,4 +32,7 @@ extern void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val); static inline void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val) {} #endif +extern void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr); +extern void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); + #endif diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 18f244aad7aa..f21e73492ce3 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -90,11 +90,6 @@ static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, return (((u64)eaddr >> 12) & 0xffff) | (vsid << 16); } -static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu) -{ - kvmppc_set_msr(vcpu, 0); -} - static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvm_vcpu *vcpu, u32 sre, gva_t eaddr, bool primary) @@ -406,7 +401,6 @@ void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu) mmu->mtsrin = kvmppc_mmu_book3s_32_mtsrin; mmu->mfsrin = kvmppc_mmu_book3s_32_mfsrin; mmu->xlate = kvmppc_mmu_book3s_32_xlate; - mmu->reset_msr = kvmppc_mmu_book3s_32_reset_msr; mmu->tlbie = kvmppc_mmu_book3s_32_tlbie; mmu->esid_to_vsid = kvmppc_mmu_book3s_32_esid_to_vsid; mmu->ea_to_vp = kvmppc_mmu_book3s_32_ea_to_vp; diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 5f63a5f7f24f..599133256a95 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -24,20 +24,6 @@ #define dprintk(X...) do { } while(0) #endif -static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu) -{ - unsigned long msr = vcpu->arch.intr_msr; - unsigned long cur_msr = kvmppc_get_msr(vcpu); - - /* If transactional, change to suspend mode on IRQ delivery */ - if (MSR_TM_TRANSACTIONAL(cur_msr)) - msr |= MSR_TS_S; - else - msr |= cur_msr & MSR_TS_MASK; - - kvmppc_set_msr(vcpu, msr); -} - static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe( struct kvm_vcpu *vcpu, gva_t eaddr) @@ -676,7 +662,6 @@ void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu) mmu->slbie = kvmppc_mmu_book3s_64_slbie; mmu->slbia = kvmppc_mmu_book3s_64_slbia; mmu->xlate = kvmppc_mmu_book3s_64_xlate; - mmu->reset_msr = kvmppc_mmu_book3s_64_reset_msr; mmu->tlbie = kvmppc_mmu_book3s_64_tlbie; mmu->esid_to_vsid = kvmppc_mmu_book3s_64_esid_to_vsid; mmu->ea_to_vp = kvmppc_mmu_book3s_64_ea_to_vp; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 9a75f0e1933b..d381526c5c9b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -275,18 +275,6 @@ int kvmppc_mmu_hv_init(void) return 0; } -static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu) -{ - unsigned long msr = vcpu->arch.intr_msr; - - /* If transactional, change to suspend mode on IRQ delivery */ - if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr)) - msr |= MSR_TS_S; - else - msr |= vcpu->arch.shregs.msr & MSR_TS_MASK; - kvmppc_set_msr(vcpu, msr); -} - static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel, unsigned long *pte_idx_ret) @@ -508,6 +496,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, struct vm_area_struct *vma; unsigned long rcbits; long mmio_update; + struct mm_struct *mm; if (kvm_is_radix(kvm)) return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr); @@ -584,6 +573,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, is_ci = false; pfn = 0; page = NULL; + mm = current->mm; pte_size = PAGE_SIZE; writing = (dsisr & DSISR_ISSTORE) != 0; /* If writing != 0, then the HPTE must allow writing, if we get here */ @@ -592,8 +582,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages); if (npages < 1) { /* Check if it's an I/O mapping */ - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, hva); + down_read(&mm->mmap_sem); + vma = find_vma(mm, hva); if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end && (vma->vm_flags & VM_PFNMAP)) { pfn = vma->vm_pgoff + @@ -602,7 +592,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot)))); write_ok = vma->vm_flags & VM_WRITE; } - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); if (!pfn) goto out_put; } else { @@ -621,8 +611,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, * hugepage split and collapse. */ local_irq_save(flags); - ptep = find_current_mm_pte(current->mm->pgd, - hva, NULL, NULL); + ptep = find_current_mm_pte(mm->pgd, hva, NULL, NULL); if (ptep) { pte = kvmppc_read_update_linux_pte(ptep, 1); if (__pte_write(pte)) @@ -2000,7 +1989,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf) ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC); if (ret < 0) { kfree(ctx); - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); return ret; } @@ -2161,7 +2150,6 @@ void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu) vcpu->arch.slb_nr = 32; /* POWER7/POWER8 */ mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate; - mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr; vcpu->arch.hflags |= BOOK3S_HFLAG_SLB; } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 5834db0a54c6..883a66e76638 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -317,7 +317,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, if (ret >= 0) list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); else - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); mutex_unlock(&kvm->lock); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 709cf1fd4cf4..ec5c0379296a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -133,7 +133,6 @@ static inline bool nesting_enabled(struct kvm *kvm) /* If set, the threads on each CPU core have to be in the same MMU mode */ static bool no_mixing_hpt_and_radix; -static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); /* @@ -338,18 +337,6 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } -static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) -{ - /* - * Check for illegal transactional state bit combination - * and if we find it, force the TS field to a safe state. - */ - if ((msr & MSR_TS_MASK) == MSR_TS_MASK) - msr &= ~MSR_TS_MASK; - vcpu->arch.shregs.msr = msr; - kvmppc_end_cede(vcpu); -} - static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) { vcpu->arch.pvr = pvr; @@ -792,6 +779,11 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, vcpu->arch.dawr = value1; vcpu->arch.dawrx = value2; return H_SUCCESS; + case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE: + /* KVM does not support mflags=2 (AIL=2) */ + if (mflags != 0 && mflags != 3) + return H_UNSUPPORTED_FLAG_START; + return H_TOO_HARD; default: return H_TOO_HARD; } @@ -2454,15 +2446,6 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) vcpu->arch.timer_running = 1; } -static void kvmppc_end_cede(struct kvm_vcpu *vcpu) -{ - vcpu->arch.ceded = 0; - if (vcpu->arch.timer_running) { - hrtimer_try_to_cancel(&vcpu->arch.dec_timer); - vcpu->arch.timer_running = 0; - } -} - extern int __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, @@ -5401,6 +5384,7 @@ static struct kvmppc_ops kvm_ops_hv = { .set_one_reg = kvmppc_set_one_reg_hv, .vcpu_load = kvmppc_core_vcpu_load_hv, .vcpu_put = kvmppc_core_vcpu_put_hv, + .inject_interrupt = kvmppc_inject_interrupt_hv, .set_msr = kvmppc_set_msr_hv, .vcpu_run = kvmppc_vcpu_run_hv, .vcpu_create = kvmppc_core_vcpu_create_hv, diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 7c1909657b55..7cd3cf3d366b 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -755,6 +755,71 @@ void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip) local_paca->kvm_hstate.kvm_split_mode = NULL; } +static void kvmppc_end_cede(struct kvm_vcpu *vcpu) +{ + vcpu->arch.ceded = 0; + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } +} + +void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) +{ + /* + * Check for illegal transactional state bit combination + * and if we find it, force the TS field to a safe state. + */ + if ((msr & MSR_TS_MASK) == MSR_TS_MASK) + msr &= ~MSR_TS_MASK; + vcpu->arch.shregs.msr = msr; + kvmppc_end_cede(vcpu); +} +EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv); + +static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) +{ + unsigned long msr, pc, new_msr, new_pc; + + msr = kvmppc_get_msr(vcpu); + pc = kvmppc_get_pc(vcpu); + new_msr = vcpu->arch.intr_msr; + new_pc = vec; + + /* If transactional, change to suspend mode on IRQ delivery */ + if (MSR_TM_TRANSACTIONAL(msr)) + new_msr |= MSR_TS_S; + else + new_msr |= msr & MSR_TS_MASK; + + /* + * Perform MSR and PC adjustment for LPCR[AIL]=3 if it is set and + * applicable. AIL=2 is not supported. + * + * AIL does not apply to SRESET, MCE, or HMI (which is never + * delivered to the guest), and does not apply if IR=0 or DR=0. + */ + if (vec != BOOK3S_INTERRUPT_SYSTEM_RESET && + vec != BOOK3S_INTERRUPT_MACHINE_CHECK && + (vcpu->arch.vcore->lpcr & LPCR_AIL) == LPCR_AIL_3 && + (msr & (MSR_IR|MSR_DR)) == (MSR_IR|MSR_DR) ) { + new_msr |= MSR_IR | MSR_DR; + new_pc += 0xC000000000004000ULL; + } + + kvmppc_set_srr0(vcpu, pc); + kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags); + kvmppc_set_pc(vcpu, new_pc); + vcpu->arch.shregs.msr = new_msr; +} + +void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) +{ + inject_interrupt(vcpu, vec, srr1_flags); + kvmppc_end_cede(vcpu); +} +EXPORT_SYMBOL_GPL(kvmppc_inject_interrupt_hv); + /* * Is there a PRIV_DOORBELL pending for the guest (on POWER9)? * Can we inject a Decrementer or a External interrupt? @@ -762,7 +827,6 @@ void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip) void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu) { int ext; - unsigned long vec = 0; unsigned long lpcr; /* Insert EXTERNAL bit into LPCR at the MER bit position */ @@ -774,26 +838,16 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu) if (vcpu->arch.shregs.msr & MSR_EE) { if (ext) { - vec = BOOK3S_INTERRUPT_EXTERNAL; + inject_interrupt(vcpu, BOOK3S_INTERRUPT_EXTERNAL, 0); } else { long int dec = mfspr(SPRN_DEC); if (!(lpcr & LPCR_LD)) dec = (int) dec; if (dec < 0) - vec = BOOK3S_INTERRUPT_DECREMENTER; + inject_interrupt(vcpu, + BOOK3S_INTERRUPT_DECREMENTER, 0); } } - if (vec) { - unsigned long msr, old_msr = vcpu->arch.shregs.msr; - - kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu)); - kvmppc_set_srr1(vcpu, old_msr); - kvmppc_set_pc(vcpu, vec); - msr = vcpu->arch.intr_msr; - if (MSR_TM_ACTIVE(old_msr)) - msr |= MSR_TS_S; - vcpu->arch.shregs.msr = msr; - } if (vcpu->arch.doorbell_request) { mtspr(SPRN_DPDES, 1); diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index cdf30c6eaf54..dc97e5be76f6 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -1186,7 +1186,7 @@ static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu, forward_to_l1: vcpu->arch.fault_dsisr = flags; if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) { - vcpu->arch.shregs.msr &= ~0x783f0000ul; + vcpu->arch.shregs.msr &= SRR1_MSR_BITS; vcpu->arch.shregs.msr |= flags; } return RESUME_HOST; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index cc65af8fe6f7..ce4fcf76e53e 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -90,7 +90,43 @@ static void kvmppc_fixup_split_real(struct kvm_vcpu *vcpu) kvmppc_set_pc(vcpu, pc | SPLIT_HACK_OFFS); } -void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu); +static void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) { + ulong pc = kvmppc_get_pc(vcpu); + ulong lr = kvmppc_get_lr(vcpu); + if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) + kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK); + if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) + kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK); + vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK; + } +} + +static void kvmppc_inject_interrupt_pr(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) +{ + unsigned long msr, pc, new_msr, new_pc; + + kvmppc_unfixup_split_real(vcpu); + + msr = kvmppc_get_msr(vcpu); + pc = kvmppc_get_pc(vcpu); + new_msr = vcpu->arch.intr_msr; + new_pc = to_book3s(vcpu)->hior + vec; + +#ifdef CONFIG_PPC_BOOK3S_64 + /* If transactional, change to suspend mode on IRQ delivery */ + if (MSR_TM_TRANSACTIONAL(msr)) + new_msr |= MSR_TS_S; + else + new_msr |= msr & MSR_TS_MASK; +#endif + + kvmppc_set_srr0(vcpu, pc); + kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags); + kvmppc_set_pc(vcpu, new_pc); + kvmppc_set_msr(vcpu, new_msr); +} static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) { @@ -1761,6 +1797,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm, #else /* default to book3s_32 (750) */ vcpu->arch.pvr = 0x84202; + vcpu->arch.intr_msr = 0; #endif kvmppc_set_pvr_pr(vcpu, vcpu->arch.pvr); vcpu->arch.slb_nr = 64; @@ -2058,6 +2095,7 @@ static struct kvmppc_ops kvm_ops_pr = { .set_one_reg = kvmppc_set_one_reg_pr, .vcpu_load = kvmppc_core_vcpu_load_pr, .vcpu_put = kvmppc_core_vcpu_put_pr, + .inject_interrupt = kvmppc_inject_interrupt_pr, .set_msr = kvmppc_set_msr_pr, .vcpu_run = kvmppc_vcpu_run_pr, .vcpu_create = kvmppc_core_vcpu_create_pr, diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 591bfb4bfd0f..66858b7d3c6b 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1211,12 +1211,52 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.xive_vcpu = NULL; } +static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu) +{ + /* We have a block of xive->nr_servers VPs. We just need to check + * raw vCPU ids are below the expected limit for this guest's + * core stride ; kvmppc_pack_vcpu_id() will pack them down to an + * index that can be safely used to compute a VP id that belongs + * to the VP block. + */ + return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode; +} + +int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp) +{ + u32 vp_id; + + if (!kvmppc_xive_vcpu_id_valid(xive, cpu)) { + pr_devel("Out of bounds !\n"); + return -EINVAL; + } + + if (xive->vp_base == XIVE_INVALID_VP) { + xive->vp_base = xive_native_alloc_vp_block(xive->nr_servers); + pr_devel("VP_Base=%x nr_servers=%d\n", xive->vp_base, xive->nr_servers); + + if (xive->vp_base == XIVE_INVALID_VP) + return -ENOSPC; + } + + vp_id = kvmppc_xive_vp(xive, cpu); + if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) { + pr_devel("Duplicate !\n"); + return -EEXIST; + } + + *vp = vp_id; + + return 0; +} + int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu) { struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc; int i, r = -EBUSY; + u32 vp_id; pr_devel("connect_vcpu(cpu=%d)\n", cpu); @@ -1228,25 +1268,25 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, return -EPERM; if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) return -EBUSY; - if (kvmppc_xive_find_server(vcpu->kvm, cpu)) { - pr_devel("Duplicate !\n"); - return -EEXIST; - } - if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { - pr_devel("Out of bounds !\n"); - return -EINVAL; - } - xc = kzalloc(sizeof(*xc), GFP_KERNEL); - if (!xc) - return -ENOMEM; /* We need to synchronize with queue provisioning */ mutex_lock(&xive->lock); + + r = kvmppc_xive_compute_vp_id(xive, cpu, &vp_id); + if (r) + goto bail; + + xc = kzalloc(sizeof(*xc), GFP_KERNEL); + if (!xc) { + r = -ENOMEM; + goto bail; + } + vcpu->arch.xive_vcpu = xc; xc->xive = xive; xc->vcpu = vcpu; xc->server_num = cpu; - xc->vp_id = kvmppc_xive_vp(xive, cpu); + xc->vp_id = vp_id; xc->mfrr = 0xff; xc->valid = true; @@ -1826,6 +1866,43 @@ int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, return 0; } +int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr) +{ + u32 __user *ubufp = (u32 __user *) addr; + u32 nr_servers; + int rc = 0; + + if (get_user(nr_servers, ubufp)) + return -EFAULT; + + pr_devel("%s nr_servers=%u\n", __func__, nr_servers); + + if (!nr_servers || nr_servers > KVM_MAX_VCPU_ID) + return -EINVAL; + + mutex_lock(&xive->lock); + if (xive->vp_base != XIVE_INVALID_VP) + /* The VP block is allocated once and freed when the device + * is released. Better not allow to change its size since its + * used by connect_vcpu to validate vCPU ids are valid (eg, + * setting it back to a higher value could allow connect_vcpu + * to come up with a VP id that goes beyond the VP block, which + * is likely to cause a crash in OPAL). + */ + rc = -EBUSY; + else if (nr_servers > KVM_MAX_VCPUS) + /* We don't need more servers. Higher vCPU ids get packed + * down below KVM_MAX_VCPUS by kvmppc_pack_vcpu_id(). + */ + xive->nr_servers = KVM_MAX_VCPUS; + else + xive->nr_servers = nr_servers; + + mutex_unlock(&xive->lock); + + return rc; +} + static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { struct kvmppc_xive *xive = dev->private; @@ -1834,6 +1911,11 @@ static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) switch (attr->group) { case KVM_DEV_XICS_GRP_SOURCES: return xive_set_source(xive, attr->attr, attr->addr); + case KVM_DEV_XICS_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_XICS_NR_SERVERS: + return kvmppc_xive_set_nr_servers(xive, attr->addr); + } } return -ENXIO; } @@ -1859,6 +1941,11 @@ static int xive_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) attr->attr < KVMPPC_XICS_NR_IRQS) return 0; break; + case KVM_DEV_XICS_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_XICS_NR_SERVERS: + return 0; + } } return -ENXIO; } @@ -1993,10 +2080,13 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) { struct kvmppc_xive *xive; struct kvm *kvm = dev->kvm; - int ret = 0; pr_devel("Creating xive for partition\n"); + /* Already there ? */ + if (kvm->arch.xive) + return -EEXIST; + xive = kvmppc_xive_get_device(kvm, type); if (!xive) return -ENOMEM; @@ -2006,12 +2096,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->kvm = kvm; mutex_init(&xive->lock); - /* Already there ? */ - if (kvm->arch.xive) - ret = -EEXIST; - else - kvm->arch.xive = xive; - /* We use the default queue size set by the host */ xive->q_order = xive_native_default_eq_shift(); if (xive->q_order < PAGE_SHIFT) @@ -2019,18 +2103,16 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) else xive->q_page_order = xive->q_order - PAGE_SHIFT; - /* Allocate a bunch of VPs */ - xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS); - pr_devel("VP_Base=%x\n", xive->vp_base); - - if (xive->vp_base == XIVE_INVALID_VP) - ret = -ENOMEM; + /* VP allocation is delayed to the first call to connect_vcpu */ + xive->vp_base = XIVE_INVALID_VP; + /* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets + * on a POWER9 system. + */ + xive->nr_servers = KVM_MAX_VCPUS; xive->single_escalation = xive_native_has_single_escalation(); - if (ret) - return ret; - + kvm->arch.xive = xive; return 0; } @@ -2100,9 +2182,9 @@ static int xive_debug_show(struct seq_file *m, void *private) if (!xc) continue; - seq_printf(m, "cpu server %#x CPPR:%#x HWCPPR:%#x" + seq_printf(m, "cpu server %#x VP:%#x CPPR:%#x HWCPPR:%#x" " MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n", - xc->server_num, xc->cppr, xc->hw_cppr, + xc->server_num, xc->vp_id, xc->cppr, xc->hw_cppr, xc->mfrr, xc->pending, xc->stat_rm_h_xirr, xc->stat_vm_h_xirr); diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 955b820ffd6d..382e3a56e789 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -135,6 +135,9 @@ struct kvmppc_xive { /* Flags */ u8 single_escalation; + /* Number of entries in the VP block */ + u32 nr_servers; + struct kvmppc_xive_ops *ops; struct address_space *mapping; struct mutex mapping_lock; @@ -220,6 +223,18 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); } +static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) +{ + struct kvm_vcpu *vcpu = NULL; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) + return true; + } + return false; +} + /* * Mapping between guest priorities and host priorities * is as follow. @@ -284,6 +299,8 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio, struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type); void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu, struct kvmppc_xive_vcpu *xc, int irq); +int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp); +int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr); #endif /* CONFIG_KVM_XICS */ #endif /* _KVM_PPC_BOOK3S_XICS_H */ diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 248c1ea9e788..34bd123fa024 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -106,6 +106,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc = NULL; int rc; + u32 vp_id; pr_devel("native_connect_vcpu(server=%d)\n", server_num); @@ -117,18 +118,12 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, return -EPERM; if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) return -EBUSY; - if (server_num >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { - pr_devel("Out of bounds !\n"); - return -EINVAL; - } mutex_lock(&xive->lock); - if (kvmppc_xive_find_server(vcpu->kvm, server_num)) { - pr_devel("Duplicate !\n"); - rc = -EEXIST; + rc = kvmppc_xive_compute_vp_id(xive, server_num, &vp_id); + if (rc) goto bail; - } xc = kzalloc(sizeof(*xc), GFP_KERNEL); if (!xc) { @@ -141,7 +136,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, xc->vcpu = vcpu; xc->server_num = server_num; - xc->vp_id = kvmppc_xive_vp(xive, server_num); + xc->vp_id = vp_id; xc->valid = true; vcpu->arch.irq_type = KVMPPC_IRQ_XIVE; @@ -926,6 +921,8 @@ static int kvmppc_xive_native_set_attr(struct kvm_device *dev, return kvmppc_xive_reset(xive); case KVM_DEV_XIVE_EQ_SYNC: return kvmppc_xive_native_eq_sync(xive); + case KVM_DEV_XIVE_NR_SERVERS: + return kvmppc_xive_set_nr_servers(xive, attr->addr); } break; case KVM_DEV_XIVE_GRP_SOURCE: @@ -965,6 +962,7 @@ static int kvmppc_xive_native_has_attr(struct kvm_device *dev, switch (attr->attr) { case KVM_DEV_XIVE_RESET: case KVM_DEV_XIVE_EQ_SYNC: + case KVM_DEV_XIVE_NR_SERVERS: return 0; } break; @@ -1065,7 +1063,6 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) { struct kvmppc_xive *xive; struct kvm *kvm = dev->kvm; - int ret = 0; pr_devel("Creating xive native device\n"); @@ -1079,27 +1076,20 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) dev->private = xive; xive->dev = dev; xive->kvm = kvm; - kvm->arch.xive = xive; mutex_init(&xive->mapping_lock); mutex_init(&xive->lock); - /* - * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for - * a default. Getting the max number of CPUs the VM was - * configured with would improve our usage of the XIVE VP space. + /* VP allocation is delayed to the first call to connect_vcpu */ + xive->vp_base = XIVE_INVALID_VP; + /* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets + * on a POWER9 system. */ - xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS); - pr_devel("VP_Base=%x\n", xive->vp_base); - - if (xive->vp_base == XIVE_INVALID_VP) - ret = -ENXIO; + xive->nr_servers = KVM_MAX_VCPUS; xive->single_escalation = xive_native_has_single_escalation(); xive->ops = &kvmppc_xive_native_ops; - if (ret) - return ret; - + kvm->arch.xive = xive; return 0; } @@ -1202,8 +1192,8 @@ static int xive_native_debug_show(struct seq_file *m, void *private) if (!xc) continue; - seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n", - xc->server_num, + seq_printf(m, "cpu server %#x VP=%#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n", + xc->server_num, xc->vp_id, vcpu->arch.xive_saved_state.nsr, vcpu->arch.xive_saved_state.cppr, vcpu->arch.xive_saved_state.ipb, diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 321db0fdb9db..425d13806645 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -355,9 +355,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, if (tlbsel == 1) { struct vm_area_struct *vma; - down_read(¤t->mm->mmap_sem); + down_read(&kvm->mm->mmap_sem); - vma = find_vma(current->mm, hva); + vma = find_vma(kvm->mm, hva); if (vma && hva >= vma->vm_start && (vma->vm_flags & VM_PFNMAP)) { /* @@ -441,7 +441,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); } - up_read(¤t->mm->mmap_sem); + up_read(&kvm->mm->mmap_sem); } if (likely(!pfnmap)) { diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 3a77bb643452..9e085e931d74 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -522,6 +522,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; + case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: + /* fall through */ case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_OSI: case KVM_CAP_PPC_GET_PVINFO: diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 104d334511cd..88cfcb96bf23 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -13,6 +13,7 @@ compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000"; chosen { + stdout-path = "serial0"; }; cpus { diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 7255f2d8395b..42292d99cc74 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -87,14 +87,6 @@ extern pgd_t swapper_pg_dir[]; #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) -#define FIXADDR_TOP VMALLOC_START -#ifdef CONFIG_64BIT -#define FIXADDR_SIZE PMD_SIZE -#else -#define FIXADDR_SIZE PGDIR_SIZE -#endif -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - /* * Roughly size the vmemmap space to be large enough to fit enough * struct pages to map half the virtual address space. Then @@ -108,6 +100,14 @@ extern pgd_t swapper_pg_dir[]; #define vmemmap ((struct page *)VMEMMAP_START) +#define FIXADDR_TOP (VMEMMAP_START) +#ifdef CONFIG_64BIT +#define FIXADDR_SIZE PMD_SIZE +#else +#define FIXADDR_SIZE PGDIR_SIZE +#endif +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) + /* * ZERO_PAGE is a global shared page that is always zero, * used for zero-mapped memory areas, etc. diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 37ae4e367ad2..f02188a5b0f4 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -10,10 +10,6 @@ #include <linux/mm_types.h> #include <asm/smp.h> -/* - * Flush entire local TLB. 'sfence.vma' implicitly fences with the instruction - * cache as well, so a 'fence.i' is not necessary. - */ static inline void local_flush_tlb_all(void) { __asm__ __volatile__ ("sfence.vma" : : : "memory"); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 93742df9067f..1ac75f7d0bff 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -124,24 +124,24 @@ static inline unsigned long get_break_insn_length(unsigned long pc) asmlinkage void do_trap_break(struct pt_regs *regs) { - if (!user_mode(regs)) { + if (user_mode(regs)) { + force_sig_fault(SIGTRAP, TRAP_BRKPT, + (void __user *)(regs->sepc)); + return; + } +#ifdef CONFIG_GENERIC_BUG + { enum bug_trap_type type; type = report_bug(regs->sepc, regs); - switch (type) { -#ifdef CONFIG_GENERIC_BUG - case BUG_TRAP_TYPE_WARN: + if (type == BUG_TRAP_TYPE_WARN) { regs->sepc += get_break_insn_length(regs->sepc); return; - case BUG_TRAP_TYPE_BUG: -#endif /* CONFIG_GENERIC_BUG */ - default: - die(regs, "Kernel BUG"); } - } else { - force_sig_fault(SIGTRAP, TRAP_BRKPT, - (void __user *)(regs->sepc)); } +#endif /* CONFIG_GENERIC_BUG */ + + die(regs, "Kernel BUG"); } #ifdef CONFIG_GENERIC_BUG diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index abe60268335d..02f4c21c57f6 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -392,6 +392,7 @@ struct kvm_vcpu_stat { u64 diagnose_10; u64 diagnose_44; u64 diagnose_9c; + u64 diagnose_9c_ignored; u64 diagnose_258; u64 diagnose_308; u64 diagnose_500; diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 45634b3d2e0a..3fb54ec2cf3e 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -158,14 +158,28 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; vcpu->stat.diagnose_9c++; - VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid); + /* yield to self */ if (tid == vcpu->vcpu_id) - return 0; + goto no_yield; + /* yield to invalid */ tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid); - if (tcpu) - kvm_vcpu_yield_to(tcpu); + if (!tcpu) + goto no_yield; + + /* target already running */ + if (READ_ONCE(tcpu->cpu) >= 0) + goto no_yield; + + if (kvm_vcpu_yield_to(tcpu) <= 0) + goto no_yield; + + VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: done", tid); + return 0; +no_yield: + VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid); + vcpu->stat.diagnose_9c_ignored++; return 0; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index d1ccc168c071..165dea4c7f19 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1477,8 +1477,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) return 0; } -static int __inject_sigp_restart(struct kvm_vcpu *vcpu, - struct kvm_s390_irq *irq) +static int __inject_sigp_restart(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -2007,7 +2006,7 @@ static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) rc = __inject_sigp_stop(vcpu, irq); break; case KVM_S390_RESTART: - rc = __inject_sigp_restart(vcpu, irq); + rc = __inject_sigp_restart(vcpu); break; case KVM_S390_INT_CLOCK_COMP: rc = __inject_ckc(vcpu); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d047e846e1b9..d9e6bf3d54f0 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -155,6 +155,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_diag_10", VCPU_STAT(diagnose_10) }, { "instruction_diag_44", VCPU_STAT(diagnose_44) }, { "instruction_diag_9c", VCPU_STAT(diagnose_9c) }, + { "diag_9c_ignored", VCPU_STAT(diagnose_9c_ignored) }, { "instruction_diag_258", VCPU_STAT(diagnose_258) }, { "instruction_diag_308", VCPU_STAT(diagnose_308) }, { "instruction_diag_500", VCPU_STAT(diagnose_500) }, @@ -453,16 +454,14 @@ static void kvm_s390_cpu_feat_init(void) int kvm_arch_init(void *opaque) { - int rc; + int rc = -ENOMEM; kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long)); if (!kvm_s390_dbf) return -ENOMEM; - if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) { - rc = -ENOMEM; - goto out_debug_unreg; - } + if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) + goto out; kvm_s390_cpu_feat_init(); @@ -470,19 +469,17 @@ int kvm_arch_init(void *opaque) rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); if (rc) { pr_err("A FLIC registration call failed with rc=%d\n", rc); - goto out_debug_unreg; + goto out; } rc = kvm_s390_gib_init(GAL_ISC); if (rc) - goto out_gib_destroy; + goto out; return 0; -out_gib_destroy: - kvm_s390_gib_destroy(); -out_debug_unreg: - debug_unregister(kvm_s390_dbf); +out: + kvm_arch_exit(); return rc; } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index fbc1aecf0f94..eb24cb1afc11 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -29,7 +29,6 @@ config SPARC select RTC_DRV_M48T59 select RTC_SYSTOHC select HAVE_ARCH_JUMP_LABEL if SPARC64 - select HAVE_FAST_GUP if SPARC64 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 149795c369f2..25019d42ae93 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -21,30 +21,6 @@ struct mem_vector immovable_mem[MAX_NUMNODES*2]; /* - * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex - * digits, and '\0' for termination. - */ -#define MAX_ADDR_LEN 19 - -static acpi_physical_address get_cmdline_acpi_rsdp(void) -{ - acpi_physical_address addr = 0; - -#ifdef CONFIG_KEXEC - char val[MAX_ADDR_LEN] = { }; - int ret; - - ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); - if (ret < 0) - return 0; - - if (kstrtoull(val, 16, &addr)) - return 0; -#endif - return addr; -} - -/* * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and * ACPI_TABLE_GUID are found, take the former, which has more features. */ @@ -298,6 +274,30 @@ acpi_physical_address get_rsdp_addr(void) } #if defined(CONFIG_RANDOMIZE_BASE) && defined(CONFIG_MEMORY_HOTREMOVE) +/* + * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex + * digits, and '\0' for termination. + */ +#define MAX_ADDR_LEN 19 + +static acpi_physical_address get_cmdline_acpi_rsdp(void) +{ + acpi_physical_address addr = 0; + +#ifdef CONFIG_KEXEC + char val[MAX_ADDR_LEN] = { }; + int ret; + + ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); + if (ret < 0) + return 0; + + if (kstrtoull(val, 16, &addr)) + return 0; +#endif + return addr; +} + /* Compute SRAT address from RSDP. */ static unsigned long get_acpi_srat_table(void) { diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 53ac0cb2396d..9652d5c2afda 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -345,6 +345,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, { const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + unsigned long needed_size; /* Retain x86 boot parameters pointer passed from startup_32/64. */ boot_params = rmode; @@ -379,26 +380,38 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + * + * On X86_64, the memory is mapped with PMD pages. Round the + * size up so that the full extent of PMD pages mapped is + * included in the check against the valid memory table + * entries. This ensures the full mapped area is usable RAM + * and doesn't include any reserved areas. + */ + needed_size = max(output_len, kernel_total_size); +#ifdef CONFIG_X86_64 + needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN); +#endif + /* Report initial kernel position details. */ debug_putaddr(input_data); debug_putaddr(input_len); debug_putaddr(output); debug_putaddr(output_len); debug_putaddr(kernel_total_size); + debug_putaddr(needed_size); #ifdef CONFIG_X86_64 /* Report address of 32-bit trampoline */ debug_putaddr(trampoline_32bit); #endif - /* - * The memory hole needed for the kernel is the larger of either - * the entire decompressed kernel plus relocation table, or the - * entire decompressed kernel plus .bss and .brk sections. - */ choose_random_location((unsigned long)input_data, input_len, (unsigned long *)&output, - max(output_len, kernel_total_size), + needed_size, &virt_addr); /* Validate memory location choices. */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fcef678c3423..937363b803c1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3323,8 +3323,19 @@ static int intel_pmu_hw_config(struct perf_event *event) return 0; } +#ifdef CONFIG_RETPOLINE +static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr); +static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr); +#endif + struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) { +#ifdef CONFIG_RETPOLINE + if (x86_pmu.guest_get_msrs == intel_guest_get_msrs) + return intel_guest_get_msrs(nr); + else if (x86_pmu.guest_get_msrs == core_guest_get_msrs) + return core_guest_get_msrs(nr); +#endif if (x86_pmu.guest_get_msrs) return x86_pmu.guest_get_msrs(nr); *nr = 0; diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5c056b8aebef..e01078e93dd3 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -260,11 +260,21 @@ void __init hv_apic_init(void) } if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) { - pr_info("Hyper-V: Using MSR based APIC access\n"); + pr_info("Hyper-V: Using enlightened APIC (%s mode)", + x2apic_enabled() ? "x2apic" : "xapic"); + /* + * With x2apic, architectural x2apic MSRs are equivalent to the + * respective synthetic MSRs, so there's no need to override + * the apic accessors. The only exception is + * hv_apic_eoi_write, because it benefits from lazy EOI when + * available, but it works for both xapic and x2apic modes. + */ apic_set_eoi_write(hv_apic_eoi_write); - apic->read = hv_apic_read; - apic->write = hv_apic_write; - apic->icr_write = hv_apic_icr_write; - apic->icr_read = hv_apic_icr_read; + if (!x2apic_enabled()) { + apic->read = hv_apic_read; + apic->write = hv_apic_write; + apic->icr_write = hv_apic_icr_write; + apic->icr_read = hv_apic_icr_read; + } } } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 50eb430b0ad8..898ab9eb4dc8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -156,10 +156,8 @@ enum kvm_reg { VCPU_REGS_R15 = __VCPU_REGS_R15, #endif VCPU_REGS_RIP, - NR_VCPU_REGS -}; + NR_VCPU_REGS, -enum kvm_reg_ex { VCPU_EXREG_PDPTR = NR_VCPU_REGS, VCPU_EXREG_CR3, VCPU_EXREG_RFLAGS, @@ -451,6 +449,11 @@ struct kvm_pmc { u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; + /* + * eventsel value for general purpose counters, + * ctrl value for fixed counters. + */ + u64 current_config; }; struct kvm_pmu { @@ -469,7 +472,21 @@ struct kvm_pmu { struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED]; struct irq_work irq_work; - u64 reprogram_pmi; + DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); + DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); + DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); + + /* + * The gate to release perf_events not marked in + * pmc_in_use only once in a vcpu time slice. + */ + bool need_cleanup; + + /* + * The total number of programmed perf_events and it helps to avoid + * redundant check before cleanup if guest don't use vPMU at all. + */ + u8 event_count; }; struct kvm_pmu_ops; @@ -562,6 +579,7 @@ struct kvm_vcpu_arch { u64 smbase; u64 smi_count; bool tpr_access_reporting; + bool xsaves_enabled; u64 ia32_xss; u64 microcode_version; u64 arch_capabilities; @@ -1035,7 +1053,6 @@ struct kvm_x86_ops { struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu); - void (*decache_cr3)(struct kvm_vcpu *vcpu); void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -1084,7 +1101,7 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); - bool (*get_enable_apicv)(struct kvm_vcpu *vcpu); + bool (*get_enable_apicv)(struct kvm *kvm); void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); @@ -1571,6 +1588,8 @@ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); void kvm_make_mclock_inprogress_request(struct kvm *kvm); void kvm_make_scan_ioapic_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap); void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 45e92cba92f5..b0889c48a2ac 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -156,7 +156,8 @@ static int x2apic_dead_cpu(unsigned int dead_cpu) { struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu); - cpumask_clear_cpu(dead_cpu, &cmsk->mask); + if (cmsk) + cpumask_clear_cpu(dead_cpu, &cmsk->mask); free_cpumask_var(per_cpu(ipi_mask, dead_cpu)); return 0; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 267daad8c036..c656d92cd708 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -216,6 +216,10 @@ static void __init ms_hyperv_init_platform(void) int hv_host_info_ecx; int hv_host_info_edx; +#ifdef CONFIG_PARAVIRT + pv_info.name = "Hyper-V"; +#endif + /* * Extract the features and hints */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 29ffa495bd1c..206a4b6144c2 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -222,13 +222,31 @@ unsigned long __head __startup_64(unsigned long physaddr, * we might write invalid pmds, when the kernel is relocated * cleanup_highmap() fixes this up along with the mappings * beyond _end. + * + * Only the region occupied by the kernel image has so far + * been checked against the table of usable memory regions + * provided by the firmware, so invalidate pages outside that + * region. A page table entry that maps to a reserved area of + * memory would allow processor speculation into that area, + * and on some hardware (particularly the UV platform) even + * speculative access to some reserved areas is caught as an + * error, causing the BIOS to halt the system. */ pmd = fixup_pointer(level2_kernel_pgt, physaddr); - for (i = 0; i < PTRS_PER_PMD; i++) { + + /* invalidate pages before the kernel image */ + for (i = 0; i < pmd_index((unsigned long)_text); i++) + pmd[i] &= ~_PAGE_PRESENT; + + /* fixup pages that are part of the kernel image */ + for (; i <= pmd_index((unsigned long)_end); i++) if (pmd[i] & _PAGE_PRESENT) pmd[i] += load_delta; - } + + /* invalidate pages after the kernel image */ + for (; i < PTRS_PER_PMD; i++) + pmd[i] &= ~_PAGE_PRESENT; /* * Fixup phys_base - remove the memory encryption mask to obtain diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e820568ed4d5..32ef1ee733b7 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -33,6 +33,7 @@ #include <asm/apicdef.h> #include <asm/hypervisor.h> #include <asm/tlb.h> +#include <asm/cpuidle_haltpoll.h> static int kvmapf = 1; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9c5029cf6f3f..f68c0c753c38 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -363,7 +363,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 698efb8c3897..952d1a4f4d7e 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2770,11 +2770,10 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) return emulate_ud(ctxt); ops->get_msr(ctxt, MSR_EFER, &efer); - setup_syscalls_segments(ctxt, &cs, &ss); - if (!(efer & EFER_SCE)) return emulate_ud(ctxt); + setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_STAR, &msr_data); msr_data >>= 32; cs_sel = (u16)(msr_data & 0xfffc); @@ -2838,12 +2837,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_PROT64) return X86EMUL_UNHANDLEABLE; - setup_syscalls_segments(ctxt, &cs, &ss); - ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); + setup_syscalls_segments(ctxt, &cs, &ss); ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index d859ae8890d0..9fd2dd89a1c5 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -271,8 +271,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; bool mask_before, mask_after; - int old_remote_irr, old_delivery_status; union kvm_ioapic_redirect_entry *e; + unsigned long vcpu_bitmap; + int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -296,6 +297,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) /* Preserve read-only fields */ old_remote_irr = e->fields.remote_irr; old_delivery_status = e->fields.delivery_status; + old_dest_id = e->fields.dest_id; + old_dest_mode = e->fields.dest_mode; if (ioapic->ioregsel & 1) { e->bits &= 0xffffffff; e->bits |= (u64) val << 32; @@ -321,7 +324,34 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && ioapic->irr & (1 << index)) ioapic_service(ioapic, index, false); - kvm_make_scan_ioapic_request(ioapic->kvm); + if (e->fields.delivery_mode == APIC_DM_FIXED) { + struct kvm_lapic_irq irq; + + irq.shorthand = 0; + irq.vector = e->fields.vector; + irq.delivery_mode = e->fields.delivery_mode << 8; + irq.dest_id = e->fields.dest_id; + irq.dest_mode = e->fields.dest_mode; + bitmap_zero(&vcpu_bitmap, 16); + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + if (old_dest_mode != e->fields.dest_mode || + old_dest_id != e->fields.dest_id) { + /* + * Update vcpu_bitmap with vcpus specified in + * the previous request as well. This is done to + * keep ioapic_handled_vectors synchronized. + */ + irq.dest_id = old_dest_id; + irq.dest_mode = old_dest_mode; + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + } + kvm_make_scan_ioapic_request_mask(ioapic->kvm, + &vcpu_bitmap); + } else { + kvm_make_scan_ioapic_request(ioapic->kvm); + } break; } } diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 1cc6c47dc77e..58767020de41 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -37,22 +37,50 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif -static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, - enum kvm_reg reg) +static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) { - if (!test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail)) + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) +{ + if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) + return 0; + + if (!kvm_register_is_available(vcpu, reg)) kvm_x86_ops->cache_reg(vcpu, reg); return vcpu->arch.regs[reg]; } -static inline void kvm_register_write(struct kvm_vcpu *vcpu, - enum kvm_reg reg, +static inline void kvm_register_write(struct kvm_vcpu *vcpu, int reg, unsigned long val) { + if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) + return; + vcpu->arch.regs[reg] = val; - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + kvm_register_mark_dirty(vcpu, reg); } static inline unsigned long kvm_rip_read(struct kvm_vcpu *vcpu) @@ -79,9 +107,8 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) { might_sleep(); /* on svm */ - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail)) - kvm_x86_ops->cache_reg(vcpu, (enum kvm_reg)VCPU_EXREG_PDPTR); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) + kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR); return vcpu->arch.walk_mmu->pdptrs[index]; } @@ -109,8 +136,8 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - kvm_x86_ops->decache_cr3(vcpu); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) + kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3); return vcpu->arch.cr3; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 87b0fcc23ef8..452cedd6382b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -562,60 +562,53 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, irq->level, irq->trig_mode, dest_map); } +static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map, + struct kvm_lapic_irq *irq, u32 min) +{ + int i, count = 0; + struct kvm_vcpu *vcpu; + + if (min > map->max_apic_id) + return 0; + + for_each_set_bit(i, ipi_bitmap, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, irq, NULL); + } + } + + return count; +} + int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { - int i; struct kvm_apic_map *map; - struct kvm_vcpu *vcpu; struct kvm_lapic_irq irq = {0}; int cluster_size = op_64_bit ? 64 : 32; - int count = 0; + int count; + + if (icr & (APIC_DEST_MASK | APIC_SHORT_MASK)) + return -KVM_EINVAL; irq.vector = icr & APIC_VECTOR_MASK; irq.delivery_mode = icr & APIC_MODE_MASK; irq.level = (icr & APIC_INT_ASSERT) != 0; irq.trig_mode = icr & APIC_INT_LEVELTRIG; - if (icr & APIC_DEST_MASK) - return -KVM_EINVAL; - if (icr & APIC_SHORT_MASK) - return -KVM_EINVAL; - rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); - if (unlikely(!map)) { - count = -EOPNOTSUPP; - goto out; - } - - if (min > map->max_apic_id) - goto out; - /* Bits above cluster_size are masked in the caller. */ - for_each_set_bit(i, &ipi_bitmap_low, - min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { - if (map->phys_map[min + i]) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); - } + count = -EOPNOTSUPP; + if (likely(map)) { + count = __pv_send_ipi(&ipi_bitmap_low, map, &irq, min); + min += cluster_size; + count += __pv_send_ipi(&ipi_bitmap_high, map, &irq, min); } - min += cluster_size; - - if (min > map->max_apic_id) - goto out; - - for_each_set_bit(i, &ipi_bitmap_high, - min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { - if (map->phys_map[min + i]) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); - } - } - -out: rcu_read_unlock(); return count; } @@ -1129,6 +1122,50 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, return result; } +/* + * This routine identifies the destination vcpus mask meant to receive the + * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find + * out the destination vcpus array and set the bitmap or it traverses to + * each available vcpu to identify the same. + */ +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap) +{ + struct kvm_lapic **dest_vcpu = NULL; + struct kvm_lapic *src = NULL; + struct kvm_apic_map *map; + struct kvm_vcpu *vcpu; + unsigned long bitmap; + int i, vcpu_idx; + bool ret; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu, + &bitmap); + if (ret) { + for_each_set_bit(i, &bitmap, 16) { + if (!dest_vcpu[i]) + continue; + vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx; + __set_bit(vcpu_idx, vcpu_bitmap); + } + } else { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + if (!kvm_apic_match_dest(vcpu, NULL, + irq->delivery_mode, + irq->dest_id, + irq->dest_mode)) + continue; + __set_bit(i, vcpu_bitmap); + } + } + rcu_read_unlock(); +} + int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) { return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; @@ -2714,7 +2751,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs * and leave the INIT pending. */ - if (is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu)) { + if (kvm_vcpu_latch_init(vcpu)) { WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) clear_bit(KVM_APIC_SIPI, &apic->pending_events); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 2aad7e226fc0..c1d77436126a 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -226,6 +226,9 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu); +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap); + bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); int kvm_vector_to_index(u32 vector, u32 dest_vcpus, diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 24c23c66b226..150d982ec1d2 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4295,7 +4295,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); if (!skip_tlb_flush) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - kvm_x86_ops->tlb_flush(vcpu, true); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } /* diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 46875bbd0419..d5e6d5b3f06f 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -62,8 +62,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, - (unsigned long *)&pmu->reprogram_pmi)) { + if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } @@ -76,8 +75,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, - (unsigned long *)&pmu->reprogram_pmi)) { + if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); @@ -137,7 +135,37 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, } pmc->perf_event = event; - clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi); + pmc_to_pmu(pmc)->event_count++; + clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); +} + +static void pmc_pause_counter(struct kvm_pmc *pmc) +{ + u64 counter = pmc->counter; + + if (!pmc->perf_event) + return; + + /* update counter, reset event value to avoid redundant accumulation */ + counter += perf_event_pause(pmc->perf_event, true); + pmc->counter = counter & pmc_bitmask(pmc); +} + +static bool pmc_resume_counter(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event) + return false; + + /* recalibrate sample period and check if it's accepted by perf core */ + if (perf_event_period(pmc->perf_event, + (-pmc->counter) & pmc_bitmask(pmc))) + return false; + + /* reuse perf_event to serve as pmc_reprogram_counter() does*/ + perf_event_enable(pmc->perf_event); + + clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); + return true; } void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) @@ -154,7 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc->eventsel = eventsel; - pmc_stop_counter(pmc); + pmc_pause_counter(pmc); if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc)) return; @@ -193,6 +221,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (type == PERF_TYPE_RAW) config = eventsel & X86_RAW_EVENT_MASK; + if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) + return; + + pmc_release_perf_event(pmc); + + pmc->current_config = eventsel; pmc_reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), !(eventsel & ARCH_PERFMON_EVENTSEL_OS), @@ -209,7 +243,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) struct kvm_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; - pmc_stop_counter(pmc); + pmc_pause_counter(pmc); if (!en_field || !pmc_is_enabled(pmc)) return; @@ -224,6 +258,12 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) return; } + if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc)) + return; + + pmc_release_perf_event(pmc); + + pmc->current_config = (u64)ctrl; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, kvm_x86_ops->pmu_ops->find_fixed_event(idx), !(en_field & 0x2), /* exclude user */ @@ -253,27 +293,32 @@ EXPORT_SYMBOL_GPL(reprogram_counter); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - u64 bitmask; int bit; - bitmask = pmu->reprogram_pmi; - - for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); if (unlikely(!pmc || !pmc->perf_event)) { - clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + clear_bit(bit, pmu->reprogram_pmi); continue; } reprogram_counter(pmu, bit); } + + /* + * Unused perf_events are only released if the corresponding MSRs + * weren't accessed during the last vCPU time slice. kvm_arch_sched_in + * triggers KVM_REQ_PMU if cleanup is needed. + */ + if (unlikely(pmu->need_cleanup)) + kvm_pmu_cleanup(vcpu); } /* check if idx is a valid index to access PMU */ -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { - return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx); + return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } bool is_vmware_backdoor_pmc(u32 pmc_idx) @@ -323,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); - pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask); + pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask); if (!pmc) return 1; @@ -339,7 +384,17 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); + return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) || + kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); +} + +static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr); + + if (pmc) + __set_bit(pmc->idx, pmu->pmc_in_use); } int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) @@ -349,6 +404,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { + kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index); return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); } @@ -376,9 +432,45 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); kvm_x86_ops->pmu_ops->init(vcpu); init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); + pmu->event_count = 0; + pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); } +static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (pmc_is_fixed(pmc)) + return fixed_ctrl_field(pmu->fixed_ctr_ctrl, + pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3; + + return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE; +} + +/* Release perf_events for vPMCs that have been unused for a full time slice. */ +void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = NULL; + DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX); + int i; + + pmu->need_cleanup = false; + + bitmap_andnot(bitmask, pmu->all_valid_pmc_idx, + pmu->pmc_in_use, X86_PMC_IDX_MAX); + + for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) { + pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i); + + if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc)) + pmc_stop_counter(pmc); + } + + bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX); +} + void kvm_pmu_destroy(struct kvm_vcpu *vcpu) { kvm_pmu_reset(vcpu); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 58265f761c3b..7ebb62326c14 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -25,9 +25,10 @@ struct kvm_pmu_ops { unsigned (*find_fixed_event)(int idx); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); - struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx, - u64 *mask); - int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx); + struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask); + struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); + int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -55,12 +56,21 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } -static inline void pmc_stop_counter(struct kvm_pmc *pmc) +static inline void pmc_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { - pmc->counter = pmc_read_counter(pmc); perf_event_release_kernel(pmc->perf_event); pmc->perf_event = NULL; + pmc->current_config = 0; + pmc_to_pmu(pmc)->event_count--; + } +} + +static inline void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + pmc_release_perf_event(pmc); } } @@ -79,6 +89,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); } +static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, + u64 data) +{ + return !(pmu->global_ctrl_mask & data); +} + /* returns general purpose PMC with the specified MSR. Note that it can be * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a * paramenter to tell them apart. @@ -110,13 +126,14 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx); +int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); +void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp); diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index c8388389a3b0..ce0b10fe5e2b 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -174,7 +174,7 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -184,7 +184,8 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) } /* idx is the ECX register of RDPMC instruction */ -static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask) +static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *counters; @@ -199,13 +200,19 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { + /* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough. */ + return false; +} + +static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) +{ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int ret = false; + struct kvm_pmc *pmc; - ret = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER) || - get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); + pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); + pmc = pmc ? pmc : get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); - return ret; + return pmc; } static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) @@ -272,6 +279,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->nr_arch_fixed_counters = 0; pmu->global_status = 0; + bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters); } static void amd_pmu_init(struct kvm_vcpu *vcpu) @@ -285,6 +293,7 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; + pmu->gp_counters[i].current_config = 0; } } @@ -306,8 +315,9 @@ struct kvm_pmu_ops amd_pmu_ops = { .find_fixed_event = amd_find_fixed_event, .pmc_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, + .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = amd_msr_idx_to_pmc, - .is_valid_msr_idx = amd_is_valid_msr_idx, + .is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx, .is_valid_msr = amd_is_valid_msr, .get_msr = amd_pmu_get_msr, .set_msr = amd_pmu_set_msr, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f8ecb6df5106..d02a73a48461 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -38,6 +38,7 @@ #include <linux/file.h> #include <linux/pagemap.h> #include <linux/swap.h> +#include <linux/rwsem.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -418,9 +419,13 @@ enum { #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL +static int sev_flush_asids(void); +static DECLARE_RWSEM(sev_deactivate_lock); +static DEFINE_MUTEX(sev_bitmap_lock); static unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned long *sev_asid_bitmap; +static unsigned long *sev_reclaim_asid_bitmap; #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) struct enc_region { @@ -1229,11 +1234,15 @@ static __init int sev_hardware_setup(void) /* Minimum ASID value that should be used for SEV guest */ min_sev_asid = cpuid_edx(0x8000001F); - /* Initialize SEV ASID bitmap */ + /* Initialize SEV ASID bitmaps */ sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) return 1; + sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + if (!sev_reclaim_asid_bitmap) + return 1; + status = kmalloc(sizeof(*status), GFP_KERNEL); if (!status) return 1; @@ -1412,8 +1421,12 @@ static __exit void svm_hardware_unsetup(void) { int cpu; - if (svm_sev_enabled()) + if (svm_sev_enabled()) { bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); + } for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -1723,25 +1736,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } -static void __sev_asid_free(int asid) +static void sev_asid_free(int asid) { struct svm_cpu_data *sd; int cpu, pos; + mutex_lock(&sev_bitmap_lock); + pos = asid - 1; - clear_bit(pos, sev_asid_bitmap); + __set_bit(pos, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); sd->sev_vmcbs[pos] = NULL; } -} -static void sev_asid_free(struct kvm *kvm) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - __sev_asid_free(sev->asid); + mutex_unlock(&sev_bitmap_lock); } static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) @@ -1758,10 +1768,12 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) /* deactivate handle */ data->handle = handle; + + /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ + down_read(&sev_deactivate_lock); sev_guest_deactivate(data, NULL); + up_read(&sev_deactivate_lock); - wbinvd_on_all_cpus(); - sev_guest_df_flush(NULL); kfree(data); decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); @@ -1910,7 +1922,7 @@ static void sev_vm_destroy(struct kvm *kvm) mutex_unlock(&kvm->lock); sev_unbind_asid(kvm, sev->handle); - sev_asid_free(kvm); + sev_asid_free(sev->asid); } static void avic_vm_destroy(struct kvm *kvm) @@ -2364,7 +2376,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); break; default: - BUG(); + WARN_ON_ONCE(1); } } @@ -2517,10 +2529,6 @@ static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { } -static void svm_decache_cr3(struct kvm_vcpu *vcpu) -{ -} - static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { } @@ -4991,6 +4999,18 @@ static int handle_exit(struct kvm_vcpu *vcpu) return 0; } +#ifdef CONFIG_RETPOLINE + if (exit_code == SVM_EXIT_MSR) + return msr_interception(svm); + else if (exit_code == SVM_EXIT_VINTR) + return interrupt_window_interception(svm); + else if (exit_code == SVM_EXIT_INTR) + return intr_interception(svm); + else if (exit_code == SVM_EXIT_HLT) + return halt_interception(svm); + else if (exit_code == SVM_EXIT_NPF) + return npf_interception(svm); +#endif return svm_exit_handlers[exit_code](svm); } @@ -5086,8 +5106,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm_nested_virtualize_tpr(vcpu) || - kvm_vcpu_apicv_active(vcpu)) + if (svm_nested_virtualize_tpr(vcpu)) return; clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); @@ -5104,9 +5123,9 @@ static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) return; } -static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu) +static bool svm_get_enable_apicv(struct kvm *kvm) { - return avic && irqchip_split(vcpu->kvm); + return avic && irqchip_split(kvm); } static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) @@ -5628,7 +5647,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); - kvm_load_guest_xcr0(vcpu); + kvm_load_guest_xsave_state(vcpu); if (lapic_in_kernel(vcpu) && vcpu->arch.apic->lapic_timer.timer_advance_ns) @@ -5778,7 +5797,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); - kvm_put_guest_xcr0(vcpu); + kvm_load_host_xsave_state(vcpu); stgi(); /* Any pending NMI will happen here */ @@ -5887,6 +5906,9 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVES); + /* Update nrips enabled cache */ svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); @@ -5962,7 +5984,7 @@ static bool svm_mpx_supported(void) static bool svm_xsaves_supported(void) { - return false; + return boot_cpu_has(X86_FEATURE_XSAVES); } static bool svm_umip_emulated(void) @@ -6264,18 +6286,73 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static int sev_flush_asids(void) +{ + int ret, error; + + /* + * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail, + * so it must be guarded. + */ + down_write(&sev_deactivate_lock); + + wbinvd_on_all_cpus(); + ret = sev_guest_df_flush(&error); + + up_write(&sev_deactivate_lock); + + if (ret) + pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error); + + return ret; +} + +/* Must be called with the sev_bitmap_lock held */ +static bool __sev_recycle_asids(void) +{ + int pos; + + /* Check if there are any ASIDs to reclaim before performing a flush */ + pos = find_next_bit(sev_reclaim_asid_bitmap, + max_sev_asid, min_sev_asid - 1); + if (pos >= max_sev_asid) + return false; + + if (sev_flush_asids()) + return false; + + bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, + max_sev_asid); + bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); + + return true; +} + static int sev_asid_new(void) { + bool retry = true; int pos; + mutex_lock(&sev_bitmap_lock); + /* * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. */ +again: pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1); - if (pos >= max_sev_asid) + if (pos >= max_sev_asid) { + if (retry && __sev_recycle_asids()) { + retry = false; + goto again; + } + mutex_unlock(&sev_bitmap_lock); return -EBUSY; + } + + __set_bit(pos, sev_asid_bitmap); + + mutex_unlock(&sev_bitmap_lock); - set_bit(pos, sev_asid_bitmap); return pos + 1; } @@ -6303,7 +6380,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) return 0; e_free: - __sev_asid_free(asid); + sev_asid_free(asid); return ret; } @@ -6313,12 +6390,6 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) int asid = sev_get_asid(kvm); int ret; - wbinvd_on_all_cpus(); - - ret = sev_guest_df_flush(error); - if (ret) - return ret; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -7208,7 +7279,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, - .decache_cr3 = svm_decache_cr3, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, .set_cr3 = svm_set_cr3, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e76eb4f07f6c..dc06e67be017 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -10,6 +10,7 @@ #include "hyperv.h" #include "mmu.h" #include "nested.h" +#include "pmu.h" #include "trace.h" #include "x86.h" @@ -27,6 +28,16 @@ module_param(nested_early_check, bool, S_IRUGO); failed; \ }) +#define SET_MSR_OR_WARN(vcpu, idx, data) \ +({ \ + bool failed = kvm_set_msr(vcpu, idx, data); \ + if (failed) \ + pr_warn_ratelimited( \ + "%s cannot write MSR (0x%x, 0x%llx)\n", \ + __func__, idx, data); \ + failed; \ +}) + /* * Hyper-V requires all of these, so mark them as supported even though * they are just treated the same as all-context. @@ -929,6 +940,57 @@ fail: return i + 1; } +static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, + u32 msr_index, + u64 *data) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * If the L0 hypervisor stored a more accurate value for the TSC that + * does not include the time taken for emulation of the L2->L1 + * VM-exit in L0, use the more accurate value. + */ + if (msr_index == MSR_IA32_TSC) { + int index = vmx_find_msr_index(&vmx->msr_autostore.guest, + MSR_IA32_TSC); + + if (index >= 0) { + u64 val = vmx->msr_autostore.guest.val[index].value; + + *data = kvm_read_l1_tsc(vcpu, val); + return true; + } + } + + if (kvm_get_msr(vcpu, msr_index, data)) { + pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, + msr_index); + return false; + } + return true; +} + +static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i, + struct vmx_msr_entry *e) +{ + if (kvm_vcpu_read_guest(vcpu, + gpa + i * sizeof(*e), + e, 2 * sizeof(u32))) { + pr_debug_ratelimited( + "%s cannot read MSR entry (%u, 0x%08llx)\n", + __func__, i, gpa + i * sizeof(*e)); + return false; + } + if (nested_vmx_store_msr_check(vcpu, e)) { + pr_debug_ratelimited( + "%s check failed (%u, 0x%x, 0x%x)\n", + __func__, i, e->index, e->reserved); + return false; + } + return true; +} + static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) { u64 data; @@ -940,26 +1002,12 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) if (unlikely(i >= max_msr_list_size)) return -EINVAL; - if (kvm_vcpu_read_guest(vcpu, - gpa + i * sizeof(e), - &e, 2 * sizeof(u32))) { - pr_debug_ratelimited( - "%s cannot read MSR entry (%u, 0x%08llx)\n", - __func__, i, gpa + i * sizeof(e)); + if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) return -EINVAL; - } - if (nested_vmx_store_msr_check(vcpu, &e)) { - pr_debug_ratelimited( - "%s check failed (%u, 0x%x, 0x%x)\n", - __func__, i, e.index, e.reserved); - return -EINVAL; - } - if (kvm_get_msr(vcpu, e.index, &data)) { - pr_debug_ratelimited( - "%s cannot read MSR (%u, 0x%x)\n", - __func__, i, e.index); + + if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data)) return -EINVAL; - } + if (kvm_vcpu_write_guest(vcpu, gpa + i * sizeof(e) + offsetof(struct vmx_msr_entry, value), @@ -973,6 +1021,60 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) return 0; } +static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + u32 count = vmcs12->vm_exit_msr_store_count; + u64 gpa = vmcs12->vm_exit_msr_store_addr; + struct vmx_msr_entry e; + u32 i; + + for (i = 0; i < count; i++) { + if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) + return false; + + if (e.index == msr_index) + return true; + } + return false; +} + +static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, + u32 msr_index) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmx_msrs *autostore = &vmx->msr_autostore.guest; + bool in_vmcs12_store_list; + int msr_autostore_index; + bool in_autostore_list; + int last; + + msr_autostore_index = vmx_find_msr_index(autostore, msr_index); + in_autostore_list = msr_autostore_index >= 0; + in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index); + + if (in_vmcs12_store_list && !in_autostore_list) { + if (autostore->nr == NR_LOADSTORE_MSRS) { + /* + * Emulated VMEntry does not fail here. Instead a less + * accurate value will be returned by + * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() + * instead of reading the value from the vmcs02 VMExit + * MSR-store area. + */ + pr_warn_ratelimited( + "Not enough msr entries in msr_autostore. Can't add msr %x\n", + msr_index); + return; + } + last = autostore->nr++; + autostore->val[last].index = msr_index; + } else if (!in_vmcs12_store_list && in_autostore_list) { + last = --autostore->nr; + autostore->val[msr_autostore_index] = autostore->val[last]; + } +} + static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) { unsigned long invalid_mask; @@ -1012,7 +1114,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne kvm_mmu_new_cr3(vcpu, cr3, false); vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_init_mmu(vcpu, false); @@ -1024,7 +1126,9 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * populated by L2 differently than TLB entries populated * by L1. * - * If L1 uses EPT, then TLB entries are tagged with different EPTP. + * If L0 uses EPT, L1 and L2 run with different EPTP because + * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries + * are tagged with different EPTP. * * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged * with different VPID (L1 entries are tagged with vmx->vpid @@ -1034,7 +1138,7 @@ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - return nested_cpu_has_ept(vmcs12) || + return enable_ept || (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02); } @@ -2018,7 +2122,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) * addresses are constant (for vmcs02), the counts can change based * on L2's behavior, e.g. switching to/from long mode. */ - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); + vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val)); vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); @@ -2073,6 +2177,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; + vmx->nested.l1_tpr_threshold = -1; if (exec_control & CPU_BASED_TPR_SHADOW) vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); #ifdef CONFIG_X86_64 @@ -2285,6 +2390,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3); } + /* + * Make sure the msr_autostore list is up to date before we set the + * count in the vmcs02. + */ + prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC); + + vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); @@ -2418,6 +2530,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* + * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 + * on nested VM-Exit, which can occur without actually running L2 and + * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the + * transition to HLT instead of running L2. + */ + if (enable_ept) + vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); + /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */ if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { @@ -2430,6 +2552,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && + SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->guest_ia32_perf_global_ctrl)) + return -EINVAL; + kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); return 0; @@ -2664,6 +2791,11 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(!kvm_pat_valid(vmcs12->host_ia32_pat))) return -EINVAL; + if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) && + CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), + vmcs12->host_ia32_perf_global_ctrl))) + return -EINVAL; + #ifdef CONFIG_X86_64 ia32e = !!(vcpu->arch.efer & EFER_LMA); #else @@ -2779,6 +2911,11 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL; } + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && + CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), + vmcs12->guest_ia32_perf_global_ctrl))) + return -EINVAL; + /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: @@ -3453,6 +3590,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) return -EBUSY; + clear_bit(KVM_APIC_INIT, &apic->pending_events); nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); return 0; } @@ -3856,8 +3994,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.pat = vmcs12->host_ia32_pat; } if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, - vmcs12->host_ia32_perf_global_ctrl); + SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->host_ia32_perf_global_ctrl); /* Set L1 segment info according to Intel SDM 27.5.2 Loading Host Segment and Descriptor-Table Registers */ @@ -3976,7 +4114,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) nested_ept_uninit_mmu_context(vcpu); vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs @@ -4104,6 +4242,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + if (vmx->nested.l1_tpr_threshold != -1) + vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold); if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -4319,6 +4459,27 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, return 0; } +void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx; + + if (!nested_vmx_allowed(vcpu)) + return; + + vmx = to_vmx(vcpu); + if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { + vmx->nested.msrs.entry_ctls_high |= + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + vmx->nested.msrs.exit_ctls_high |= + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + } else { + vmx->nested.msrs.entry_ctls_high &= + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + vmx->nested.msrs.exit_ctls_high &= + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + } +} + static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) { gva_t gva; @@ -5758,7 +5919,7 @@ error_guest_mode: return ret; } -void nested_vmx_vcpu_setup(void) +void nested_vmx_set_vmcs_shadowing_bitmap(void) { if (enable_shadow_vmcs) { vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); @@ -6039,23 +6200,23 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) init_vmcs_shadow_fields(); } - exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear, - exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch, - exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld, - exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst, - exit_handlers[EXIT_REASON_VMREAD] = handle_vmread, - exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume, - exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite, - exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff, - exit_handlers[EXIT_REASON_VMON] = handle_vmon, - exit_handlers[EXIT_REASON_INVEPT] = handle_invept, - exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid, - exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc, + exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear; + exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch; + exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld; + exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst; + exit_handlers[EXIT_REASON_VMREAD] = handle_vmread; + exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume; + exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite; + exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff; + exit_handlers[EXIT_REASON_VMON] = handle_vmon; + exit_handlers[EXIT_REASON_INVEPT] = handle_invept; + exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; + exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; kvm_x86_ops->check_nested_events = vmx_check_nested_events; kvm_x86_ops->get_nested_state = vmx_get_nested_state; kvm_x86_ops->set_nested_state = vmx_set_nested_state; - kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages, + kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages; kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs; kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 187d39bf0bf1..b9e519840f28 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -11,7 +11,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, bool apicv); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); -void nested_vmx_vcpu_setup(void); +void nested_vmx_set_vmcs_shadowing_bitmap(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason); @@ -22,6 +22,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); +void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { @@ -245,7 +246,7 @@ static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1) return ((val & fixed1) | fixed0) == val; } -static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1; @@ -259,7 +260,7 @@ static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) return fixed_bits_valid(val, fixed0, fixed1); } -static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1; @@ -267,7 +268,7 @@ static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) return fixed_bits_valid(val, fixed0, fixed1); } -static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 3e9c059099e9..7023138b1cb0 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -15,6 +15,7 @@ #include "x86.h" #include "cpuid.h" #include "lapic.h" +#include "nested.h" #include "pmu.h" static struct kvm_event_hw_type_mapping intel_arch_events[] = { @@ -46,6 +47,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) if (old_ctrl == new_ctrl) continue; + __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); reprogram_fixed_counter(pmc, new_ctrl, i); } @@ -111,7 +113,7 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); @@ -122,8 +124,8 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) (fixed && idx >= pmu->nr_arch_fixed_counters); } -static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, - unsigned idx, u64 *mask) +static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); @@ -162,6 +164,18 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) return ret; } +static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + pmc = get_fixed_pmc(pmu, msr); + pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0); + pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0); + + return pmc; +} + static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -223,7 +237,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_CORE_PERF_GLOBAL_CTRL: if (pmu->global_ctrl == data) return 0; - if (!(data & pmu->global_ctrl_mask)) { + if (kvm_valid_perf_global_ctrl(pmu, data)) { global_ctrl_changed(pmu, data); return 0; } @@ -317,6 +331,13 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; + + bitmap_set(pmu->all_valid_pmc_idx, + 0, pmu->nr_arch_gp_counters); + bitmap_set(pmu->all_valid_pmc_idx, + INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); + + nested_vmx_pmu_entry_exit_ctls_update(vcpu); } static void intel_pmu_init(struct kvm_vcpu *vcpu) @@ -328,12 +349,14 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; + pmu->gp_counters[i].current_config = 0; } for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + pmu->fixed_counters[i].current_config = 0; } } @@ -366,8 +389,9 @@ struct kvm_pmu_ops intel_pmu_ops = { .find_fixed_event = intel_find_fixed_event, .pmc_is_enabled = intel_pmc_is_enabled, .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, + .rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = intel_msr_idx_to_pmc, - .is_valid_msr_idx = intel_is_valid_msr_idx, + .is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx, .is_valid_msr = intel_is_valid_msr, .get_msr = intel_pmu_get_msr, .set_msr = intel_pmu_set_msr, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e7970a2e8eae..89253d60e23a 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -106,8 +106,6 @@ module_param(enable_apicv, bool, S_IRUGO); static bool __read_mostly nested = 1; module_param(nested, bool, S_IRUGO); -static u64 __read_mostly host_xss; - bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); @@ -726,8 +724,8 @@ static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, bool ret; u32 mask = 1 << (seg * SEG_FIELD_NR + field); - if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) { - vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS); + if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) { + kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS); vmx->segment_cache.bitmask = 0; } ret = vmx->segment_cache.bitmask & mask; @@ -835,7 +833,7 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, vm_exit_controls_clearbit(vmx, exit); } -static int find_msr(struct vmx_msrs *m, unsigned int msr) +int vmx_find_msr_index(struct vmx_msrs *m, u32 msr) { unsigned int i; @@ -869,7 +867,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) } break; } - i = find_msr(&m->guest, msr); + i = vmx_find_msr_index(&m->guest, msr); if (i < 0) goto skip_guest; --m->guest.nr; @@ -877,7 +875,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); skip_guest: - i = find_msr(&m->host, msr); + i = vmx_find_msr_index(&m->host, msr); if (i < 0) return; @@ -936,12 +934,12 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } - i = find_msr(&m->guest, msr); + i = vmx_find_msr_index(&m->guest, msr); if (!entry_only) - j = find_msr(&m->host, msr); + j = vmx_find_msr_index(&m->host, msr); - if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) || - (j < 0 && m->host.nr == NR_AUTOLOAD_MSRS)) { + if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) || + (j < 0 && m->host.nr == NR_LOADSTORE_MSRS)) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; @@ -1412,35 +1410,44 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long rflags, save_rflags; - if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) { - __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) { + kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); rflags = vmcs_readl(GUEST_RFLAGS); - if (to_vmx(vcpu)->rmode.vm86_active) { + if (vmx->rmode.vm86_active) { rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - save_rflags = to_vmx(vcpu)->rmode.save_rflags; + save_rflags = vmx->rmode.save_rflags; rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; } - to_vmx(vcpu)->rflags = rflags; + vmx->rflags = rflags; } - return to_vmx(vcpu)->rflags; + return vmx->rflags; } void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { - unsigned long old_rflags = vmx_get_rflags(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long old_rflags; - __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); - to_vmx(vcpu)->rflags = rflags; - if (to_vmx(vcpu)->rmode.vm86_active) { - to_vmx(vcpu)->rmode.save_rflags = rflags; + if (enable_unrestricted_guest) { + kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); + vmx->rflags = rflags; + vmcs_writel(GUEST_RFLAGS, rflags); + return; + } + + old_rflags = vmx_get_rflags(vcpu); + vmx->rflags = rflags; + if (vmx->rmode.vm86_active) { + vmx->rmode.save_rflags = rflags; rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; } vmcs_writel(GUEST_RFLAGS, rflags); - if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM) - to_vmx(vcpu)->emulation_required = emulation_required(vcpu); + if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) + vmx->emulation_required = emulation_required(vcpu); } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) @@ -1820,14 +1827,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data); - case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) - return 1; - msr_info->data = vcpu->arch.ia32_xss; - break; case MSR_IA32_RTIT_CTL: if (pt_mode != PT_MODE_HOST_GUEST) return 1; @@ -2063,25 +2062,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!nested_vmx_allowed(vcpu)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); - case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) - return 1; - /* - * The only supported bit as of Skylake is bit 8, but - * it is not supported on KVM. - */ - if (data != 0) - return 1; - vcpu->arch.ia32_xss = data; - if (vcpu->arch.ia32_xss != host_xss) - add_atomic_switch_msr(vmx, MSR_IA32_XSS, - vcpu->arch.ia32_xss, host_xss, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_XSS); - break; case MSR_IA32_RTIT_CTL: if ((pt_mode != PT_MODE_HOST_GUEST) || vmx_rtit_ctl_check(vcpu, data) || @@ -2170,7 +2150,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, reg); + switch (reg) { case VCPU_REGS_RSP: vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); @@ -2182,7 +2163,12 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) if (enable_ept) ept_save_pdptrs(vcpu); break; + case VCPU_EXREG_CR3: + if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + break; default: + WARN_ON_ONCE(1); break; } } @@ -2853,13 +2839,6 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits; } -static void vmx_decache_cr3(struct kvm_vcpu *vcpu) -{ - if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); -} - static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; @@ -2872,8 +2851,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty)) + if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR)) return; if (is_pae_paging(vcpu)) { @@ -2895,10 +2873,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); } - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); } static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, @@ -2907,8 +2882,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - vmx_decache_cr3(vcpu); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) + vmx_cache_reg(vcpu, VCPU_EXREG_CR3); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING | @@ -2989,6 +2964,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; + bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; @@ -3005,15 +2981,20 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - if (enable_unrestricted_guest || is_paging(vcpu) || - is_guest_mode(vcpu)) - guest_cr3 = kvm_read_cr3(vcpu); - else + /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ + if (is_guest_mode(vcpu)) + update_guest_cr3 = false; + else if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; + else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + guest_cr3 = vcpu->arch.cr3; + else /* vmcs01.GUEST_CR3 is already up-to-date. */ + update_guest_cr3 = false; ept_load_pdptrs(vcpu); } - vmcs_writel(GUEST_CR3, guest_cr3); + if (update_guest_cr3) + vmcs_writel(GUEST_CR3, guest_cr3); } int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -3747,7 +3728,7 @@ void pt_update_intercept_for_msr(struct vcpu_vmx *vmx) } } -static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) +static bool vmx_get_enable_apicv(struct kvm *kvm) { return enable_apicv; } @@ -4040,6 +4021,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); + vcpu->arch.xsaves_enabled = xsaves_enabled; + if (!xsaves_enabled) exec_control &= ~SECONDARY_EXEC_XSAVES; @@ -4152,14 +4135,13 @@ static void ept_set_mmio_spte_mask(void) #define VMX_XSS_EXIT_BITMAP 0 /* - * Sets up the vmcs for emulated real mode. + * Noting that the initialization of Guest-state Area of VMCS is in + * vmx_vcpu_reset(). */ -static void vmx_vcpu_setup(struct vcpu_vmx *vmx) +static void init_vmcs(struct vcpu_vmx *vmx) { - int i; - if (nested) - nested_vmx_vcpu_setup(); + nested_vmx_set_vmcs_shadowing_bitmap(); if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); @@ -4168,7 +4150,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) /* Control */ pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - vmx->hv_deadline_tsc = -1; exec_controls_set(vmx, vmx_exec_control(vmx)); @@ -4217,21 +4198,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { - u32 index = vmx_msr_index[i]; - u32 data_low, data_high; - int j = vmx->nmsrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - vmx->guest_msrs[j].index = i; - vmx->guest_msrs[j].data = 0; - vmx->guest_msrs[j].mask = -1ull; - ++vmx->nmsrs; - } - vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ @@ -4242,6 +4208,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) set_cr4_guest_host_mask(vmx); + if (vmx->vpid != 0) + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + if (vmx_xsaves_supported()) vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); @@ -4344,9 +4313,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx->vpid != 0) - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; vmx->vcpu.arch.cr0 = cr0; vmx_set_cr0(vcpu, cr0); /* enter rmode */ @@ -4701,7 +4667,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) return 0; } -static int handle_external_interrupt(struct kvm_vcpu *vcpu) +static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; @@ -4973,21 +4939,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) vmcs_writel(GUEST_DR7, val); } -static int handle_cpuid(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_cpuid(vcpu); -} - -static int handle_rdmsr(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_rdmsr(vcpu); -} - -static int handle_wrmsr(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_wrmsr(vcpu); -} - static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { kvm_apic_update_ppr(vcpu); @@ -5004,11 +4955,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) return 1; } -static int handle_halt(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_halt(vcpu); -} - static int handle_vmcall(struct kvm_vcpu *vcpu) { return kvm_emulate_hypercall(vcpu); @@ -5543,14 +5489,6 @@ static int handle_encls(struct kvm_vcpu *vcpu) return 1; } -static int handle_unexpected_vmexit(struct kvm_vcpu *vcpu) -{ - kvm_skip_emulated_instruction(vcpu); - WARN_ONCE(1, "Unexpected VM-Exit Reason = 0x%x", - vmcs_read32(VM_EXIT_REASON)); - return 1; -} - /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5564,11 +5502,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_IO_INSTRUCTION] = handle_io, [EXIT_REASON_CR_ACCESS] = handle_cr, [EXIT_REASON_DR_ACCESS] = handle_dr, - [EXIT_REASON_CPUID] = handle_cpuid, - [EXIT_REASON_MSR_READ] = handle_rdmsr, - [EXIT_REASON_MSR_WRITE] = handle_wrmsr, + [EXIT_REASON_CPUID] = kvm_emulate_cpuid, + [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, + [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, - [EXIT_REASON_HLT] = handle_halt, + [EXIT_REASON_HLT] = kvm_emulate_halt, [EXIT_REASON_INVD] = handle_invd, [EXIT_REASON_INVLPG] = handle_invlpg, [EXIT_REASON_RDPMC] = handle_rdpmc, @@ -5602,15 +5540,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_INVVPID] = handle_vmx_instruction, [EXIT_REASON_RDRAND] = handle_invalid_op, [EXIT_REASON_RDSEED] = handle_invalid_op, - [EXIT_REASON_XSAVES] = handle_unexpected_vmexit, - [EXIT_REASON_XRSTORS] = handle_unexpected_vmexit, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, - [EXIT_REASON_UMWAIT] = handle_unexpected_vmexit, - [EXIT_REASON_TPAUSE] = handle_unexpected_vmexit, }; static const int kvm_vmx_max_exit_handlers = @@ -5945,9 +5879,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) + && kvm_vmx_exit_handlers[exit_reason]) { +#ifdef CONFIG_RETPOLINE + if (exit_reason == EXIT_REASON_MSR_WRITE) + return kvm_emulate_wrmsr(vcpu); + else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) + return handle_preemption_timer(vcpu); + else if (exit_reason == EXIT_REASON_PENDING_INTERRUPT) + return handle_interrupt_window(vcpu); + else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + return handle_external_interrupt(vcpu); + else if (exit_reason == EXIT_REASON_HLT) + return kvm_emulate_halt(vcpu); + else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) + return handle_ept_misconfig(vcpu); +#endif return kvm_vmx_exit_handlers[exit_reason](vcpu); - else { + } else { vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); dump_vmcs(); @@ -6033,17 +5981,17 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu) static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + int tpr_threshold; if (is_guest_mode(vcpu) && nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return; - if (irr == -1 || tpr < irr) { - vmcs_write32(TPR_THRESHOLD, 0); - return; - } - - vmcs_write32(TPR_THRESHOLD, irr); + tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr; + if (is_guest_mode(vcpu)) + to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold; + else + vmcs_write32(TPR_THRESHOLD, tpr_threshold); } void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) @@ -6517,9 +6465,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); - if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); - if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); @@ -6542,7 +6490,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - kvm_load_guest_xcr0(vcpu); + kvm_load_guest_xsave_state(vcpu); if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && @@ -6649,7 +6597,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } - kvm_put_guest_xcr0(vcpu); + kvm_load_host_xsave_state(vcpu); vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; @@ -6703,7 +6651,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) int err; struct vcpu_vmx *vmx; unsigned long *msr_bitmap; - int cpu; + int i, cpu; BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0, "struct kvm_vcpu must be at offset 0 for arch usercopy region"); @@ -6755,6 +6703,21 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; + for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { + u32 index = vmx_msr_index[i]; + u32 data_low, data_high; + int j = vmx->nmsrs; + + if (rdmsr_safe(index, &data_low, &data_high) < 0) + continue; + if (wrmsr_safe(index, data_low, data_high) < 0) + continue; + vmx->guest_msrs[j].index = i; + vmx->guest_msrs[j].data = 0; + vmx->guest_msrs[j].mask = -1ull; + ++vmx->nmsrs; + } + err = alloc_loaded_vmcs(&vmx->vmcs01); if (err < 0) goto free_msrs; @@ -6779,7 +6742,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; - vmx_vcpu_setup(vmx); + init_vmcs(vmx); vmx_vcpu_put(&vmx->vcpu); put_cpu(); if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { @@ -6999,6 +6962,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP)); cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU)); cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP)); + cr4_fixed1_update(X86_CR4_LA57, ecx, bit(X86_FEATURE_LA57)); #undef cr4_fixed1_update } @@ -7093,6 +7057,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ + vcpu->arch.xsaves_enabled = false; + if (cpu_has_secondary_exec_ctrls()) { vmx_compute_secondary_exec_control(vmx); vmcs_set_secondary_exec_control(vmx); @@ -7601,9 +7568,6 @@ static __init int hardware_setup(void) WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); } - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; @@ -7784,7 +7748,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_cpl = vmx_get_cpl, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr3 = vmx_decache_cr3, .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, .set_cr0 = vmx_set_cr0, .set_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index bee16687dc0b..90b97d9d4f7d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -22,11 +22,11 @@ extern u32 get_umwait_control_msr(void); #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) -#define NR_AUTOLOAD_MSRS 8 +#define NR_LOADSTORE_MSRS 8 struct vmx_msrs { unsigned int nr; - struct vmx_msr_entry val[NR_AUTOLOAD_MSRS]; + struct vmx_msr_entry val[NR_LOADSTORE_MSRS]; }; struct shared_msr_entry { @@ -167,6 +167,9 @@ struct nested_vmx { u64 vmcs01_debugctl; u64 vmcs01_guest_bndcfgs; + /* to migrate it to L1 if L2 writes to L1's CR8 directly */ + int l1_tpr_threshold; + u16 vpid02; u16 last_vpid; @@ -230,6 +233,10 @@ struct vcpu_vmx { struct vmx_msrs host; } msr_autoload; + struct msr_autostore { + struct vmx_msrs guest; + } msr_autostore; + struct { int vm86_active; ulong save_rflags; @@ -334,6 +341,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct vcpu_vmx *vmx); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +int vmx_find_msr_index(struct vmx_msrs *m, u32 msr); #define POSTED_INTR_ON 0 #define POSTED_INTR_SN 1 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 661e2bf38526..050961a51f84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -176,6 +176,8 @@ struct kvm_shared_msrs { static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; static struct kvm_shared_msrs __percpu *shared_msrs; +static u64 __read_mostly host_xss; + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -360,8 +362,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base); asmlinkage __visible void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ - if (!kvm_rebooting) - BUG(); + BUG_ON(!kvm_rebooting); } EXPORT_SYMBOL_GPL(kvm_spurious_fault); @@ -709,10 +710,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) ret = 1; memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + out: return ret; @@ -722,7 +721,6 @@ EXPORT_SYMBOL_GPL(load_pdptrs); bool pdptrs_changed(struct kvm_vcpu *vcpu) { u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; - bool changed = true; int offset; gfn_t gfn; int r; @@ -730,8 +728,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) if (!is_pae_paging(vcpu)) return false; - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail)) + if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) return true; gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; @@ -739,11 +736,9 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), PFERR_USER_MASK | PFERR_WRITE_MASK); if (r < 0) - goto out; - changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; -out: + return true; - return changed; + return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; } EXPORT_SYMBOL_GPL(pdptrs_changed); @@ -812,27 +807,34 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) { - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && - !vcpu->guest_xcr0_loaded) { - /* kvm_set_xcr() also depends on this */ + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - vcpu->guest_xcr0_loaded = 1; + + if (vcpu->arch.xsaves_enabled && + vcpu->arch.ia32_xss != host_xss) + wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } } -EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); +EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); -void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) { - if (vcpu->guest_xcr0_loaded) { + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); - vcpu->guest_xcr0_loaded = 0; + + if (vcpu->arch.xsaves_enabled && + vcpu->arch.ia32_xss != host_xss) + wrmsrl(MSR_IA32_XSS, host_xss); } + } -EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); +EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -984,7 +986,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush); vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); return 0; } @@ -1521,20 +1523,25 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) } #ifdef CONFIG_X86_64 +struct pvclock_clock { + int vclock_mode; + u64 cycle_last; + u64 mask; + u32 mult; + u32 shift; +}; + struct pvclock_gtod_data { seqcount_t seq; - struct { /* extract of a clocksource struct */ - int vclock_mode; - u64 cycle_last; - u64 mask; - u32 mult; - u32 shift; - } clock; + struct pvclock_clock clock; /* extract of a clocksource struct */ + struct pvclock_clock raw_clock; /* extract of a clocksource struct */ + u64 boot_ns_raw; u64 boot_ns; u64 nsec_base; u64 wall_time_sec; + u64 monotonic_raw_nsec; }; static struct pvclock_gtod_data pvclock_gtod_data; @@ -1542,9 +1549,10 @@ static struct pvclock_gtod_data pvclock_gtod_data; static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; - u64 boot_ns; + u64 boot_ns, boot_ns_raw; boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); + boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); @@ -1555,11 +1563,20 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->clock.mult = tk->tkr_mono.mult; vdata->clock.shift = tk->tkr_mono.shift; + vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->archdata.vclock_mode; + vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; + vdata->raw_clock.mask = tk->tkr_raw.mask; + vdata->raw_clock.mult = tk->tkr_raw.mult; + vdata->raw_clock.shift = tk->tkr_raw.shift; + vdata->boot_ns = boot_ns; vdata->nsec_base = tk->tkr_mono.xtime_nsec; vdata->wall_time_sec = tk->xtime_sec; + vdata->boot_ns_raw = boot_ns_raw; + vdata->monotonic_raw_nsec = tk->tkr_raw.xtime_nsec; + write_seqcount_end(&vdata->seq); } #endif @@ -1983,21 +2000,21 @@ static u64 read_tsc(void) return last; } -static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) +static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, + int *mode) { long v; - struct pvclock_gtod_data *gtod = &pvclock_gtod_data; u64 tsc_pg_val; - switch (gtod->clock.vclock_mode) { + switch (clock->vclock_mode) { case VCLOCK_HVCLOCK: tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(), tsc_timestamp); if (tsc_pg_val != U64_MAX) { /* TSC page valid */ *mode = VCLOCK_HVCLOCK; - v = (tsc_pg_val - gtod->clock.cycle_last) & - gtod->clock.mask; + v = (tsc_pg_val - clock->cycle_last) & + clock->mask; } else { /* TSC page invalid */ *mode = VCLOCK_NONE; @@ -2006,8 +2023,8 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) case VCLOCK_TSC: *mode = VCLOCK_TSC; *tsc_timestamp = read_tsc(); - v = (*tsc_timestamp - gtod->clock.cycle_last) & - gtod->clock.mask; + v = (*tsc_timestamp - clock->cycle_last) & + clock->mask; break; default: *mode = VCLOCK_NONE; @@ -2016,10 +2033,10 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) if (*mode == VCLOCK_NONE) *tsc_timestamp = v = 0; - return v * gtod->clock.mult; + return v * clock->mult; } -static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) +static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -2028,10 +2045,10 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); - ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); + ns = gtod->monotonic_raw_nsec; + ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; - ns += gtod->boot_ns; + ns += gtod->boot_ns_raw; } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; @@ -2049,7 +2066,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); + ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -2066,7 +2083,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns, + return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns, tsc_timestamp)); } @@ -2537,6 +2554,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { vcpu->arch.pv_time_enabled = false; + vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) @@ -2688,6 +2706,20 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_XSS: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return 1; + /* + * We do support PT if kvm_x86_ops->pt_supported(), but we do + * not support IA32_XSS[bit 8]. Guests will have to use + * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT + * MSRs. + */ + if (data != 0) + return 1; + vcpu->arch.ia32_xss = data; + break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) return 1; @@ -2702,8 +2734,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_KVM_SYSTEM_TIME: { struct kvm_arch *ka = &vcpu->kvm->arch; - kvmclock_reset(vcpu); - if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) { bool tmp = (msr == MSR_KVM_SYSTEM_TIME); @@ -2717,14 +2747,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ + vcpu->arch.pv_time_enabled = false; if (!(data & 1)) break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (!kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) - vcpu->arch.pv_time_enabled = false; - else vcpu->arch.pv_time_enabled = true; break; @@ -3018,6 +3047,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: return get_msr_mce(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); + case MSR_IA32_XSS: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return 1; + msr_info->data = vcpu->arch.ia32_xss; + break; case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -3795,12 +3830,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (lapic_in_kernel(vcpu)) { - if (events->smi.latched_init) - set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - else - clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - } + } + + if (lapic_in_kernel(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } } @@ -4916,9 +4952,6 @@ set_identity_unlock: if (!irqchip_kernel(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); - if (r) - goto set_irqchip_out; - r = 0; set_irqchip_out: kfree(chip); break; @@ -6111,7 +6144,7 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc); + return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -7841,6 +7874,20 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap) +{ + cpumask_var_t cpus; + bool called; + + zalloc_cpumask_var(&cpus, GFP_ATOMIC); + + called = kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, + vcpu_bitmap, cpus); + + free_cpumask_var(cpus); +} + void kvm_make_scan_ioapic_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); @@ -7918,7 +7965,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) */ put_page(page); } -EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) { @@ -8673,8 +8719,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, mp_state->mp_state != KVM_MP_STATE_RUNNABLE) goto out; - /* INITs are latched while in SMM */ - if ((is_smm(vcpu) || vcpu->arch.smi_pending) && + /* + * KVM_MP_STATE_INIT_RECEIVED means the processor is in + * INIT state; latched init should be reported using + * KVM_SET_VCPU_EVENTS, so reject it here. + */ + if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) goto out; @@ -8766,7 +8816,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); @@ -9293,6 +9343,9 @@ int kvm_arch_hardware_setup(void) kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; } + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + kvm_init_msr_list(); return 0; } @@ -9346,7 +9399,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_pio_data; if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm); r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; @@ -9415,7 +9468,13 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + vcpu->arch.l1tf_flush_l1d = true; + if (pmu->version && unlikely(pmu->event_count)) { + pmu->need_cleanup = true; + kvm_make_request(KVM_REQ_PMU, vcpu); + } kvm_x86_ops->sched_in(vcpu, cpu); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index dbf7442a822b..29391af8871d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -238,8 +238,7 @@ static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) return false; } -static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, - enum kvm_reg reg) +static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, int reg) { unsigned long val = kvm_register_read(vcpu, reg); @@ -247,8 +246,7 @@ static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, } static inline void kvm_register_writel(struct kvm_vcpu *vcpu, - enum kvm_reg reg, - unsigned long val) + int reg, unsigned long val) { if (!is_64_bit_mode(vcpu)) val = (u32)val; @@ -260,6 +258,11 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) return !(kvm->arch.disabled_quirks & quirk); } +static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) +{ + return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu); +} + void kvm_set_pending_timer(struct kvm_vcpu *vcpu); void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); @@ -366,7 +369,7 @@ static inline bool kvm_pat_valid(u64 data) return (data | ((data & 0x0202020202020202ull) << 1)) == data; } -void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); -void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); +void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); #endif diff --git a/arch/xtensa/boot/dts/virt.dts b/arch/xtensa/boot/dts/virt.dts index a9dcd87b6eb1..611b98a02a65 100644 --- a/arch/xtensa/boot/dts/virt.dts +++ b/arch/xtensa/boot/dts/virt.dts @@ -56,7 +56,7 @@ reg = <0xf0100000 0x03f00000>; // BUS_ADDRESS(3) CPU_PHYSICAL(1) SIZE(2) - ranges = <0x01000000 0x0 0xf0000000 0xf0000000 0x0 0x00010000>, + ranges = <0x01000000 0x0 0x00000000 0xf0000000 0x0 0x00010000>, <0x02000000 0x0 0xf4000000 0xf4000000 0x0 0x08000000>; // PCI_DEVICE(3) INT#(1) CONTROLLER(PHANDLE) CONTROLLER_DATA(2) diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h index aeb15f4c755b..be8b2be5a98b 100644 --- a/arch/xtensa/include/asm/bitops.h +++ b/arch/xtensa/include/asm/bitops.h @@ -148,7 +148,7 @@ static inline void change_bit(unsigned int bit, volatile unsigned long *p) " getex %0\n" " beqz %0, 1b\n" : "=&a" (tmp) - : "a" (~mask), "a" (p) + : "a" (mask), "a" (p) : "memory"); } diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index 6792928ba84a..3f80386f1883 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -100,7 +100,7 @@ do { \ case 4: __put_user_asm(x, ptr, retval, 4, "s32i", __cb); break; \ case 8: { \ __typeof__(*ptr) __v64 = x; \ - retval = __copy_to_user(ptr, &__v64, 8); \ + retval = __copy_to_user(ptr, &__v64, 8) ? -EFAULT : 0; \ break; \ } \ default: __put_user_bad(); \ @@ -132,14 +132,14 @@ do { \ #define __check_align_1 "" #define __check_align_2 \ - " _bbci.l %3, 0, 1f \n" \ - " movi %0, %4 \n" \ + " _bbci.l %[addr], 0, 1f \n" \ + " movi %[err], %[efault] \n" \ " _j 2f \n" #define __check_align_4 \ - " _bbsi.l %3, 0, 0f \n" \ - " _bbci.l %3, 1, 1f \n" \ - "0: movi %0, %4 \n" \ + " _bbsi.l %[addr], 0, 0f \n" \ + " _bbci.l %[addr], 1, 1f \n" \ + "0: movi %[err], %[efault] \n" \ " _j 2f \n" @@ -151,40 +151,40 @@ do { \ * WARNING: If you modify this macro at all, verify that the * __check_align_* macros still work. */ -#define __put_user_asm(x, addr, err, align, insn, cb) \ +#define __put_user_asm(x_, addr_, err_, align, insn, cb)\ __asm__ __volatile__( \ __check_align_##align \ - "1: "insn" %2, %3, 0 \n" \ + "1: "insn" %[x], %[addr], 0 \n" \ "2: \n" \ " .section .fixup,\"ax\" \n" \ " .align 4 \n" \ " .literal_position \n" \ "5: \n" \ - " movi %1, 2b \n" \ - " movi %0, %4 \n" \ - " jx %1 \n" \ + " movi %[tmp], 2b \n" \ + " movi %[err], %[efault] \n" \ + " jx %[tmp] \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ " .long 1b, 5b \n" \ " .previous" \ - :"=r" (err), "=r" (cb) \ - :"r" ((int)(x)), "r" (addr), "i" (-EFAULT), "0" (err)) + :[err] "+r"(err_), [tmp] "=r"(cb) \ + :[x] "r"(x_), [addr] "r"(addr_), [efault] "i"(-EFAULT)) #define __get_user_nocheck(x, ptr, size) \ ({ \ - long __gu_err, __gu_val; \ - __get_user_size(__gu_val, (ptr), (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + long __gu_err; \ + __get_user_size((x), (ptr), (size), __gu_err); \ __gu_err; \ }) #define __get_user_check(x, ptr, size) \ ({ \ - long __gu_err = -EFAULT, __gu_val = 0; \ + long __gu_err = -EFAULT; \ const __typeof__(*(ptr)) *__gu_addr = (ptr); \ - if (access_ok(__gu_addr, size)) \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + if (access_ok(__gu_addr, size)) \ + __get_user_size((x), __gu_addr, (size), __gu_err); \ + else \ + (x) = 0; \ __gu_err; \ }) @@ -198,8 +198,17 @@ do { \ case 1: __get_user_asm(x, ptr, retval, 1, "l8ui", __cb); break;\ case 2: __get_user_asm(x, ptr, retval, 2, "l16ui", __cb); break;\ case 4: __get_user_asm(x, ptr, retval, 4, "l32i", __cb); break;\ - case 8: retval = __copy_from_user(&x, ptr, 8); break; \ - default: (x) = __get_user_bad(); \ + case 8: { \ + u64 __x; \ + if (unlikely(__copy_from_user(&__x, ptr, 8))) { \ + retval = -EFAULT; \ + (x) = 0; \ + } else { \ + (x) = *(__force __typeof__((ptr)))&__x; \ + } \ + break; \ + } \ + default: (x) = 0; __get_user_bad(); \ } \ } while (0) @@ -208,25 +217,28 @@ do { \ * WARNING: If you modify this macro at all, verify that the * __check_align_* macros still work. */ -#define __get_user_asm(x, addr, err, align, insn, cb) \ -__asm__ __volatile__( \ - __check_align_##align \ - "1: "insn" %2, %3, 0 \n" \ - "2: \n" \ - " .section .fixup,\"ax\" \n" \ - " .align 4 \n" \ - " .literal_position \n" \ - "5: \n" \ - " movi %1, 2b \n" \ - " movi %2, 0 \n" \ - " movi %0, %4 \n" \ - " jx %1 \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " .long 1b, 5b \n" \ - " .previous" \ - :"=r" (err), "=r" (cb), "=r" (x) \ - :"r" (addr), "i" (-EFAULT), "0" (err)) +#define __get_user_asm(x_, addr_, err_, align, insn, cb) \ +do { \ + u32 __x = 0; \ + __asm__ __volatile__( \ + __check_align_##align \ + "1: "insn" %[x], %[addr], 0 \n" \ + "2: \n" \ + " .section .fixup,\"ax\" \n" \ + " .align 4 \n" \ + " .literal_position \n" \ + "5: \n" \ + " movi %[tmp], 2b \n" \ + " movi %[err], %[efault] \n" \ + " jx %[tmp] \n" \ + " .previous \n" \ + " .section __ex_table,\"a\" \n" \ + " .long 1b, 5b \n" \ + " .previous" \ + :[err] "+r"(err_), [tmp] "=r"(cb), [x] "+r"(__x) \ + :[addr] "r"(addr_), [efault] "i"(-EFAULT)); \ + (x_) = (__force __typeof__(*(addr_)))__x; \ +} while (0) /* diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 04f19de46700..4092555828b1 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -119,13 +119,6 @@ EXPORT_SYMBOL(__invalidate_icache_range); // FIXME EXPORT_SYMBOL(screen_info); #endif -EXPORT_SYMBOL(outsb); -EXPORT_SYMBOL(outsw); -EXPORT_SYMBOL(outsl); -EXPORT_SYMBOL(insb); -EXPORT_SYMBOL(insw); -EXPORT_SYMBOL(insl); - extern long common_exception_return; EXPORT_SYMBOL(common_exception_return); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index b6f20be0fc78..5d21027b1faf 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1362,7 +1362,7 @@ int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol) { struct blkg_policy_data *pd_prealloc = NULL; - struct blkcg_gq *blkg; + struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; if (blkcg_policy_enabled(q, pol)) @@ -1370,49 +1370,82 @@ int blkcg_activate_policy(struct request_queue *q, if (queue_is_mq(q)) blk_mq_freeze_queue(q); -pd_prealloc: - if (!pd_prealloc) { - pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, &blkcg_root); - if (!pd_prealloc) { - ret = -ENOMEM; - goto out_bypass_end; - } - } - +retry: spin_lock_irq(&q->queue_lock); - /* blkg_list is pushed at the head, reverse walk to init parents first */ + /* blkg_list is pushed at the head, reverse walk to allocate parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; - pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, &blkcg_root); - if (!pd) - swap(pd, pd_prealloc); + /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ + if (blkg == pinned_blkg) { + pd = pd_prealloc; + pd_prealloc = NULL; + } else { + pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, + blkg->blkcg); + } + if (!pd) { + /* + * GFP_NOWAIT failed. Free the existing one and + * prealloc for @blkg w/ GFP_KERNEL. + */ + if (pinned_blkg) + blkg_put(pinned_blkg); + blkg_get(blkg); + pinned_blkg = blkg; + spin_unlock_irq(&q->queue_lock); - goto pd_prealloc; + + if (pd_prealloc) + pol->pd_free_fn(pd_prealloc); + pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, + blkg->blkcg); + if (pd_prealloc) + goto retry; + else + goto enomem; } blkg->pd[pol->plid] = pd; pd->blkg = blkg; pd->plid = pol->plid; - if (pol->pd_init_fn) - pol->pd_init_fn(pd); } + /* all allocated, init in the same order */ + if (pol->pd_init_fn) + list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) + pol->pd_init_fn(blkg->pd[pol->plid]); + __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); -out_bypass_end: +out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); + if (pinned_blkg) + blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; + +enomem: + /* alloc failed, nothing's initialized yet, free everything */ + spin_lock_irq(&q->queue_lock); + list_for_each_entry(blkg, &q->blkg_list, q_node) { + if (blkg->pd[pol->plid]) { + pol->pd_free_fn(blkg->pd[pol->plid]); + blkg->pd[pol->plid] = NULL; + } + } + spin_unlock_irq(&q->queue_lock); + ret = -ENOMEM; + goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index e8cb68f6958a..2bc43e94f4c4 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -108,16 +108,13 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) { - struct rq_qos *cur, *prev = NULL; - for (cur = q->rq_qos; cur; cur = cur->next) { - if (cur == rqos) { - if (prev) - prev->next = rqos->next; - else - q->rq_qos = cur; + struct rq_qos **cur; + + for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { + if (*cur == rqos) { + *cur = rqos->next; break; } - prev = cur; } blk_mq_debugfs_unregister_rqos(rqos); diff --git a/block/elevator.c b/block/elevator.c index 5437059c9261..076ba7308e65 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -616,7 +616,8 @@ out: static inline bool elv_support_iosched(struct request_queue *q) { - if (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)) + if (!q->mq_ops || + (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED))) return false; return true; } diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 3b2525908dd8..a1a858ad4d18 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -905,8 +905,8 @@ void acpi_cppc_processor_exit(struct acpi_processor *pr) pcc_data[pcc_ss_id]->refcount--; if (!pcc_data[pcc_ss_id]->refcount) { pcc_mbox_free_channel(pcc_data[pcc_ss_id]->pcc_channel); - pcc_data[pcc_ss_id]->pcc_channel_acquired = 0; kfree(pcc_data[pcc_ss_id]); + pcc_data[pcc_ss_id] = NULL; } } } diff --git a/drivers/acpi/hmat/hmat.c b/drivers/acpi/hmat/hmat.c index 8f9a28a870b0..8b0de8a3c647 100644 --- a/drivers/acpi/hmat/hmat.c +++ b/drivers/acpi/hmat/hmat.c @@ -403,7 +403,7 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade pr_info("HMAT: Memory Flags:%04x Processor Domain:%d Memory Domain:%d\n", p->flags, p->processor_PD, p->memory_PD); - if (p->flags & ACPI_HMAT_MEMORY_PD_VALID) { + if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) { target = find_mem_target(p->memory_PD); if (!target) { pr_debug("HMAT: Memory Domain missing from SRAT\n"); diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 2261713d1aec..930a49fa4dfc 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -162,21 +162,23 @@ void acpi_processor_ppc_init(int cpu) struct acpi_processor *pr = per_cpu(processors, cpu); int ret; + if (!pr) + return; + ret = dev_pm_qos_add_request(get_cpu_device(cpu), &pr->perflib_req, DEV_PM_QOS_MAX_FREQUENCY, INT_MAX); - if (ret < 0) { + if (ret < 0) pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu, ret); - return; - } } void acpi_processor_ppc_exit(int cpu) { struct acpi_processor *pr = per_cpu(processors, cpu); - dev_pm_qos_remove_request(&pr->perflib_req); + if (pr) + dev_pm_qos_remove_request(&pr->perflib_req); } static int acpi_processor_get_performance_control(struct acpi_processor *pr) diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c index ec2638f1df4f..8227c7dd75b1 100644 --- a/drivers/acpi/processor_thermal.c +++ b/drivers/acpi/processor_thermal.c @@ -130,21 +130,23 @@ void acpi_thermal_cpufreq_init(int cpu) struct acpi_processor *pr = per_cpu(processors, cpu); int ret; + if (!pr) + return; + ret = dev_pm_qos_add_request(get_cpu_device(cpu), &pr->thermal_req, DEV_PM_QOS_MAX_FREQUENCY, INT_MAX); - if (ret < 0) { + if (ret < 0) pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu, ret); - return; - } } void acpi_thermal_cpufreq_exit(int cpu) { struct acpi_processor *pr = per_cpu(processors, cpu); - dev_pm_qos_remove_request(&pr->thermal_req); + if (pr) + dev_pm_qos_remove_request(&pr->thermal_req); } #else /* ! CONFIG_CPU_FREQ */ static int cpufreq_get_max_state(unsigned int cpu) diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 9fa77d72ef27..2af937a8b1c5 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -362,19 +362,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { }, }, /* - * https://bugzilla.kernel.org/show_bug.cgi?id=196907 - * Some Dell XPS13 9360 cannot do suspend-to-idle using the Low Power - * S0 Idle firmware interface. - */ - { - .callback = init_default_s3, - .ident = "Dell XPS13 9360", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"), - }, - }, - /* * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using * the Low Power S0 Idle firmware interface (see * https://bugzilla.kernel.org/show_bug.cgi?id=199057). diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index dd92faf197d5..05c2b32dcc4d 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1600,7 +1600,9 @@ static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hp */ if (!id || id->vendor != PCI_VENDOR_ID_INTEL) return; - if (((enum board_ids) id->driver_data) < board_ahci_pcs7) + + /* Skip applying the quirk on Denverton and beyond */ + if (((enum board_ids) id->driver_data) >= board_ahci_pcs7) return; /* diff --git a/drivers/base/core.c b/drivers/base/core.c index 2db62d98e395..7bd9cd366d41 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -9,6 +9,7 @@ */ #include <linux/acpi.h> +#include <linux/cpufreq.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fwnode.h> @@ -3179,6 +3180,8 @@ void device_shutdown(void) wait_for_device_probe(); device_block_probing(); + cpufreq_suspend(); + spin_lock(&devices_kset->list_lock); /* * Walk the devices list backward, shutting down each in turn. diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 6bea4f3f8040..55907c27075b 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -540,6 +540,9 @@ static ssize_t soft_offline_page_store(struct device *dev, pfn >>= PAGE_SHIFT; if (!pfn_valid(pfn)) return -ENXIO; + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ + if (!pfn_to_online_page(pfn)) + return -EIO; ret = soft_offline_page(pfn_to_page(pfn), 0); return ret == 0 ? count : ret; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 7c4350c0fb77..39136675dae5 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -6639,10 +6639,13 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) queue_delayed_work(rbd_dev->task_wq, &rbd_dev->lock_dwork, 0); ret = wait_for_completion_killable_timeout(&rbd_dev->acquire_wait, ceph_timeout_jiffies(rbd_dev->opts->lock_timeout)); - if (ret > 0) + if (ret > 0) { ret = rbd_dev->acquire_err; - else if (!ret) - ret = -ETIMEDOUT; + } else { + cancel_delayed_work_sync(&rbd_dev->lock_dwork); + if (!ret) + ret = -ETIMEDOUT; + } if (ret) { rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d58a359a6622..4285e75e52c3 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -413,13 +413,14 @@ static void reset_bdev(struct zram *zram) static ssize_t backing_dev_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct file *file; struct zram *zram = dev_to_zram(dev); - struct file *file = zram->backing_dev; char *p; ssize_t ret; down_read(&zram->init_lock); - if (!zram->backing_dev) { + file = zram->backing_dev; + if (!file) { memcpy(buf, "none\n", 5); up_read(&zram->init_lock); return 5; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index c52d6fa32aac..bffc11b87247 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2737,14 +2737,6 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) } EXPORT_SYMBOL_GPL(cpufreq_unregister_driver); -/* - * Stop cpufreq at shutdown to make sure it isn't holding any locks - * or mutexes when secondary CPUs are halted. - */ -static struct syscore_ops cpufreq_syscore_ops = { - .shutdown = cpufreq_suspend, -}; - struct kobject *cpufreq_global_kobject; EXPORT_SYMBOL(cpufreq_global_kobject); @@ -2756,8 +2748,6 @@ static int __init cpufreq_core_init(void) cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj); BUG_ON(!cpufreq_global_kobject); - register_syscore_ops(&cpufreq_syscore_ops); - return 0; } module_param(off, int, 0444); diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index 6b17d179ef8a..39fdd0641637 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -21,6 +21,8 @@ #include <linux/ccp.h> #include <linux/firmware.h> +#include <asm/smp.h> + #include "sp-dev.h" #include "psp-dev.h" @@ -235,6 +237,13 @@ static int __sev_platform_init_locked(int *error) return rc; psp->sev_state = SEV_STATE_INIT; + + /* Prepare for first SEV guest launch after INIT */ + wbinvd_on_all_cpus(); + rc = __sev_do_cmd_locked(SEV_CMD_DF_FLUSH, NULL, error); + if (rc) + return rc; + dev_dbg(psp->dev, "SEV firmware initialized\n"); return rc; diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 42a8f3f11681..709002515550 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -471,7 +471,7 @@ unlock: if (pfence_excl) *pfence_excl = fence_excl; else if (fence_excl) - shared[++shared_count] = fence_excl; + shared[shared_count++] = fence_excl; if (!shared_count) { kfree(shared); diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 35ed56b9c34f..1e21fc3e9851 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -408,7 +408,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) bytes = ~0ull; else if (size & 0x8000) bytes = (u64)(size & 0x7fff) << 10; - else if (size != 0x7fff) + else if (size != 0x7fff || dm->length < 0x20) bytes = (u64)size << 20; else bytes = (u64)get_unaligned((u32 *)&d[0x1C]) << 20; diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c index 4d835f9089df..86a10c808ef6 100644 --- a/drivers/gpio/gpio-intel-mid.c +++ b/drivers/gpio/gpio-intel-mid.c @@ -293,8 +293,9 @@ static void intel_mid_irq_handler(struct irq_desc *desc) chip->irq_eoi(data); } -static void intel_mid_irq_init_hw(struct intel_mid_gpio *priv) +static int intel_mid_irq_init_hw(struct gpio_chip *chip) { + struct intel_mid_gpio *priv = gpiochip_get_data(chip); void __iomem *reg; unsigned base; @@ -309,6 +310,8 @@ static void intel_mid_irq_init_hw(struct intel_mid_gpio *priv) reg = gpio_reg(&priv->chip, base, GEDR); writel(~0, reg); } + + return 0; } static int __maybe_unused intel_gpio_runtime_idle(struct device *dev) @@ -372,6 +375,7 @@ static int intel_gpio_probe(struct pci_dev *pdev, girq = &priv->chip.irq; girq->chip = &intel_mid_irqchip; + girq->init_hw = intel_mid_irq_init_hw; girq->parent_handler = intel_mid_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents, @@ -384,9 +388,8 @@ static int intel_gpio_probe(struct pci_dev *pdev, girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_simple_irq; - intel_mid_irq_init_hw(priv); - pci_set_drvdata(pdev, priv); + retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv); if (retval) { dev_err(&pdev->dev, "gpiochip_add error %d\n", retval); diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c index 6bb9741ad036..e9e47c0d5be7 100644 --- a/drivers/gpio/gpio-lynxpoint.c +++ b/drivers/gpio/gpio-lynxpoint.c @@ -294,8 +294,9 @@ static struct irq_chip lp_irqchip = { .flags = IRQCHIP_SKIP_SET_WAKE, }; -static void lp_gpio_irq_init_hw(struct lp_gpio *lg) +static int lp_gpio_irq_init_hw(struct gpio_chip *chip) { + struct lp_gpio *lg = gpiochip_get_data(chip); unsigned long reg; unsigned base; @@ -307,6 +308,8 @@ static void lp_gpio_irq_init_hw(struct lp_gpio *lg) reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT); outl(0xffffffff, reg); } + + return 0; } static int lp_gpio_probe(struct platform_device *pdev) @@ -364,6 +367,7 @@ static int lp_gpio_probe(struct platform_device *pdev) girq = &gc->irq; girq->chip = &lp_irqchip; + girq->init_hw = lp_gpio_irq_init_hw; girq->parent_handler = lp_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents, @@ -373,9 +377,7 @@ static int lp_gpio_probe(struct platform_device *pdev) return -ENOMEM; girq->parents[0] = (unsigned)irq_rc->start; girq->default_type = IRQ_TYPE_NONE; - girq->handler = handle_simple_irq; - - lp_gpio_irq_init_hw(lg); + girq->handler = handle_bad_irq; } ret = devm_gpiochip_add_data(dev, gc, lg); diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c index 4f27ddfe1e2f..2f1e9da81c1e 100644 --- a/drivers/gpio/gpio-merrifield.c +++ b/drivers/gpio/gpio-merrifield.c @@ -362,8 +362,9 @@ static void mrfld_irq_handler(struct irq_desc *desc) chained_irq_exit(irqchip, desc); } -static void mrfld_irq_init_hw(struct mrfld_gpio *priv) +static int mrfld_irq_init_hw(struct gpio_chip *chip) { + struct mrfld_gpio *priv = gpiochip_get_data(chip); void __iomem *reg; unsigned int base; @@ -375,6 +376,8 @@ static void mrfld_irq_init_hw(struct mrfld_gpio *priv) reg = gpio_reg(&priv->chip, base, GFER); writel(0, reg); } + + return 0; } static const char *mrfld_gpio_get_pinctrl_dev_name(struct mrfld_gpio *priv) @@ -447,6 +450,7 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id girq = &priv->chip.irq; girq->chip = &mrfld_irqchip; + girq->init_hw = mrfld_irq_init_hw; girq->parent_handler = mrfld_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents, @@ -455,11 +459,10 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id if (!girq->parents) return -ENOMEM; girq->parents[0] = pdev->irq; + girq->first = irq_base; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; - mrfld_irq_init_hw(priv); - pci_set_drvdata(pdev, priv); retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv); if (retval) { diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 5833e4f380d6..104ed299d5ea 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -86,6 +86,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip, struct lock_class_key *lock_key, struct lock_class_key *request_key); static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip); +static int gpiochip_irqchip_init_hw(struct gpio_chip *gpiochip); static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip); static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gpiochip); @@ -1406,6 +1407,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, machine_gpiochip_add(chip); + ret = gpiochip_irqchip_init_hw(chip); + if (ret) + goto err_remove_acpi_chip; + ret = gpiochip_irqchip_init_valid_mask(chip); if (ret) goto err_remove_acpi_chip; @@ -1622,6 +1627,16 @@ static struct gpio_chip *find_chip_by_name(const char *name) * The following is irqchip helper code for gpiochips. */ +static int gpiochip_irqchip_init_hw(struct gpio_chip *gc) +{ + struct gpio_irq_chip *girq = &gc->irq; + + if (!girq->init_hw) + return 0; + + return girq->init_hw(gc); +} + static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gc) { struct gpio_irq_chip *girq = &gc->irq; @@ -2446,8 +2461,13 @@ static inline int gpiochip_add_irqchip(struct gpio_chip *gpiochip, { return 0; } - static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip) {} + +static inline int gpiochip_irqchip_init_hw(struct gpio_chip *gpiochip) +{ + return 0; +} + static inline int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip) { return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 6f8aaf655a9f..2a00a36106b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1048,6 +1048,41 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, return -ENODEV; } +#ifdef CONFIG_DRM_AMDGPU_SI + if (!amdgpu_si_support) { + switch (flags & AMD_ASIC_MASK) { + case CHIP_TAHITI: + case CHIP_PITCAIRN: + case CHIP_VERDE: + case CHIP_OLAND: + case CHIP_HAINAN: + dev_info(&pdev->dev, + "SI support provided by radeon.\n"); + dev_info(&pdev->dev, + "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n" + ); + return -ENODEV; + } + } +#endif +#ifdef CONFIG_DRM_AMDGPU_CIK + if (!amdgpu_cik_support) { + switch (flags & AMD_ASIC_MASK) { + case CHIP_KAVERI: + case CHIP_BONAIRE: + case CHIP_HAWAII: + case CHIP_KABINI: + case CHIP_MULLINS: + dev_info(&pdev->dev, + "CIK support provided by radeon.\n"); + dev_info(&pdev->dev, + "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n" + ); + return -ENODEV; + } + } +#endif + /* Get rid of things like offb */ ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "amdgpudrmfb"); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index f2c097983f48..d55f5baa83d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -144,41 +144,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) struct amdgpu_device *adev; int r, acpi_status; -#ifdef CONFIG_DRM_AMDGPU_SI - if (!amdgpu_si_support) { - switch (flags & AMD_ASIC_MASK) { - case CHIP_TAHITI: - case CHIP_PITCAIRN: - case CHIP_VERDE: - case CHIP_OLAND: - case CHIP_HAINAN: - dev_info(dev->dev, - "SI support provided by radeon.\n"); - dev_info(dev->dev, - "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n" - ); - return -ENODEV; - } - } -#endif -#ifdef CONFIG_DRM_AMDGPU_CIK - if (!amdgpu_cik_support) { - switch (flags & AMD_ASIC_MASK) { - case CHIP_KAVERI: - case CHIP_BONAIRE: - case CHIP_HAWAII: - case CHIP_KABINI: - case CHIP_MULLINS: - dev_info(dev->dev, - "CIK support provided by radeon.\n"); - dev_info(dev->dev, - "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n" - ); - return -ENODEV; - } - } -#endif - adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL); if (adev == NULL) { return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index fa2f70ce2e2b..f6e81680dd7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1129,7 +1129,7 @@ static void sdma_v5_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring) amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); /* reference */ - amdgpu_ring_write(ring, 0xfffffff); /* mask */ + amdgpu_ring_write(ring, 0xffffffff); /* mask */ amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */ } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c index dc754447f0dd..23c12018dbc1 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c @@ -655,7 +655,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, count = SMU_MAX_SMIO_LEVELS; for (level = 0; level < count; level++) { table->SmioTable2.Pattern[level].Voltage = - PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE); + PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE); /* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/ table->SmioTable2.Pattern[level].Smio = (uint8_t) level; diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c index 7c960b07746f..ae18fbcb26fb 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c @@ -456,7 +456,7 @@ static int vegam_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, count = SMU_MAX_SMIO_LEVELS; for (level = 0; level < count; level++) { table->SmioTable2.Pattern[level].Voltage = PP_HOST_TO_SMC_US( - data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE); + data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE); /* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/ table->SmioTable2.Pattern[level].Smio = (uint8_t) level; diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 82a4ceed3fcf..6b0177112e18 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -159,6 +159,9 @@ static const struct edid_quirk { /* Medion MD 30217 PG */ { "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 }, + /* Lenovo G50 */ + { "SDC", 18514, EDID_QUIRK_FORCE_6BPC }, + /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */ { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC }, diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index efb39f350b19..3250c1b8dcca 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1270,7 +1270,7 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv, DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, " "disabling port %c DVI/HDMI support\n", port_name(port), info->alternate_ddc_pin, - port_name(p), port_name(port)); + port_name(p), port_name(p)); /* * If we have multiple ports supposedly sharing the @@ -1278,9 +1278,14 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv, * port. Otherwise they share the same ddc bin and * system couldn't communicate with them separately. * - * Give child device order the priority, first come first - * served. + * Give inverse child device order the priority, + * last one wins. Yes, there are real machines + * (eg. Asrock B250M-HDV) where VBT has both + * port A and port E with the same AUX ch and + * we must pick port E :( */ + info = &dev_priv->vbt.ddi_port_info[p]; + info->supports_dvi = false; info->supports_hdmi = false; info->alternate_ddc_pin = 0; @@ -1316,7 +1321,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv, DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, " "disabling port %c DP support\n", port_name(port), info->alternate_aux_channel, - port_name(p), port_name(port)); + port_name(p), port_name(p)); /* * If we have multiple ports supposedlt sharing the @@ -1324,9 +1329,14 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv, * port. Otherwise they share the same aux channel * and system couldn't communicate with them separately. * - * Give child device order the priority, first come first - * served. + * Give inverse child device order the priority, + * last one wins. Yes, there are real machines + * (eg. Asrock B250M-HDV) where VBT has both + * port A and port E with the same AUX ch and + * we must pick port E :( */ + info = &dev_priv->vbt.ddi_port_info[p]; + info->supports_dp = false; info->alternate_aux_channel = 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 91051e178021..05289edbafe3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -364,6 +364,7 @@ err: return VM_FAULT_OOM; case -ENOSPC: case -EFAULT: + case -ENODEV: /* bad object, how did you get here! */ return VM_FAULT_SIGBUS; default: WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret); @@ -475,10 +476,16 @@ i915_gem_mmap_gtt(struct drm_file *file, if (!obj) return -ENOENT; + if (i915_gem_object_never_bind_ggtt(obj)) { + ret = -ENODEV; + goto out; + } + ret = create_mmap_offset(obj); if (ret == 0) *offset = drm_vma_node_offset_addr(&obj->base.vma_node); +out: i915_gem_object_put(obj); return ret; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 5efb9936e05b..ddf3605bea8e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -153,6 +153,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj) } static inline bool +i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj) +{ + return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT; +} + +static inline bool i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj) { return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index ede0eb4218a8..646859fea224 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops { #define I915_GEM_OBJECT_HAS_STRUCT_PAGE BIT(0) #define I915_GEM_OBJECT_IS_SHRINKABLE BIT(1) #define I915_GEM_OBJECT_IS_PROXY BIT(2) -#define I915_GEM_OBJECT_ASYNC_CANCEL BIT(3) +#define I915_GEM_OBJECT_NO_GGTT BIT(3) +#define I915_GEM_OBJECT_ASYNC_CANCEL BIT(4) /* Interface between the GEM object and its backing storage. * get_pages() is called once prior to the use of the associated set diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 11b231c187c5..6b3b50f0f6d9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -702,6 +702,7 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj) static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = { .flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE | I915_GEM_OBJECT_IS_SHRINKABLE | + I915_GEM_OBJECT_NO_GGTT | I915_GEM_OBJECT_ASYNC_CANCEL, .get_pages = i915_gem_userptr_get_pages, .put_pages = i915_gem_userptr_put_pages, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index bdfcc7bdadbf..06a506c29463 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -234,6 +234,13 @@ static void execlists_init_reg_state(u32 *reg_state, struct intel_engine_cs *engine, struct intel_ring *ring); +static void mark_eio(struct i915_request *rq) +{ + if (!i915_request_signaled(rq)) + dma_fence_set_error(&rq->fence, -EIO); + i915_request_mark_complete(rq); +} + static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine) { return (i915_ggtt_offset(engine->status_page.vma) + @@ -1236,6 +1243,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) submit = true; last = rq; } + i915_request_put(rq); /* * Hmm, we have a bunch of virtual engine requests, @@ -2574,12 +2582,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) __execlists_reset(engine, true); /* Mark all executing requests as skipped. */ - list_for_each_entry(rq, &engine->active.requests, sched.link) { - if (!i915_request_signaled(rq)) - dma_fence_set_error(&rq->fence, -EIO); - - i915_request_mark_complete(rq); - } + list_for_each_entry(rq, &engine->active.requests, sched.link) + mark_eio(rq); /* Flush the queued requests to the timeline list (for retiring). */ while ((rb = rb_first_cached(&execlists->queue))) { @@ -2587,9 +2591,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) int i; priolist_for_each_request_consume(rq, rn, p, i) { + mark_eio(rq); __i915_request_submit(rq); - dma_fence_set_error(&rq->fence, -EIO); - i915_request_mark_complete(rq); } rb_erase_cached(&p->node, &execlists->queue); @@ -2605,13 +2608,15 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) RB_CLEAR_NODE(rb); spin_lock(&ve->base.active.lock); - if (ve->request) { - ve->request->engine = engine; - __i915_request_submit(ve->request); - dma_fence_set_error(&ve->request->fence, -EIO); - i915_request_mark_complete(ve->request); + rq = fetch_and_zero(&ve->request); + if (rq) { + mark_eio(rq); + + rq->engine = engine; + __i915_request_submit(rq); + i915_request_put(rq); + ve->base.execlists.queue_priority_hint = INT_MIN; - ve->request = NULL; } spin_unlock(&ve->base.active.lock); } @@ -3615,6 +3620,8 @@ submit_engine: static void virtual_submit_request(struct i915_request *rq) { struct virtual_engine *ve = to_virtual_engine(rq->engine); + struct i915_request *old; + unsigned long flags; GEM_TRACE("%s: rq=%llx:%lld\n", ve->base.name, @@ -3623,15 +3630,31 @@ static void virtual_submit_request(struct i915_request *rq) GEM_BUG_ON(ve->base.submit_request != virtual_submit_request); - GEM_BUG_ON(ve->request); - GEM_BUG_ON(!list_empty(virtual_queue(ve))); + spin_lock_irqsave(&ve->base.active.lock, flags); + + old = ve->request; + if (old) { /* background completion event from preempt-to-busy */ + GEM_BUG_ON(!i915_request_completed(old)); + __i915_request_submit(old); + i915_request_put(old); + } - ve->base.execlists.queue_priority_hint = rq_prio(rq); - WRITE_ONCE(ve->request, rq); + if (i915_request_completed(rq)) { + __i915_request_submit(rq); - list_move_tail(&rq->sched.link, virtual_queue(ve)); + ve->base.execlists.queue_priority_hint = INT_MIN; + ve->request = NULL; + } else { + ve->base.execlists.queue_priority_hint = rq_prio(rq); + ve->request = i915_request_get(rq); + + GEM_BUG_ON(!list_empty(virtual_queue(ve))); + list_move_tail(&rq->sched.link, virtual_queue(ve)); + + tasklet_schedule(&ve->base.execlists.tasklet); + } - tasklet_schedule(&ve->base.execlists.tasklet); + spin_unlock_irqrestore(&ve->base.active.lock, flags); } static struct ve_bond * diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 95e7c52cf8ed..d0f94f239919 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -969,6 +969,9 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, lockdep_assert_held(&obj->base.dev->struct_mutex); + if (i915_gem_object_never_bind_ggtt(obj)) + return ERR_PTR(-ENODEV); + if (flags & PIN_MAPPABLE && (!view || view->type == I915_GGTT_VIEW_NORMAL)) { /* If the required space is larger than the available diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 663ff9f4fac9..1e7b1be25bb0 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -26,6 +26,8 @@ #include "dsi_cfg.h" #include "msm_kms.h" +#define DSI_RESET_TOGGLE_DELAY_MS 20 + static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor) { u32 ver; @@ -986,7 +988,7 @@ static void dsi_sw_reset(struct msm_dsi_host *msm_host) wmb(); /* clocks need to be enabled before reset */ dsi_write(msm_host, REG_DSI_RESET, 1); - wmb(); /* make sure reset happen */ + msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */ dsi_write(msm_host, REG_DSI_RESET, 0); } @@ -1396,7 +1398,7 @@ static void dsi_sw_reset_restore(struct msm_dsi_host *msm_host) /* dsi controller can only be reset while clocks are running */ dsi_write(msm_host, REG_DSI_RESET, 1); - wmb(); /* make sure reset happen */ + msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */ dsi_write(msm_host, REG_DSI_RESET, 0); wmb(); /* controller out of reset */ dsi_write(msm_host, REG_DSI_CTRL, data0); diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index f67ed925c0ef..8822ec13a0d6 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -208,6 +208,9 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev) pfdev->features.mem_features = gpu_read(pfdev, GPU_MEM_FEATURES); pfdev->features.mmu_features = gpu_read(pfdev, GPU_MMU_FEATURES); pfdev->features.thread_features = gpu_read(pfdev, GPU_THREAD_FEATURES); + pfdev->features.max_threads = gpu_read(pfdev, GPU_THREAD_MAX_THREADS); + pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE); + pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE); pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES); for (i = 0; i < 4; i++) pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i)); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index a58551668d9a..21f34d44aac2 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job) job_read(pfdev, JS_TAIL_LO(js)), sched_job); - mutex_lock(&pfdev->reset_lock); + if (!mutex_trylock(&pfdev->reset_lock)) + return; - for (i = 0; i < NUM_JOB_SLOTS; i++) - drm_sched_stop(&pfdev->js->queue[i].sched, sched_job); + for (i = 0; i < NUM_JOB_SLOTS; i++) { + struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched; + + drm_sched_stop(sched, sched_job); + if (js != i) + /* Ensure any timeouts on other slots have finished */ + cancel_delayed_work_sync(&sched->work_tdr); + } - if (sched_job) - drm_sched_increase_karma(sched_job); + drm_sched_increase_karma(sched_job); spin_lock_irqsave(&pfdev->js->job_lock, flags); for (i = 0; i < NUM_JOB_SLOTS; i++) { diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index d0bc91ed7c90..9e55076578c6 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -379,19 +379,11 @@ radeon_pci_remove(struct pci_dev *pdev) static void radeon_pci_shutdown(struct pci_dev *pdev) { - struct drm_device *ddev = pci_get_drvdata(pdev); - /* if we are running in a VM, make sure the device * torn down properly on reboot/shutdown */ if (radeon_device_is_virtual()) radeon_pci_remove(pdev); - - /* Some adapters need to be suspended before a - * shutdown occurs in order to prevent an error - * during kexec. - */ - radeon_suspend_kms(ddev, true, true, false); } static int radeon_pmops_suspend(struct device *dev) diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index 504763423d46..a46ac284dd5e 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -63,7 +63,6 @@ config TINYDRM_REPAPER depends on DRM && SPI select DRM_KMS_HELPER select DRM_KMS_CMA_HELPER - depends on THERMAL || !THERMAL help DRM driver for the following Pervasive Displays panels: 1.44" TFT EPD Panel (E1144CS021) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 20ff56f27aa4..98819462f025 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -185,8 +185,9 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo, list_add_tail(&bo->lru, &man->lru[bo->priority]); kref_get(&bo->list_kref); - if (bo->ttm && !(bo->ttm->page_flags & - (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) { + if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm && + !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG | + TTM_PAGE_FLAG_SWAPPED))) { list_add_tail(&bo->swap, &bdev->glob->swap_lru[bo->priority]); kref_get(&bo->list_kref); } @@ -878,11 +879,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev, if (!bo) { if (busy_bo) - ttm_bo_get(busy_bo); + kref_get(&busy_bo->list_kref); spin_unlock(&glob->lru_lock); ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket); if (busy_bo) - ttm_bo_put(busy_bo); + kref_put(&busy_bo->list_kref, ttm_bo_release_list); return ret; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 76eedb963693..46dc3de7e81b 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -278,15 +278,13 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) else ret = vmf_insert_pfn(&cvma, address, pfn); - /* - * Somebody beat us to this PTE or prefaulting to - * an already populated PTE, or prefaulting error. - */ - - if (unlikely((ret == VM_FAULT_NOPAGE && i > 0))) - break; - else if (unlikely(ret & VM_FAULT_ERROR)) - goto out_io_unlock; + /* Never error on prefaulted PTEs */ + if (unlikely((ret & VM_FAULT_ERROR))) { + if (i == 0) + goto out_io_unlock; + else + break; + } address += PAGE_SIZE; if (unlikely(++page_offset >= page_last)) diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c index dace8577fa43..79851923ee57 100644 --- a/drivers/input/misc/da9063_onkey.c +++ b/drivers/input/misc/da9063_onkey.c @@ -232,10 +232,7 @@ static int da9063_onkey_probe(struct platform_device *pdev) onkey->input->phys = onkey->phys; onkey->input->dev.parent = &pdev->dev; - if (onkey->key_power) - input_set_capability(onkey->input, EV_KEY, KEY_POWER); - - input_set_capability(onkey->input, EV_KEY, KEY_SLEEP); + input_set_capability(onkey->input, EV_KEY, KEY_POWER); INIT_DELAYED_WORK(&onkey->work, da9063_poll_on); diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index 97e3639e99d0..08520b3a18b8 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -92,11 +92,18 @@ soc_button_device_create(struct platform_device *pdev, continue; gpio = soc_button_lookup_gpio(&pdev->dev, info->acpi_index); - if (gpio < 0 && gpio != -ENOENT) { - error = gpio; - goto err_free_mem; - } else if (!gpio_is_valid(gpio)) { - /* Skip GPIO if not present */ + if (!gpio_is_valid(gpio)) { + /* + * Skip GPIO if not present. Note we deliberately + * ignore -EPROBE_DEFER errors here. On some devices + * Intel is using so called virtual GPIOs which are not + * GPIOs at all but some way for AML code to check some + * random status bits without need a custom opregion. + * In some cases the resources table we parse points to + * such a virtual GPIO, since these are not real GPIOs + * we do not have a driver for these so they will never + * show up, therefore we ignore -EPROBE_DEFER. + */ continue; } diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 04fe43440a3c..2d8434b7b623 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1827,31 +1827,6 @@ static int elantech_create_smbus(struct psmouse *psmouse, leave_breadcrumbs); } -static bool elantech_use_host_notify(struct psmouse *psmouse, - struct elantech_device_info *info) -{ - if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version)) - return true; - - switch (info->bus) { - case ETP_BUS_PS2_ONLY: - /* expected case */ - break; - case ETP_BUS_SMB_HST_NTFY_ONLY: - case ETP_BUS_PS2_SMB_HST_NTFY: - /* SMbus implementation is stable since 2018 */ - if (dmi_get_bios_year() >= 2018) - return true; - /* fall through */ - default: - psmouse_dbg(psmouse, - "Ignoring SMBus bus provider %d\n", info->bus); - break; - } - - return false; -} - /** * elantech_setup_smbus - called once the PS/2 devices are enumerated * and decides to instantiate a SMBus InterTouch device. @@ -1871,7 +1846,7 @@ static int elantech_setup_smbus(struct psmouse *psmouse, * i2c_blacklist_pnp_ids. * Old ICs are up to the user to decide. */ - if (!elantech_use_host_notify(psmouse, info) || + if (!ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version) || psmouse_matches_pnp_id(psmouse, i2c_blacklist_pnp_ids)) return -ENXIO; } @@ -1891,6 +1866,34 @@ static int elantech_setup_smbus(struct psmouse *psmouse, return 0; } +static bool elantech_use_host_notify(struct psmouse *psmouse, + struct elantech_device_info *info) +{ + if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version)) + return true; + + switch (info->bus) { + case ETP_BUS_PS2_ONLY: + /* expected case */ + break; + case ETP_BUS_SMB_ALERT_ONLY: + /* fall-through */ + case ETP_BUS_PS2_SMB_ALERT: + psmouse_dbg(psmouse, "Ignoring SMBus provider through alert protocol.\n"); + break; + case ETP_BUS_SMB_HST_NTFY_ONLY: + /* fall-through */ + case ETP_BUS_PS2_SMB_HST_NTFY: + return true; + default: + psmouse_dbg(psmouse, + "Ignoring SMBus bus provider %d.\n", + info->bus); + } + + return false; +} + int elantech_init_smbus(struct psmouse *psmouse) { struct elantech_device_info info; diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 772493b1f665..190b9974526b 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -146,7 +146,7 @@ static int rmi_process_interrupt_requests(struct rmi_device *rmi_dev) } mutex_lock(&data->irq_mutex); - bitmap_and(data->irq_status, data->irq_status, data->current_irq_mask, + bitmap_and(data->irq_status, data->irq_status, data->fn_irq_bits, data->irq_count); /* * At this point, irq_status has all bits that are set in the @@ -385,6 +385,8 @@ static int rmi_driver_set_irq_bits(struct rmi_device *rmi_dev, bitmap_copy(data->current_irq_mask, data->new_irq_mask, data->num_of_irq_regs); + bitmap_or(data->fn_irq_bits, data->fn_irq_bits, mask, data->irq_count); + error_unlock: mutex_unlock(&data->irq_mutex); return error; @@ -398,6 +400,8 @@ static int rmi_driver_clear_irq_bits(struct rmi_device *rmi_dev, struct device *dev = &rmi_dev->dev; mutex_lock(&data->irq_mutex); + bitmap_andnot(data->fn_irq_bits, + data->fn_irq_bits, mask, data->irq_count); bitmap_andnot(data->new_irq_mask, data->current_irq_mask, mask, data->irq_count); diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 5178ea8b5f30..fb43aa708660 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -53,6 +53,7 @@ struct goodix_ts_data { const char *cfg_name; struct completion firmware_loading_complete; unsigned long irq_flags; + unsigned int contact_size; }; #define GOODIX_GPIO_INT_NAME "irq" @@ -62,6 +63,7 @@ struct goodix_ts_data { #define GOODIX_MAX_WIDTH 4096 #define GOODIX_INT_TRIGGER 1 #define GOODIX_CONTACT_SIZE 8 +#define GOODIX_MAX_CONTACT_SIZE 9 #define GOODIX_MAX_CONTACTS 10 #define GOODIX_CONFIG_MAX_LENGTH 240 @@ -144,6 +146,19 @@ static const struct dmi_system_id rotated_screen[] = { {} }; +static const struct dmi_system_id nine_bytes_report[] = { +#if defined(CONFIG_DMI) && defined(CONFIG_X86) + { + .ident = "Lenovo YogaBook", + /* YB1-X91L/F and YB1-X90L/F */ + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9") + } + }, +#endif + {} +}; + /** * goodix_i2c_read - read data from a register of the i2c slave device. * @@ -249,7 +264,7 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) max_timeout = jiffies + msecs_to_jiffies(GOODIX_BUFFER_STATUS_TIMEOUT); do { error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR, - data, GOODIX_CONTACT_SIZE + 1); + data, ts->contact_size + 1); if (error) { dev_err(&ts->client->dev, "I2C transfer error: %d\n", error); @@ -262,12 +277,12 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) return -EPROTO; if (touch_num > 1) { - data += 1 + GOODIX_CONTACT_SIZE; + data += 1 + ts->contact_size; error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR + - 1 + GOODIX_CONTACT_SIZE, + 1 + ts->contact_size, data, - GOODIX_CONTACT_SIZE * + ts->contact_size * (touch_num - 1)); if (error) return error; @@ -286,7 +301,7 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) return 0; } -static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data) +static void goodix_ts_report_touch_8b(struct goodix_ts_data *ts, u8 *coor_data) { int id = coor_data[0] & 0x0F; int input_x = get_unaligned_le16(&coor_data[1]); @@ -301,6 +316,21 @@ static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data) input_report_abs(ts->input_dev, ABS_MT_WIDTH_MAJOR, input_w); } +static void goodix_ts_report_touch_9b(struct goodix_ts_data *ts, u8 *coor_data) +{ + int id = coor_data[1] & 0x0F; + int input_x = get_unaligned_le16(&coor_data[3]); + int input_y = get_unaligned_le16(&coor_data[5]); + int input_w = get_unaligned_le16(&coor_data[7]); + + input_mt_slot(ts->input_dev, id); + input_mt_report_slot_state(ts->input_dev, MT_TOOL_FINGER, true); + touchscreen_report_pos(ts->input_dev, &ts->prop, + input_x, input_y, true); + input_report_abs(ts->input_dev, ABS_MT_TOUCH_MAJOR, input_w); + input_report_abs(ts->input_dev, ABS_MT_WIDTH_MAJOR, input_w); +} + /** * goodix_process_events - Process incoming events * @@ -311,7 +341,7 @@ static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data) */ static void goodix_process_events(struct goodix_ts_data *ts) { - u8 point_data[1 + GOODIX_CONTACT_SIZE * GOODIX_MAX_CONTACTS]; + u8 point_data[1 + GOODIX_MAX_CONTACT_SIZE * GOODIX_MAX_CONTACTS]; int touch_num; int i; @@ -326,8 +356,12 @@ static void goodix_process_events(struct goodix_ts_data *ts) input_report_key(ts->input_dev, KEY_LEFTMETA, point_data[0] & BIT(4)); for (i = 0; i < touch_num; i++) - goodix_ts_report_touch(ts, - &point_data[1 + GOODIX_CONTACT_SIZE * i]); + if (ts->contact_size == 9) + goodix_ts_report_touch_9b(ts, + &point_data[1 + ts->contact_size * i]); + else + goodix_ts_report_touch_8b(ts, + &point_data[1 + ts->contact_size * i]); input_mt_sync_frame(ts->input_dev); input_sync(ts->input_dev); @@ -730,6 +764,13 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) "Applying '180 degrees rotated screen' quirk\n"); } + if (dmi_check_system(nine_bytes_report)) { + ts->contact_size = 9; + + dev_dbg(&ts->client->dev, + "Non-standard 9-bytes report format quirk\n"); + } + error = input_mt_init_slots(ts->input_dev, ts->max_touch_num, INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED); if (error) { @@ -810,6 +851,7 @@ static int goodix_ts_probe(struct i2c_client *client, ts->client = client; i2c_set_clientdata(client, ts); init_completion(&ts->firmware_loading_complete); + ts->contact_size = GOODIX_CONTACT_SIZE; error = goodix_get_gpio_config(ts); if (error) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 2369b8af81f3..dd555078258c 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -583,7 +583,8 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt) retry: type = (event[1] >> EVENT_TYPE_SHIFT) & EVENT_TYPE_MASK; devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK; - pasid = PPR_PASID(*(u64 *)&event[0]); + pasid = (event[0] & EVENT_DOMID_MASK_HI) | + (event[1] & EVENT_DOMID_MASK_LO); flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; address = (u64)(((u64)event[3]) << 32) | event[2]; @@ -616,7 +617,7 @@ retry: address, flags); break; case EVENT_TYPE_PAGE_TAB_ERR: - dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n", + dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n", PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), pasid, address, flags); break; @@ -1463,6 +1464,7 @@ static void free_pagetable(struct protection_domain *domain) * to 64 bits. */ static bool increase_address_space(struct protection_domain *domain, + unsigned long address, gfp_t gfp) { unsigned long flags; @@ -1471,8 +1473,8 @@ static bool increase_address_space(struct protection_domain *domain, spin_lock_irqsave(&domain->lock, flags); - if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL)) - /* address space already 64 bit large */ + if (address <= PM_LEVEL_SIZE(domain->mode) || + WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL)) goto out; pte = (void *)get_zeroed_page(gfp); @@ -1505,7 +1507,7 @@ static u64 *alloc_pte(struct protection_domain *domain, BUG_ON(!is_power_of_2(page_size)); while (address > PM_LEVEL_SIZE(domain->mode)) - *updated = increase_address_space(domain, gfp) || *updated; + *updated = increase_address_space(domain, address, gfp) || *updated; level = domain->mode - 1; pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index c9c1612d52e0..17bd5a349119 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -130,8 +130,8 @@ #define EVENT_TYPE_INV_PPR_REQ 0x9 #define EVENT_DEVID_MASK 0xffff #define EVENT_DEVID_SHIFT 0 -#define EVENT_DOMID_MASK 0xffff -#define EVENT_DOMID_SHIFT 0 +#define EVENT_DOMID_MASK_LO 0xffff +#define EVENT_DOMID_MASK_HI 0xf0000 #define EVENT_FLAGS_MASK 0xfff #define EVENT_FLAGS_SHIFT 0x10 diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index b18aac4c105e..7c503a6bc585 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -812,6 +812,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, return 0; out_clear_smmu: + __arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx); smmu_domain->smmu = NULL; out_unlock: mutex_unlock(&smmu_domain->init_mutex); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 4c91359057c5..ca51036aa53c 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -166,6 +166,9 @@ #define ARM_MALI_LPAE_TTBR_READ_INNER BIT(2) #define ARM_MALI_LPAE_TTBR_SHARE_OUTER BIT(4) +#define ARM_MALI_LPAE_MEMATTR_IMP_DEF 0x88ULL +#define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL + /* IOPTE accessors */ #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d)) @@ -1015,27 +1018,56 @@ arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) static struct io_pgtable * arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) { - struct io_pgtable *iop; + struct arm_lpae_io_pgtable *data; - if (cfg->ias != 48 || cfg->oas > 40) + /* No quirks for Mali (hopefully) */ + if (cfg->quirks) + return NULL; + + if (cfg->ias > 48 || cfg->oas > 40) return NULL; cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G); - iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie); - if (iop) { - u64 mair, ttbr; - /* Copy values as union fields overlap */ - mair = cfg->arm_lpae_s1_cfg.mair[0]; - ttbr = cfg->arm_lpae_s1_cfg.ttbr[0]; + data = arm_lpae_alloc_pgtable(cfg); + if (!data) + return NULL; - cfg->arm_mali_lpae_cfg.memattr = mair; - cfg->arm_mali_lpae_cfg.transtab = ttbr | - ARM_MALI_LPAE_TTBR_READ_INNER | - ARM_MALI_LPAE_TTBR_ADRMODE_TABLE; + /* Mali seems to need a full 4-level table regardless of IAS */ + if (data->levels < ARM_LPAE_MAX_LEVELS) { + data->levels = ARM_LPAE_MAX_LEVELS; + data->pgd_size = sizeof(arm_lpae_iopte); } + /* + * MEMATTR: Mali has no actual notion of a non-cacheable type, so the + * best we can do is mimic the out-of-tree driver and hope that the + * "implementation-defined caching policy" is good enough. Similarly, + * we'll use it for the sake of a valid attribute for our 'device' + * index, although callers should never request that in practice. + */ + cfg->arm_mali_lpae_cfg.memattr = + (ARM_MALI_LPAE_MEMATTR_IMP_DEF + << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) | + (ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC + << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) | + (ARM_MALI_LPAE_MEMATTR_IMP_DEF + << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV)); - return iop; + data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg); + if (!data->pgd) + goto out_free_data; + + /* Ensure the empty pgd is visible before TRANSTAB can be written */ + wmb(); + + cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) | + ARM_MALI_LPAE_TTBR_READ_INNER | + ARM_MALI_LPAE_TTBR_ADRMODE_TABLE; + return &data->iop; + +out_free_data: + kfree(data); + return NULL; } struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = { diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 9da8309f7170..237103465b82 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -1086,8 +1086,6 @@ static int ipmmu_probe(struct platform_device *pdev) mmu->num_ctx = min(IPMMU_CTX_MAX, mmu->features->number_of_contexts); - irq = platform_get_irq(pdev, 0); - /* * Determine if this IPMMU instance is a root device by checking for * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property. @@ -1106,6 +1104,7 @@ static int ipmmu_probe(struct platform_device *pdev) /* Root devices have mandatory IRQs */ if (ipmmu_is_root(mmu)) { + irq = platform_get_irq(pdev, 0); if (irq < 0) { dev_err(&pdev->dev, "no IRQ found\n"); return irq; diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 26290f310f90..4dcbf68dfda4 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -100,6 +100,7 @@ struct rk_iommu { struct device *dev; void __iomem **bases; int num_mmu; + int num_irq; struct clk_bulk_data *clocks; int num_clocks; bool reset_disabled; @@ -1136,7 +1137,7 @@ static int rk_iommu_probe(struct platform_device *pdev) struct rk_iommu *iommu; struct resource *res; int num_res = pdev->num_resources; - int err, i, irq; + int err, i; iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL); if (!iommu) @@ -1163,6 +1164,10 @@ static int rk_iommu_probe(struct platform_device *pdev) if (iommu->num_mmu == 0) return PTR_ERR(iommu->bases[0]); + iommu->num_irq = platform_irq_count(pdev); + if (iommu->num_irq < 0) + return iommu->num_irq; + iommu->reset_disabled = device_property_read_bool(dev, "rockchip,disable-mmu-reset"); @@ -1219,8 +1224,9 @@ static int rk_iommu_probe(struct platform_device *pdev) pm_runtime_enable(dev); - i = 0; - while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) { + for (i = 0; i < iommu->num_irq; i++) { + int irq = platform_get_irq(pdev, i); + if (irq < 0) return irq; @@ -1245,10 +1251,13 @@ err_unprepare_clocks: static void rk_iommu_shutdown(struct platform_device *pdev) { struct rk_iommu *iommu = platform_get_drvdata(pdev); - int i = 0, irq; + int i; + + for (i = 0; i < iommu->num_irq; i++) { + int irq = platform_get_irq(pdev, i); - while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) devm_free_irq(iommu->dev, irq, iommu); + } pm_runtime_force_suspend(&pdev->dev); } diff --git a/drivers/irqchip/irq-al-fic.c b/drivers/irqchip/irq-al-fic.c index 1a57cee3efab..0b0a73739756 100644 --- a/drivers/irqchip/irq-al-fic.c +++ b/drivers/irqchip/irq-al-fic.c @@ -15,6 +15,7 @@ /* FIC Registers */ #define AL_FIC_CAUSE 0x00 +#define AL_FIC_SET_CAUSE 0x08 #define AL_FIC_MASK 0x10 #define AL_FIC_CONTROL 0x28 @@ -126,6 +127,16 @@ static void al_fic_irq_handler(struct irq_desc *desc) chained_irq_exit(irqchip, desc); } +static int al_fic_irq_retrigger(struct irq_data *data) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data); + struct al_fic *fic = gc->private; + + writel_relaxed(BIT(data->hwirq), fic->base + AL_FIC_SET_CAUSE); + + return 1; +} + static int al_fic_register(struct device_node *node, struct al_fic *fic) { @@ -159,6 +170,7 @@ static int al_fic_register(struct device_node *node, gc->chip_types->chip.irq_unmask = irq_gc_mask_clr_bit; gc->chip_types->chip.irq_ack = irq_gc_ack_clr_bit; gc->chip_types->chip.irq_set_type = al_fic_irq_set_type; + gc->chip_types->chip.irq_retrigger = al_fic_irq_retrigger; gc->chip_types->chip.flags = IRQCHIP_SKIP_SET_WAKE; gc->private = fic; diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c index 6acad2ea0fb3..29333497ba10 100644 --- a/drivers/irqchip/irq-atmel-aic5.c +++ b/drivers/irqchip/irq-atmel-aic5.c @@ -313,6 +313,7 @@ static void __init sama5d3_aic_irq_fixup(void) static const struct of_device_id aic5_irq_fixups[] __initconst = { { .compatible = "atmel,sama5d3", .data = sama5d3_aic_irq_fixup }, { .compatible = "atmel,sama5d4", .data = sama5d3_aic_irq_fixup }, + { .compatible = "microchip,sam9x60", .data = sama5d3_aic_irq_fixup }, { /* sentinel */ }, }; @@ -390,3 +391,12 @@ static int __init sama5d4_aic5_of_init(struct device_node *node, return aic5_of_init(node, parent, NR_SAMA5D4_IRQS); } IRQCHIP_DECLARE(sama5d4_aic5, "atmel,sama5d4-aic", sama5d4_aic5_of_init); + +#define NR_SAM9X60_IRQS 50 + +static int __init sam9x60_aic5_of_init(struct device_node *node, + struct device_node *parent) +{ + return aic5_of_init(node, parent, NR_SAM9X60_IRQS); +} +IRQCHIP_DECLARE(sam9x60_aic5, "microchip,sam9x60-aic", sam9x60_aic5_of_init); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 422664ac5f53..1edc99335a94 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -59,7 +59,7 @@ static struct gic_chip_data gic_data __read_mostly; static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); #define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer)) -#define GIC_LINE_NR max(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U) +#define GIC_LINE_NR min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U) #define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer) /* diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index c72c036aea76..daefc52b0ec5 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -97,7 +97,7 @@ static inline void plic_irq_toggle(const struct cpumask *mask, } } -static void plic_irq_enable(struct irq_data *d) +static void plic_irq_unmask(struct irq_data *d) { unsigned int cpu = cpumask_any_and(irq_data_get_affinity_mask(d), cpu_online_mask); @@ -106,7 +106,7 @@ static void plic_irq_enable(struct irq_data *d) plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1); } -static void plic_irq_disable(struct irq_data *d) +static void plic_irq_mask(struct irq_data *d) { plic_irq_toggle(cpu_possible_mask, d->hwirq, 0); } @@ -125,10 +125,8 @@ static int plic_set_affinity(struct irq_data *d, if (cpu >= nr_cpu_ids) return -EINVAL; - if (!irqd_irq_disabled(d)) { - plic_irq_toggle(cpu_possible_mask, d->hwirq, 0); - plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1); - } + plic_irq_toggle(cpu_possible_mask, d->hwirq, 0); + plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1); irq_data_update_effective_affinity(d, cpumask_of(cpu)); @@ -136,14 +134,18 @@ static int plic_set_affinity(struct irq_data *d, } #endif +static void plic_irq_eoi(struct irq_data *d) +{ + struct plic_handler *handler = this_cpu_ptr(&plic_handlers); + + writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); +} + static struct irq_chip plic_chip = { .name = "SiFive PLIC", - /* - * There is no need to mask/unmask PLIC interrupts. They are "masked" - * by reading claim and "unmasked" when writing it back. - */ - .irq_enable = plic_irq_enable, - .irq_disable = plic_irq_disable, + .irq_mask = plic_irq_mask, + .irq_unmask = plic_irq_unmask, + .irq_eoi = plic_irq_eoi, #ifdef CONFIG_SMP .irq_set_affinity = plic_set_affinity, #endif @@ -152,7 +154,7 @@ static struct irq_chip plic_chip = { static int plic_irqdomain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq) { - irq_set_chip_and_handler(irq, &plic_chip, handle_simple_irq); + irq_set_chip_and_handler(irq, &plic_chip, handle_fasteoi_irq); irq_set_chip_data(irq, NULL); irq_set_noprobe(irq); return 0; @@ -188,7 +190,6 @@ static void plic_handle_irq(struct pt_regs *regs) hwirq); else generic_handle_irq(irq); - writel(hwirq, claim); } csr_set(sie, SIE_SEIE); } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index d249cf8ac277..8346e6d1816c 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -542,7 +542,7 @@ static void wake_migration_worker(struct cache *cache) static struct dm_bio_prison_cell_v2 *alloc_prison_cell(struct cache *cache) { - return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOWAIT); + return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOIO); } static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell_v2 *cell) @@ -554,9 +554,7 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache) { struct dm_cache_migration *mg; - mg = mempool_alloc(&cache->migration_pool, GFP_NOWAIT); - if (!mg) - return NULL; + mg = mempool_alloc(&cache->migration_pool, GFP_NOIO); memset(mg, 0, sizeof(*mg)); @@ -664,10 +662,6 @@ static bool bio_detain_shared(struct cache *cache, dm_oblock_t oblock, struct bi struct dm_bio_prison_cell_v2 *cell_prealloc, *cell; cell_prealloc = alloc_prison_cell(cache); /* FIXME: allow wait if calling from worker */ - if (!cell_prealloc) { - defer_bio(cache, bio); - return false; - } build_key(oblock, end, &key); r = dm_cell_get_v2(cache->prison, &key, lock_level(bio), bio, cell_prealloc, &cell); @@ -1493,11 +1487,6 @@ static int mg_lock_writes(struct dm_cache_migration *mg) struct dm_bio_prison_cell_v2 *prealloc; prealloc = alloc_prison_cell(cache); - if (!prealloc) { - DMERR_LIMIT("%s: alloc_prison_cell failed", cache_device_name(cache)); - mg_complete(mg, false); - return -ENOMEM; - } /* * Prevent writes to the block, but allow reads to continue. @@ -1535,11 +1524,6 @@ static int mg_start(struct cache *cache, struct policy_work *op, struct bio *bio } mg = alloc_migration(cache); - if (!mg) { - policy_complete_background_work(cache->policy, op, false); - background_work_end(cache); - return -ENOMEM; - } mg->op = op; mg->overwrite_bio = bio; @@ -1628,10 +1612,6 @@ static int invalidate_lock(struct dm_cache_migration *mg) struct dm_bio_prison_cell_v2 *prealloc; prealloc = alloc_prison_cell(cache); - if (!prealloc) { - invalidate_complete(mg, false); - return -ENOMEM; - } build_key(mg->invalidate_oblock, oblock_succ(mg->invalidate_oblock), &key); r = dm_cell_lock_v2(cache->prison, &key, @@ -1669,10 +1649,6 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock, return -EPERM; mg = alloc_migration(cache); - if (!mg) { - background_work_end(cache); - return -ENOMEM; - } mg->overwrite_bio = bio; mg->invalidate_cblock = cblock; diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index cd6f9e9fc98e..4ca8f1977222 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -591,8 +591,8 @@ static struct hash_table_bucket *get_hash_table_bucket(struct clone *clone, * * NOTE: Must be called with the bucket lock held */ -struct dm_clone_region_hydration *__hash_find(struct hash_table_bucket *bucket, - unsigned long region_nr) +static struct dm_clone_region_hydration *__hash_find(struct hash_table_bucket *bucket, + unsigned long region_nr) { struct dm_clone_region_hydration *hd; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index f150f5c5492b..4fb1a40e68a0 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -18,7 +18,6 @@ #include <linux/vmalloc.h> #include <linux/log2.h> #include <linux/dm-kcopyd.h> -#include <linux/semaphore.h> #include "dm.h" @@ -107,8 +106,8 @@ struct dm_snapshot { /* The on disk metadata handler */ struct dm_exception_store *store; - /* Maximum number of in-flight COW jobs. */ - struct semaphore cow_count; + unsigned in_progress; + struct wait_queue_head in_progress_wait; struct dm_kcopyd_client *kcopyd_client; @@ -162,8 +161,8 @@ struct dm_snapshot { */ #define DEFAULT_COW_THRESHOLD 2048 -static int cow_threshold = DEFAULT_COW_THRESHOLD; -module_param_named(snapshot_cow_threshold, cow_threshold, int, 0644); +static unsigned cow_threshold = DEFAULT_COW_THRESHOLD; +module_param_named(snapshot_cow_threshold, cow_threshold, uint, 0644); MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write"); DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, @@ -1327,7 +1326,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_hash_tables; } - sema_init(&s->cow_count, (cow_threshold > 0) ? cow_threshold : INT_MAX); + init_waitqueue_head(&s->in_progress_wait); s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle); if (IS_ERR(s->kcopyd_client)) { @@ -1509,9 +1508,56 @@ static void snapshot_dtr(struct dm_target *ti) dm_put_device(ti, s->origin); + WARN_ON(s->in_progress); + kfree(s); } +static void account_start_copy(struct dm_snapshot *s) +{ + spin_lock(&s->in_progress_wait.lock); + s->in_progress++; + spin_unlock(&s->in_progress_wait.lock); +} + +static void account_end_copy(struct dm_snapshot *s) +{ + spin_lock(&s->in_progress_wait.lock); + BUG_ON(!s->in_progress); + s->in_progress--; + if (likely(s->in_progress <= cow_threshold) && + unlikely(waitqueue_active(&s->in_progress_wait))) + wake_up_locked(&s->in_progress_wait); + spin_unlock(&s->in_progress_wait.lock); +} + +static bool wait_for_in_progress(struct dm_snapshot *s, bool unlock_origins) +{ + if (unlikely(s->in_progress > cow_threshold)) { + spin_lock(&s->in_progress_wait.lock); + if (likely(s->in_progress > cow_threshold)) { + /* + * NOTE: this throttle doesn't account for whether + * the caller is servicing an IO that will trigger a COW + * so excess throttling may result for chunks not required + * to be COW'd. But if cow_threshold was reached, extra + * throttling is unlikely to negatively impact performance. + */ + DECLARE_WAITQUEUE(wait, current); + __add_wait_queue(&s->in_progress_wait, &wait); + __set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock(&s->in_progress_wait.lock); + if (unlock_origins) + up_read(&_origins_lock); + io_schedule(); + remove_wait_queue(&s->in_progress_wait, &wait); + return false; + } + spin_unlock(&s->in_progress_wait.lock); + } + return true; +} + /* * Flush a list of buffers. */ @@ -1527,7 +1573,7 @@ static void flush_bios(struct bio *bio) } } -static int do_origin(struct dm_dev *origin, struct bio *bio); +static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit); /* * Flush a list of buffers. @@ -1540,7 +1586,7 @@ static void retry_origin_bios(struct dm_snapshot *s, struct bio *bio) while (bio) { n = bio->bi_next; bio->bi_next = NULL; - r = do_origin(s->origin, bio); + r = do_origin(s->origin, bio, false); if (r == DM_MAPIO_REMAPPED) generic_make_request(bio); bio = n; @@ -1732,7 +1778,7 @@ static void copy_callback(int read_err, unsigned long write_err, void *context) rb_link_node(&pe->out_of_order_node, parent, p); rb_insert_color(&pe->out_of_order_node, &s->out_of_order_tree); } - up(&s->cow_count); + account_end_copy(s); } /* @@ -1756,7 +1802,7 @@ static void start_copy(struct dm_snap_pending_exception *pe) dest.count = src.count; /* Hand over to kcopyd */ - down(&s->cow_count); + account_start_copy(s); dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe); } @@ -1776,7 +1822,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, pe->full_bio = bio; pe->full_bio_end_io = bio->bi_end_io; - down(&s->cow_count); + account_start_copy(s); callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, copy_callback, pe); @@ -1866,7 +1912,7 @@ static void zero_callback(int read_err, unsigned long write_err, void *context) struct bio *bio = context; struct dm_snapshot *s = bio->bi_private; - up(&s->cow_count); + account_end_copy(s); bio->bi_status = write_err ? BLK_STS_IOERR : 0; bio_endio(bio); } @@ -1880,7 +1926,7 @@ static void zero_exception(struct dm_snapshot *s, struct dm_exception *e, dest.sector = bio->bi_iter.bi_sector; dest.count = s->store->chunk_size; - down(&s->cow_count); + account_start_copy(s); WARN_ON_ONCE(bio->bi_private); bio->bi_private = s; dm_kcopyd_zero(s->kcopyd_client, 1, &dest, 0, zero_callback, bio); @@ -1916,6 +1962,11 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) if (!s->valid) return DM_MAPIO_KILL; + if (bio_data_dir(bio) == WRITE) { + while (unlikely(!wait_for_in_progress(s, false))) + ; /* wait_for_in_progress() has slept */ + } + down_read(&s->lock); dm_exception_table_lock(&lock); @@ -2112,7 +2163,7 @@ redirect_to_origin: if (bio_data_dir(bio) == WRITE) { up_write(&s->lock); - return do_origin(s->origin, bio); + return do_origin(s->origin, bio, false); } out_unlock: @@ -2487,15 +2538,24 @@ next_snapshot: /* * Called on a write from the origin driver. */ -static int do_origin(struct dm_dev *origin, struct bio *bio) +static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit) { struct origin *o; int r = DM_MAPIO_REMAPPED; +again: down_read(&_origins_lock); o = __lookup_origin(origin->bdev); - if (o) + if (o) { + if (limit) { + struct dm_snapshot *s; + list_for_each_entry(s, &o->snapshots, list) + if (unlikely(!wait_for_in_progress(s, true))) + goto again; + } + r = __origin_write(&o->snapshots, bio->bi_iter.bi_sector, bio); + } up_read(&_origins_lock); return r; @@ -2608,7 +2668,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio) dm_accept_partial_bio(bio, available_sectors); /* Only tell snapshots if this is a write */ - return do_origin(o->dev, bio); + return do_origin(o->dev, bio, true); } /* diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f61693e59684..1e772287b1c8 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -154,7 +154,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) } else { pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", mdname(mddev)); - pr_err("md/raid0: please set raid.default_layout to 1 or 2\n"); + pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); err = -ENOTSUPP; goto abort; } diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c index 32747425297d..64fff6abe60e 100644 --- a/drivers/memstick/host/jmb38x_ms.c +++ b/drivers/memstick/host/jmb38x_ms.c @@ -941,7 +941,7 @@ static int jmb38x_ms_probe(struct pci_dev *pdev, if (!cnt) { rc = -ENODEV; pci_dev_busy = 1; - goto err_out; + goto err_out_int; } jm = kzalloc(sizeof(struct jmb38x_ms) diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index d4ada5cca2d1..234551a68739 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -646,8 +646,8 @@ int renesas_sdhi_probe(struct platform_device *pdev, struct tmio_mmc_dma *dma_priv; struct tmio_mmc_host *host; struct renesas_sdhi *priv; + int num_irqs, irq, ret, i; struct resource *res; - int irq, ret, i; u16 ver; of_data = of_device_get_match_data(&pdev->dev); @@ -825,24 +825,31 @@ int renesas_sdhi_probe(struct platform_device *pdev, host->hs400_complete = renesas_sdhi_hs400_complete; } - i = 0; - while (1) { + num_irqs = platform_irq_count(pdev); + if (num_irqs < 0) { + ret = num_irqs; + goto eirq; + } + + /* There must be at least one IRQ source */ + if (!num_irqs) { + ret = -ENXIO; + goto eirq; + } + + for (i = 0; i < num_irqs; i++) { irq = platform_get_irq(pdev, i); - if (irq < 0) - break; - i++; + if (irq < 0) { + ret = irq; + goto eirq; + } + ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0, dev_name(&pdev->dev), host); if (ret) goto eirq; } - /* There must be at least one IRQ source */ - if (!i) { - ret = irq; - goto eirq; - } - dev_info(&pdev->dev, "%s base at 0x%08lx max clock rate %u MHz\n", mmc_hostname(host->mmc), (unsigned long) (platform_get_resource(pdev, IORESOURCE_MEM, 0)->start), diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c index 2b9cdcd1dd9d..f4f5f0a70cda 100644 --- a/drivers/mmc/host/sdhci-iproc.c +++ b/drivers/mmc/host/sdhci-iproc.c @@ -262,6 +262,7 @@ static const struct sdhci_iproc_data bcm2835_data = { }; static const struct sdhci_pltfm_data sdhci_bcm2711_pltfm_data = { + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .ops = &sdhci_iproc_32only_ops, }; diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 81bd9afb0980..98c575de43c7 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -1393,11 +1393,9 @@ static int sh_mmcif_probe(struct platform_device *pdev) const char *name; irq[0] = platform_get_irq(pdev, 0); - irq[1] = platform_get_irq(pdev, 1); - if (irq[0] < 0) { - dev_err(dev, "Get irq error\n"); + irq[1] = platform_get_irq_optional(pdev, 1); + if (irq[0] < 0) return -ENXIO; - } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); reg = devm_ioremap_resource(dev, res); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 931d9d935686..21d8fcc83c9c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4039,7 +4039,7 @@ out: * this to-be-skipped slave to send a packet out. */ old_arr = rtnl_dereference(bond->slave_arr); - for (idx = 0; idx < old_arr->count; idx++) { + for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) { if (skipslave == old_arr->arr[idx]) { old_arr->arr[idx] = old_arr->arr[old_arr->count-1]; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 526ba2ab66f1..cc3536315eff 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1845,7 +1845,6 @@ int b53_mirror_add(struct dsa_switch *ds, int port, loc = B53_EG_MIR_CTL; b53_read16(dev, B53_MGMT_PAGE, loc, ®); - reg &= ~MIRROR_MASK; reg |= BIT(port); b53_write16(dev, B53_MGMT_PAGE, loc, reg); diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index a23d3ffdf0c4..24a5e99f7fd5 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1224,10 +1224,6 @@ static int ksz8795_switch_init(struct ksz_device *dev) { int i; - mutex_init(&dev->stats_mutex); - mutex_init(&dev->alu_mutex); - mutex_init(&dev->vlan_mutex); - dev->ds->ops = &ksz8795_switch_ops; for (i = 0; i < ARRAY_SIZE(ksz8795_switch_chips); i++) { diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c index d0f8153e86b7..8b00f8e6c02f 100644 --- a/drivers/net/dsa/microchip/ksz8795_spi.c +++ b/drivers/net/dsa/microchip/ksz8795_spi.c @@ -25,6 +25,7 @@ KSZ_REGMAP_TABLE(ksz8795, 16, SPI_ADDR_SHIFT, static int ksz8795_spi_probe(struct spi_device *spi) { + struct regmap_config rc; struct ksz_device *dev; int i, ret; @@ -33,9 +34,9 @@ static int ksz8795_spi_probe(struct spi_device *spi) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(ksz8795_regmap_config); i++) { - dev->regmap[i] = devm_regmap_init_spi(spi, - &ksz8795_regmap_config - [i]); + rc = ksz8795_regmap_config[i]; + rc.lock_arg = &dev->regmap_mutex; + dev->regmap[i] = devm_regmap_init_spi(spi, &rc); if (IS_ERR(dev->regmap[i])) { ret = PTR_ERR(dev->regmap[i]); dev_err(&spi->dev, diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 0b1e01f0873d..fdffd9e0c518 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -17,6 +17,7 @@ KSZ_REGMAP_TABLE(ksz9477, not_used, 16, 0, 0); static int ksz9477_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *i2c_id) { + struct regmap_config rc; struct ksz_device *dev; int i, ret; @@ -25,8 +26,9 @@ static int ksz9477_i2c_probe(struct i2c_client *i2c, return -ENOMEM; for (i = 0; i < ARRAY_SIZE(ksz9477_regmap_config); i++) { - dev->regmap[i] = devm_regmap_init_i2c(i2c, - &ksz9477_regmap_config[i]); + rc = ksz9477_regmap_config[i]; + rc.lock_arg = &dev->regmap_mutex; + dev->regmap[i] = devm_regmap_init_i2c(i2c, &rc); if (IS_ERR(dev->regmap[i])) { ret = PTR_ERR(dev->regmap[i]); dev_err(&i2c->dev, diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index 2938e892b631..16939f29faa5 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * +/* SPDX-License-Identifier: GPL-2.0 */ +/* * Microchip KSZ9477 register definitions * * Copyright (C) 2017-2018 Microchip Technology Inc. diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index f4198d6f72be..c5f64959a184 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -24,6 +24,7 @@ KSZ_REGMAP_TABLE(ksz9477, 32, SPI_ADDR_SHIFT, static int ksz9477_spi_probe(struct spi_device *spi) { + struct regmap_config rc; struct ksz_device *dev; int i, ret; @@ -32,8 +33,9 @@ static int ksz9477_spi_probe(struct spi_device *spi) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(ksz9477_regmap_config); i++) { - dev->regmap[i] = devm_regmap_init_spi(spi, - &ksz9477_regmap_config[i]); + rc = ksz9477_regmap_config[i]; + rc.lock_arg = &dev->regmap_mutex; + dev->regmap[i] = devm_regmap_init_spi(spi, &rc); if (IS_ERR(dev->regmap[i])) { ret = PTR_ERR(dev->regmap[i]); dev_err(&spi->dev, diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index b0b870f0c252..fe47180c908b 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -436,7 +436,7 @@ int ksz_switch_register(struct ksz_device *dev, } mutex_init(&dev->dev_mutex); - mutex_init(&dev->stats_mutex); + mutex_init(&dev->regmap_mutex); mutex_init(&dev->alu_mutex); mutex_init(&dev->vlan_mutex); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index dd60d0837fc6..a20ebb749377 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Microchip switch driver common header +/* SPDX-License-Identifier: GPL-2.0 */ +/* Microchip switch driver common header * * Copyright (C) 2017-2019 Microchip Technology Inc. */ @@ -47,7 +47,7 @@ struct ksz_device { const char *name; struct mutex dev_mutex; /* device access */ - struct mutex stats_mutex; /* status access */ + struct mutex regmap_mutex; /* regmap access */ struct mutex alu_mutex; /* ALU access */ struct mutex vlan_mutex; /* vlan access */ const struct ksz_dev_ops *dev_ops; @@ -290,6 +290,18 @@ static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset, ksz_write32(dev, dev->dev_ops->get_port_addr(port, offset), data); } +static inline void ksz_regmap_lock(void *__mtx) +{ + struct mutex *mtx = __mtx; + mutex_lock(mtx); +} + +static inline void ksz_regmap_unlock(void *__mtx) +{ + struct mutex *mtx = __mtx; + mutex_unlock(mtx); +} + /* Regmap tables generation */ #define KSZ_SPI_OP_RD 3 #define KSZ_SPI_OP_WR 2 @@ -314,6 +326,8 @@ static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset, .write_flag_mask = \ KSZ_SPI_OP_FLAG_MASK(KSZ_SPI_OP_WR, swp, \ regbits, regpad), \ + .lock = ksz_regmap_lock, \ + .unlock = ksz_regmap_unlock, \ .reg_format_endian = REGMAP_ENDIAN_BIG, \ .val_format_endian = REGMAP_ENDIAN_BIG \ } diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index e53e494c22e0..fbb564c3beb8 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Sensor-Technik Wiedemann GmbH * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com> */ #ifndef _SJA1105_H diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h index 740dadf43f01..1fc0d13dc623 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com> +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com> */ #ifndef _SJA1105_DYNAMIC_CONFIG_H #define _SJA1105_DYNAMIC_CONFIG_H diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index af456b0a4d27..394e12a6ad59 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com> +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com> */ #ifndef _SJA1105_PTP_H #define _SJA1105_PTP_H diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index 7f87022a2d61..f4a5c5c04311 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: BSD-3-Clause - * Copyright (c) 2016-2018, NXP Semiconductors +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Copyright (c) 2016-2018, NXP Semiconductors * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com> */ #ifndef _SJA1105_STATIC_CONFIG_H diff --git a/drivers/net/dsa/sja1105/sja1105_tas.h b/drivers/net/dsa/sja1105/sja1105_tas.h index 0b803c30e640..0aad212d88b2 100644 --- a/drivers/net/dsa/sja1105/sja1105_tas.h +++ b/drivers/net/dsa/sja1105/sja1105_tas.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com> +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com> */ #ifndef _SJA1105_TAS_H #define _SJA1105_TAS_H diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index b4a0fb281e69..bb65dd39f847 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -194,9 +194,7 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); - aq_nic_set_packet_filter(aq_nic, ndev->flags); - - aq_nic_set_multicast_list(aq_nic, ndev); + (void)aq_nic_set_multicast_list(aq_nic, ndev); } static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 8f66e7817811..137c1de4c6ec 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -631,9 +631,12 @@ err_exit: int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) { - unsigned int packet_filter = self->packet_filter; + const struct aq_hw_ops *hw_ops = self->aq_hw_ops; + struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg; + unsigned int packet_filter = ndev->flags; struct netdev_hw_addr *ha = NULL; unsigned int i = 0U; + int err = 0; self->mc_list.count = 0; if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { @@ -641,29 +644,28 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) } else { netdev_for_each_uc_addr(ha, ndev) { ether_addr_copy(self->mc_list.ar[i++], ha->addr); - - if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) - break; } } - if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { - packet_filter |= IFF_ALLMULTI; - } else { - netdev_for_each_mc_addr(ha, ndev) { - ether_addr_copy(self->mc_list.ar[i++], ha->addr); - - if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) - break; + cfg->is_mc_list_enabled = !!(packet_filter & IFF_MULTICAST); + if (cfg->is_mc_list_enabled) { + if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_ALLMULTI; + } else { + netdev_for_each_mc_addr(ha, ndev) { + ether_addr_copy(self->mc_list.ar[i++], + ha->addr); + } } } if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) { - packet_filter |= IFF_MULTICAST; self->mc_list.count = i; - self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, - self->mc_list.ar, - self->mc_list.count); + err = hw_ops->hw_multicast_list_set(self->aq_hw, + self->mc_list.ar, + self->mc_list.count); + if (err < 0) + return err; } return aq_nic_set_packet_filter(self, packet_filter); } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 3901d7994ca1..76bdbe1596d6 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -313,6 +313,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, break; buff->is_error |= buff_->is_error; + buff->is_cso_err |= buff_->is_cso_err; } while (!buff_->is_eop); @@ -320,7 +321,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, err = 0; goto err_exit; } - if (buff->is_error) { + if (buff->is_error || buff->is_cso_err) { buff_ = buff; do { next_ = buff_->next, 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 30f7fc4c97ff..2ad3fa6316ce 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 @@ -818,14 +818,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, cfg->is_vlan_force_promisc); hw_atl_rpfl2multicast_flr_en_set(self, - IS_FILTER_ENABLED(IFF_ALLMULTI), 0); + IS_FILTER_ENABLED(IFF_ALLMULTI) && + IS_FILTER_ENABLED(IFF_MULTICAST), 0); hw_atl_rpfl2_accept_all_mc_packets_set(self, - IS_FILTER_ENABLED(IFF_ALLMULTI)); + IS_FILTER_ENABLED(IFF_ALLMULTI) && + IS_FILTER_ENABLED(IFF_MULTICAST)); hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST)); - cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST); for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i) hw_atl_rpfl2_uc_flr_en_set(self, @@ -968,14 +969,26 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self) static int hw_atl_b0_hw_stop(struct aq_hw_s *self) { + int err; + u32 val; + hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK); /* Invalidate Descriptor Cache to prevent writing to the cached * descriptors and to the data pointer of those descriptors */ - hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1); + hw_atl_rdm_rx_dma_desc_cache_init_tgl(self); - return aq_hw_err_from_flags(self); + err = aq_hw_err_from_flags(self); + + if (err) + goto err_exit; + + readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get, + self, val, val == 1, 1000U, 10000U); + +err_exit: + return err; } static int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index 1149812ae463..6f340695e6bd 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -606,12 +606,25 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode); } -void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init) +void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw) { + u32 val; + + val = aq_hw_read_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT); + aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT, - init); + val ^ 1); +} + +u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw) +{ + return aq_hw_read_reg_bit(aq_hw, RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR, + RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK, + RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT); } void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index 0c37abbabca5..c3ee278c3747 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -313,8 +313,11 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer); -/* set rdm rx dma descriptor cache init */ -void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init); +/* toggle rdm rx dma descriptor cache init */ +void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw); + +/* get rdm rx dma descriptor cache init done */ +u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw); /* set rx xoff enable (per tc) */ void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index c3febcdfa92e..35887ad89025 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -318,6 +318,25 @@ /* default value of bitfield rdm_desc_init_i */ #define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0 +/* rdm_desc_init_done_i bitfield definitions + * preprocessor definitions for the bitfield rdm_desc_init_done_i. + * port="pif_rdm_desc_init_done_i" + */ + +/* register address for bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR 0x00005a10 +/* bitmask for bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK 0x00000001U +/* inverted bitmask for bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSKN 0xfffffffe +/* lower bit position of bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT 0U +/* width of bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_WIDTH 1 +/* default value of bitfield rdm_desc_init_done_i */ +#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_DEFAULT 0x0 + + /* rx int_desc_wrb_en bitfield definitions * preprocessor definitions for the bitfield "int_desc_wrb_en". * port="pif_rdm_int_desc_wrb_en_i" diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index da726489e3c8..7bc51f8d6f2f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -337,7 +337,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp) /* Convert PHY temperature from 1/256 degree Celsius * to 1/1000 degree Celsius. */ - *temp = temp_res * 1000 / 256; + *temp = (temp_res & 0xFFFF) * 1000 / 256; return 0; } diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index e24f5d2b6afe..53055ce5dfd6 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -8,7 +8,6 @@ config NET_VENDOR_BROADCOM default y depends on (SSB_POSSIBLE && HAS_DMA) || PCI || BCM63XX || \ SIBYTE_SB1xxx_SOC - select DIMLIB ---help--- If you have a network (Ethernet) chipset belonging to this class, say Y. @@ -69,6 +68,7 @@ config BCMGENET select FIXED_PHY select BCM7XXX_PHY select MDIO_BCM_UNIMAC + select DIMLIB help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. @@ -188,6 +188,7 @@ config SYSTEMPORT select MII select PHYLIB select FIXED_PHY + select DIMLIB help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset using an internal @@ -200,6 +201,7 @@ config BNXT select LIBCRC32C select NET_DEVLINK select PAGE_POOL + select DIMLIB ---help--- This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit Ethernet cards. To compile this driver as a module, choose M here: diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 12cb77ef1081..0f138280315a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2018,6 +2018,8 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv) */ if (priv->internal_phy) { int0_enable |= UMAC_IRQ_LINK_EVENT; + if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv)) + int0_enable |= UMAC_IRQ_PHY_DET_R; } else if (priv->ext_phy) { int0_enable |= UMAC_IRQ_LINK_EVENT; } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { @@ -2611,11 +2613,14 @@ static void bcmgenet_irq_task(struct work_struct *work) priv->irq0_stat = 0; spin_unlock_irq(&priv->lock); + if (status & UMAC_IRQ_PHY_DET_R && + priv->dev->phydev->autoneg != AUTONEG_ENABLE) + phy_init_hw(priv->dev->phydev); + /* Link UP/DOWN event */ - if (status & UMAC_IRQ_LINK_EVENT) { - priv->dev->phydev->link = !!(status & UMAC_IRQ_LINK_UP); + if (status & UMAC_IRQ_LINK_EVENT) phy_mac_interrupt(priv->dev->phydev); - } + } /* bcmgenet_isr1: handle Rx and Tx priority queues */ @@ -2710,7 +2715,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) } /* all other interested interrupts handled in bottom half */ - status &= UMAC_IRQ_LINK_EVENT; + status &= (UMAC_IRQ_LINK_EVENT | UMAC_IRQ_PHY_DET_R); if (status) { /* Save irq status for bottom-half processing. */ spin_lock_irqsave(&priv->lock, flags); @@ -2874,6 +2879,12 @@ static int bcmgenet_open(struct net_device *dev) if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + ret = bcmgenet_mii_connect(dev); + if (ret) { + netdev_err(dev, "failed to connect to PHY\n"); + goto err_clk_disable; + } + /* take MAC out of reset */ bcmgenet_umac_reset(priv); @@ -2883,6 +2894,12 @@ static int bcmgenet_open(struct net_device *dev) reg = bcmgenet_umac_readl(priv, UMAC_CMD); priv->crc_fwd_en = !!(reg & CMD_CRC_FWD); + ret = bcmgenet_mii_config(dev, true); + if (ret) { + netdev_err(dev, "unsupported PHY\n"); + goto err_disconnect_phy; + } + bcmgenet_set_hw_addr(priv, dev->dev_addr); if (priv->internal_phy) { @@ -2898,7 +2915,7 @@ static int bcmgenet_open(struct net_device *dev) ret = bcmgenet_init_dma(priv); if (ret) { netdev_err(dev, "failed to initialize DMA\n"); - goto err_clk_disable; + goto err_disconnect_phy; } /* Always enable ring 16 - descriptor ring */ @@ -2921,25 +2938,19 @@ static int bcmgenet_open(struct net_device *dev) goto err_irq0; } - ret = bcmgenet_mii_probe(dev); - if (ret) { - netdev_err(dev, "failed to connect to PHY\n"); - goto err_irq1; - } - bcmgenet_netif_start(dev); netif_tx_start_all_queues(dev); return 0; -err_irq1: - free_irq(priv->irq1, priv); err_irq0: free_irq(priv->irq0, priv); err_fini_dma: bcmgenet_dma_teardown(priv); bcmgenet_fini_dma(priv); +err_disconnect_phy: + phy_disconnect(dev->phydev); err_clk_disable: if (priv->internal_phy) bcmgenet_power_down(priv, GENET_POWER_PASSIVE); @@ -3620,6 +3631,8 @@ static int bcmgenet_resume(struct device *d) if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + phy_init_hw(dev->phydev); + bcmgenet_umac_reset(priv); init_umac(priv); @@ -3628,8 +3641,6 @@ static int bcmgenet_resume(struct device *d) if (priv->wolopts) clk_disable_unprepare(priv->clk_wol); - phy_init_hw(dev->phydev); - /* Speed settings must be restored */ bcmgenet_mii_config(priv->dev, false); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 4a8fc03d82fd..7fbf573d8d52 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -366,6 +366,7 @@ struct bcmgenet_mib_counters { #define EXT_PWR_DOWN_PHY_EN (1 << 20) #define EXT_RGMII_OOB_CTRL 0x0C +#define RGMII_MODE_EN_V123 (1 << 0) #define RGMII_LINK (1 << 4) #define OOB_DISABLE (1 << 5) #define RGMII_MODE_EN (1 << 6) @@ -719,8 +720,8 @@ GENET_IO_MACRO(rbuf, GENET_RBUF_OFF); /* MDIO routines */ int bcmgenet_mii_init(struct net_device *dev); +int bcmgenet_mii_connect(struct net_device *dev); int bcmgenet_mii_config(struct net_device *dev, bool init); -int bcmgenet_mii_probe(struct net_device *dev); void bcmgenet_mii_exit(struct net_device *dev); void bcmgenet_phy_power_set(struct net_device *dev, bool enable); void bcmgenet_mii_setup(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 970e478a9017..17bb8d60a157 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -173,6 +173,46 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) bcmgenet_fixed_phy_link_update); } +int bcmgenet_mii_connect(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; + struct phy_device *phydev; + u32 phy_flags = 0; + int ret; + + /* Communicate the integrated PHY revision */ + if (priv->internal_phy) + phy_flags = priv->gphy_rev; + + /* Initialize link state variables that bcmgenet_mii_setup() uses */ + priv->old_link = -1; + priv->old_speed = -1; + priv->old_duplex = -1; + priv->old_pause = -1; + + if (dn) { + phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, + phy_flags, priv->phy_interface); + if (!phydev) { + pr_err("could not attach to PHY\n"); + return -ENODEV; + } + } else { + phydev = dev->phydev; + phydev->dev_flags = phy_flags; + + ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, + priv->phy_interface); + if (ret) { + pr_err("could not attach to PHY\n"); + return -ENODEV; + } + } + + return 0; +} + int bcmgenet_mii_config(struct net_device *dev, bool init) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -258,74 +298,29 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) */ if (priv->ext_phy) { reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); - reg |= RGMII_MODE_EN | id_mode_dis; + reg |= id_mode_dis; + if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv)) + reg |= RGMII_MODE_EN_V123; + else + reg |= RGMII_MODE_EN; bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } - if (init) - dev_info(kdev, "configuring instance for %s\n", phy_name); - - return 0; -} - -int bcmgenet_mii_probe(struct net_device *dev) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device_node *dn = priv->pdev->dev.of_node; - struct phy_device *phydev; - u32 phy_flags; - int ret; - - /* Communicate the integrated PHY revision */ - phy_flags = priv->gphy_rev; - - /* Initialize link state variables that bcmgenet_mii_setup() uses */ - priv->old_link = -1; - priv->old_speed = -1; - priv->old_duplex = -1; - priv->old_pause = -1; - - if (dn) { - phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, - phy_flags, priv->phy_interface); - if (!phydev) { - pr_err("could not attach to PHY\n"); - return -ENODEV; - } - } else { - phydev = dev->phydev; - phydev->dev_flags = phy_flags; + if (init) { + linkmode_copy(phydev->advertising, phydev->supported); - ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, - priv->phy_interface); - if (ret) { - pr_err("could not attach to PHY\n"); - return -ENODEV; - } - } + /* The internal PHY has its link interrupts routed to the + * Ethernet MAC ISRs. On GENETv5 there is a hardware issue + * that prevents the signaling of link UP interrupts when + * the link operates at 10Mbps, so fallback to polling for + * those versions of GENET. + */ + if (priv->internal_phy && !GENET_IS_V5(priv)) + phydev->irq = PHY_IGNORE_INTERRUPT; - /* Configure port multiplexer based on what the probed PHY device since - * reading the 'max-speed' property determines the maximum supported - * PHY speed which is needed for bcmgenet_mii_config() to configure - * things appropriately. - */ - ret = bcmgenet_mii_config(dev, true); - if (ret) { - phy_disconnect(dev->phydev); - return ret; + dev_info(kdev, "configuring instance for %s\n", phy_name); } - linkmode_copy(phydev->advertising, phydev->supported); - - /* The internal PHY has its link interrupts routed to the - * Ethernet MAC ISRs. On GENETv5 there is a hardware issue - * that prevents the signaling of link UP interrupts when - * the link operates at 10Mbps, so fallback to polling for - * those versions of GENET. - */ - if (priv->internal_phy && !GENET_IS_V5(priv)) - dev->phydev->irq = PHY_IGNORE_INTERRUPT; - return 0; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 8e8d557901a9..1e1b774e1953 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3405,17 +3405,17 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk, return err; } - *tx_clk = devm_clk_get(&pdev->dev, "tx_clk"); + *tx_clk = devm_clk_get_optional(&pdev->dev, "tx_clk"); if (IS_ERR(*tx_clk)) - *tx_clk = NULL; + return PTR_ERR(*tx_clk); - *rx_clk = devm_clk_get(&pdev->dev, "rx_clk"); + *rx_clk = devm_clk_get_optional(&pdev->dev, "rx_clk"); if (IS_ERR(*rx_clk)) - *rx_clk = NULL; + return PTR_ERR(*rx_clk); - *tsu_clk = devm_clk_get(&pdev->dev, "tsu_clk"); + *tsu_clk = devm_clk_get_optional(&pdev->dev, "tsu_clk"); if (IS_ERR(*tsu_clk)) - *tsu_clk = NULL; + return PTR_ERR(*tsu_clk); err = clk_prepare_enable(*pclk); if (err) { diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.h b/drivers/net/ethernet/cavium/common/cavium_ptp.h index be2bafc7beeb..a04eccbc78e8 100644 --- a/drivers/net/ethernet/cavium/common/cavium_ptp.h +++ b/drivers/net/ethernet/cavium/common/cavium_ptp.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* cavium_ptp.h - PTP 1588 clock on Cavium hardware * Copyright (c) 2003-2015, 2017 Cavium, Inc. */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 162d7d8fb295..19379bae0144 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1235,6 +1235,8 @@ static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable) priv->rx_td_enabled = enable; } +static void update_tx_fqids(struct dpaa2_eth_priv *priv); + static int link_state_update(struct dpaa2_eth_priv *priv) { struct dpni_link_state state = {0}; @@ -1261,6 +1263,7 @@ static int link_state_update(struct dpaa2_eth_priv *priv) goto out; if (state.up) { + update_tx_fqids(priv); netif_carrier_on(priv->net_dev); netif_tx_start_all_queues(priv->net_dev); } else { @@ -2533,6 +2536,47 @@ static int set_pause(struct dpaa2_eth_priv *priv) return 0; } +static void update_tx_fqids(struct dpaa2_eth_priv *priv) +{ + struct dpni_queue_id qid = {0}; + struct dpaa2_eth_fq *fq; + struct dpni_queue queue; + int i, j, err; + + /* We only use Tx FQIDs for FQID-based enqueue, so check + * if DPNI version supports it before updating FQIDs + */ + if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR, + DPNI_ENQUEUE_FQID_VER_MINOR) < 0) + return; + + for (i = 0; i < priv->num_fqs; i++) { + fq = &priv->fq[i]; + if (fq->type != DPAA2_TX_CONF_FQ) + continue; + for (j = 0; j < dpaa2_eth_tc_count(priv); j++) { + err = dpni_get_queue(priv->mc_io, 0, priv->mc_token, + DPNI_QUEUE_TX, j, fq->flowid, + &queue, &qid); + if (err) + goto out_err; + + fq->tx_fqid[j] = qid.fqid; + if (fq->tx_fqid[j] == 0) + goto out_err; + } + } + + priv->enqueue = dpaa2_eth_enqueue_fq; + + return; + +out_err: + netdev_info(priv->net_dev, + "Error reading Tx FQID, fallback to QDID-based enqueue\n"); + priv->enqueue = dpaa2_eth_enqueue_qd; +} + /* Configure the DPNI object this interface is associated with */ static int setup_dpni(struct fsl_mc_device *ls_dev) { @@ -3306,6 +3350,9 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg) if (status & DPNI_IRQ_EVENT_LINK_CHANGED) link_state_update(netdev_priv(net_dev)); + if (status & DPNI_IRQ_EVENT_ENDPOINT_CHANGED) + set_mac_addr(netdev_priv(net_dev)); + return IRQ_HANDLED; } @@ -3331,7 +3378,8 @@ static int setup_irqs(struct fsl_mc_device *ls_dev) } err = dpni_set_irq_mask(ls_dev->mc_io, 0, ls_dev->mc_handle, - DPNI_IRQ_INDEX, DPNI_IRQ_EVENT_LINK_CHANGED); + DPNI_IRQ_INDEX, DPNI_IRQ_EVENT_LINK_CHANGED | + DPNI_IRQ_EVENT_ENDPOINT_CHANGED); if (err < 0) { dev_err(&ls_dev->dev, "dpni_set_irq_mask(): %d\n", err); goto free_irq; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h index fd583911b6c0..ee0711d06b3a 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h @@ -133,9 +133,12 @@ int dpni_reset(struct fsl_mc_io *mc_io, */ #define DPNI_IRQ_INDEX 0 /** - * IRQ event - indicates a change in link state + * IRQ events: + * indicates a change in link state + * indicates a change in endpoint */ #define DPNI_IRQ_EVENT_LINK_CHANGED 0x00000001 +#define DPNI_IRQ_EVENT_ENDPOINT_CHANGED 0x00000002 int dpni_set_irq_enable(struct fsl_mc_io *mc_io, u32 cmd_flags, diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index c4b7bf851a28..75ccc1e7076b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -32,6 +32,8 @@ #define HNAE3_MOD_VERSION "1.0" +#define HNAE3_MIN_VECTOR_NUM 2 /* first one for misc, another for IO */ + /* Device IDs */ #define HNAE3_DEV_ID_GE 0xA220 #define HNAE3_DEV_ID_25GE 0xA221 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index fd7f94372ff0..e02e01bd9eff 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -906,6 +906,9 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); + /* nic's msix numbers is always equals to the roce's. */ + hdev->num_nic_msi = hdev->num_roce_msi; + /* PF should have NIC vectors and Roce vectors, * NIC vectors are queued before Roce vectors. */ @@ -915,6 +918,15 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) hdev->num_msi = hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); + + hdev->num_nic_msi = hdev->num_msi; + } + + if (hdev->num_nic_msi < HNAE3_MIN_VECTOR_NUM) { + dev_err(&hdev->pdev->dev, + "Just %u msi resources, not enough for pf(min:2).\n", + hdev->num_nic_msi); + return -EINVAL; } return 0; @@ -1507,6 +1519,10 @@ static int hclge_assign_tqp(struct hclge_vport *vport, u16 num_tqps) kinfo->rss_size = min_t(u16, hdev->rss_size_max, vport->alloc_tqps / hdev->tm_info.num_tc); + /* ensure one to one mapping between irq and queue at default */ + kinfo->rss_size = min_t(u16, kinfo->rss_size, + (hdev->num_nic_msi - 1) / hdev->tm_info.num_tc); + return 0; } @@ -2285,7 +2301,8 @@ static int hclge_init_msi(struct hclge_dev *hdev) int vectors; int i; - vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi, + vectors = pci_alloc_irq_vectors(pdev, HNAE3_MIN_VECTOR_NUM, + hdev->num_msi, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (vectors < 0) { dev_err(&pdev->dev, @@ -2300,6 +2317,7 @@ static int hclge_init_msi(struct hclge_dev *hdev) hdev->num_msi = vectors; hdev->num_msi_left = vectors; + hdev->base_msi_vector = pdev->irq; hdev->roce_base_vector = hdev->base_msi_vector + hdev->roce_base_msix_offset; @@ -3903,6 +3921,7 @@ static int hclge_get_vector(struct hnae3_handle *handle, u16 vector_num, int alloc = 0; int i, j; + vector_num = min_t(u16, hdev->num_nic_msi - 1, vector_num); vector_num = min(hdev->num_msi_left, vector_num); for (j = 0; j < vector_num; j++) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 3e9574a9e22d..c3d56b872ed7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -763,6 +763,7 @@ struct hclge_dev { u32 base_msi_vector; u16 *vector_status; int *vector_irq; + u16 num_nic_msi; /* Num of nic vectors for this PF */ u16 num_roce_msi; /* Num of roce vectors for this PF */ int roce_base_vector; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 9f0e35f27789..62399cc1c5a6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -537,9 +537,16 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) kinfo->rss_size = kinfo->req_rss_size; } else if (kinfo->rss_size > max_rss_size || (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) { + /* if user not set rss, the rss_size should compare with the + * valid msi numbers to ensure one to one map between tqp and + * irq as default. + */ + if (!kinfo->req_rss_size) + max_rss_size = min_t(u16, max_rss_size, + (hdev->num_nic_msi - 1) / + kinfo->num_tc); + /* Set to the maximum specification value (max_rss_size). */ - dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n", - kinfo->rss_size, max_rss_size); kinfo->rss_size = max_rss_size; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index e3090b3dab1d..7d7e712691b9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -411,6 +411,13 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev) kinfo->tqp[i] = &hdev->htqp[i].q; } + /* after init the max rss_size and tqps, adjust the default tqp numbers + * and rss size with the actual vector numbers + */ + kinfo->num_tqps = min_t(u16, hdev->num_nic_msix - 1, kinfo->num_tqps); + kinfo->rss_size = min_t(u16, kinfo->num_tqps / kinfo->num_tc, + kinfo->rss_size); + return 0; } @@ -502,6 +509,7 @@ static int hclgevf_get_vector(struct hnae3_handle *handle, u16 vector_num, int alloc = 0; int i, j; + vector_num = min_t(u16, hdev->num_nic_msix - 1, vector_num); vector_num = min(hdev->num_msi_left, vector_num); for (j = 0; j < vector_num; j++) { @@ -2246,13 +2254,14 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev) int vectors; int i; - if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) + if (hnae3_dev_roce_supported(hdev)) vectors = pci_alloc_irq_vectors(pdev, hdev->roce_base_msix_offset + 1, hdev->num_msi, PCI_IRQ_MSIX); else - vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi, + vectors = pci_alloc_irq_vectors(pdev, HNAE3_MIN_VECTOR_NUM, + hdev->num_msi, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (vectors < 0) { @@ -2268,6 +2277,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev) hdev->num_msi = vectors; hdev->num_msi_left = vectors; + hdev->base_msi_vector = pdev->irq; hdev->roce_base_vector = pdev->irq + hdev->roce_base_msix_offset; @@ -2533,7 +2543,7 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev) req = (struct hclgevf_query_res_cmd *)desc.data; - if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) { + if (hnae3_dev_roce_supported(hdev)) { hdev->roce_base_msix_offset = hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee), HCLGEVF_MSIX_OFT_ROCEE_M, @@ -2542,6 +2552,9 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev) hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number), HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S); + /* nic's msix numbers is always equals to the roce's. */ + hdev->num_nic_msix = hdev->num_roce_msix; + /* VF should have NIC vectors and Roce vectors, NIC vectors * are queued before Roce vectors. The offset is fixed to 64. */ @@ -2551,6 +2564,15 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev) hdev->num_msi = hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number), HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S); + + hdev->num_nic_msix = hdev->num_msi; + } + + if (hdev->num_nic_msix < HNAE3_MIN_VECTOR_NUM) { + dev_err(&hdev->pdev->dev, + "Just %u msi resources, not enough for vf(min:2).\n", + hdev->num_nic_msix); + return -EINVAL; } return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index bdde3afc286b..2b8d6bc6d224 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -270,6 +270,7 @@ struct hclgevf_dev { u16 num_msi; u16 num_msi_left; u16 num_msi_used; + u16 num_nic_msix; /* Num of nic vectors for this VF */ u16 num_roce_msix; /* Num of roce vectors for this VF */ u16 roce_base_msix_offset; int roce_base_vector; diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c index 211c5f74b4c8..aec7e98bcc85 100644 --- a/drivers/net/ethernet/i825xx/lasi_82596.c +++ b/drivers/net/ethernet/i825xx/lasi_82596.c @@ -96,6 +96,8 @@ #define OPT_SWAP_PORT 0x0001 /* Need to wordswp on the MPU port */ +#define LIB82596_DMA_ATTR DMA_ATTR_NON_CONSISTENT + #define DMA_WBACK(ndev, addr, len) \ do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_TO_DEVICE); } while (0) @@ -200,7 +202,7 @@ static int __exit lan_remove_chip(struct parisc_device *pdev) unregister_netdev (dev); dma_free_attrs(&pdev->dev, sizeof(struct i596_private), lp->dma, - lp->dma_addr, DMA_ATTR_NON_CONSISTENT); + lp->dma_addr, LIB82596_DMA_ATTR); free_netdev (dev); return 0; } diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c index 1274ad24d6af..f9742af7f142 100644 --- a/drivers/net/ethernet/i825xx/lib82596.c +++ b/drivers/net/ethernet/i825xx/lib82596.c @@ -1065,7 +1065,7 @@ static int i82596_probe(struct net_device *dev) dma = dma_alloc_attrs(dev->dev.parent, sizeof(struct i596_dma), &lp->dma_addr, GFP_KERNEL, - DMA_ATTR_NON_CONSISTENT); + LIB82596_DMA_ATTR); if (!dma) { printk(KERN_ERR "%s: Couldn't get shared memory\n", __FILE__); return -ENOMEM; @@ -1087,7 +1087,7 @@ static int i82596_probe(struct net_device *dev) i = register_netdev(dev); if (i) { dma_free_attrs(dev->dev.parent, sizeof(struct i596_dma), - dma, lp->dma_addr, DMA_ATTR_NON_CONSISTENT); + dma, lp->dma_addr, LIB82596_DMA_ATTR); return i; } diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c index 6eb6c2ff7f09..6436a98c5953 100644 --- a/drivers/net/ethernet/i825xx/sni_82596.c +++ b/drivers/net/ethernet/i825xx/sni_82596.c @@ -24,6 +24,8 @@ static const char sni_82596_string[] = "snirm_82596"; +#define LIB82596_DMA_ATTR 0 + #define DMA_WBACK(priv, addr, len) do { } while (0) #define DMA_INV(priv, addr, len) do { } while (0) #define DMA_WBACK_INV(priv, addr, len) do { } while (0) @@ -152,7 +154,7 @@ static int sni_82596_driver_remove(struct platform_device *pdev) unregister_netdev(dev); dma_free_attrs(dev->dev.parent, sizeof(struct i596_private), lp->dma, - lp->dma_addr, DMA_ATTR_NON_CONSISTENT); + lp->dma_addr, LIB82596_DMA_ATTR); iounmap(lp->ca); iounmap(lp->mpu_port); free_netdev (dev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 2b073a3c0b84..f59d9a8e35e2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2878,12 +2878,10 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter, if (test_bit(0, &adapter->resetting) && adapter->reset_reason == VNIC_RESET_MOBILITY) { - u64 val = (0xff000000) | scrq->hw_irq; + struct irq_desc *desc = irq_to_desc(scrq->irq); + struct irq_chip *chip = irq_desc_get_chip(desc); - rc = plpar_hcall_norets(H_EOI, val); - if (rc) - dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n", - val, rc); + chip->irq_eoi(&desc->irq_data); } rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index c61069340f4f..703adb96429e 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -261,6 +261,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, ge_mode = 0; switch (state->interface) { case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_GMII: ge_mode = 1; break; case PHY_INTERFACE_MODE_REVMII: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 4187f2b112b8..e8b656075c6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -788,12 +788,10 @@ again: * it means that all the previous stes are the same, * if so, this rule is duplicated. */ - if (mlx5dr_ste_is_last_in_rule(nic_matcher, - matched_ste->ste_chain_location)) { - mlx5dr_info(dmn, "Duplicate rule inserted, aborting!!\n"); - return NULL; - } - return matched_ste; + if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste_location)) + return matched_ste; + + mlx5dr_dbg(dmn, "Duplicate rule inserted\n"); } if (!skip_rehash && dr_rule_need_enlarge_hash(cur_htbl, dmn, nic_dmn)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 899450b28621..7c03b661ae7e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -99,6 +99,7 @@ static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, devlink = priv_to_devlink(mlxsw_sp->core); in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, local_port); + skb_push(skb, ETH_HLEN); devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port); consume_skb(skb); } diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 141571e2ec11..544012a67221 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1356,9 +1356,6 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) if (!is_valid_ether_addr(ndev->dev_addr)) eth_hw_addr_random(ndev); - /* Reset the ethernet controller */ - __lpc_eth_reset(pldat); - /* then shut everything down to save power */ __lpc_eth_shutdown(pldat); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 812190e729c2..6a95b42a8d8c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -182,6 +182,8 @@ struct ionic_lif { #define lif_to_txqcq(lif, i) ((lif)->txqcqs[i].qcq) #define lif_to_rxqcq(lif, i) ((lif)->rxqcqs[i].qcq) +#define lif_to_txstats(lif, i) ((lif)->txqcqs[i].stats->tx) +#define lif_to_rxstats(lif, i) ((lif)->rxqcqs[i].stats->rx) #define lif_to_txq(lif, i) (&lif_to_txqcq((lif), i)->q) #define lif_to_rxq(lif, i) (&lif_to_txqcq((lif), i)->q) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c index e2907884f843..03916b6d47f2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -117,7 +117,8 @@ static u64 ionic_sw_stats_get_count(struct ionic_lif *lif) /* rx stats */ total += MAX_Q(lif) * IONIC_NUM_RX_STATS; - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { /* tx debug stats */ total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS + IONIC_NUM_TX_Q_STATS + @@ -149,7 +150,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf) *buf += ETH_GSTRING_LEN; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { snprintf(*buf, ETH_GSTRING_LEN, "txq_%d_%s", @@ -187,7 +189,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf) *buf += ETH_GSTRING_LEN; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { snprintf(*buf, ETH_GSTRING_LEN, "rxq_%d_cq_%s", @@ -223,6 +226,8 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) { struct ionic_lif_sw_stats lif_stats; struct ionic_qcq *txqcq, *rxqcq; + struct ionic_tx_stats *txstats; + struct ionic_rx_stats *rxstats; int i, q_num; ionic_get_lif_stats(lif, &lif_stats); @@ -233,15 +238,17 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - txqcq = lif_to_txqcq(lif, q_num); + txstats = &lif_to_txstats(lif, q_num); for (i = 0; i < IONIC_NUM_TX_STATS; i++) { - **buf = IONIC_READ_STAT64(&txqcq->stats->tx, + **buf = IONIC_READ_STAT64(txstats, &ionic_tx_stats_desc[i]); (*buf)++; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + txqcq = lif_to_txqcq(lif, q_num); for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { **buf = IONIC_READ_STAT64(&txqcq->q, &ionic_txq_stats_desc[i]); @@ -258,22 +265,24 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) (*buf)++; } for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { - **buf = txqcq->stats->tx.sg_cntr[i]; + **buf = txstats->sg_cntr[i]; (*buf)++; } } } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - rxqcq = lif_to_rxqcq(lif, q_num); + rxstats = &lif_to_rxstats(lif, q_num); for (i = 0; i < IONIC_NUM_RX_STATS; i++) { - **buf = IONIC_READ_STAT64(&rxqcq->stats->rx, + **buf = IONIC_READ_STAT64(rxstats, &ionic_rx_stats_desc[i]); (*buf)++; } - if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + if (test_bit(IONIC_LIF_UP, lif->state) && + test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + rxqcq = lif_to_rxqcq(lif, q_num); for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { **buf = IONIC_READ_STAT64(&rxqcq->cq, &ionic_dbg_cq_stats_desc[i]); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 74f81fe03810..350b0d949611 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4146,6 +4146,14 @@ static void rtl_hw_jumbo_disable(struct rtl8169_private *tp) rtl_lock_config_regs(tp); } +static void rtl_jumbo_config(struct rtl8169_private *tp, int mtu) +{ + if (mtu > ETH_DATA_LEN) + rtl_hw_jumbo_enable(tp); + else + rtl_hw_jumbo_disable(tp); +} + DECLARE_RTL_COND(rtl_chipcmd_cond) { return RTL_R8(tp, ChipCmd) & CmdReset; @@ -4442,11 +4450,6 @@ static void rtl8168g_set_pause_thresholds(struct rtl8169_private *tp, static void rtl_hw_start_8168bb(struct rtl8169_private *tp) { RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - - if (tp->dev->mtu <= ETH_DATA_LEN) { - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B | - PCI_EXP_DEVCTL_NOSNOOP_EN); - } } static void rtl_hw_start_8168bef(struct rtl8169_private *tp) @@ -4462,9 +4465,6 @@ static void __rtl_hw_start_8168cp(struct rtl8169_private *tp) RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - rtl_disable_clock_request(tp); } @@ -4490,9 +4490,6 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp) rtl_set_def_aspm_entry_latency(tp); RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); } static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) @@ -4503,9 +4500,6 @@ static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) /* Magic. */ RTL_W8(tp, DBG_REG, 0x20); - - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); } static void rtl_hw_start_8168c_1(struct rtl8169_private *tp) @@ -4611,9 +4605,6 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8168e_1); - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - rtl_disable_clock_request(tp); /* Reset tx FIFO pointer */ @@ -4636,9 +4627,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8168e_2); - if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000); rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06); @@ -5485,6 +5473,8 @@ static void rtl_hw_start(struct rtl8169_private *tp) rtl_set_rx_tx_desc_registers(tp); rtl_lock_config_regs(tp); + rtl_jumbo_config(tp, tp->dev->mtu); + /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ RTL_R16(tp, CPlusCmd); RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); @@ -5498,10 +5488,7 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu) { struct rtl8169_private *tp = netdev_priv(dev); - if (new_mtu > ETH_DATA_LEN) - rtl_hw_jumbo_enable(tp); - else - rtl_hw_jumbo_disable(tp); + rtl_jumbo_config(tp, new_mtu); dev->mtu = new_mtu; netdev_update_features(dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index f97a4096f8fc..ddcc191febdb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -651,7 +651,8 @@ static void sun8i_dwmac_set_filter(struct mac_device_info *hw, } } } else { - netdev_info(dev, "Too many address, switching to promiscuous\n"); + if (!(readl(ioaddr + EMAC_RX_FRM_FLT) & EMAC_FRM_FLT_RXALL)) + netdev_info(dev, "Too many address, switching to promiscuous\n"); v = EMAC_FRM_FLT_RXALL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 2cb9c53f93b8..5a7b0aca1d31 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -448,7 +448,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw, value |= GMAC_PACKET_FILTER_HPF; /* Handle multiple unicast addresses */ - if (netdev_uc_count(dev) > GMAC_MAX_PERFECT_ADDRESSES) { + if (netdev_uc_count(dev) > hw->unicast_filter_entries) { /* Switch to promiscuous mode if more than 128 addrs * are required */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 3f4f3132e16b..e436fa160c7d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -515,6 +515,7 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, if (!enable) { val |= PPSCMDx(index, 0x5); + val |= PPSEN0; writel(val, ioaddr + MAC_PPS_CONTROL); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c76a1336a451..3dfd04e0506a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2610,7 +2610,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) } if (priv->hw->pcs) - stmmac_pcs_ctrl_ane(priv, priv->hw, 1, priv->hw->ps, 0); + stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, priv->hw->ps, 0); /* set TX and RX rings length */ stmmac_set_rings_length(priv); @@ -4742,8 +4742,10 @@ int stmmac_suspend(struct device *dev) stmmac_mac_set(priv, priv->ioaddr, false); pinctrl_pm_select_sleep_state(priv->device); /* Disable clock in case of PWM is off */ - clk_disable(priv->plat->pclk); - clk_disable(priv->plat->stmmac_clk); + if (priv->plat->clk_ptp_ref) + clk_disable_unprepare(priv->plat->clk_ptp_ref); + clk_disable_unprepare(priv->plat->pclk); + clk_disable_unprepare(priv->plat->stmmac_clk); } mutex_unlock(&priv->lock); @@ -4806,8 +4808,10 @@ int stmmac_resume(struct device *dev) } else { pinctrl_pm_select_default_state(priv->device); /* enable the clk previously disabled */ - clk_enable(priv->plat->stmmac_clk); - clk_enable(priv->plat->pclk); + clk_prepare_enable(priv->plat->stmmac_clk); + clk_prepare_enable(priv->plat->pclk); + if (priv->plat->clk_ptp_ref) + clk_prepare_enable(priv->plat->clk_ptp_ref); /* reset the phy so that it's ready */ if (priv->mii) stmmac_mdio_reset(priv->mii); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 173493db038c..df638b18b72c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -164,7 +164,7 @@ static int stmmac_enable(struct ptp_clock_info *ptp, /* structure describing a PTP hardware clock */ static struct ptp_clock_info stmmac_ptp_clock_ops = { .owner = THIS_MODULE, - .name = "stmmac_ptp_clock", + .name = "stmmac ptp", .max_adj = 62500000, .n_alarm = 0, .n_ext_ts = 0, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index cc76a42c7466..e4ac3c401432 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -487,8 +487,8 @@ static int stmmac_filter_check(struct stmmac_priv *priv) static int stmmac_test_hfilt(struct stmmac_priv *priv) { - unsigned char gd_addr[ETH_ALEN] = {0x01, 0x00, 0xcc, 0xcc, 0xdd, 0xdd}; - unsigned char bd_addr[ETH_ALEN] = {0x09, 0x00, 0xaa, 0xaa, 0xbb, 0xbb}; + unsigned char gd_addr[ETH_ALEN] = {0x01, 0xee, 0xdd, 0xcc, 0xbb, 0xaa}; + unsigned char bd_addr[ETH_ALEN] = {0x01, 0x01, 0x02, 0x03, 0x04, 0x05}; struct stmmac_packet_attrs attr = { }; int ret; @@ -496,6 +496,9 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv) if (ret) return ret; + if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; + ret = dev_mc_add(priv->dev, gd_addr); if (ret) return ret; @@ -573,6 +576,8 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv) if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (!priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; /* Remove all MC addresses */ __dev_mc_unsync(priv->dev, NULL); @@ -611,6 +616,8 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv) if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (!priv->hw->multicast_filter_bins) + return -EOPNOTSUPP; /* Remove all UC addresses */ __dev_uc_unsync(priv->dev, NULL); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index e231098061b6..f9a9a9d82233 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -510,7 +510,7 @@ static struct stmmac_flow_entry *tc_find_flow(struct stmmac_priv *priv, return NULL; } -struct { +static struct { int (*fn)(struct stmmac_priv *priv, struct flow_cls_offload *cls, struct stmmac_flow_entry *entry); } tc_flow_parsers[] = { diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index a65edd2770e6..37ba708ac781 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -722,7 +722,7 @@ static void cpdma_chan_set_descs(struct cpdma_ctlr *ctlr, * cpdma_chan_split_pool - Splits ctrl pool between all channels. * Has to be called under ctlr lock */ -int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr) +static int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr) { int tx_per_ch_desc = 0, rx_per_ch_desc = 0; int free_rx_num = 0, free_tx_num = 0; diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index f61d094746c0..1a251f76d09b 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -241,8 +241,8 @@ static struct pernet_operations nsim_fib_net_ops = { void nsim_fib_exit(void) { - unregister_pernet_subsys(&nsim_fib_net_ops); unregister_fib_notifier(&nsim_fib_nb); + unregister_pernet_subsys(&nsim_fib_net_ops); } int nsim_fib_init(void) @@ -258,6 +258,7 @@ int nsim_fib_init(void) err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent); if (err < 0) { pr_err("Failed to register fib notifier\n"); + unregister_pernet_subsys(&nsim_fib_net_ops); goto err_out; } diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 8fc33867e524..af8eabe7a6d4 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -572,6 +572,7 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) .name = _name, \ /* PHY_BASIC_FEATURES */ \ .flags = PHY_IS_INTERNAL, \ + .soft_reset = genphy_soft_reset, \ .config_init = bcm7xxx_config_init, \ .suspend = bcm7xxx_suspend, \ .resume = bcm7xxx_config_init, \ diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 2fea5541c35a..63dedec0433d 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -341,6 +341,35 @@ static int ksz8041_config_aneg(struct phy_device *phydev) return genphy_config_aneg(phydev); } +static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev, + const u32 ksz_phy_id) +{ + int ret; + + if ((phydev->phy_id & MICREL_PHY_ID_MASK) != ksz_phy_id) + return 0; + + ret = phy_read(phydev, MII_BMSR); + if (ret < 0) + return ret; + + /* KSZ8051 PHY and KSZ8794/KSZ8795/KSZ8765 switch share the same + * exact PHY ID. However, they can be told apart by the extended + * capability registers presence. The KSZ8051 PHY has them while + * the switch does not. + */ + ret &= BMSR_ERCAP; + if (ksz_phy_id == PHY_ID_KSZ8051) + return ret; + else + return !ret; +} + +static int ksz8051_match_phy_device(struct phy_device *phydev) +{ + return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8051); +} + static int ksz8081_config_init(struct phy_device *phydev) { /* KSZPHY_OMSO_FACTORY_TEST is set at de-assertion of the reset line @@ -364,6 +393,11 @@ static int ksz8061_config_init(struct phy_device *phydev) return kszphy_config_init(phydev); } +static int ksz8795_match_phy_device(struct phy_device *phydev) +{ + return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ87XX); +} + static int ksz9021_load_values_from_of(struct phy_device *phydev, const struct device_node *of_node, u16 reg, @@ -1017,8 +1051,6 @@ static struct phy_driver ksphy_driver[] = { .suspend = genphy_suspend, .resume = genphy_resume, }, { - .phy_id = PHY_ID_KSZ8051, - .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Micrel KSZ8051", /* PHY_BASIC_FEATURES */ .driver_data = &ksz8051_type, @@ -1029,6 +1061,7 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, + .match_phy_device = ksz8051_match_phy_device, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -1141,13 +1174,12 @@ static struct phy_driver ksphy_driver[] = { .suspend = genphy_suspend, .resume = genphy_resume, }, { - .phy_id = PHY_ID_KSZ8795, - .phy_id_mask = MICREL_PHY_ID_MASK, - .name = "Micrel KSZ8795", + .name = "Micrel KSZ87XX Switch", /* PHY_BASIC_FEATURES */ .config_init = kszphy_config_init, .config_aneg = ksz8873mll_config_aneg, .read_status = ksz8873mll_read_status, + .match_phy_device = ksz8795_match_phy_device, .suspend = genphy_suspend, .resume = genphy_resume, }, { diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 7935593debb1..a1caeee12236 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -323,6 +323,8 @@ int genphy_c45_read_pma(struct phy_device *phydev) { int val; + linkmode_zero(phydev->lp_advertising); + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL1); if (val < 0) return val; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 119e6f466056..105d389b58e7 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -572,9 +572,6 @@ int phy_start_aneg(struct phy_device *phydev) if (AUTONEG_DISABLE == phydev->autoneg) phy_sanitize_settings(phydev); - /* Invalidate LP advertising flags */ - linkmode_zero(phydev->lp_advertising); - err = phy_config_aneg(phydev); if (err < 0) goto out_unlock; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 9d2bbb13293e..adb66a2fae18 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1787,7 +1787,14 @@ int genphy_read_lpa(struct phy_device *phydev) { int lpa, lpagb; - if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { + if (phydev->autoneg == AUTONEG_ENABLE) { + if (!phydev->autoneg_complete) { + mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, + 0); + mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, 0); + return 0; + } + if (phydev->is_gigabit_capable) { lpagb = phy_read(phydev, MII_STAT1000); if (lpagb < 0) @@ -1815,6 +1822,8 @@ int genphy_read_lpa(struct phy_device *phydev) return lpa; mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa); + } else { + linkmode_zero(phydev->lp_advertising); } return 0; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a5a57ca94c1a..20e2ebe458f2 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -576,7 +576,7 @@ static int phylink_register_sfp(struct phylink *pl, /** * phylink_create() - create a phylink instance - * @ndev: a pointer to the &struct net_device + * @config: a pointer to the target &struct phylink_config * @fwnode: a pointer to a &struct fwnode_handle describing the network * interface * @iface: the desired link mode defined by &typedef phy_interface_t diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 812dc3a65efb..a8d3141582a5 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -526,8 +526,8 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ - if (e->queue_index != queue_index) - e->queue_index = queue_index; + if (READ_ONCE(e->queue_index) != queue_index) + WRITE_ONCE(e->queue_index, queue_index); if (e->updated != jiffies) e->updated = jiffies; sock_rps_record_flow_hash(e->rps_rxhash); diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index a505b2ab88b8..74849da031fa 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -186,7 +186,7 @@ struct hso_tiocmget { int intr_completed; struct usb_endpoint_descriptor *endp; struct urb *urb; - struct hso_serial_state_notification serial_state_notification; + struct hso_serial_state_notification *serial_state_notification; u16 prev_UART_state_bitmap; struct uart_icount icount; }; @@ -1432,7 +1432,7 @@ static int tiocmget_submit_urb(struct hso_serial *serial, usb_rcvintpipe(usb, tiocmget->endp-> bEndpointAddress & 0x7F), - &tiocmget->serial_state_notification, + tiocmget->serial_state_notification, sizeof(struct hso_serial_state_notification), tiocmget_intr_callback, serial, tiocmget->endp->bInterval); @@ -1479,7 +1479,7 @@ static void tiocmget_intr_callback(struct urb *urb) /* wIndex should be the USB interface number of the port to which the * notification applies, which should always be the Modem port. */ - serial_state_notification = &tiocmget->serial_state_notification; + serial_state_notification = tiocmget->serial_state_notification; if (serial_state_notification->bmRequestType != BM_REQUEST_TYPE || serial_state_notification->bNotification != B_NOTIFICATION || le16_to_cpu(serial_state_notification->wValue) != W_VALUE || @@ -2565,6 +2565,8 @@ static void hso_free_tiomget(struct hso_serial *serial) usb_free_urb(tiocmget->urb); tiocmget->urb = NULL; serial->tiocmget = NULL; + kfree(tiocmget->serial_state_notification); + tiocmget->serial_state_notification = NULL; kfree(tiocmget); } } @@ -2615,10 +2617,13 @@ static struct hso_device *hso_create_bulk_serial_device( num_urbs = 2; serial->tiocmget = kzalloc(sizeof(struct hso_tiocmget), GFP_KERNEL); + serial->tiocmget->serial_state_notification + = kzalloc(sizeof(struct hso_serial_state_notification), + GFP_KERNEL); /* it isn't going to break our heart if serial->tiocmget * allocation fails don't bother checking this. */ - if (serial->tiocmget) { + if (serial->tiocmget && serial->tiocmget->serial_state_notification) { tiocmget = serial->tiocmget; tiocmget->endp = hso_get_ep(interface, USB_ENDPOINT_XFER_INT, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 58f5a219fb65..62948098191f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3782,10 +3782,14 @@ static int lan78xx_probe(struct usb_interface *intf, /* driver requires remote-wakeup capability during autosuspend. */ intf->needs_remote_wakeup = 1; + ret = lan78xx_phy_init(dev); + if (ret < 0) + goto out4; + ret = register_netdev(netdev); if (ret != 0) { netif_err(dev, probe, netdev, "couldn't register the device\n"); - goto out4; + goto out5; } usb_set_intfdata(intf, dev); @@ -3798,14 +3802,10 @@ static int lan78xx_probe(struct usb_interface *intf, pm_runtime_set_autosuspend_delay(&udev->dev, DEFAULT_AUTOSUSPEND_DELAY); - ret = lan78xx_phy_init(dev); - if (ret < 0) - goto out5; - return 0; out5: - unregister_netdev(netdev); + phy_disconnect(netdev->phydev); out4: usb_free_urb(dev->urb_intr); out3: diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3d77cd402ba9..596428ec71df 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1327,6 +1327,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index c5d4a0060124..681e0def6356 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -335,7 +335,7 @@ static void sr_set_multicast(struct net_device *net) static int sr_mdio_read(struct net_device *net, int phy_id, int loc) { struct usbnet *dev = netdev_priv(net); - __le16 res; + __le16 res = 0; mutex_lock(&dev->phy_mutex); sr_set_sw_mii(dev); diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index dc45d16e8d21..383d4fa555a8 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -2118,12 +2118,15 @@ static int ath10k_init_uart(struct ath10k *ar) return ret; } - if (!uart_print && ar->hw_params.uart_pin_workaround) { - ret = ath10k_bmi_write32(ar, hi_dbg_uart_txpin, - ar->hw_params.uart_pin); - if (ret) { - ath10k_warn(ar, "failed to set UART TX pin: %d", ret); - return ret; + if (!uart_print) { + if (ar->hw_params.uart_pin_workaround) { + ret = ath10k_bmi_write32(ar, hi_dbg_uart_txpin, + ar->hw_params.uart_pin); + if (ret) { + ath10k_warn(ar, "failed to set UART TX pin: %d", + ret); + return ret; + } } return 0; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 7573af2d88ce..c2db758b9d54 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -162,12 +162,13 @@ int iwl_acpi_get_mcc(struct device *dev, char *mcc) wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data, ACPI_WRDD_WIFI_DATA_SIZE, &tbl_rev); - if (IS_ERR(wifi_pkg) || tbl_rev != 0) { + if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; } - if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) { + if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER || + tbl_rev != 0) { ret = -EINVAL; goto out_free; } @@ -224,12 +225,13 @@ int iwl_acpi_get_eckv(struct device *dev, u32 *extl_clk) wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data, ACPI_ECKV_WIFI_DATA_SIZE, &tbl_rev); - if (IS_ERR(wifi_pkg) || tbl_rev != 0) { + if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; } - if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) { + if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER || + tbl_rev != 0) { ret = -EINVAL; goto out_free; } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index 5c8602de9168..87421807e040 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -646,6 +646,7 @@ static struct scatterlist *alloc_sgtable(int size) if (new_page) __free_page(new_page); } + kfree(table); return NULL; } alloc_size = min_t(int, size, PAGE_SIZE); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.h b/drivers/net/wireless/intel/iwlwifi/iwl-io.h index f8e4f0f5de0c..f09e368c7040 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-io.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.h @@ -112,38 +112,38 @@ int iwl_dump_fh(struct iwl_trans *trans, char **buf); */ static inline u32 iwl_umac_prph(struct iwl_trans *trans, u32 ofs) { - return ofs + trans->cfg->trans.umac_prph_offset; + return ofs + trans->trans_cfg->umac_prph_offset; } static inline u32 iwl_read_umac_prph_no_grab(struct iwl_trans *trans, u32 ofs) { return iwl_read_prph_no_grab(trans, ofs + - trans->cfg->trans.umac_prph_offset); + trans->trans_cfg->umac_prph_offset); } static inline u32 iwl_read_umac_prph(struct iwl_trans *trans, u32 ofs) { - return iwl_read_prph(trans, ofs + trans->cfg->trans.umac_prph_offset); + return iwl_read_prph(trans, ofs + trans->trans_cfg->umac_prph_offset); } static inline void iwl_write_umac_prph_no_grab(struct iwl_trans *trans, u32 ofs, u32 val) { - iwl_write_prph_no_grab(trans, ofs + trans->cfg->trans.umac_prph_offset, + iwl_write_prph_no_grab(trans, ofs + trans->trans_cfg->umac_prph_offset, val); } static inline void iwl_write_umac_prph(struct iwl_trans *trans, u32 ofs, u32 val) { - iwl_write_prph(trans, ofs + trans->cfg->trans.umac_prph_offset, val); + iwl_write_prph(trans, ofs + trans->trans_cfg->umac_prph_offset, val); } static inline int iwl_poll_umac_prph_bit(struct iwl_trans *trans, u32 addr, u32 bits, u32 mask, int timeout) { return iwl_poll_prph_bit(trans, addr + - trans->cfg->trans.umac_prph_offset, + trans->trans_cfg->umac_prph_offset, bits, mask, timeout); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 32a5e4e5461f..d9eb2b286438 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -420,6 +420,9 @@ static int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm) }; int ret; + if (mvm->trans->cfg->tx_with_siso_diversity) + init_cfg.init_flags |= cpu_to_le32(BIT(IWL_INIT_PHY)); + lockdep_assert_held(&mvm->mutex); mvm->rfkill_safe_init_done = false; @@ -694,12 +697,13 @@ static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm) wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data, ACPI_WRDS_WIFI_DATA_SIZE, &tbl_rev); - if (IS_ERR(wifi_pkg) || tbl_rev != 0) { + if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; } - if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) { + if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER || + tbl_rev != 0) { ret = -EINVAL; goto out_free; } @@ -731,13 +735,14 @@ static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm) wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data, ACPI_EWRD_WIFI_DATA_SIZE, &tbl_rev); - if (IS_ERR(wifi_pkg) || tbl_rev != 0) { + if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; } if ((wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) || - (wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER)) { + (wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER) || + tbl_rev != 0) { ret = -EINVAL; goto out_free; } @@ -791,11 +796,16 @@ static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm) wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data, ACPI_WGDS_WIFI_DATA_SIZE, &tbl_rev); - if (IS_ERR(wifi_pkg) || tbl_rev > 1) { + if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; } + if (tbl_rev != 0) { + ret = -EINVAL; + goto out_free; + } + mvm->geo_rev = tbl_rev; for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) { for (j = 0; j < ACPI_GEO_TABLE_SIZE; j++) { @@ -889,15 +899,17 @@ static bool iwl_mvm_sar_geo_support(struct iwl_mvm *mvm) * firmware versions. Unfortunately, we don't have a TLV API * flag to rely on, so rely on the major version which is in * the first byte of ucode_ver. This was implemented - * initially on version 38 and then backported to29 and 17. - * The intention was to have it in 36 as well, but not all - * 8000 family got this feature enabled. The 8000 family is - * the only one using version 36, so skip this version - * entirely. + * initially on version 38 and then backported to 17. It was + * also backported to 29, but only for 7265D devices. The + * intention was to have it in 36 as well, but not all 8000 + * family got this feature enabled. The 8000 family is the + * only one using version 36, so skip this version entirely. */ return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 38 || - IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 || - IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17; + IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17 || + (IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 && + ((mvm->trans->hw_rev & CSR_HW_REV_TYPE_MSK) == + CSR_HW_REV_TYPE_7265D)); } int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) @@ -1020,11 +1032,16 @@ static int iwl_mvm_get_ppag_table(struct iwl_mvm *mvm) wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data, ACPI_PPAG_WIFI_DATA_SIZE, &tbl_rev); - if (IS_ERR(wifi_pkg) || tbl_rev != 0) { + if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; } + if (tbl_rev != 0) { + ret = -EINVAL; + goto out_free; + } + enabled = &wifi_pkg->package.elements[1]; if (enabled->type != ACPI_TYPE_INTEGER || (enabled->integer.value != 0 && enabled->integer.value != 1)) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index cd1b10042fbf..d31f96c3f925 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -4881,11 +4881,11 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, if (!iwl_mvm_has_new_rx_api(mvm)) return; - notif->cookie = mvm->queue_sync_cookie; - - if (notif->sync) + if (notif->sync) { + notif->cookie = mvm->queue_sync_cookie; atomic_set(&mvm->queue_sync_counter, mvm->trans->num_rx_queues); + } ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, size, !notif->sync); @@ -4905,7 +4905,8 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, out: atomic_set(&mvm->queue_sync_counter, 0); - mvm->queue_sync_cookie++; + if (notif->sync) + mvm->queue_sync_cookie++; } static void iwl_mvm_sync_rx_queues(struct ieee80211_hw *hw) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index 75fa8a6aafee..74980382e64c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -107,13 +107,9 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, /* allocate ucode sections in dram and set addresses */ ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram); - if (ret) { - dma_free_coherent(trans->dev, - sizeof(*prph_scratch), - prph_scratch, - trans_pcie->prph_scratch_dma_addr); - return ret; - } + if (ret) + goto err_free_prph_scratch; + /* Allocate prph information * currently we don't assign to the prph info anything, but it would get @@ -121,16 +117,20 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, prph_info = dma_alloc_coherent(trans->dev, sizeof(*prph_info), &trans_pcie->prph_info_dma_addr, GFP_KERNEL); - if (!prph_info) - return -ENOMEM; + if (!prph_info) { + ret = -ENOMEM; + goto err_free_prph_scratch; + } /* Allocate context info */ ctxt_info_gen3 = dma_alloc_coherent(trans->dev, sizeof(*ctxt_info_gen3), &trans_pcie->ctxt_info_dma_addr, GFP_KERNEL); - if (!ctxt_info_gen3) - return -ENOMEM; + if (!ctxt_info_gen3) { + ret = -ENOMEM; + goto err_free_prph_info; + } ctxt_info_gen3->prph_info_base_addr = cpu_to_le64(trans_pcie->prph_info_dma_addr); @@ -186,6 +186,20 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT); return 0; + +err_free_prph_info: + dma_free_coherent(trans->dev, + sizeof(*prph_info), + prph_info, + trans_pcie->prph_info_dma_addr); + +err_free_prph_scratch: + dma_free_coherent(trans->dev, + sizeof(*prph_scratch), + prph_scratch, + trans_pcie->prph_scratch_dma_addr); + return ret; + } void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index e29c47744ef5..6f4bb7ce71a5 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -513,31 +513,33 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x24FD, 0x9074, iwl8265_2ac_cfg)}, /* 9000 Series */ - {IWL_PCI_DEVICE(0x02F0, 0x0030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0034, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0038, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x003C, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0060, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0064, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x00A0, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x00A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0230, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0234, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0238, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x023C, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0260, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0264, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x02A0, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x02A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x1551, iwl9560_killer_s_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x1552, iwl9560_killer_i_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x2030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x2034, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x4030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x4034, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x40A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x4234, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x42A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x06F0, 0x0030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x0034, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x0038, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)}, @@ -643,34 +645,34 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2720, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9460_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_soc)}, + + {IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x31DC, 0x0030, iwl9560_2ac_160_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x0034, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x0038, iwl9560_2ac_160_cfg_shared_clk)}, @@ -726,62 +728,60 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x34F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0038, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x003C, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0060, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0064, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x00A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x00A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0230, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0238, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x023C, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0260, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0264, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x02A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x02A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x1010, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x4034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x40A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x4234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0038, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x003C, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0060, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0064, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x00A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x00A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0230, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0238, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x023C, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0260, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0264, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x02A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x02A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x1010, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x4034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x40A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x4234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x42A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x3DF0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + + {IWL_PCI_DEVICE(0x43F0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x9DF0, 0x0000, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x0010, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x0030, iwl9560_2ac_160_cfg_soc)}, @@ -821,34 +821,34 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x9DF0, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0038, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x003C, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0060, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0064, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x00A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x00A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0230, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0238, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x023C, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0260, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0264, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x02A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x02A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x1010, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x4034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x40A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x4234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x42A4, iwl9462_2ac_cfg_soc)}, + + {IWL_PCI_DEVICE(0xA0F0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0xA370, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x0034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x0038, iwl9560_2ac_160_cfg_soc)}, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index f8a1f985a1d8..6961f00ff812 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -3272,11 +3272,17 @@ static struct iwl_trans_dump_data ptr = cmdq->write_ptr; for (i = 0; i < cmdq->n_window; i++) { u8 idx = iwl_pcie_get_cmd_index(cmdq, ptr); + u8 tfdidx; u32 caplen, cmdlen; + if (trans->trans_cfg->use_tfh) + tfdidx = idx; + else + tfdidx = ptr; + cmdlen = iwl_trans_pcie_get_cmdlen(trans, - cmdq->tfds + - tfd_size * ptr); + (u8 *)cmdq->tfds + + tfd_size * tfdidx); caplen = min_t(u32, TFD_MAX_PAYLOAD_SIZE, cmdlen); if (cmdlen) { @@ -3450,6 +3456,15 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, spin_lock_init(&trans_pcie->reg_lock); mutex_init(&trans_pcie->mutex); init_waitqueue_head(&trans_pcie->ucode_write_waitq); + + trans_pcie->rba.alloc_wq = alloc_workqueue("rb_allocator", + WQ_HIGHPRI | WQ_UNBOUND, 1); + if (!trans_pcie->rba.alloc_wq) { + ret = -ENOMEM; + goto out_free_trans; + } + INIT_WORK(&trans_pcie->rba.rx_alloc, iwl_pcie_rx_allocator_work); + trans_pcie->tso_hdr_page = alloc_percpu(struct iwl_tso_hdr_page); if (!trans_pcie->tso_hdr_page) { ret = -ENOMEM; @@ -3584,10 +3599,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, trans_pcie->inta_mask = CSR_INI_SET_MASK; } - trans_pcie->rba.alloc_wq = alloc_workqueue("rb_allocator", - WQ_HIGHPRI | WQ_UNBOUND, 1); - INIT_WORK(&trans_pcie->rba.rx_alloc, iwl_pcie_rx_allocator_work); - #ifdef CONFIG_IWLWIFI_DEBUGFS trans_pcie->fw_mon_data.state = IWL_FW_MON_DBGFS_STATE_CLOSED; mutex_init(&trans_pcie->fw_mon_data.mutex); @@ -3599,6 +3610,8 @@ out_free_ict: iwl_pcie_free_ict(trans); out_no_pci: free_percpu(trans_pcie->tso_hdr_page); + destroy_workqueue(trans_pcie->rba.alloc_wq); +out_free_trans: iwl_trans_free(trans); return ERR_PTR(ret); } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 45c73a6f09a1..14f562cd715c 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -4026,7 +4026,7 @@ static int __init init_mac80211_hwsim(void) err = dev_alloc_name(hwsim_mon, hwsim_mon->name); if (err < 0) { rtnl_unlock(); - goto out_free_radios; + goto out_free_mon; } err = register_netdevice(hwsim_mon); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h index 2b216edd0c7d..a90a518b40d3 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h @@ -23,7 +23,6 @@ #include <linux/leds.h> #include <linux/mutex.h> #include <linux/etherdevice.h> -#include <linux/input-polldev.h> #include <linux/kfifo.h> #include <linux/hrtimer.h> #include <linux/average.h> diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c index 4d4e3888ef20..f2395309ec00 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c @@ -555,7 +555,7 @@ static ssize_t rt2x00debug_write_restart_hw(struct file *file, { struct rt2x00debug_intf *intf = file->private_data; struct rt2x00_dev *rt2x00dev = intf->rt2x00dev; - static unsigned long last_reset; + static unsigned long last_reset = INITIAL_JIFFIES; if (!rt2x00_has_cap_restart_hw(rt2x00dev)) return -EOPNOTSUPP; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 240f762b3749..103ed00775eb 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -719,7 +719,6 @@ err_unmap: xenvif_unmap_frontend_data_rings(queue); netif_napi_del(&queue->napi); err: - module_put(THIS_MODULE); return err; } diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index c5289eaf17ee..e897e4d768ef 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -547,18 +547,25 @@ static int pn533_usb_probe(struct usb_interface *interface, rc = pn533_finalize_setup(priv); if (rc) - goto error; + goto err_deregister; usb_set_intfdata(interface, phy); return 0; +err_deregister: + pn533_unregister_device(phy->priv); error: + usb_kill_urb(phy->in_urb); + usb_kill_urb(phy->out_urb); + usb_kill_urb(phy->ack_urb); + usb_free_urb(phy->in_urb); usb_free_urb(phy->out_urb); usb_free_urb(phy->ack_urb); usb_put_dev(phy->udev); kfree(in_buf); + kfree(phy->ack_buffer); return rc; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fd7dea36c3b6..fa7ba09dca77 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -116,10 +116,26 @@ static void nvme_queue_scan(struct nvme_ctrl *ctrl) /* * Only new queue scan work when admin and IO queues are both alive */ - if (ctrl->state == NVME_CTRL_LIVE) + if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset) queue_work(nvme_wq, &ctrl->scan_work); } +/* + * Use this function to proceed with scheduling reset_work for a controller + * that had previously been set to the resetting state. This is intended for + * code paths that can't be interrupted by other reset attempts. A hot removal + * may prevent this from succeeding. + */ +int nvme_try_sched_reset(struct nvme_ctrl *ctrl) +{ + if (ctrl->state != NVME_CTRL_RESETTING) + return -EBUSY; + if (!queue_work(nvme_reset_wq, &ctrl->reset_work)) + return -EBUSY; + return 0; +} +EXPORT_SYMBOL_GPL(nvme_try_sched_reset); + int nvme_reset_ctrl(struct nvme_ctrl *ctrl) { if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) @@ -137,8 +153,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) ret = nvme_reset_ctrl(ctrl); if (!ret) { flush_work(&ctrl->reset_work); - if (ctrl->state != NVME_CTRL_LIVE && - ctrl->state != NVME_CTRL_ADMIN_ONLY) + if (ctrl->state != NVME_CTRL_LIVE) ret = -ENETRESET; } @@ -315,15 +330,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, old_state = ctrl->state; switch (new_state) { - case NVME_CTRL_ADMIN_ONLY: - switch (old_state) { - case NVME_CTRL_CONNECTING: - changed = true; - /* FALLTHRU */ - default: - break; - } - break; case NVME_CTRL_LIVE: switch (old_state) { case NVME_CTRL_NEW: @@ -339,7 +345,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_NEW: case NVME_CTRL_LIVE: - case NVME_CTRL_ADMIN_ONLY: changed = true; /* FALLTHRU */ default: @@ -359,7 +364,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_DELETING: switch (old_state) { case NVME_CTRL_LIVE: - case NVME_CTRL_ADMIN_ONLY: case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: changed = true; @@ -381,8 +385,10 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, break; } - if (changed) + if (changed) { ctrl->state = new_state; + wake_up_all(&ctrl->state_wq); + } spin_unlock_irqrestore(&ctrl->lock, flags); if (changed && ctrl->state == NVME_CTRL_LIVE) @@ -391,6 +397,39 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); +/* + * Returns true for sink states that can't ever transition back to live. + */ +static bool nvme_state_terminal(struct nvme_ctrl *ctrl) +{ + switch (ctrl->state) { + case NVME_CTRL_NEW: + case NVME_CTRL_LIVE: + case NVME_CTRL_RESETTING: + case NVME_CTRL_CONNECTING: + return false; + case NVME_CTRL_DELETING: + case NVME_CTRL_DEAD: + return true; + default: + WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state); + return true; + } +} + +/* + * Waits for the controller state to be resetting, or returns false if it is + * not possible to ever transition to that state. + */ +bool nvme_wait_reset(struct nvme_ctrl *ctrl) +{ + wait_event(ctrl->state_wq, + nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) || + nvme_state_terminal(ctrl)); + return ctrl->state == NVME_CTRL_RESETTING; +} +EXPORT_SYMBOL_GPL(nvme_wait_reset); + static void nvme_free_ns_head(struct kref *ref) { struct nvme_ns_head *head = @@ -1306,8 +1345,6 @@ static void nvme_update_formats(struct nvme_ctrl *ctrl) if (ns->disk && nvme_revalidate_disk(ns->disk)) nvme_set_queue_dying(ns); up_read(&ctrl->namespaces_rwsem); - - nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL); } static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) @@ -1323,6 +1360,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) nvme_unfreeze(ctrl); nvme_mpath_unfreeze(ctrl->subsys); mutex_unlock(&ctrl->subsys->lock); + nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL); mutex_unlock(&ctrl->scan_lock); } if (effects & NVME_CMD_EFFECTS_CCC) @@ -2874,7 +2912,6 @@ static int nvme_dev_open(struct inode *inode, struct file *file) switch (ctrl->state) { case NVME_CTRL_LIVE: - case NVME_CTRL_ADMIN_ONLY: break; default: return -EWOULDBLOCK; @@ -3168,7 +3205,6 @@ static ssize_t nvme_sysfs_show_state(struct device *dev, static const char *const state_name[] = { [NVME_CTRL_NEW] = "new", [NVME_CTRL_LIVE] = "live", - [NVME_CTRL_ADMIN_ONLY] = "only-admin", [NVME_CTRL_RESETTING] = "resetting", [NVME_CTRL_CONNECTING] = "connecting", [NVME_CTRL_DELETING] = "deleting", @@ -3679,11 +3715,10 @@ static void nvme_scan_work(struct work_struct *work) struct nvme_id_ctrl *id; unsigned nn; - if (ctrl->state != NVME_CTRL_LIVE) + /* No tagset on a live ctrl means IO queues could not created */ + if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset) return; - WARN_ON_ONCE(!ctrl->tagset); - if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) { dev_info(ctrl->device, "rescanning namespaces.\n"); nvme_clear_changed_ns_log(ctrl); @@ -3844,13 +3879,13 @@ static void nvme_fw_act_work(struct work_struct *work) if (time_after(jiffies, fw_act_timeout)) { dev_warn(ctrl->device, "Fw activation timeout, reset controller\n"); - nvme_reset_ctrl(ctrl); - break; + nvme_try_sched_reset(ctrl); + return; } msleep(100); } - if (ctrl->state != NVME_CTRL_LIVE) + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) return; nvme_start_queues(ctrl); @@ -3870,7 +3905,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) nvme_queue_scan(ctrl); break; case NVME_AER_NOTICE_FW_ACT_STARTING: - queue_work(nvme_wq, &ctrl->fw_act_work); + /* + * We are (ab)using the RESETTING state to prevent subsequent + * recovery actions from interfering with the controller's + * firmware activation. + */ + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + queue_work(nvme_wq, &ctrl->fw_act_work); break; #ifdef CONFIG_NVME_MULTIPATH case NVME_AER_NOTICE_ANA: @@ -3993,6 +4034,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, INIT_WORK(&ctrl->async_event_work, nvme_async_event_work); INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work); + init_waitqueue_head(&ctrl->state_wq); INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work); memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd)); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 93f08d77c896..a0ec40ab62ee 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -182,8 +182,7 @@ bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live) { - if (likely(ctrl->state == NVME_CTRL_LIVE || - ctrl->state == NVME_CTRL_ADMIN_ONLY)) + if (likely(ctrl->state == NVME_CTRL_LIVE)) return true; return __nvmf_check_ready(ctrl, rq, queue_live); } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 38a83ef5bcd3..22e8401352c2 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -15,6 +15,7 @@ #include <linux/sed-opal.h> #include <linux/fault-inject.h> #include <linux/rcupdate.h> +#include <linux/wait.h> #include <trace/events/block.h> @@ -161,7 +162,6 @@ static inline u16 nvme_req_qid(struct request *req) enum nvme_ctrl_state { NVME_CTRL_NEW, NVME_CTRL_LIVE, - NVME_CTRL_ADMIN_ONLY, /* Only admin queue live */ NVME_CTRL_RESETTING, NVME_CTRL_CONNECTING, NVME_CTRL_DELETING, @@ -199,6 +199,7 @@ struct nvme_ctrl { struct cdev cdev; struct work_struct reset_work; struct work_struct delete_work; + wait_queue_head_t state_wq; struct nvme_subsystem *subsys; struct list_head subsys_entry; @@ -449,6 +450,7 @@ void nvme_complete_rq(struct request *req); bool nvme_cancel_request(struct request *req, void *data, bool reserved); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state); +bool nvme_wait_reset(struct nvme_ctrl *ctrl); int nvme_disable_ctrl(struct nvme_ctrl *ctrl); int nvme_enable_ctrl(struct nvme_ctrl *ctrl); int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl); @@ -499,6 +501,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl); +int nvme_try_sched_reset(struct nvme_ctrl *ctrl); int nvme_delete_ctrl(struct nvme_ctrl *ctrl); int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index bb88681f4dc3..869f462e6b6e 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -773,7 +773,8 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev, struct bio_vec *bv) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - unsigned int first_prp_len = dev->ctrl.page_size - bv->bv_offset; + unsigned int offset = bv->bv_offset & (dev->ctrl.page_size - 1); + unsigned int first_prp_len = dev->ctrl.page_size - offset; iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0); if (dma_mapping_error(dev->dev, iod->first_dma)) @@ -2263,10 +2264,7 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode) return true; } -/* - * return error value only when tagset allocation failed - */ -static int nvme_dev_add(struct nvme_dev *dev) +static void nvme_dev_add(struct nvme_dev *dev) { int ret; @@ -2296,7 +2294,7 @@ static int nvme_dev_add(struct nvme_dev *dev) if (ret) { dev_warn(dev->ctrl.device, "IO queues tagset allocation failed %d\n", ret); - return ret; + return; } dev->ctrl.tagset = &dev->tagset; } else { @@ -2307,7 +2305,6 @@ static int nvme_dev_add(struct nvme_dev *dev) } nvme_dbbuf_set(dev); - return 0; } static int nvme_pci_enable(struct nvme_dev *dev) @@ -2467,6 +2464,14 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) mutex_unlock(&dev->shutdown_lock); } +static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown) +{ + if (!nvme_wait_reset(&dev->ctrl)) + return -EBUSY; + nvme_dev_disable(dev, shutdown); + return 0; +} + static int nvme_setup_prp_pools(struct nvme_dev *dev) { dev->prp_page_pool = dma_pool_create("prp list page", dev->dev, @@ -2490,14 +2495,20 @@ static void nvme_release_prp_pools(struct nvme_dev *dev) dma_pool_destroy(dev->prp_small_pool); } +static void nvme_free_tagset(struct nvme_dev *dev) +{ + if (dev->tagset.tags) + blk_mq_free_tag_set(&dev->tagset); + dev->ctrl.tagset = NULL; +} + static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) { struct nvme_dev *dev = to_nvme_dev(ctrl); nvme_dbbuf_dma_free(dev); put_device(dev->dev); - if (dev->tagset.tags) - blk_mq_free_tag_set(&dev->tagset); + nvme_free_tagset(dev); if (dev->ctrl.admin_q) blk_put_queue(dev->ctrl.admin_q); kfree(dev->queues); @@ -2508,6 +2519,11 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) static void nvme_remove_dead_ctrl(struct nvme_dev *dev) { + /* + * Set state to deleting now to avoid blocking nvme_wait_reset(), which + * may be holding this pci_dev's device lock. + */ + nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING); nvme_get_ctrl(&dev->ctrl); nvme_dev_disable(dev, false); nvme_kill_queues(&dev->ctrl); @@ -2521,7 +2537,6 @@ static void nvme_reset_work(struct work_struct *work) container_of(work, struct nvme_dev, ctrl.reset_work); bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result; - enum nvme_ctrl_state new_state = NVME_CTRL_LIVE; if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) { result = -ENODEV; @@ -2615,13 +2630,11 @@ static void nvme_reset_work(struct work_struct *work) dev_warn(dev->ctrl.device, "IO queues not created\n"); nvme_kill_queues(&dev->ctrl); nvme_remove_namespaces(&dev->ctrl); - new_state = NVME_CTRL_ADMIN_ONLY; + nvme_free_tagset(dev); } else { nvme_start_queues(&dev->ctrl); nvme_wait_freeze(&dev->ctrl); - /* hit this only when allocate tagset fails */ - if (nvme_dev_add(dev)) - new_state = NVME_CTRL_ADMIN_ONLY; + nvme_dev_add(dev); nvme_unfreeze(&dev->ctrl); } @@ -2629,9 +2642,9 @@ static void nvme_reset_work(struct work_struct *work) * If only admin queue live, keep it to do further investigation or * recovery. */ - if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) { + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) { dev_warn(dev->ctrl.device, - "failed to mark controller state %d\n", new_state); + "failed to mark controller live state\n"); result = -ENODEV; goto out; } @@ -2672,7 +2685,7 @@ static int nvme_pci_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val) static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val) { - *val = readq(to_nvme_dev(ctrl)->bar + off); + *val = lo_hi_readq(to_nvme_dev(ctrl)->bar + off); return 0; } @@ -2836,19 +2849,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) static void nvme_reset_prepare(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); - nvme_dev_disable(dev, false); + + /* + * We don't need to check the return value from waiting for the reset + * state as pci_dev device lock is held, making it impossible to race + * with ->remove(). + */ + nvme_disable_prepare_reset(dev, false); + nvme_sync_queues(&dev->ctrl); } static void nvme_reset_done(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); - nvme_reset_ctrl_sync(&dev->ctrl); + + if (!nvme_try_sched_reset(&dev->ctrl)) + flush_work(&dev->ctrl.reset_work); } static void nvme_shutdown(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); - nvme_dev_disable(dev, true); + nvme_disable_prepare_reset(dev, true); } /* @@ -2901,7 +2923,7 @@ static int nvme_resume(struct device *dev) if (ndev->last_ps == U32_MAX || nvme_set_power_state(ctrl, ndev->last_ps) != 0) - nvme_reset_ctrl(ctrl); + return nvme_try_sched_reset(&ndev->ctrl); return 0; } @@ -2929,17 +2951,14 @@ static int nvme_suspend(struct device *dev) */ if (pm_suspend_via_firmware() || !ctrl->npss || !pcie_aspm_enabled(pdev) || - (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND)) { - nvme_dev_disable(ndev, true); - return 0; - } + (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND)) + return nvme_disable_prepare_reset(ndev, true); nvme_start_freeze(ctrl); nvme_wait_freeze(ctrl); nvme_sync_queues(ctrl); - if (ctrl->state != NVME_CTRL_LIVE && - ctrl->state != NVME_CTRL_ADMIN_ONLY) + if (ctrl->state != NVME_CTRL_LIVE) goto unfreeze; ret = nvme_get_power_state(ctrl, &ndev->last_ps); @@ -2965,9 +2984,8 @@ static int nvme_suspend(struct device *dev) * Clearing npss forces a controller reset on resume. The * correct value will be resdicovered then. */ - nvme_dev_disable(ndev, true); + ret = nvme_disable_prepare_reset(ndev, true); ctrl->npss = 0; - ret = 0; } unfreeze: nvme_unfreeze(ctrl); @@ -2977,9 +2995,7 @@ unfreeze: static int nvme_simple_suspend(struct device *dev) { struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev)); - - nvme_dev_disable(ndev, true); - return 0; + return nvme_disable_prepare_reset(ndev, true); } static int nvme_simple_resume(struct device *dev) @@ -2987,8 +3003,7 @@ static int nvme_simple_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct nvme_dev *ndev = pci_get_drvdata(pdev); - nvme_reset_ctrl(&ndev->ctrl); - return 0; + return nvme_try_sched_reset(&ndev->ctrl); } static const struct dev_pm_ops nvme_dev_pm_ops = { diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 4d280160dd3f..f19a28b4e997 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1701,6 +1701,14 @@ nvme_rdma_timeout(struct request *rq, bool reserved) dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", rq->tag, nvme_rdma_queue_idx(queue)); + /* + * Restart the timer if a controller reset is already scheduled. Any + * timed out commands would be handled before entering the connecting + * state. + */ + if (ctrl->ctrl.state == NVME_CTRL_RESETTING) + return BLK_EH_RESET_TIMER; + if (ctrl->ctrl.state != NVME_CTRL_LIVE) { /* * Teardown immediately if controller times out while starting diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 385a5212c10f..770dbcbc999e 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1386,7 +1386,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; queue->sock->sk->sk_state_change = nvme_tcp_state_change; queue->sock->sk->sk_write_space = nvme_tcp_write_space; +#ifdef CONFIG_NET_RX_BUSY_POLL queue->sock->sk->sk_ll_usec = 1; +#endif write_unlock_bh(&queue->sock->sk->sk_callback_lock); return 0; @@ -2044,6 +2046,14 @@ nvme_tcp_timeout(struct request *rq, bool reserved) struct nvme_tcp_ctrl *ctrl = req->queue->ctrl; struct nvme_tcp_cmd_pdu *pdu = req->pdu; + /* + * Restart the timer if a controller reset is already scheduled. Any + * timed out commands would be handled before entering the connecting + * state. + */ + if (ctrl->ctrl.state == NVME_CTRL_RESETTING) + return BLK_EH_RESET_TIMER; + dev_warn(ctrl->ctrl.device, "queue %d: timeout request %#x type %d\n", nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type); @@ -2126,6 +2136,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns, ret = nvme_tcp_map_data(queue, rq); if (unlikely(ret)) { + nvme_cleanup_cmd(rq); dev_err(queue->ctrl->ctrl.device, "Failed to map data (%d)\n", ret); return ret; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 748a39fca771..11f5aea97d1b 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -157,8 +157,10 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, iod->sg_table.sgl = iod->first_sgl; if (sg_alloc_table_chained(&iod->sg_table, blk_rq_nr_phys_segments(req), - iod->sg_table.sgl, SG_CHUNK_SIZE)) + iod->sg_table.sgl, SG_CHUNK_SIZE)) { + nvme_cleanup_cmd(req); return BLK_STS_RESOURCE; + } iod->req.sg = iod->sg_table.sgl; iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl); diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index ed50502cc65a..de8e4e347249 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -678,14 +678,6 @@ static int sba_dma_supported( struct device *dev, u64 mask) return(0); } - /* Documentation/DMA-API-HOWTO.txt tells drivers to try 64-bit - * first, then fall back to 32-bit if that fails. - * We are just "encouraging" 32-bit DMA masks here since we can - * never allow IOMMU bypass unless we add special support for ZX1. - */ - if (mask > ~0U) - return 0; - ioc = GET_IOC(dev); if (!ioc) return 0; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..a97e2571a527 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -959,19 +959,6 @@ void pci_refresh_power_state(struct pci_dev *dev) } /** - * pci_power_up - Put the given device into D0 forcibly - * @dev: PCI device to power up - */ -void pci_power_up(struct pci_dev *dev) -{ - if (platform_pci_power_manageable(dev)) - platform_pci_set_power_state(dev, PCI_D0); - - pci_raw_set_power_state(dev, PCI_D0); - pci_update_current_state(dev, PCI_D0); -} - -/** * pci_platform_power_transition - Use platform to change device power state * @dev: PCI device to handle. * @state: State to put the device into. @@ -1154,6 +1141,17 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) EXPORT_SYMBOL(pci_set_power_state); /** + * pci_power_up - Put the given device into D0 forcibly + * @dev: PCI device to power up + */ +void pci_power_up(struct pci_dev *dev) +{ + __pci_start_power_transition(dev, PCI_D0); + pci_raw_set_power_state(dev, PCI_D0); + pci_update_current_state(dev, PCI_D0); +} + +/** * pci_choose_state - Choose the power state of a PCI device * @dev: PCI device to be suspended * @state: target sleep state for the whole system. This is the value diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index 648ddb7f038a..c6800d220920 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -87,7 +87,7 @@ FUNC_GROUP_DECL(MACLINK3, L23); #define K25 7 SIG_EXPR_LIST_DECL_SESG(K25, MACLINK4, MACLINK4, SIG_DESC_SET(SCU410, 7)); -SIG_EXPR_LIST_DECL_SESG(K25, SDA14, SDA14, SIG_DESC_SET(SCU4B0, 7)); +SIG_EXPR_LIST_DECL_SESG(K25, SDA14, I2C14, SIG_DESC_SET(SCU4B0, 7)); PIN_DECL_2(K25, GPIOA7, MACLINK4, SDA14); FUNC_GROUP_DECL(MACLINK4, K25); @@ -1262,13 +1262,13 @@ GROUP_DECL(SPI1, AB11, AC11, AA11); #define AD11 206 SIG_EXPR_LIST_DECL_SEMG(AD11, SPI1DQ2, QSPI1, SPI1, SIG_DESC_SET(SCU438, 14)); SIG_EXPR_LIST_DECL_SEMG(AD11, TXD13, UART13G1, UART13, - SIG_DESC_SET(SCU438, 14)); + SIG_DESC_CLEAR(SCU4B8, 2), SIG_DESC_SET(SCU4D8, 14)); PIN_DECL_2(AD11, GPIOZ6, SPI1DQ2, TXD13); #define AF10 207 SIG_EXPR_LIST_DECL_SEMG(AF10, SPI1DQ3, QSPI1, SPI1, SIG_DESC_SET(SCU438, 15)); SIG_EXPR_LIST_DECL_SEMG(AF10, RXD13, UART13G1, UART13, - SIG_DESC_SET(SCU438, 15)); + SIG_DESC_CLEAR(SCU4B8, 3), SIG_DESC_SET(SCU4D8, 15)); PIN_DECL_2(AF10, GPIOZ7, SPI1DQ3, RXD13); GROUP_DECL(QSPI1, AB11, AC11, AA11, AD11, AF10); @@ -1440,91 +1440,85 @@ FUNC_GROUP_DECL(RGMII2, D4, C2, C1, D3, E4, F5, D2, E3, D1, F4, E2, E1); FUNC_GROUP_DECL(RMII2, D4, C2, C1, D3, D2, D1, F4, E2, E1); #define AB4 232 -SIG_EXPR_LIST_DECL_SESG(AB4, SD3CLK, SD3, SIG_DESC_SET(SCU400, 24)); -PIN_DECL_1(AB4, GPIO18D0, SD3CLK); +SIG_EXPR_LIST_DECL_SEMG(AB4, EMMCCLK, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 24)); +PIN_DECL_1(AB4, GPIO18D0, EMMCCLK); #define AA4 233 -SIG_EXPR_LIST_DECL_SESG(AA4, SD3CMD, SD3, SIG_DESC_SET(SCU400, 25)); -PIN_DECL_1(AA4, GPIO18D1, SD3CMD); +SIG_EXPR_LIST_DECL_SEMG(AA4, EMMCCMD, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 25)); +PIN_DECL_1(AA4, GPIO18D1, EMMCCMD); #define AC4 234 -SIG_EXPR_LIST_DECL_SESG(AC4, SD3DAT0, SD3, SIG_DESC_SET(SCU400, 26)); -PIN_DECL_1(AC4, GPIO18D2, SD3DAT0); +SIG_EXPR_LIST_DECL_SEMG(AC4, EMMCDAT0, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 26)); +PIN_DECL_1(AC4, GPIO18D2, EMMCDAT0); #define AA5 235 -SIG_EXPR_LIST_DECL_SESG(AA5, SD3DAT1, SD3, SIG_DESC_SET(SCU400, 27)); -PIN_DECL_1(AA5, GPIO18D3, SD3DAT1); +SIG_EXPR_LIST_DECL_SEMG(AA5, EMMCDAT1, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 27)); +PIN_DECL_1(AA5, GPIO18D3, EMMCDAT1); #define Y5 236 -SIG_EXPR_LIST_DECL_SESG(Y5, SD3DAT2, SD3, SIG_DESC_SET(SCU400, 28)); -PIN_DECL_1(Y5, GPIO18D4, SD3DAT2); +SIG_EXPR_LIST_DECL_SEMG(Y5, EMMCDAT2, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 28)); +PIN_DECL_1(Y5, GPIO18D4, EMMCDAT2); #define AB5 237 -SIG_EXPR_LIST_DECL_SESG(AB5, SD3DAT3, SD3, SIG_DESC_SET(SCU400, 29)); -PIN_DECL_1(AB5, GPIO18D5, SD3DAT3); +SIG_EXPR_LIST_DECL_SEMG(AB5, EMMCDAT3, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 29)); +PIN_DECL_1(AB5, GPIO18D5, EMMCDAT3); #define AB6 238 -SIG_EXPR_LIST_DECL_SESG(AB6, SD3CD, SD3, SIG_DESC_SET(SCU400, 30)); -PIN_DECL_1(AB6, GPIO18D6, SD3CD); +SIG_EXPR_LIST_DECL_SEMG(AB6, EMMCCD, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 30)); +PIN_DECL_1(AB6, GPIO18D6, EMMCCD); #define AC5 239 -SIG_EXPR_LIST_DECL_SESG(AC5, SD3WP, SD3, SIG_DESC_SET(SCU400, 31)); -PIN_DECL_1(AC5, GPIO18D7, SD3WP); +SIG_EXPR_LIST_DECL_SEMG(AC5, EMMCWP, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 31)); +PIN_DECL_1(AC5, GPIO18D7, EMMCWP); -FUNC_GROUP_DECL(SD3, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5); +GROUP_DECL(EMMCG1, AB4, AA4, AC4, AB6, AC5); +GROUP_DECL(EMMCG4, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5); #define Y1 240 SIG_EXPR_LIST_DECL_SEMG(Y1, FWSPIDCS, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y1, VBCS, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y1, SD3DAT4, SD3DAT4, SIG_DESC_SET(SCU404, 0)); -PIN_DECL_3(Y1, GPIO18E0, FWSPIDCS, VBCS, SD3DAT4); -FUNC_GROUP_DECL(SD3DAT4, Y1); +SIG_EXPR_LIST_DECL_SEMG(Y1, EMMCDAT4, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 0)); +PIN_DECL_3(Y1, GPIO18E0, FWSPIDCS, VBCS, EMMCDAT4); #define Y2 241 SIG_EXPR_LIST_DECL_SEMG(Y2, FWSPIDCK, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y2, VBCK, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y2, SD3DAT5, SD3DAT5, SIG_DESC_SET(SCU404, 1)); -PIN_DECL_3(Y2, GPIO18E1, FWSPIDCK, VBCK, SD3DAT5); -FUNC_GROUP_DECL(SD3DAT5, Y2); +SIG_EXPR_LIST_DECL_SEMG(Y2, EMMCDAT5, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 1)); +PIN_DECL_3(Y2, GPIO18E1, FWSPIDCK, VBCK, EMMCDAT5); #define Y3 242 SIG_EXPR_LIST_DECL_SEMG(Y3, FWSPIDMOSI, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y3, VBMOSI, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y3, SD3DAT6, SD3DAT6, SIG_DESC_SET(SCU404, 2)); -PIN_DECL_3(Y3, GPIO18E2, FWSPIDMOSI, VBMOSI, SD3DAT6); -FUNC_GROUP_DECL(SD3DAT6, Y3); +SIG_EXPR_LIST_DECL_SEMG(Y3, EMMCDAT6, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 2)); +PIN_DECL_3(Y3, GPIO18E2, FWSPIDMOSI, VBMOSI, EMMCDAT6); #define Y4 243 SIG_EXPR_LIST_DECL_SEMG(Y4, FWSPIDMISO, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y4, VBMISO, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y4, SD3DAT7, SD3DAT7, SIG_DESC_SET(SCU404, 3)); -PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, SD3DAT7); -FUNC_GROUP_DECL(SD3DAT7, Y4); +SIG_EXPR_LIST_DECL_SEMG(Y4, EMMCDAT7, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 3)); +PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, EMMCDAT7); GROUP_DECL(FWSPID, Y1, Y2, Y3, Y4); GROUP_DECL(FWQSPID, Y1, Y2, Y3, Y4, AE12, AF12); +GROUP_DECL(EMMCG8, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5, Y1, Y2, Y3, Y4); FUNC_DECL_2(FWSPID, FWSPID, FWQSPID); FUNC_GROUP_DECL(VB, Y1, Y2, Y3, Y4); - +FUNC_DECL_3(EMMC, EMMCG1, EMMCG4, EMMCG8); /* * FIXME: Confirm bits and priorities are the right way around for the * following 4 pins */ #define AF25 244 -SIG_EXPR_LIST_DECL_SEMG(AF25, I3C3SCL, I3C3, I3C3, SIG_DESC_SET(SCU438, 20), - SIG_DESC_SET(SCU4D8, 20)); -SIG_EXPR_LIST_DECL_SESG(AF25, FSI1CLK, FSI1, SIG_DESC_CLEAR(SCU438, 20), - SIG_DESC_SET(SCU4D8, 20)); +SIG_EXPR_LIST_DECL_SEMG(AF25, I3C3SCL, I3C3, I3C3, SIG_DESC_SET(SCU438, 20)); +SIG_EXPR_LIST_DECL_SESG(AF25, FSI1CLK, FSI1, SIG_DESC_SET(SCU4D8, 20)); PIN_DECL_(AF25, SIG_EXPR_LIST_PTR(AF25, I3C3SCL), SIG_EXPR_LIST_PTR(AF25, FSI1CLK)); #define AE26 245 -SIG_EXPR_LIST_DECL_SEMG(AE26, I3C3SDA, I3C3, I3C3, SIG_DESC_SET(SCU438, 21), - SIG_DESC_SET(SCU4D8, 21)); -SIG_EXPR_LIST_DECL_SESG(AE26, FSI1DATA, FSI1, SIG_DESC_CLEAR(SCU438, 21), - SIG_DESC_SET(SCU4D8, 21)); +SIG_EXPR_LIST_DECL_SEMG(AE26, I3C3SDA, I3C3, I3C3, SIG_DESC_SET(SCU438, 21)); +SIG_EXPR_LIST_DECL_SESG(AE26, FSI1DATA, FSI1, SIG_DESC_SET(SCU4D8, 21)); PIN_DECL_(AE26, SIG_EXPR_LIST_PTR(AE26, I3C3SDA), SIG_EXPR_LIST_PTR(AE26, FSI1DATA)); @@ -1533,18 +1527,14 @@ FUNC_DECL_2(I3C3, HVI3C3, I3C3); FUNC_GROUP_DECL(FSI1, AF25, AE26); #define AE25 246 -SIG_EXPR_LIST_DECL_SEMG(AE25, I3C4SCL, I3C4, I3C4, SIG_DESC_SET(SCU438, 22), - SIG_DESC_SET(SCU4D8, 22)); -SIG_EXPR_LIST_DECL_SESG(AE25, FSI2CLK, FSI2, SIG_DESC_CLEAR(SCU438, 22), - SIG_DESC_SET(SCU4D8, 22)); +SIG_EXPR_LIST_DECL_SEMG(AE25, I3C4SCL, I3C4, I3C4, SIG_DESC_SET(SCU438, 22)); +SIG_EXPR_LIST_DECL_SESG(AE25, FSI2CLK, FSI2, SIG_DESC_SET(SCU4D8, 22)); PIN_DECL_(AE25, SIG_EXPR_LIST_PTR(AE25, I3C4SCL), SIG_EXPR_LIST_PTR(AE25, FSI2CLK)); #define AF24 247 -SIG_EXPR_LIST_DECL_SEMG(AF24, I3C4SDA, I3C4, I3C4, SIG_DESC_SET(SCU438, 23), - SIG_DESC_SET(SCU4D8, 23)); -SIG_EXPR_LIST_DECL_SESG(AF24, FSI2DATA, FSI2, SIG_DESC_CLEAR(SCU438, 23), - SIG_DESC_SET(SCU4D8, 23)); +SIG_EXPR_LIST_DECL_SEMG(AF24, I3C4SDA, I3C4, I3C4, SIG_DESC_SET(SCU438, 23)); +SIG_EXPR_LIST_DECL_SESG(AF24, FSI2DATA, FSI2, SIG_DESC_SET(SCU4D8, 23)); PIN_DECL_(AF24, SIG_EXPR_LIST_PTR(AF24, I3C4SDA), SIG_EXPR_LIST_PTR(AF24, FSI2DATA)); @@ -1574,6 +1564,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(A3), ASPEED_PINCTRL_PIN(AA11), ASPEED_PINCTRL_PIN(AA12), + ASPEED_PINCTRL_PIN(AA16), + ASPEED_PINCTRL_PIN(AA17), ASPEED_PINCTRL_PIN(AA23), ASPEED_PINCTRL_PIN(AA24), ASPEED_PINCTRL_PIN(AA25), @@ -1585,6 +1577,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AB11), ASPEED_PINCTRL_PIN(AB12), ASPEED_PINCTRL_PIN(AB15), + ASPEED_PINCTRL_PIN(AB16), + ASPEED_PINCTRL_PIN(AB17), ASPEED_PINCTRL_PIN(AB18), ASPEED_PINCTRL_PIN(AB19), ASPEED_PINCTRL_PIN(AB22), @@ -1602,6 +1596,7 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AC11), ASPEED_PINCTRL_PIN(AC12), ASPEED_PINCTRL_PIN(AC15), + ASPEED_PINCTRL_PIN(AC16), ASPEED_PINCTRL_PIN(AC17), ASPEED_PINCTRL_PIN(AC18), ASPEED_PINCTRL_PIN(AC19), @@ -1619,6 +1614,7 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AD12), ASPEED_PINCTRL_PIN(AD14), ASPEED_PINCTRL_PIN(AD15), + ASPEED_PINCTRL_PIN(AD16), ASPEED_PINCTRL_PIN(AD19), ASPEED_PINCTRL_PIN(AD20), ASPEED_PINCTRL_PIN(AD22), @@ -1634,8 +1630,11 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AE12), ASPEED_PINCTRL_PIN(AE14), ASPEED_PINCTRL_PIN(AE15), + ASPEED_PINCTRL_PIN(AE16), ASPEED_PINCTRL_PIN(AE18), ASPEED_PINCTRL_PIN(AE19), + ASPEED_PINCTRL_PIN(AE25), + ASPEED_PINCTRL_PIN(AE26), ASPEED_PINCTRL_PIN(AE7), ASPEED_PINCTRL_PIN(AE8), ASPEED_PINCTRL_PIN(AF10), @@ -1643,6 +1642,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AF12), ASPEED_PINCTRL_PIN(AF14), ASPEED_PINCTRL_PIN(AF15), + ASPEED_PINCTRL_PIN(AF24), + ASPEED_PINCTRL_PIN(AF25), ASPEED_PINCTRL_PIN(AF7), ASPEED_PINCTRL_PIN(AF8), ASPEED_PINCTRL_PIN(AF9), @@ -1792,17 +1793,6 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(Y3), ASPEED_PINCTRL_PIN(Y4), ASPEED_PINCTRL_PIN(Y5), - ASPEED_PINCTRL_PIN(AB16), - ASPEED_PINCTRL_PIN(AA17), - ASPEED_PINCTRL_PIN(AB17), - ASPEED_PINCTRL_PIN(AE16), - ASPEED_PINCTRL_PIN(AC16), - ASPEED_PINCTRL_PIN(AA16), - ASPEED_PINCTRL_PIN(AD16), - ASPEED_PINCTRL_PIN(AF25), - ASPEED_PINCTRL_PIN(AE26), - ASPEED_PINCTRL_PIN(AE25), - ASPEED_PINCTRL_PIN(AF24), }; static const struct aspeed_pin_group aspeed_g6_groups[] = { @@ -1976,11 +1966,9 @@ static const struct aspeed_pin_group aspeed_g6_groups[] = { ASPEED_PINCTRL_GROUP(SALT9G1), ASPEED_PINCTRL_GROUP(SD1), ASPEED_PINCTRL_GROUP(SD2), - ASPEED_PINCTRL_GROUP(SD3), - ASPEED_PINCTRL_GROUP(SD3DAT4), - ASPEED_PINCTRL_GROUP(SD3DAT5), - ASPEED_PINCTRL_GROUP(SD3DAT6), - ASPEED_PINCTRL_GROUP(SD3DAT7), + ASPEED_PINCTRL_GROUP(EMMCG1), + ASPEED_PINCTRL_GROUP(EMMCG4), + ASPEED_PINCTRL_GROUP(EMMCG8), ASPEED_PINCTRL_GROUP(SGPM1), ASPEED_PINCTRL_GROUP(SGPS1), ASPEED_PINCTRL_GROUP(SIOONCTRL), @@ -2059,6 +2047,7 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = { ASPEED_PINCTRL_FUNC(ADC8), ASPEED_PINCTRL_FUNC(ADC9), ASPEED_PINCTRL_FUNC(BMCINT), + ASPEED_PINCTRL_FUNC(EMMC), ASPEED_PINCTRL_FUNC(ESPI), ASPEED_PINCTRL_FUNC(ESPIALT), ASPEED_PINCTRL_FUNC(FSI1), @@ -2191,11 +2180,6 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = { ASPEED_PINCTRL_FUNC(SALT9), ASPEED_PINCTRL_FUNC(SD1), ASPEED_PINCTRL_FUNC(SD2), - ASPEED_PINCTRL_FUNC(SD3), - ASPEED_PINCTRL_FUNC(SD3DAT4), - ASPEED_PINCTRL_FUNC(SD3DAT5), - ASPEED_PINCTRL_FUNC(SD3DAT6), - ASPEED_PINCTRL_FUNC(SD3DAT7), ASPEED_PINCTRL_FUNC(SGPM1), ASPEED_PINCTRL_FUNC(SGPS1), ASPEED_PINCTRL_FUNC(SIOONCTRL), diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h index a2c0d52e4f7b..140c5ce9fbc1 100644 --- a/drivers/pinctrl/aspeed/pinmux-aspeed.h +++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h @@ -508,7 +508,7 @@ struct aspeed_pin_desc { * @idx: The bit index in the register */ #define SIG_DESC_SET(reg, idx) SIG_DESC_IP_BIT(ASPEED_IP_SCU, reg, idx, 1) -#define SIG_DESC_CLEAR(reg, idx) SIG_DESC_IP_BIT(ASPEED_IP_SCU, reg, idx, 0) +#define SIG_DESC_CLEAR(reg, idx) { ASPEED_IP_SCU, reg, BIT_MASK(idx), 0, 0 } #define SIG_DESC_LIST_SYM(sig, group) sig_descs_ ## sig ## _ ## group #define SIG_DESC_LIST_DECL(sig, group, ...) \ @@ -738,6 +738,7 @@ struct aspeed_pin_desc { static const char *FUNC_SYM(func)[] = { __VA_ARGS__ } #define FUNC_DECL_2(func, one, two) FUNC_DECL_(func, #one, #two) +#define FUNC_DECL_3(func, one, two, three) FUNC_DECL_(func, #one, #two, #three) #define FUNC_GROUP_DECL(func, ...) \ GROUP_DECL(func, __VA_ARGS__); \ diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c index 6f7d3a2f2e97..42f7ab383ad9 100644 --- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c @@ -1,14 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2014-2017 Broadcom - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ /* @@ -853,7 +845,7 @@ static int iproc_gpio_probe(struct platform_device *pdev) /* optional GPIO interrupt support */ irq = platform_get_irq(pdev, 0); - if (irq) { + if (irq > 0) { struct irq_chip *irqc; struct gpio_irq_chip *girq; diff --git a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c index 2bf6af7df7d9..9fabc451550e 100644 --- a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c +++ b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c @@ -640,8 +640,8 @@ static int ns2_pinmux_enable(struct pinctrl_dev *pctrl_dev, const struct ns2_pin_function *func; const struct ns2_pin_group *grp; - if (grp_select > pinctrl->num_groups || - func_select > pinctrl->num_functions) + if (grp_select >= pinctrl->num_groups || + func_select >= pinctrl->num_functions) return -EINVAL; func = &pinctrl->functions[func_select]; diff --git a/drivers/pinctrl/berlin/pinctrl-as370.c b/drivers/pinctrl/berlin/pinctrl-as370.c index 44f8ccdbeeff..9dfdc275ee33 100644 --- a/drivers/pinctrl/berlin/pinctrl-as370.c +++ b/drivers/pinctrl/berlin/pinctrl-as370.c @@ -43,7 +43,7 @@ static const struct berlin_desc_group as370_soc_pinctrl_groups[] = { BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO5 */ BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO3 */ BERLIN_PINCTRL_FUNCTION(0x2, "pwm"), /* PWM5 */ - BERLIN_PINCTRL_FUNCTION(0x3, "spififib"), /* SPDIFIB */ + BERLIN_PINCTRL_FUNCTION(0x3, "spdifib"), /* SPDIFIB */ BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */ BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG5 */ BERLIN_PINCTRL_GROUP("I2S1_MCLK", 0x0, 0x3, 0x12, diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index aae51c507f59..c6251eac8946 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1513,7 +1513,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1521,7 +1520,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1529,7 +1527,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Cyan"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1537,7 +1534,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Celes"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, {} diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 1f13bcd0e4e1..bc013599a9a3 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -96,6 +96,7 @@ struct intel_pinctrl_context { * @pctldesc: Pin controller description * @pctldev: Pointer to the pin controller device * @chip: GPIO chip in this pin controller + * @irqchip: IRQ chip in this pin controller * @soc: SoC/PCH specific pin configuration data * @communities: All communities in this pin controller * @ncommunities: Number of communities in this pin controller @@ -108,6 +109,7 @@ struct intel_pinctrl { struct pinctrl_desc pctldesc; struct pinctrl_dev *pctldev; struct gpio_chip chip; + struct irq_chip irqchip; const struct intel_pinctrl_soc_data *soc; struct intel_community *communities; size_t ncommunities; @@ -1139,16 +1141,6 @@ static irqreturn_t intel_gpio_irq(int irq, void *data) return ret; } -static struct irq_chip intel_gpio_irqchip = { - .name = "intel-gpio", - .irq_ack = intel_gpio_irq_ack, - .irq_mask = intel_gpio_irq_mask, - .irq_unmask = intel_gpio_irq_unmask, - .irq_set_type = intel_gpio_irq_type, - .irq_set_wake = intel_gpio_irq_wake, - .flags = IRQCHIP_MASK_ON_SUSPEND, -}; - static int intel_gpio_add_pin_ranges(struct intel_pinctrl *pctrl, const struct intel_community *community) { @@ -1198,12 +1190,22 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq) pctrl->chip = intel_gpio_chip; + /* Setup GPIO chip */ pctrl->chip.ngpio = intel_gpio_ngpio(pctrl); pctrl->chip.label = dev_name(pctrl->dev); pctrl->chip.parent = pctrl->dev; pctrl->chip.base = -1; pctrl->irq = irq; + /* Setup IRQ chip */ + pctrl->irqchip.name = dev_name(pctrl->dev); + pctrl->irqchip.irq_ack = intel_gpio_irq_ack; + pctrl->irqchip.irq_mask = intel_gpio_irq_mask; + pctrl->irqchip.irq_unmask = intel_gpio_irq_unmask; + pctrl->irqchip.irq_set_type = intel_gpio_irq_type; + pctrl->irqchip.irq_set_wake = intel_gpio_irq_wake; + pctrl->irqchip.flags = IRQCHIP_MASK_ON_SUSPEND; + ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl); if (ret) { dev_err(pctrl->dev, "failed to register gpiochip\n"); @@ -1233,15 +1235,14 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq) return ret; } - ret = gpiochip_irqchip_add(&pctrl->chip, &intel_gpio_irqchip, 0, + ret = gpiochip_irqchip_add(&pctrl->chip, &pctrl->irqchip, 0, handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add irqchip\n"); return ret; } - gpiochip_set_chained_irqchip(&pctrl->chip, &intel_gpio_irqchip, irq, - NULL); + gpiochip_set_chained_irqchip(&pctrl->chip, &pctrl->irqchip, irq, NULL); return 0; } diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index 6462d3ca7ceb..f2f5fcd9a237 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -183,10 +183,10 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = { PIN_GRP_EXTRA("uart2", 9, 2, BIT(1) | BIT(13) | BIT(14) | BIT(19), BIT(1) | BIT(13) | BIT(14), BIT(1) | BIT(19), 18, 2, "gpio", "uart"), - PIN_GRP_GPIO("led0_od", 11, 1, BIT(20), "led"), - PIN_GRP_GPIO("led1_od", 12, 1, BIT(21), "led"), - PIN_GRP_GPIO("led2_od", 13, 1, BIT(22), "led"), - PIN_GRP_GPIO("led3_od", 14, 1, BIT(23), "led"), + PIN_GRP_GPIO_2("led0_od", 11, 1, BIT(20), BIT(20), 0, "led"), + PIN_GRP_GPIO_2("led1_od", 12, 1, BIT(21), BIT(21), 0, "led"), + PIN_GRP_GPIO_2("led2_od", 13, 1, BIT(22), BIT(22), 0, "led"), + PIN_GRP_GPIO_2("led3_od", 14, 1, BIT(23), BIT(23), 0, "led"), }; @@ -221,11 +221,11 @@ static const struct armada_37xx_pin_data armada_37xx_pin_sb = { }; static inline void armada_37xx_update_reg(unsigned int *reg, - unsigned int offset) + unsigned int *offset) { /* We never have more than 2 registers */ - if (offset >= GPIO_PER_REG) { - offset -= GPIO_PER_REG; + if (*offset >= GPIO_PER_REG) { + *offset -= GPIO_PER_REG; *reg += sizeof(u32); } } @@ -376,7 +376,7 @@ static inline void armada_37xx_irq_update_reg(unsigned int *reg, { int offset = irqd_to_hwirq(d); - armada_37xx_update_reg(reg, offset); + armada_37xx_update_reg(reg, &offset); } static int armada_37xx_gpio_direction_input(struct gpio_chip *chip, @@ -386,7 +386,7 @@ static int armada_37xx_gpio_direction_input(struct gpio_chip *chip, unsigned int reg = OUTPUT_EN; unsigned int mask; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); return regmap_update_bits(info->regmap, reg, mask, 0); @@ -399,7 +399,7 @@ static int armada_37xx_gpio_get_direction(struct gpio_chip *chip, unsigned int reg = OUTPUT_EN; unsigned int val, mask; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); regmap_read(info->regmap, reg, &val); @@ -413,7 +413,7 @@ static int armada_37xx_gpio_direction_output(struct gpio_chip *chip, unsigned int reg = OUTPUT_EN; unsigned int mask, val, ret; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); ret = regmap_update_bits(info->regmap, reg, mask, mask); @@ -434,7 +434,7 @@ static int armada_37xx_gpio_get(struct gpio_chip *chip, unsigned int offset) unsigned int reg = INPUT_VAL; unsigned int val, mask; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); regmap_read(info->regmap, reg, &val); @@ -449,7 +449,7 @@ static void armada_37xx_gpio_set(struct gpio_chip *chip, unsigned int offset, unsigned int reg = OUTPUT_VAL; unsigned int mask, val; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); val = value ? mask : 0; diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c index 974973777395..564660028fcc 100644 --- a/drivers/pinctrl/pinctrl-stmfx.c +++ b/drivers/pinctrl/pinctrl-stmfx.c @@ -705,7 +705,7 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) static int stmfx_pinctrl_remove(struct platform_device *pdev) { - struct stmfx *stmfx = dev_get_platdata(&pdev->dev); + struct stmfx *stmfx = dev_get_drvdata(pdev->dev.parent); return stmfx_function_disable(stmfx, STMFX_FUNC_GPIO | diff --git a/drivers/platform/x86/classmate-laptop.c b/drivers/platform/x86/classmate-laptop.c index 86cc2cc68fb5..af063f690846 100644 --- a/drivers/platform/x86/classmate-laptop.c +++ b/drivers/platform/x86/classmate-laptop.c @@ -420,12 +420,6 @@ failed_sensitivity: static int cmpc_accel_remove_v4(struct acpi_device *acpi) { - struct input_dev *inputdev; - struct cmpc_accel *accel; - - inputdev = dev_get_drvdata(&acpi->dev); - accel = dev_get_drvdata(&inputdev->dev); - device_remove_file(&acpi->dev, &cmpc_accel_sensitivity_attr_v4); device_remove_file(&acpi->dev, &cmpc_accel_g_select_attr_v4); return cmpc_remove_acpi_notify_device(acpi); @@ -656,12 +650,6 @@ failed_file: static int cmpc_accel_remove(struct acpi_device *acpi) { - struct input_dev *inputdev; - struct cmpc_accel *accel; - - inputdev = dev_get_drvdata(&acpi->dev); - accel = dev_get_drvdata(&inputdev->dev); - device_remove_file(&acpi->dev, &cmpc_accel_sensitivity_attr); return cmpc_remove_acpi_notify_device(acpi); } diff --git a/drivers/platform/x86/i2c-multi-instantiate.c b/drivers/platform/x86/i2c-multi-instantiate.c index ea68f6ed66ae..ffb8d5d1eb5f 100644 --- a/drivers/platform/x86/i2c-multi-instantiate.c +++ b/drivers/platform/x86/i2c-multi-instantiate.c @@ -108,6 +108,7 @@ static int i2c_multi_inst_probe(struct platform_device *pdev) if (ret < 0) { dev_dbg(dev, "Error requesting irq at index %d: %d\n", inst_data[i].irq_idx, ret); + goto error; } board_info.irq = ret; break; diff --git a/drivers/platform/x86/intel_punit_ipc.c b/drivers/platform/x86/intel_punit_ipc.c index ab7ae1950867..fa97834fdb78 100644 --- a/drivers/platform/x86/intel_punit_ipc.c +++ b/drivers/platform/x86/intel_punit_ipc.c @@ -293,9 +293,8 @@ static int intel_punit_ipc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, punit_ipcdev); - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq < 0) { - punit_ipcdev->irq = 0; dev_warn(&pdev->dev, "Invalid IRQ, using polling mode\n"); } else { ret = devm_request_irq(&pdev->dev, irq, intel_punit_ioc, diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 960961fb0d7c..0517272a268e 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -97,8 +97,8 @@ config PTP_1588_CLOCK_PCH help This driver adds support for using the PCH EG20T as a PTP clock. The hardware supports time stamping of PTP packets - when using the end-to-end delay (E2E) mechansim. The peer - delay mechansim (P2P) is not supported. + when using the end-to-end delay (E2E) mechanism. The peer + delay mechanism (P2P) is not supported. This clock is only useful if your PTP programs are getting hardware time stamps on the PTP Ethernet packets using the diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index b8799cd3e7aa..bd8143e51747 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -2021,10 +2021,10 @@ static bool qeth_l2_vnicc_recover_char(struct qeth_card *card, u32 vnicc, static void qeth_l2_vnicc_init(struct qeth_card *card) { u32 *timeout = &card->options.vnicc.learning_timeout; + bool enable, error = false; unsigned int chars_len, i; unsigned long chars_tmp; u32 sup_cmds, vnicc; - bool enable, error; QETH_CARD_TEXT(card, 2, "vniccini"); /* reset rx_bcast */ @@ -2045,17 +2045,24 @@ static void qeth_l2_vnicc_init(struct qeth_card *card) chars_len = sizeof(card->options.vnicc.sup_chars) * BITS_PER_BYTE; for_each_set_bit(i, &chars_tmp, chars_len) { vnicc = BIT(i); - qeth_l2_vnicc_query_cmds(card, vnicc, &sup_cmds); - if (!(sup_cmds & IPA_VNICC_SET_TIMEOUT) || - !(sup_cmds & IPA_VNICC_GET_TIMEOUT)) + if (qeth_l2_vnicc_query_cmds(card, vnicc, &sup_cmds)) { + sup_cmds = 0; + error = true; + } + if ((sup_cmds & IPA_VNICC_SET_TIMEOUT) && + (sup_cmds & IPA_VNICC_GET_TIMEOUT)) + card->options.vnicc.getset_timeout_sup |= vnicc; + else card->options.vnicc.getset_timeout_sup &= ~vnicc; - if (!(sup_cmds & IPA_VNICC_ENABLE) || - !(sup_cmds & IPA_VNICC_DISABLE)) + if ((sup_cmds & IPA_VNICC_ENABLE) && + (sup_cmds & IPA_VNICC_DISABLE)) + card->options.vnicc.set_char_sup |= vnicc; + else card->options.vnicc.set_char_sup &= ~vnicc; } /* enforce assumed default values and recover settings, if changed */ - error = qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING, - timeout); + error |= qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING, + timeout); chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT; chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE; chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE; diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 296bbc3c4606..cf63916814cc 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -27,6 +27,11 @@ struct kmem_cache *zfcp_fsf_qtcb_cache; +static bool ber_stop = true; +module_param(ber_stop, bool, 0600); +MODULE_PARM_DESC(ber_stop, + "Shuts down FCP devices for FCP channels that report a bit-error count in excess of its threshold (default on)"); + static void zfcp_fsf_request_timeout_handler(struct timer_list *t) { struct zfcp_fsf_req *fsf_req = from_timer(fsf_req, t, timer); @@ -236,10 +241,15 @@ static void zfcp_fsf_status_read_handler(struct zfcp_fsf_req *req) case FSF_STATUS_READ_SENSE_DATA_AVAIL: break; case FSF_STATUS_READ_BIT_ERROR_THRESHOLD: - dev_warn(&adapter->ccw_device->dev, - "The error threshold for checksum statistics " - "has been exceeded\n"); zfcp_dbf_hba_bit_err("fssrh_3", req); + if (ber_stop) { + dev_warn(&adapter->ccw_device->dev, + "All paths over this FCP device are disused because of excessive bit errors\n"); + zfcp_erp_adapter_shutdown(adapter, 0, "fssrh_b"); + } else { + dev_warn(&adapter->ccw_device->dev, + "The error threshold for checksum statistics has been exceeded\n"); + } break; case FSF_STATUS_READ_LINK_DOWN: zfcp_fsf_status_read_link_down(req); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 4c26630c1c3e..009fd5a33fcd 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2837,8 +2837,6 @@ qla2x00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt) if (sense_len == 0) { rsp->status_srb = NULL; sp->done(sp, cp->result); - } else { - WARN_ON_ONCE(true); } } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 1c470e31ae81..ae2fa170f6ad 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -967,6 +967,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, ses->data_direction = scmd->sc_data_direction; ses->sdb = scmd->sdb; ses->result = scmd->result; + ses->resid_len = scmd->req.resid_len; ses->underflow = scmd->underflow; ses->prot_op = scmd->prot_op; ses->eh_eflags = scmd->eh_eflags; @@ -977,6 +978,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, memset(scmd->cmnd, 0, BLK_MAX_CDB); memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->result = 0; + scmd->req.resid_len = 0; if (sense_bytes) { scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE, @@ -1029,6 +1031,7 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->sc_data_direction = ses->data_direction; scmd->sdb = ses->sdb; scmd->result = ses->result; + scmd->req.resid_len = ses->resid_len; scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index dc210b9d4896..5447738906ac 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1834,6 +1834,7 @@ static const struct blk_mq_ops scsi_mq_ops_no_commit = { .init_request = scsi_mq_init_request, .exit_request = scsi_mq_exit_request, .initialize_rq_fn = scsi_initialize_rq, + .cleanup_rq = scsi_cleanup_rq, .busy = scsi_mq_lld_busy, .map_queues = scsi_map_queues, }; @@ -1921,7 +1922,8 @@ struct scsi_device *scsi_device_from_queue(struct request_queue *q) { struct scsi_device *sdev = NULL; - if (q->mq_ops == &scsi_mq_ops) + if (q->mq_ops == &scsi_mq_ops_no_commit || + q->mq_ops == &scsi_mq_ops) sdev = q->queuedata; if (!sdev || !get_device(&sdev->sdev_gendev)) sdev = NULL; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 50928bc266eb..03163ac5fe95 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1654,7 +1654,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) /* we need to evaluate the error return */ if (scsi_sense_valid(sshdr) && (sshdr->asc == 0x3a || /* medium not present */ - sshdr->asc == 0x20)) /* invalid command */ + sshdr->asc == 0x20 || /* invalid command */ + (sshdr->asc == 0x74 && sshdr->ascq == 0x71))) /* drive is password locked */ /* this is no error here */ return 0; diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 7804869c6a31..056308008288 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -161,6 +161,7 @@ static int vhost_test_release(struct inode *inode, struct file *f) vhost_test_stop(n, &private); vhost_test_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_cleanup(&n->dev); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ @@ -237,6 +238,7 @@ static long vhost_test_reset_owner(struct vhost_test *n) } vhost_test_stop(n, &priv); vhost_test_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); done: mutex_unlock(&n->dev.mutex); diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 69a626b0e594..c57c71b7d53d 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -775,7 +775,7 @@ static int pvcalls_back_poll(struct xenbus_device *dev, mappass->reqcopy = *req; icsk = inet_csk(mappass->sock->sk); queue = &icsk->icsk_accept_queue; - data = queue->rskq_accept_head != NULL; + data = READ_ONCE(queue->rskq_accept_head) != NULL; if (data) { mappass->reqcopy.cmd = 0; ret = 0; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a8a8f84f3bbf..a5163296d9d9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -384,8 +384,8 @@ static int parse_reply_info_readdir(void **p, void *end, } done: - if (*p != end) - goto bad; + /* Skip over any unrecognized fields */ + *p = end; return 0; bad: @@ -406,12 +406,10 @@ static int parse_reply_info_filelock(void **p, void *end, goto bad; info->filelock_reply = *p; - *p += sizeof(*info->filelock_reply); - if (unlikely(*p != end)) - goto bad; + /* Skip over any unrecognized fields */ + *p = end; return 0; - bad: return -EIO; } @@ -425,18 +423,21 @@ static int parse_reply_info_create(void **p, void *end, { if (features == (u64)-1 || (features & CEPH_FEATURE_REPLY_CREATE_INODE)) { + /* Malformed reply? */ if (*p == end) { info->has_create_ino = false; } else { info->has_create_ino = true; - info->ino = ceph_decode_64(p); + ceph_decode_64_safe(p, end, info->ino, bad); } + } else { + if (*p != end) + goto bad; } - if (unlikely(*p != end)) - goto bad; + /* Skip over any unrecognized fields */ + *p = end; return 0; - bad: return -EIO; } diff --git a/fs/direct-io.c b/fs/direct-io.c index ae196784f487..9329ced91f1d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -241,9 +241,8 @@ void dio_warn_stale_pagecache(struct file *filp) } } -/** +/* * dio_complete() - called when all DIO BIO I/O has been completed - * @offset: the byte offset in the file of the completed operation * * This drops i_dio_count, lets interested parties know that a DIO operation * has completed, and calculates the resulting return code for the operation. diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e88421d9a48d..8461a6322039 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -905,7 +905,7 @@ restart: * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id - * @nr_pages: number of pages to write, 0 for best-effort dirty flushing + * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * diff --git a/fs/io_uring.c b/fs/io_uring.c index 76fdbe84aff5..67dbe0201e0d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -322,6 +322,8 @@ struct io_kiocb { #define REQ_F_FAIL_LINK 256 /* fail rest of links */ #define REQ_F_SHADOW_DRAIN 512 /* link-drain shadow req */ #define REQ_F_TIMEOUT 1024 /* timeout request */ +#define REQ_F_ISREG 2048 /* regular file */ +#define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */ u64 user_data; u32 result; u32 sequence; @@ -914,26 +916,26 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, return ret; } -static void kiocb_end_write(struct kiocb *kiocb) +static void kiocb_end_write(struct io_kiocb *req) { - if (kiocb->ki_flags & IOCB_WRITE) { - struct inode *inode = file_inode(kiocb->ki_filp); + /* + * Tell lockdep we inherited freeze protection from submission + * thread. + */ + if (req->flags & REQ_F_ISREG) { + struct inode *inode = file_inode(req->file); - /* - * Tell lockdep we inherited freeze protection from submission - * thread. - */ - if (S_ISREG(inode->i_mode)) - __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); - file_end_write(kiocb->ki_filp); + __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); } + file_end_write(req->file); } static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); - kiocb_end_write(kiocb); + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); if ((req->flags & REQ_F_LINK) && res != req->result) req->flags |= REQ_F_FAIL_LINK; @@ -945,7 +947,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); - kiocb_end_write(kiocb); + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); if ((req->flags & REQ_F_LINK) && res != req->result) req->flags |= REQ_F_FAIL_LINK; @@ -1059,8 +1062,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, if (!req->file) return -EBADF; - if (force_nonblock && !io_file_supports_async(req->file)) - force_nonblock = false; + if (S_ISREG(file_inode(req->file)->i_mode)) + req->flags |= REQ_F_ISREG; + + /* + * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so + * we know to async punt it even if it was opened O_NONBLOCK + */ + if (force_nonblock && !io_file_supports_async(req->file)) { + req->flags |= REQ_F_MUST_PUNT; + return -EAGAIN; + } kiocb->ki_pos = READ_ONCE(sqe->off); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); @@ -1081,7 +1093,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, return ret; /* don't allow async punt if RWF_NOWAIT was requested */ - if (kiocb->ki_flags & IOCB_NOWAIT) + if ((kiocb->ki_flags & IOCB_NOWAIT) || + (req->file->f_flags & O_NONBLOCK)) req->flags |= REQ_F_NOWAIT; if (force_nonblock) @@ -1382,7 +1395,9 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, * need async punt anyway, so it's more efficient to do it * here. */ - if (force_nonblock && ret2 > 0 && ret2 < read_size) + if (force_nonblock && !(req->flags & REQ_F_NOWAIT) && + (req->flags & REQ_F_ISREG) && + ret2 > 0 && ret2 < read_size) ret2 = -EAGAIN; /* Catch -EAGAIN return for forced non-blocking submission */ if (!force_nonblock || ret2 != -EAGAIN) { @@ -1447,7 +1462,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, * released so that it doesn't complain about the held lock when * we return to userspace. */ - if (S_ISREG(file_inode(file)->i_mode)) { + if (req->flags & REQ_F_ISREG) { __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); __sb_writers_release(file_inode(file)->i_sb, @@ -1884,7 +1899,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - unsigned count, req_dist, tail_index; + unsigned count; struct io_ring_ctx *ctx = req->ctx; struct list_head *entry; struct timespec64 ts; @@ -1907,21 +1922,36 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) count = 1; req->sequence = ctx->cached_sq_head + count - 1; + /* reuse it to store the count */ + req->submit.sequence = count; req->flags |= REQ_F_TIMEOUT; /* * Insertion sort, ensuring the first entry in the list is always * the one we need first. */ - tail_index = ctx->cached_cq_tail - ctx->rings->sq_dropped; - req_dist = req->sequence - tail_index; spin_lock_irq(&ctx->completion_lock); list_for_each_prev(entry, &ctx->timeout_list) { struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list); - unsigned dist; + unsigned nxt_sq_head; + long long tmp, tmp_nxt; - dist = nxt->sequence - tail_index; - if (req_dist >= dist) + /* + * Since cached_sq_head + count - 1 can overflow, use type long + * long to store it. + */ + tmp = (long long)ctx->cached_sq_head + count - 1; + nxt_sq_head = nxt->sequence - nxt->submit.sequence + 1; + tmp_nxt = (long long)nxt_sq_head + nxt->submit.sequence - 1; + + /* + * cached_sq_head may overflow, and it will never overflow twice + * once there is some timeout req still be valid. + */ + if (ctx->cached_sq_head < nxt_sq_head) + tmp += UINT_MAX; + + if (tmp >= tmp_nxt) break; } list_add(&req->list, entry); @@ -2267,7 +2297,13 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, int ret; ret = __io_submit_sqe(ctx, req, s, force_nonblock); - if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { + + /* + * We async punt it if the file wasn't marked NOWAIT, or if the file + * doesn't support non-blocking read/write attempts + */ + if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) || + (req->flags & REQ_F_MUST_PUNT))) { struct io_uring_sqe *sqe_copy; sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL); diff --git a/fs/libfs.c b/fs/libfs.c index 540611b99b9a..1463b038ffc4 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -473,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes - * @available: See .write_end of address_space_operations - * @file: " + * @file: See .write_end of address_space_operations * @mapping: " * @pos: " * @len: " diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 2e982db3e1ae..53939bf9d7d2 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1230,6 +1230,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid)); if (IS_ERR(transfer_to[USRQUOTA])) { status = PTR_ERR(transfer_to[USRQUOTA]); + transfer_to[USRQUOTA] = NULL; goto bail_unlock; } } @@ -1239,6 +1240,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid)); if (IS_ERR(transfer_to[GRPQUOTA])) { status = PTR_ERR(transfer_to[GRPQUOTA]); + transfer_to[GRPQUOTA] = NULL; goto bail_unlock; } } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 930e3d388579..699a560efbb0 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -217,7 +217,8 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb) /* At this point, we know that no more recovery threads can be * launched, so wait for any recovery completion work to * complete. */ - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); /* * Now that recovery is shut down, and the osb is about to be diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 158e5af767fd..720e9f94957e 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -377,7 +377,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) struct ocfs2_dinode *alloc = NULL; cancel_delayed_work(&osb->la_enable_wq); - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index ac9247371871..8c1f1bb1a5ce 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -132,9 +132,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR); show_val_kb(m, "ShmemPmdMapped: ", global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); - show_val_kb(m, "FileHugePages: ", + show_val_kb(m, "FileHugePages: ", global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR); - show_val_kb(m, "FilePmdMapped: ", + show_val_kb(m, "FilePmdMapped: ", global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR); #endif diff --git a/fs/proc/page.c b/fs/proc/page.c index 544d1ee15aee..7c952ee732e6 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -42,10 +42,12 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); + if (!ppage || PageSlab(ppage) || page_has_type(ppage)) pcount = 0; else @@ -216,10 +218,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (put_user(stable_page_flags(ppage), out)) { ret = -EFAULT; @@ -261,10 +264,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (ppage) ino = page_cgroup_ino(ppage); diff --git a/fs/readdir.c b/fs/readdir.c index 6e2623e57b2e..d26d5ea4de7b 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -105,9 +105,9 @@ EXPORT_SYMBOL(iterate_dir); */ static int verify_dirent_name(const char *name, int len) { - if (WARN_ON_ONCE(!len)) + if (!len) return -EIO; - if (WARN_ON_ONCE(memchr(name, '/', len))) + if (memchr(name, '/', len)) return -EIO; return 0; } diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 39dd2b908106..e9371a8e0e26 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -366,11 +366,11 @@ struct xfs_bulkstat { uint64_t bs_blocks; /* number of blocks */ uint64_t bs_xflags; /* extended flags */ - uint64_t bs_atime; /* access time, seconds */ - uint64_t bs_mtime; /* modify time, seconds */ + int64_t bs_atime; /* access time, seconds */ + int64_t bs_mtime; /* modify time, seconds */ - uint64_t bs_ctime; /* inode change time, seconds */ - uint64_t bs_btime; /* creation time, seconds */ + int64_t bs_ctime; /* inode change time, seconds */ + int64_t bs_btime; /* creation time, seconds */ uint32_t bs_gen; /* generation count */ uint32_t bs_uid; /* user id */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 90528f12bdfa..29fc933df3bf 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -326,10 +326,11 @@ static inline int bitmap_equal(const unsigned long *src1, } /** - * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third + * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 + * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f8245d67f070..5dd9c982e2cb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -202,6 +202,14 @@ struct gpio_irq_chip { bool threaded; /** + * @init_hw: optional routine to initialize hardware before + * an IRQ chip will be added. This is quite useful when + * a particular driver wants to clear IRQ related registers + * in order to avoid undesired events. + */ + int (*init_hw)(struct gpio_chip *chip); + + /** * @init_valid_mask: optional routine to initialize @valid_mask, to be * used if not all GPIO lines are valid interrupts. Sometimes some * lines just cannot fire interrupts, and this routine, when defined, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7a26d5513471..7a61ab50ca62 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -266,7 +266,8 @@ struct kvm_vcpu { struct preempt_notifier preempt_notifier; #endif int cpu; - int vcpu_id; + int vcpu_id; /* id given by userspace at creation */ + int vcpu_idx; /* index in kvm->vcpus array */ int srcu_idx; int mode; u64 requests; @@ -278,7 +279,6 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - int guest_xcr0_loaded; struct swait_queue_head wq; struct pid __rcu *pid; int sigset_active; @@ -571,13 +571,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *tmp; - int idx; - - kvm_for_each_vcpu(idx, tmp, vcpu->kvm) - if (tmp == vcpu) - return idx; - BUG(); + return vcpu->vcpu_idx; } #define kvm_for_each_memslot(memslot, slots) \ @@ -622,6 +616,7 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { @@ -813,6 +808,8 @@ void kvm_reload_remote_mmus(struct kvm *kvm); bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); +bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index ad24554f11f9..75f880c25bb8 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,7 +31,7 @@ #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -#define PHY_ID_KSZ8795 0x00221550 +#define PHY_ID_KSZ87XX 0x00221550 #define PHY_ID_KSZ9477 0x00221631 diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 682fd465df06..cfce186f0c4e 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -18,7 +18,7 @@ struct page_ext_operations { enum page_ext_flags { PAGE_EXT_OWNER, - PAGE_EXT_OWNER_ACTIVE, + PAGE_EXT_OWNER_ALLOCATED, #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, @@ -36,6 +36,7 @@ struct page_ext { unsigned long flags; }; +extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); #ifdef CONFIG_SPARSEMEM @@ -52,6 +53,13 @@ static inline void page_ext_init(void) struct page_ext *lookup_page_ext(const struct page *page); +static inline struct page_ext *page_ext_next(struct page_ext *curr) +{ + void *next = curr; + next += page_ext_size; + return next; +} + #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 61448c19a132..e9768bfc76f6 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1336,6 +1336,8 @@ extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); +extern int perf_event_period(struct perf_event *event, u64 value); +extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, @@ -1415,6 +1417,14 @@ static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } +static inline int perf_event_period(struct perf_event *event, u64 value) +{ + return -EINVAL; +} +static inline u64 perf_event_pause(struct perf_event *event, bool reset) +{ + return 0; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c2e56bd8913..67a1d86981a9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -223,6 +223,7 @@ extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); +asmlinkage void preempt_schedule_irq(void); extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4351577b14d7..7914fdaf4226 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3510,8 +3510,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); -int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto); +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, + int mac_len); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 99617e528ea2..668e25a76d69 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -393,7 +393,7 @@ struct tcp_sock { /* fastopen_rsk points to request_sock that resulted in this big * socket. Used to retransmit SYNACKs etc. */ - struct request_sock *fastopen_rsk; + struct request_sock __rcu *fastopen_rsk; u32 *saved_syn; }; @@ -447,8 +447,8 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) static inline bool tcp_passive_fastopen(const struct sock *sk) { - return (sk->sk_state == TCP_SYN_RECV && - tcp_sk(sk)->fastopen_rsk != NULL); + return sk->sk_state == TCP_SYN_RECV && + rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL; } static inline void fastopen_queue_tune(struct sock *sk, int backlog) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5921599b6dc4..86eecbd98e84 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -230,8 +230,8 @@ static inline int xa_err(void *entry) * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Two common ranges are predefined for you: - * * xa_limit_32b - [0 - UINT_MAX] - * * xa_limit_31b - [0 - INT_MAX] + * * xa_limit_32b - [0 - UINT_MAX] + * * xa_limit_31b - [0 - INT_MAX] */ struct xa_limit { u32 max; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ff45c3e1abff..4ab2c49423dc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5550,6 +5550,14 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, const char *reg_initiator_name(enum nl80211_reg_initiator initiator); /** + * regulatory_pre_cac_allowed - check if pre-CAC allowed in the current regdom + * @wiphy: wiphy for which pre-CAC capability is checked. + * + * Pre-CAC is allowed only in some regdomains (notable ETSI). + */ +bool regulatory_pre_cac_allowed(struct wiphy *wiphy); + +/** * DOC: Internal regulatory db functions * */ diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index df528a623548..ea985aa7a6c5 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -104,7 +104,7 @@ void llc_sk_reset(struct sock *sk); /* Access to a connection */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb); -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit); void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index f8712bbeb2e0..4c2cd9378699 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -52,6 +52,9 @@ struct bpf_prog; #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { + /* First cache line can be often dirtied. + * Do not place here read-mostly fields. + */ refcount_t passive; /* To decide when the network * namespace should be freed. */ @@ -60,7 +63,13 @@ struct net { */ spinlock_t rules_mod_lock; - u32 hash_mix; + unsigned int dev_unreg_count; + + unsigned int dev_base_seq; /* protected by rtnl_mutex */ + int ifindex; + + spinlock_t nsid_lock; + atomic_t fnhe_genid; struct list_head list; /* list of network namespaces */ struct list_head exit_list; /* To linked to call pernet exit @@ -76,11 +85,11 @@ struct net { #endif struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; - spinlock_t nsid_lock; struct idr netns_ids; struct ns_common ns; + struct list_head dev_base_head; struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; @@ -93,17 +102,18 @@ struct net { struct uevent_sock *uevent_sock; /* uevent socket */ - struct list_head dev_base_head; struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; - unsigned int dev_base_seq; /* protected by rtnl_mutex */ - int ifindex; - unsigned int dev_unreg_count; + /* Note that @hash_mix can be read millions times per second, + * it is critical that it is on a read_mostly cache line. + */ + u32 hash_mix; + + struct net_device *loopback_dev; /* The loopback */ /* core fib_rules */ struct list_head rules_ops; - struct net_device *loopback_dev; /* The loopback */ struct netns_core core; struct netns_mib mib; struct netns_packet packet; @@ -171,7 +181,6 @@ struct net { struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; - atomic_t fnhe_genid; } __randomize_layout; #include <linux/seq_file_net.h> diff --git a/include/net/request_sock.h b/include/net/request_sock.h index fd178d58fa84..cf8b33213bbc 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -185,7 +185,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) { - return queue->rskq_accept_head == NULL; + return READ_ONCE(queue->rskq_accept_head) == NULL; } static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, @@ -197,7 +197,7 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue req = queue->rskq_accept_head; if (req) { sk_acceptq_removed(parent); - queue->rskq_accept_head = req->dl_next; + WRITE_ONCE(queue->rskq_accept_head, req->dl_next); if (queue->rskq_accept_head == NULL) queue->rskq_accept_tail = NULL; } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 5d60f13d2347..3ab5c6bbb90b 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -610,4 +610,9 @@ static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize) return sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, datasize); } +static inline bool sctp_newsk_ready(const struct sock *sk) +{ + return sock_flag(sk, SOCK_DEAD) || sk->sk_socket; +} + #endif /* __net_sctp_h__ */ diff --git a/include/net/sock.h b/include/net/sock.h index 2c53f1a1d905..f69b58bff7e5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -878,12 +878,17 @@ static inline bool sk_acceptq_is_full(const struct sock *sk) */ static inline int sk_stream_min_wspace(const struct sock *sk) { - return sk->sk_wmem_queued >> 1; + return READ_ONCE(sk->sk_wmem_queued) >> 1; } static inline int sk_stream_wspace(const struct sock *sk) { - return sk->sk_sndbuf - sk->sk_wmem_queued; + return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); +} + +static inline void sk_wmem_queued_add(struct sock *sk, int val) +{ + WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } void sk_stream_write_space(struct sock *sk); @@ -1207,7 +1212,7 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { - if (sk->sk_wmem_queued >= sk->sk_sndbuf) + if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? @@ -1467,7 +1472,7 @@ DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - sk->sk_wmem_queued -= skb->truesize; + sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && !sk->sk_tx_skb_cache && !skb_cloned(skb)) { @@ -2014,7 +2019,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } @@ -2220,10 +2225,14 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band) static inline void sk_stream_moderate_sndbuf(struct sock *sk) { - if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) { - sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); - sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF); - } + u32 val; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); + + WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, @@ -2251,7 +2260,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); */ static inline bool sock_writeable(const struct sock *sk) { - return refcount_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1); + return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); } static inline gfp_t gfp_any(void) @@ -2271,7 +2280,9 @@ static inline long sock_sndtimeo(const struct sock *sk, bool noblock) static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { - return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1; + int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); + + return v ?: 1; } /* Alas, with timeout socket operations are not restartable. diff --git a/include/net/tcp.h b/include/net/tcp.h index c9a3f9688223..ab4eb5eb5d07 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -258,7 +258,7 @@ static inline bool tcp_under_memory_pressure(const struct sock *sk) mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; - return tcp_memory_pressure; + return READ_ONCE(tcp_memory_pressure); } /* * The next routines deal with comparing 32 bit unsigned ints @@ -1380,13 +1380,14 @@ static inline int tcp_win_from_space(const struct sock *sk, int space) /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { - return tcp_win_from_space(sk, sk->sk_rcvbuf - sk->sk_backlog.len - + return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - + READ_ONCE(sk->sk_backlog.len) - atomic_read(&sk->sk_rmem_alloc)); } static inline int tcp_full_space(const struct sock *sk) { - return tcp_win_from_space(sk, sk->sk_rcvbuf); + return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } extern void tcp_openreq_init_rwin(struct request_sock *req, @@ -1916,7 +1917,8 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); - u32 notsent_bytes = tp->write_seq - tp->snd_nxt; + u32 notsent_bytes = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 3810b340551c..6bd5ed695a5e 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -32,6 +32,7 @@ extern int scsi_ioctl_reset(struct scsi_device *, int __user *); struct scsi_eh_save { /* saved state */ int result; + unsigned int resid_len; int eh_eflags; enum dma_data_direction data_direction; unsigned underflow; diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h index 0fd39295b426..057d2a2d0bd0 100644 --- a/include/sound/hda_register.h +++ b/include/sound/hda_register.h @@ -264,6 +264,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; #define AZX_REG_ML_LOUTPAY 0x20 #define AZX_REG_ML_LINPAY 0x30 +/* bit0 is reserved, with BIT(1) mapping to stream1 */ +#define ML_LOSIDV_STREAM_MASK 0xFFFE + #define ML_LCTL_SCF_MASK 0xF #define AZX_MLCTL_SPA (0x1 << 16) #define AZX_MLCTL_CPA (0x1 << 23) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index edc5c887a44c..191fe447f990 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -519,10 +519,10 @@ TRACE_EVENT(rxrpc_local, ); TRACE_EVENT(rxrpc_peer, - TP_PROTO(struct rxrpc_peer *peer, enum rxrpc_peer_trace op, + TP_PROTO(unsigned int peer_debug_id, enum rxrpc_peer_trace op, int usage, const void *where), - TP_ARGS(peer, op, usage, where), + TP_ARGS(peer_debug_id, op, usage, where), TP_STRUCT__entry( __field(unsigned int, peer ) @@ -532,7 +532,7 @@ TRACE_EVENT(rxrpc_peer, ), TP_fast_assign( - __entry->peer = peer->debug_id; + __entry->peer = peer_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; @@ -546,10 +546,10 @@ TRACE_EVENT(rxrpc_peer, ); TRACE_EVENT(rxrpc_conn, - TP_PROTO(struct rxrpc_connection *conn, enum rxrpc_conn_trace op, + TP_PROTO(unsigned int conn_debug_id, enum rxrpc_conn_trace op, int usage, const void *where), - TP_ARGS(conn, op, usage, where), + TP_ARGS(conn_debug_id, op, usage, where), TP_STRUCT__entry( __field(unsigned int, conn ) @@ -559,7 +559,7 @@ TRACE_EVENT(rxrpc_conn, ), TP_fast_assign( - __entry->conn = conn->debug_id; + __entry->conn = conn_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; @@ -606,10 +606,10 @@ TRACE_EVENT(rxrpc_client, ); TRACE_EVENT(rxrpc_call, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_call_trace op, + TP_PROTO(unsigned int call_debug_id, enum rxrpc_call_trace op, int usage, const void *where, const void *aux), - TP_ARGS(call, op, usage, where, aux), + TP_ARGS(call_debug_id, op, usage, where, aux), TP_STRUCT__entry( __field(unsigned int, call ) @@ -620,7 +620,7 @@ TRACE_EVENT(rxrpc_call, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index a0c4b8a30966..51fe9f6719eb 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -82,7 +82,7 @@ TRACE_EVENT(sock_rcvqueue_full, TP_fast_assign( __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->truesize = skb->truesize; - __entry->sk_rcvbuf = sk->sk_rcvbuf; + __entry->sk_rcvbuf = READ_ONCE(sk->sk_rcvbuf); ), TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d", @@ -115,7 +115,7 @@ TRACE_EVENT(sock_exceed_buf_limit, __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->sysctl_wmem = sk_get_wmem0(sk, prot); __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); - __entry->wmem_queued = sk->sk_wmem_queued; + __entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued); __entry->kind = kind; ), diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index fb47c0fad6a6..e6f17c8e2dba 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1006,8 +1006,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PMU_EVENT_FILTER 173 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174 #define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175 -#define KVM_CAP_ARM_NISV_TO_USER 176 -#define KVM_CAP_ARM_INJECT_EXT_DABT 177 +#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176 +#define KVM_CAP_ARM_NISV_TO_USER 177 +#define KVM_CAP_ARM_INJECT_EXT_DABT 178 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/kernel/events/core.c b/kernel/events/core.c index 9ec0b0bfddbd..fc9f5ebf4849 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5029,6 +5029,24 @@ static void _perf_event_reset(struct perf_event *event) perf_event_update_userpage(event); } +/* Assume it's not an event with inherit set. */ +u64 perf_event_pause(struct perf_event *event, bool reset) +{ + struct perf_event_context *ctx; + u64 count; + + ctx = perf_event_ctx_lock(event); + WARN_ON_ONCE(event->attr.inherit); + _perf_event_disable(event); + count = local64_read(&event->count); + if (reset) + local64_set(&event->count, 0); + perf_event_ctx_unlock(event, ctx); + + return count; +} +EXPORT_SYMBOL_GPL(perf_event_pause); + /* * Holding the top-level event's child_mutex means that any * descendant process that has inherited this event will block @@ -5106,16 +5124,11 @@ static int perf_event_check_period(struct perf_event *event, u64 value) return event->pmu->check_period(event, value); } -static int perf_event_period(struct perf_event *event, u64 __user *arg) +static int _perf_event_period(struct perf_event *event, u64 value) { - u64 value; - if (!is_sampling_event(event)) return -EINVAL; - if (copy_from_user(&value, arg, sizeof(value))) - return -EFAULT; - if (!value) return -EINVAL; @@ -5133,6 +5146,19 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) return 0; } +int perf_event_period(struct perf_event *event, u64 value) +{ + struct perf_event_context *ctx; + int ret; + + ctx = perf_event_ctx_lock(event); + ret = _perf_event_period(event, value); + perf_event_ctx_unlock(event, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(perf_event_period); + static const struct file_operations perf_fops; static inline int perf_fget_light(int fd, struct fd *p) @@ -5176,8 +5202,14 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon return _perf_event_refresh(event, arg); case PERF_EVENT_IOC_PERIOD: - return perf_event_period(event, (u64 __user *)arg); + { + u64 value; + if (copy_from_user(&value, (u64 __user *)arg, sizeof(value))) + return -EFAULT; + + return _perf_event_period(event, value); + } case PERF_EVENT_IOC_ID: { u64 id = primary_event_id(event); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 94d38a39d72e..c74761004ee5 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -474,14 +474,17 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, struct vm_area_struct *vma; int ret, is_register, ref_ctr_updated = 0; bool orig_page_huge = false; + unsigned int gup_flags = FOLL_FORCE; is_register = is_swbp_insn(&opcode); uprobe = container_of(auprobe, struct uprobe, arch); retry: + if (is_register) + gup_flags |= FOLL_SPLIT_PMD; /* Read the page with vaddr into memory */ - ret = get_user_pages_remote(NULL, mm, vaddr, 1, - FOLL_FORCE | FOLL_SPLIT_PMD, &old_page, &vma, NULL); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags, + &old_page, &vma, NULL); if (ret <= 0) return ret; @@ -489,6 +492,12 @@ retry: if (ret <= 0) goto put_old; + if (WARN(!is_register && PageCompound(old_page), + "uprobe unregister should never work on compound page\n")) { + ret = -EINVAL; + goto put_old; + } + /* We are going to replace instruction, update ref_ctr. */ if (!ref_ctr_updated && uprobe->ref_ctr_offset) { ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index aff79e461fc9..5a0fc0b0403a 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -71,10 +71,13 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 find $cpio_dir -type f -print0 | xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' -# Create archive and try to normalize metadata for reproducibility -tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ - --owner=0 --group=0 --sort=name --numeric-owner \ - -Jcf $tarfile -C $cpio_dir/ . > /dev/null +# Create archive and try to normalize metadata for reproducibility. +# For compatibility with older versions of tar, files are fed to tar +# pre-sorted, as --sort=name might not be available. +find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \ + tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --owner=0 --group=0 --numeric-owner --no-recursion \ + -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null echo "$src_files_md5" > kernel/kheaders.md5 echo "$obj_files_md5" >> kernel/kheaders.md5 diff --git a/kernel/kthread.c b/kernel/kthread.c index 621467c33fef..b262f47046ca 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -866,9 +866,9 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); -void __kthread_queue_delayed_work(struct kthread_worker *worker, - struct kthread_delayed_work *dwork, - unsigned long delay) +static void __kthread_queue_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay) { struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; diff --git a/kernel/power/main.c b/kernel/power/main.c index e8710d179b35..e26de7af520b 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -15,6 +15,7 @@ #include <linux/seq_file.h> #include <linux/suspend.h> #include <linux/syscalls.h> +#include <linux/pm_runtime.h> #include "power.h" diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index c7031a22aa7b..998d50ee2d9b 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -7,6 +7,7 @@ * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> */ +#include <linux/compiler.h> #include <linux/completion.h> #include <linux/cpu.h> #include <linux/init.h> @@ -167,7 +168,7 @@ static void set_state(struct multi_stop_data *msdata, /* Reset ack counter. */ atomic_set(&msdata->thread_ack, msdata->num_threads); smp_wmb(); - msdata->state = newstate; + WRITE_ONCE(msdata->state, newstate); } /* Last one to ack a state moves to the next state. */ @@ -186,7 +187,7 @@ void __weak stop_machine_yield(const struct cpumask *cpumask) static int multi_cpu_stop(void *data) { struct multi_stop_data *msdata = data; - enum multi_stop_state curstate = MULTI_STOP_NONE; + enum multi_stop_state newstate, curstate = MULTI_STOP_NONE; int cpu = smp_processor_id(), err = 0; const struct cpumask *cpumask; unsigned long flags; @@ -210,8 +211,9 @@ static int multi_cpu_stop(void *data) do { /* Chill out and ensure we re-read multi_stop_state. */ stop_machine_yield(cpumask); - if (msdata->state != curstate) { - curstate = msdata->state; + newstate = READ_ONCE(msdata->state); + if (newstate != curstate) { + curstate = newstate; switch (curstate) { case MULTI_STOP_DISABLE_IRQ: local_irq_disable(); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 00fcea236eba..b6f2f35d0bcf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -163,7 +163,7 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); #ifdef CONFIG_SPARC #endif -#ifdef __hppa__ +#ifdef CONFIG_PARISC extern int pwrsw_enabled; #endif @@ -620,7 +620,7 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef __hppa__ +#ifdef CONFIG_PARISC { .procname = "soft-power", .data = &pwrsw_enabled, diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 0d4dc241c0fb..65605530ee34 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -164,7 +164,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, struct hrtimer_clock_base *base; for (;;) { - base = timer->base; + base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) @@ -244,7 +244,7 @@ again: return base; /* See the comment in lock_hrtimer_base() */ - timer->base = &migration_base; + WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); @@ -253,10 +253,10 @@ again: raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; - timer->base = base; + WRITE_ONCE(timer->base, base); goto again; } - timer->base = new_base; + WRITE_ONCE(timer->base, new_base); } else { if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index ae25e2fa2187..f25eb111c051 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -2,6 +2,7 @@ #include <linux/export.h> #include <linux/generic-radix-tree.h> #include <linux/gfp.h> +#include <linux/kmemleak.h> #define GENRADIX_ARY (PAGE_SIZE / sizeof(struct genradix_node *)) #define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) @@ -75,6 +76,27 @@ void *__genradix_ptr(struct __genradix *radix, size_t offset) } EXPORT_SYMBOL(__genradix_ptr); +static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) +{ + struct genradix_node *node; + + node = (struct genradix_node *)__get_free_page(gfp_mask|__GFP_ZERO); + + /* + * We're using pages (not slab allocations) directly for kernel data + * structures, so we need to explicitly inform kmemleak of them in order + * to avoid false positive memory leak reports. + */ + kmemleak_alloc(node, PAGE_SIZE, 1, gfp_mask); + return node; +} + +static inline void genradix_free_node(struct genradix_node *node) +{ + kmemleak_free(node); + free_page((unsigned long)node); +} + /* * Returns pointer to the specified byte @offset within @radix, allocating it if * necessary - newly allocated slots are always zeroed out: @@ -97,8 +119,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, break; if (!new_node) { - new_node = (void *) - __get_free_page(gfp_mask|__GFP_ZERO); + new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } @@ -121,8 +142,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, n = READ_ONCE(*p); if (!n) { if (!new_node) { - new_node = (void *) - __get_free_page(gfp_mask|__GFP_ZERO); + new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } @@ -133,7 +153,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, } if (new_node) - free_page((unsigned long) new_node); + genradix_free_node(new_node); return &n->data[offset]; } @@ -191,7 +211,7 @@ static void genradix_free_recurse(struct genradix_node *n, unsigned level) genradix_free_recurse(n->children[i], level - 1); } - free_page((unsigned long) n); + genradix_free_node(n); } int __genradix_prealloc(struct __genradix *radix, size_t size, diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 9729f271d150..9742e5cb853a 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -297,6 +297,32 @@ out: return 1; } +static int __init do_kmem_cache_size_bulk(int size, int *total_failures) +{ + struct kmem_cache *c; + int i, iter, maxiter = 1024; + int num, bytes; + bool fail = false; + void *objects[10]; + + c = kmem_cache_create("test_cache", size, size, 0, NULL); + for (iter = 0; (iter < maxiter) && !fail; iter++) { + num = kmem_cache_alloc_bulk(c, GFP_KERNEL, ARRAY_SIZE(objects), + objects); + for (i = 0; i < num; i++) { + bytes = count_nonzero_bytes(objects[i], size); + if (bytes) + fail = true; + fill_with_garbage(objects[i], size); + } + + if (num) + kmem_cache_free_bulk(c, num, objects); + } + *total_failures += fail; + return 1; +} + /* * Test kmem_cache allocation by creating caches of different sizes, with and * without constructors, with and without SLAB_TYPESAFE_BY_RCU. @@ -318,6 +344,7 @@ static int __init test_kmemcache(int *total_failures) num_tests += do_kmem_cache_size(size, ctor, rcu, zero, &failures); } + num_tests += do_kmem_cache_size_bulk(size, &failures); } REPORT_FAILURES_IN_FN(); *total_failures += failures; diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c index e365ace06538..5ff04d8fe971 100644 --- a/lib/test_user_copy.c +++ b/lib/test_user_copy.c @@ -47,18 +47,35 @@ static bool is_zeroed(void *from, size_t size) static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size) { int ret = 0; - size_t start, end, i; - size_t zero_start = size / 4; - size_t zero_end = size - zero_start; + size_t start, end, i, zero_start, zero_end; + + if (test(size < 2 * PAGE_SIZE, "buffer too small")) + return -EINVAL; + + /* + * We want to cross a page boundary to exercise the code more + * effectively. We also don't want to make the size we scan too large, + * otherwise the test can take a long time and cause soft lockups. So + * scan a 1024 byte region across the page boundary. + */ + size = 1024; + start = PAGE_SIZE - (size / 2); + + kmem += start; + umem += start; + + zero_start = size / 4; + zero_end = size - zero_start; /* - * We conduct a series of check_nonzero_user() tests on a block of memory - * with the following byte-pattern (trying every possible [start,end] - * pair): + * We conduct a series of check_nonzero_user() tests on a block of + * memory with the following byte-pattern (trying every possible + * [start,end] pair): * * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ] * - * And we verify that check_nonzero_user() acts identically to memchr_inv(). + * And we verify that check_nonzero_user() acts identically to + * memchr_inv(). */ memset(kmem, 0x0, size); @@ -93,11 +110,13 @@ static int test_copy_struct_from_user(char *kmem, char __user *umem, size_t ksize, usize; umem_src = kmalloc(size, GFP_KERNEL); - if ((ret |= test(umem_src == NULL, "kmalloc failed"))) + ret = test(umem_src == NULL, "kmalloc failed"); + if (ret) goto out_free; expected = kmalloc(size, GFP_KERNEL); - if ((ret |= test(expected == NULL, "kmalloc failed"))) + ret = test(expected == NULL, "kmalloc failed"); + if (ret) goto out_free; /* Fill umem with a fixed byte pattern. */ diff --git a/mm/compaction.c b/mm/compaction.c index ce08b39d85d4..672d3c78c6ab 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -270,14 +270,15 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, /* Ensure the start of the pageblock or zone is online and valid */ block_pfn = pageblock_start_pfn(pfn); - block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn)); + block_pfn = max(block_pfn, zone->zone_start_pfn); + block_page = pfn_to_online_page(block_pfn); if (block_page) { page = block_page; pfn = block_pfn; } /* Ensure the end of the pageblock or zone is online and valid */ - block_pfn += pageblock_nr_pages; + block_pfn = pageblock_end_pfn(pfn) - 1; block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); end_page = pfn_to_online_page(block_pfn); if (!end_page) @@ -303,7 +304,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, page += (1 << PAGE_ALLOC_COSTLY_ORDER); pfn += (1 << PAGE_ALLOC_COSTLY_ORDER); - } while (page < end_page); + } while (page <= end_page); return false; } diff --git a/mm/filemap.c b/mm/filemap.c index 1146fcfa3215..85b7d087eb45 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -40,6 +40,7 @@ #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> +#include <linux/ramfs.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -1973,7 +1973,8 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, } static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { unsigned long pte_end; struct page *head, *page; @@ -1986,7 +1987,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, pte = READ_ONCE(*ptep); - if (!pte_access_permitted(pte, write)) + if (!pte_access_permitted(pte, flags & FOLL_WRITE)) return 0; /* hugepages are never "special" */ @@ -2023,7 +2024,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, } static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned int pdshift, unsigned long end, int write, + unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { pte_t *ptep; @@ -2033,7 +2034,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr)) + if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr)) return 0; } while (ptep++, addr = next, addr != end); @@ -2041,7 +2042,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, } #else static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, int write, + unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; @@ -2049,7 +2050,8 @@ static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, #endif /* CONFIG_ARCH_HAS_HUGEPD */ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { struct page *head, *page; int refs; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c5cb6dcd6c69..13cc93785006 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2789,8 +2789,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) ds_queue->split_queue_len--; list_del(page_deferred_list(head)); } - if (mapping) - __dec_node_page_state(page, NR_SHMEM_THPS); + if (mapping) { + if (PageSwapBacked(page)) + __dec_node_page_state(page, NR_SHMEM_THPS); + else + __dec_node_page_state(page, NR_FILE_THPS); + } + spin_unlock(&ds_queue->split_queue_lock); __split_huge_page(page, list, end, flags); if (PageSwapCache(head)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ef37c85423a5..b45a95363a84 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1084,11 +1084,10 @@ static bool pfn_range_valid_gigantic(struct zone *z, struct page *page; for (i = start_pfn; i < end_pfn; i++) { - if (!pfn_valid(i)) + page = pfn_to_online_page(i); + if (!page) return false; - page = pfn_to_page(i); - if (page_zone(page) != z) return false; diff --git a/mm/init-mm.c b/mm/init-mm.c index fb1e15028ef0..19603302a77f 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -5,6 +5,7 @@ #include <linux/spinlock.h> #include <linux/list.h> #include <linux/cpumask.h> +#include <linux/mman.h> #include <linux/atomic.h> #include <linux/user_namespace.h> diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 03a8d84badad..244607663363 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -527,6 +527,16 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) } /* + * Remove an object from the object_tree_root and object_list. Must be called + * with the kmemleak_lock held _if_ kmemleak is still enabled. + */ +static void __remove_object(struct kmemleak_object *object) +{ + rb_erase(&object->rb_node, &object_tree_root); + list_del_rcu(&object->object_list); +} + +/* * Look up an object in the object search tree and remove it from both * object_tree_root and object_list. The returned object's use_count should be * at least 1, as initially set by create_object(). @@ -538,10 +548,8 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali write_lock_irqsave(&kmemleak_lock, flags); object = lookup_object(ptr, alias); - if (object) { - rb_erase(&object->rb_node, &object_tree_root); - list_del_rcu(&object->object_list); - } + if (object) + __remove_object(object); write_unlock_irqrestore(&kmemleak_lock, flags); return object; @@ -1834,12 +1842,16 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { - struct kmemleak_object *object; + struct kmemleak_object *object, *tmp; - rcu_read_lock(); - list_for_each_entry_rcu(object, &object_list, object_list) - delete_object_full(object->pointer); - rcu_read_unlock(); + /* + * Kmemleak has already been disabled, no need for RCU list traversal + * or kmemleak_lock held. + */ + list_for_each_entry_safe(object, tmp, &object_list, object_list) { + __remove_object(object); + __delete_object(object); + } } /* diff --git a/mm/memblock.c b/mm/memblock.c index 7d4f61ae666a..c4b16cae2bc9 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1356,9 +1356,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, align = SMP_CACHE_BYTES; } - if (end > memblock.current_limit) - end = memblock.current_limit; - again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); @@ -1469,6 +1466,9 @@ static void * __init memblock_alloc_internal( if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); + if (max_addr > memblock.current_limit) + max_addr = memblock.current_limit; + alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid); /* retry allocation without lower limit */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bdac56009a38..363106578876 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5420,6 +5420,8 @@ static int mem_cgroup_move_account(struct page *page, struct mem_cgroup *from, struct mem_cgroup *to) { + struct lruvec *from_vec, *to_vec; + struct pglist_data *pgdat; unsigned long flags; unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret; @@ -5443,11 +5445,15 @@ static int mem_cgroup_move_account(struct page *page, anon = PageAnon(page); + pgdat = page_pgdat(page); + from_vec = mem_cgroup_lruvec(pgdat, from); + to_vec = mem_cgroup_lruvec(pgdat, to); + spin_lock_irqsave(&from->move_lock, flags); if (!anon && page_mapped(page)) { - __mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages); - __mod_memcg_state(to, NR_FILE_MAPPED, nr_pages); + __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); } /* @@ -5459,14 +5465,14 @@ static int mem_cgroup_move_account(struct page *page, struct address_space *mapping = page_mapping(page); if (mapping_cap_account_dirty(mapping)) { - __mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages); - __mod_memcg_state(to, NR_FILE_DIRTY, nr_pages); + __mod_lruvec_state(from_vec, NR_FILE_DIRTY, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_DIRTY, nr_pages); } } if (PageWriteback(page)) { - __mod_memcg_state(from, NR_WRITEBACK, -nr_pages); - __mod_memcg_state(to, NR_WRITEBACK, nr_pages); + __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages); + __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7ef849da8278..3151c87dff73 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -199,7 +199,6 @@ struct to_kill { struct task_struct *tsk; unsigned long addr; short size_shift; - char addr_valid; }; /* @@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } } tk->addr = page_address_in_vma(p, vma); - tk->addr_valid = 1; if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(p, vma); else tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; /* - * In theory we don't have to kill when the page was - * munmaped. But it could be also a mremap. Since that's - * likely very rare kill anyways just out of paranoia, but use - * a SIGKILL because the error is not contained anymore. + * Send SIGKILL if "tk->addr == -EFAULT". Also, as + * "tk->size_shift" is always non-zero for !is_zone_device_page(), + * so "tk->size_shift == 0" effectively checks no mapping on + * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times + * to a process' address space, it's possible not all N VMAs + * contain mappings for the page, but at least one VMA does. + * Only deliver SIGBUS with payload derived from the VMA that + * has a mapping for the page. */ - if (tk->addr == -EFAULT || tk->size_shift == 0) { + if (tk->addr == -EFAULT) { pr_info("Memory failure: Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); - tk->addr_valid = 0; + } else if (tk->size_shift == 0) { + kfree(tk); + return; } get_task_struct(tsk); tk->tsk = tsk; @@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * make sure the process doesn't catch the * signal and then access the memory. Just kill it. */ - if (fail || tk->addr_valid == 0) { + if (fail || tk->addr == -EFAULT) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); do_send_sig_info(SIGKILL, SEND_SIG_PRIV, @@ -1253,17 +1257,19 @@ int memory_failure(unsigned long pfn, int flags) if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); - if (!pfn_valid(pfn)) { + p = pfn_to_online_page(pfn); + if (!p) { + if (pfn_valid(pfn)) { + pgmap = get_dev_pagemap(pfn, NULL); + if (pgmap) + return memory_failure_dev_pagemap(pfn, flags, + pgmap); + } pr_err("Memory failure: %#lx: memory outside kernel control\n", pfn); return -ENXIO; } - pgmap = get_dev_pagemap(pfn, NULL); - if (pgmap) - return memory_failure_dev_pagemap(pfn, flags, pgmap); - - p = pfn_to_page(pfn); if (PageHuge(p)) return memory_failure_hugetlb(pfn, flags); if (TestSetPageHWPoison(p)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b1be791f772d..df570e5c71cc 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -436,67 +436,25 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, zone_span_writeunlock(zone); } -static void shrink_pgdat_span(struct pglist_data *pgdat, - unsigned long start_pfn, unsigned long end_pfn) +static void update_pgdat_span(struct pglist_data *pgdat) { - unsigned long pgdat_start_pfn = pgdat->node_start_pfn; - unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */ - unsigned long pgdat_end_pfn = p; - unsigned long pfn; - int nid = pgdat->node_id; - - if (pgdat_start_pfn == start_pfn) { - /* - * If the section is smallest section in the pgdat, it need - * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages. - * In this case, we find second smallest valid mem_section - * for shrinking zone. - */ - pfn = find_smallest_section_pfn(nid, NULL, end_pfn, - pgdat_end_pfn); - if (pfn) { - pgdat->node_start_pfn = pfn; - pgdat->node_spanned_pages = pgdat_end_pfn - pfn; - } - } else if (pgdat_end_pfn == end_pfn) { - /* - * If the section is biggest section in the pgdat, it need - * shrink pgdat->node_spanned_pages. - * In this case, we find second biggest valid mem_section for - * shrinking zone. - */ - pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn, - start_pfn); - if (pfn) - pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1; - } - - /* - * If the section is not biggest or smallest mem_section in the pgdat, - * it only creates a hole in the pgdat. So in this case, we need not - * change the pgdat. - * But perhaps, the pgdat has only hole data. Thus it check the pgdat - * has only hole or not. - */ - pfn = pgdat_start_pfn; - for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) - continue; - - if (pfn_to_nid(pfn) != nid) - continue; + unsigned long node_start_pfn = 0, node_end_pfn = 0; + struct zone *zone; - /* Skip range to be removed */ - if (pfn >= start_pfn && pfn < end_pfn) - continue; + for (zone = pgdat->node_zones; + zone < pgdat->node_zones + MAX_NR_ZONES; zone++) { + unsigned long zone_end_pfn = zone->zone_start_pfn + + zone->spanned_pages; - /* If we find valid section, we have nothing to do */ - return; + /* No need to lock the zones, they can't change. */ + if (zone_end_pfn > node_end_pfn) + node_end_pfn = zone_end_pfn; + if (zone->zone_start_pfn < node_start_pfn) + node_start_pfn = zone->zone_start_pfn; } - /* The pgdat has no valid section */ - pgdat->node_start_pfn = 0; - pgdat->node_spanned_pages = 0; + pgdat->node_start_pfn = node_start_pfn; + pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } static void __remove_zone(struct zone *zone, unsigned long start_pfn, @@ -507,7 +465,7 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); - shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages); + update_pgdat_span(pgdat); pgdat_resize_unlock(zone->zone_pgdat, &flags); } diff --git a/mm/memremap.c b/mm/memremap.c index 68204912cc0a..03ccbdfeb697 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -103,6 +103,7 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) void memunmap_pages(struct dev_pagemap *pgmap) { struct resource *res = &pgmap->res; + struct page *first_page; unsigned long pfn; int nid; @@ -111,14 +112,16 @@ void memunmap_pages(struct dev_pagemap *pgmap) put_page(pfn_to_page(pfn)); dev_pagemap_cleanup(pgmap); + /* make sure to access a memmap that was actually initialized */ + first_page = pfn_to_page(pfn_first(pgmap)); + /* pages are dead and unused, undo the arch mapping */ - nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start))); + nid = page_to_nid(first_page); mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - pfn = PHYS_PFN(res->start); - __remove_pages(page_zone(pfn_to_page(pfn)), pfn, - PHYS_PFN(resource_size(res)), NULL); + __remove_pages(page_zone(first_page), PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), NULL); } else { arch_remove_memory(nid, res->start, resource_size(res), pgmap_altmap(pgmap)); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c0b2e0306720..ecc3dbad606b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4473,12 +4473,14 @@ retry_cpuset: if (page) goto got_pg; - if (order >= pageblock_order && (gfp_mask & __GFP_IO)) { + if (order >= pageblock_order && (gfp_mask & __GFP_IO) && + !(gfp_mask & __GFP_RETRY_MAYFAIL)) { /* * If allocating entire pageblock(s) and compaction * failed because all zones are below low watermarks * or is prohibited because it recently failed at this - * order, fail immediately. + * order, fail immediately unless the allocator has + * requested compaction and reclaim retry. * * Reclaim is * - potentially very expensive because zones are far diff --git a/mm/page_ext.c b/mm/page_ext.c index 5f5769c7db3b..4ade843ff588 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -67,8 +67,9 @@ static struct page_ext_operations *page_ext_ops[] = { #endif }; +unsigned long page_ext_size = sizeof(struct page_ext); + static unsigned long total_usage; -static unsigned long extra_mem; static bool __init invoke_need_callbacks(void) { @@ -78,9 +79,8 @@ static bool __init invoke_need_callbacks(void) for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need && page_ext_ops[i]->need()) { - page_ext_ops[i]->offset = sizeof(struct page_ext) + - extra_mem; - extra_mem += page_ext_ops[i]->size; + page_ext_ops[i]->offset = page_ext_size; + page_ext_size += page_ext_ops[i]->size; need = true; } } @@ -99,14 +99,9 @@ static void __init invoke_init_callbacks(void) } } -static unsigned long get_entry_size(void) -{ - return sizeof(struct page_ext) + extra_mem; -} - static inline struct page_ext *get_entry(void *base, unsigned long index) { - return base + get_entry_size() * index; + return base + page_ext_size * index; } #if !defined(CONFIG_SPARSEMEM) @@ -156,7 +151,7 @@ static int __init alloc_node_page_ext(int nid) !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; - table_size = get_entry_size() * nr_pages; + table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), @@ -234,7 +229,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) if (section->page_ext) return 0; - table_size = get_entry_size() * PAGES_PER_SECTION; + table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* @@ -254,7 +249,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; - section->page_ext = (void *)base - get_entry_size() * pfn; + section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } @@ -267,7 +262,7 @@ static void free_page_ext(void *addr) struct page *page = virt_to_page(addr); size_t table_size; - table_size = get_entry_size() * PAGES_PER_SECTION; + table_size = page_ext_size * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); kmemleak_free(addr); diff --git a/mm/page_owner.c b/mm/page_owner.c index dee931184788..18ecde9f45b2 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -24,12 +24,10 @@ struct page_owner { short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; -#ifdef CONFIG_DEBUG_PAGEALLOC depot_stack_handle_t free_handle; -#endif }; -static bool page_owner_disabled = true; +static bool page_owner_enabled = false; DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; @@ -44,7 +42,7 @@ static int __init early_page_owner_param(char *buf) return -EINVAL; if (strcmp(buf, "on") == 0) - page_owner_disabled = false; + page_owner_enabled = true; return 0; } @@ -52,10 +50,7 @@ early_param("page_owner", early_page_owner_param); static bool need_page_owner(void) { - if (page_owner_disabled) - return false; - - return true; + return page_owner_enabled; } static __always_inline depot_stack_handle_t create_dummy_stack(void) @@ -84,7 +79,7 @@ static noinline void register_early_stack(void) static void init_page_owner(void) { - if (page_owner_disabled) + if (!page_owner_enabled) return; register_dummy_stack(); @@ -148,25 +143,19 @@ void __reset_page_owner(struct page *page, unsigned int order) { int i; struct page_ext *page_ext; -#ifdef CONFIG_DEBUG_PAGEALLOC depot_stack_handle_t handle = 0; struct page_owner *page_owner; - if (debug_pagealloc_enabled()) - handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); -#endif + handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; for (i = 0; i < (1 << order); i++) { - page_ext = lookup_page_ext(page + i); - if (unlikely(!page_ext)) - continue; - __clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled()) { - page_owner = get_page_owner(page_ext); - page_owner->free_handle = handle; - } -#endif + __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_owner = get_page_owner(page_ext); + page_owner->free_handle = handle; + page_ext = page_ext_next(page_ext); } } @@ -184,9 +173,9 @@ static inline void __set_page_owner_handle(struct page *page, page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); - __set_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - page_ext = lookup_page_ext(page + i); + page_ext = page_ext_next(page_ext); } } @@ -224,12 +213,10 @@ void __split_page_owner(struct page *page, unsigned int order) if (unlikely(!page_ext)) return; - page_owner = get_page_owner(page_ext); - page_owner->order = 0; - for (i = 1; i < (1 << order); i++) { - page_ext = lookup_page_ext(page + i); + for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; + page_ext = page_ext_next(page_ext); } } @@ -260,7 +247,7 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) * the new page, which will be freed. */ __set_bit(PAGE_EXT_OWNER, &new_ext->flags); - __set_bit(PAGE_EXT_OWNER_ACTIVE, &new_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); } void pagetypeinfo_showmixedcount_print(struct seq_file *m, @@ -284,7 +271,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { - if (!pfn_valid(pfn)) { + page = pfn_to_online_page(pfn); + if (!page) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } @@ -292,13 +280,13 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); - page = pfn_to_page(pfn); pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { if (!pfn_valid_within(pfn)) continue; + /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); if (page_zone(page) != zone) @@ -320,7 +308,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, if (unlikely(!page_ext)) continue; - if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); @@ -435,7 +423,7 @@ void __dump_page_owner(struct page *page) return; } - if (test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) pr_alert("page_owner tracks the page as allocated\n"); else pr_alert("page_owner tracks the page as freed\n"); @@ -451,7 +439,6 @@ void __dump_page_owner(struct page *page) stack_trace_print(entries, nr_entries, 0); } -#ifdef CONFIG_DEBUG_PAGEALLOC handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); @@ -460,7 +447,6 @@ void __dump_page_owner(struct page *page) pr_alert("page last free stack trace:\n"); stack_trace_print(entries, nr_entries, 0); } -#endif if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", @@ -527,7 +513,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ - if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); diff --git a/mm/rmap.c b/mm/rmap.c index d9a23bb773bf..0c7b2a9400d4 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -61,6 +61,7 @@ #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> +#include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> diff --git a/mm/slab.c b/mm/slab.c index 9df370558e5d..66e5d8032bae 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4206,9 +4206,12 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, /** * __ksize -- Uninstrumented ksize. + * @objp: pointer to the object * * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same * safety checks as ksize() with KASAN instrumentation enabled. + * + * Return: size of the actual memory used by @objp in bytes */ size_t __ksize(const void *objp) { diff --git a/mm/slab_common.c b/mm/slab_common.c index c29f03adca91..f9fb27b4c843 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -178,10 +178,13 @@ static int init_memcg_params(struct kmem_cache *s, static void destroy_memcg_params(struct kmem_cache *s) { - if (is_root_cache(s)) + if (is_root_cache(s)) { kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); - else + } else { + mem_cgroup_put(s->memcg_params.memcg); + WRITE_ONCE(s->memcg_params.memcg, NULL); percpu_ref_exit(&s->memcg_params.refcnt); + } } static void free_memcg_params(struct rcu_head *rcu) @@ -253,8 +256,6 @@ static void memcg_unlink_cache(struct kmem_cache *s) } else { list_del(&s->memcg_params.children_node); list_del(&s->memcg_params.kmem_caches_node); - mem_cgroup_put(s->memcg_params.memcg); - WRITE_ONCE(s->memcg_params.memcg, NULL); } } #else diff --git a/mm/slub.c b/mm/slub.c index 3d63ae320d31..b25c807a111f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2672,6 +2672,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, } /* + * If the object has been wiped upon free, make sure it's fully initialized by + * zeroing out freelist pointer. + */ +static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, + void *obj) +{ + if (unlikely(slab_want_init_on_free(s)) && obj) + memset((void *)((char *)obj + s->offset), 0, sizeof(void *)); +} + +/* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call * overhead for requests that can be satisfied on the fastpath. @@ -2759,12 +2770,8 @@ redo: prefetch_freepointer(s, next_object); stat(s, ALLOC_FASTPATH); } - /* - * If the object has been wiped upon free, make sure it's fully - * initialized by zeroing out freelist pointer. - */ - if (unlikely(slab_want_init_on_free(s)) && object) - memset(object + s->offset, 0, sizeof(void *)); + + maybe_wipe_obj_freeptr(s, object); if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(object, 0, s->object_size); @@ -3178,10 +3185,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, goto error; c = this_cpu_ptr(s->cpu_slab); + maybe_wipe_obj_freeptr(s, p[i]); + continue; /* goto for-loop */ } c->freelist = get_freepointer(s, object); p[i] = object; + maybe_wipe_obj_freeptr(s, p[i]); } c->tid = next_tid(c->tid); local_irq_enable(); @@ -4846,7 +4856,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s, } } - get_online_mems(); + /* + * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex" + * already held which will conflict with an existing lock order: + * + * mem_hotplug_lock->slab_mutex->kernfs_mutex + * + * We don't really need mem_hotplug_lock (to hold off + * slab_mem_going_offline_callback) here because slab's memory hot + * unplug code doesn't destroy the kmem_cache->node[] data. + */ + #ifdef CONFIG_SLUB_DEBUG if (flags & SO_ALL) { struct kmem_cache_node *n; @@ -4887,7 +4907,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s, x += sprintf(buf + x, " N%d=%lu", node, nodes[node]); #endif - put_online_mems(); kfree(nodes); return x + sprintf(buf + x, "\n"); } diff --git a/mm/truncate.c b/mm/truncate.c index 8563339041f6..dd9ebc1da356 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -592,6 +592,16 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, unlock_page(page); continue; } + + /* Take a pin outside pagevec */ + get_page(page); + + /* + * Drop extra pins before trying to invalidate + * the huge page. + */ + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); } ret = invalidate_inode_page(page); @@ -602,6 +612,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ if (!ret) deactivate_file_page(page); + if (PageTransHuge(page)) + put_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); diff --git a/mm/vmscan.c b/mm/vmscan.c index c6659bb758a4..ee4eecc7e1c2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -351,12 +351,13 @@ unsigned long zone_reclaimable_pages(struct zone *zone) */ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { - unsigned long lru_size; + unsigned long lru_size = 0; int zid; - if (!mem_cgroup_disabled()) - lru_size = lruvec_page_state_local(lruvec, NR_LRU_BASE + lru); - else + if (!mem_cgroup_disabled()) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) + lru_size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); + } else lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) { @@ -932,10 +933,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under the i_pages lock, then this ordering is not required. */ - if (unlikely(PageTransHuge(page)) && PageSwapCache(page)) - refcount = 1 + HPAGE_PMD_NR; - else - refcount = 2; + refcount = 1 + compound_nr(page); if (!page_ref_freeze(page, refcount)) goto cannot_free; /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 8842798c29e6..506d6141e44e 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -33,6 +33,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; unsigned int hlen, ll_rs, mtu; + ktime_t tstamp = skb->tstamp; struct ip_frag_state state; struct iphdr *iph; int err; @@ -80,6 +81,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, if (iter.frag) ip_fraglist_prepare(skb, &iter); + skb->tstamp = tstamp; err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -104,6 +106,7 @@ slow_path: goto blackhole; } + skb2->tstamp = tstamp; err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/core/datagram.c b/net/core/datagram.c index 4cc8dc5db2b7..c210fc116103 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -640,7 +640,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->len += copied; skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { - sk->sk_wmem_queued += truesize; + sk_wmem_queued_add(sk, truesize); sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); diff --git a/net/core/filter.c b/net/core/filter.c index ed6563622ce3..3fed5755494b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4252,12 +4252,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, case SO_RCVBUF: val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); break; case SO_MAX_PACING_RATE: /* 32bit version */ if (val != ~0U) @@ -4274,7 +4276,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_MARK: if (sk->sk_mark != val) { diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a0e0d298c991..6d3e4821b02d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -245,7 +245,8 @@ static int __peernet2id(struct net *net, struct net *peer) return __peernet2id_alloc(net, peer, &no); } -static void rtnl_net_notifyid(struct net *net, int cmd, int id); +static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, + struct nlmsghdr *nlh); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ @@ -268,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer) id = __peernet2id_alloc(net, peer, &alloc); spin_unlock_bh(&net->nsid_lock); if (alloc && id >= 0) - rtnl_net_notifyid(net, RTM_NEWNSID, id); + rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL); if (alive) put_net(peer); return id; @@ -532,7 +533,7 @@ static void unhash_nsid(struct net *net, struct net *last) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) - rtnl_net_notifyid(tmp, RTM_DELNSID, id); + rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL); if (tmp == last) break; } @@ -764,7 +765,8 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { - rtnl_net_notifyid(net, RTM_NEWNSID, err); + rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, + nlh); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; @@ -1051,9 +1053,12 @@ end: return err < 0 ? err : skb->len; } -static void rtnl_net_notifyid(struct net *net, int cmd, int id) +static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, + struct nlmsghdr *nlh) { struct net_fill_args fillargs = { + .portid = portid, + .seq = nlh ? nlh->nlmsg_seq : 0, .cmd = cmd, .nsid = id, }; @@ -1068,7 +1073,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id) if (err < 0) goto err_out; - rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0); + rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, 0); return; err_out: diff --git a/net/core/request_sock.c b/net/core/request_sock.c index c9bb00008528..f35c2e998406 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq; - tcp_sk(sk)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL); spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; tcp_rsk(req)->tfo_listener = false; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 529133611ea2..867e61df00db 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4415,7 +4415,7 @@ static void skb_set_err_queue(struct sk_buff *skb) int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned int)sk->sk_rcvbuf) + (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); @@ -5477,12 +5477,14 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) + * @mac_len: length of the MAC header * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto) +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, + int mac_len) { struct mpls_shim_hdr *lse; int err; @@ -5499,15 +5501,15 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto) return err; if (!skb->inner_protocol) { - skb_set_inner_network_header(skb, skb->mac_len); + skb_set_inner_network_header(skb, mac_len); skb_set_inner_protocol(skb, skb->protocol); } skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), - skb->mac_len); + mac_len); skb_reset_mac_header(skb); - skb_set_network_header(skb, skb->mac_len); + skb_set_network_header(skb, mac_len); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; @@ -5526,29 +5528,30 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header + * @mac_len: length of the MAC header * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto) +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) - return -EINVAL; + return 0; - err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); + err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), - skb->mac_len); + mac_len); __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); - skb_set_network_header(skb, skb->mac_len); + skb_set_network_header(skb, mac_len); if (skb->dev && skb->dev->type == ARPHRD_ETHER) { struct ethhdr *hdr; diff --git a/net/core/sock.c b/net/core/sock.c index fac2b4d80de5..a515392ba84b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -522,7 +522,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); - } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; @@ -785,7 +785,8 @@ set_sndbuf: */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -831,7 +832,8 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_RCVBUFFORCE: @@ -974,7 +976,7 @@ set_rcvbuf: if (sock->ops->set_rcvlowat) ret = sock->ops->set_rcvlowat(sk, val); else - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_RCVTIMEO_OLD: @@ -2088,8 +2090,10 @@ EXPORT_SYMBOL(sock_i_ino); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { - if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { + if (force || + refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); + if (skb) { skb_set_owner_w(skb, sk); return skb; @@ -2190,7 +2194,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) + if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (sk->sk_shutdown & SEND_SHUTDOWN) break; @@ -2225,7 +2229,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (sk->sk_shutdown & SEND_SHUTDOWN) goto failure; - if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf) + if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -2334,8 +2338,8 @@ static void sk_leave_memory_pressure(struct sock *sk) } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; - if (memory_pressure && *memory_pressure) - *memory_pressure = 0; + if (memory_pressure && READ_ONCE(*memory_pressure)) + WRITE_ONCE(*memory_pressure, 0); } } @@ -2806,7 +2810,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | @@ -3204,13 +3208,13 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); - mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; + mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); - mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; + mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; - mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; + mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 73002022c9d8..716d265ba8ca 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -46,7 +46,7 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index) dst->index = index; INIT_LIST_HEAD(&dst->list); - list_add_tail(&dsa_tree_list, &dst->list); + list_add_tail(&dst->list, &dsa_tree_list); kref_init(&dst->refcount); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index a9183543ca30..eb30fc1770de 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -906,7 +906,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, percpu_counter_inc(sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { - BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if @@ -915,7 +915,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ - tcp_sk(child)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } @@ -934,7 +934,7 @@ struct sock *inet_csk_reqsk_queue_add(struct sock *sk, req->sk = child; req->dl_next = NULL; if (queue->rskq_accept_head == NULL) - queue->rskq_accept_head = req; + WRITE_ONCE(queue->rskq_accept_head, req); else queue->rskq_accept_tail->dl_next = req; queue->rskq_accept_tail = req; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index bbb005eb5218..7dc79b973e6e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -193,7 +193,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), - .idiag_wmem = sk->sk_wmem_queued, + .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), .idiag_fmem = sk->sk_forward_alloc, .idiag_tmem = sk_wmem_alloc_get(sk), }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 28fca408812c..814b9b8882a0 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -771,6 +771,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; + ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; @@ -846,6 +847,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ip_fraglist_prepare(skb, &iter); } + skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) @@ -900,6 +902,7 @@ slow_path: /* * Put this fragment into the sending queue. */ + skb2->tstamp = tstamp; err = output(net, sk, skb2); if (err) goto fail; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 14654876127e..621f83434b24 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1482,7 +1482,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { - dst_dev_put(&orig->dst); + rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { @@ -2470,14 +2470,17 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; - int err = -ENETUNREACH; + int err; if (fl4->saddr) { - rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || - ipv4_is_zeronet(fl4->saddr)) + ipv4_is_zeronet(fl4->saddr)) { + rth = ERR_PTR(-EINVAL); goto out; + } + + rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. It was wrong for two reasons: diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f98a1882e537..42187a3b82f4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -326,7 +326,7 @@ void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; - if (tcp_memory_pressure) + if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; @@ -341,7 +341,7 @@ void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; - if (!tcp_memory_pressure) + if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) @@ -450,8 +450,8 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; + WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); sk_sockets_allocated_inc(sk); sk->sk_route_forced_caps = NETIF_F_GSO; @@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (tp->rcv_nxt - tp->copied_seq >= target) || + return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || (sk->sk_prot->stream_memory_read ? sk->sk_prot->stream_memory_read(sk) : false); } @@ -543,10 +543,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && - (state != TCP_SYN_RECV || tp->fastopen_rsk)) { + (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); - if (tp->urg_seq == tp->copied_seq && + if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) target++; @@ -607,7 +607,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && tp->urg_seq == tp->copied_seq; + answ = tp->urg_data && + READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) @@ -616,7 +617,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_una; + answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) @@ -625,7 +626,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_nxt; + answ = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; @@ -657,7 +659,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) tcb->sacked = 0; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; @@ -1032,10 +1034,10 @@ new_segment: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); skb->ip_summed = CHECKSUM_PARTIAL; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1362,7 +1364,7 @@ new_segment: if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1668,9 +1670,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb); if (!desc->count) break; - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); } - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -1699,7 +1701,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) else cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1; val = min(val, cap); - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); @@ -1709,7 +1711,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) val <<= 1; if (val > sk->sk_rcvbuf) { - sk->sk_rcvbuf = val; + WRITE_ONCE(sk->sk_rcvbuf, val); tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); } return 0; @@ -1819,7 +1821,7 @@ static int tcp_zerocopy_receive(struct sock *sk, out: up_read(¤t->mm->mmap_sem); if (length) { - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ @@ -2117,7 +2119,7 @@ found_ok_skb: if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { - ++*seq; + WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; @@ -2139,7 +2141,7 @@ found_ok_skb: } } - *seq += used; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; @@ -2166,7 +2168,7 @@ skip_copy: found_fin_ok: /* Process the FIN. */ - ++*seq; + WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; @@ -2487,7 +2489,10 @@ adjudge_to_death: } if (sk->sk_state == TCP_CLOSE) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. @@ -2559,6 +2564,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -2585,7 +2591,7 @@ int tcp_disconnect(struct sock *sk, int flags) __kfree_skb(sk->sk_rx_skb_cache); sk->sk_rx_skb_cache = NULL; } - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); @@ -2601,9 +2607,12 @@ int tcp_disconnect(struct sock *sk, int flags) tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; - tp->write_seq += tp->max_window + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + + seq = tp->write_seq + tp->max_window + 2; + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; @@ -2930,9 +2939,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sk->sk_state != TCP_CLOSE) err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) - tp->write_seq = val; + WRITE_ONCE(tp->write_seq, val); else if (tp->repair_queue == TCP_RECV_QUEUE) - tp->rcv_nxt = val; + WRITE_ONCE(tp->rcv_nxt, val); else err = -EINVAL; break; @@ -3831,7 +3840,13 @@ EXPORT_SYMBOL(tcp_md5_hash_key); void tcp_done(struct sock *sk) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + /* We might be called with a new socket, after + * inet_csk_prepare_forced_close() has been called + * so we can not use lockdep_sock_is_held(sk) + */ + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 81a8221d650a..549506162dde 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -26,8 +26,9 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); - r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); - r->idiag_wqueue = tp->write_seq - tp->snd_una; + r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); + r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3fd451271a70..a915ade0c818 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -253,7 +253,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, */ tp = tcp_sk(child); - tp->fastopen_rsk = req; + rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3578357abe30..a2e52ad7cdab 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -359,7 +359,8 @@ static void tcp_sndbuf_expand(struct sock *sk) sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) - sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]); + WRITE_ONCE(sk->sk_sndbuf, + min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2])); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -483,8 +484,9 @@ static void tcp_clamp_window(struct sock *sk) !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { - sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), - net->ipv4.sysctl_tcp_rmem[2]); + WRITE_ONCE(sk->sk_rcvbuf, + min(atomic_read(&sk->sk_rmem_alloc), + net->ipv4.sysctl_tcp_rmem[2])); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); @@ -648,7 +650,7 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, rcvwin * rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { - sk->sk_rcvbuf = rcvbuf; + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */ tp->window_clamp = tcp_win_from_space(sk, rcvbuf); @@ -2666,7 +2668,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); - if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) && + if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) && tcp_try_undo_loss(sk, false)) return; @@ -2990,7 +2992,7 @@ void tcp_rearm_rto(struct sock *sk) /* If the retrans timer is currently being used by Fast Open * for SYN-ACK retrans purpose, stay put. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return; if (!tp->packets_out) { @@ -3362,7 +3364,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) sock_owned_by_me((struct sock *)tp); tp->bytes_received += delta; - tp->rcv_nxt = seq; + WRITE_ONCE(tp->rcv_nxt, seq); } /* Update our send window. @@ -5356,7 +5358,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) } tp->urg_data = TCP_URG_NOTYET; - tp->urg_seq = ptr; + WRITE_ONCE(tp->urg_seq, ptr); /* Disable header prediction. */ tp->pred_flags = 0; @@ -5932,7 +5934,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Ok.. it's good. Set up sequence numbers and * move to established. */ - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -5961,7 +5963,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); smc_check_reset_syn(tp); @@ -6035,8 +6037,8 @@ discard: tp->tcp_header_len = sizeof(struct tcphdr); } - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -6087,6 +6089,8 @@ reset_and_undo: static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { + struct request_sock *req; + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ @@ -6096,7 +6100,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) /* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1, * we no longer need req so release it. */ - reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false); + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); + reqsk_fastopen_remove(sk, req, false); /* Re-arm the timer because data may have been sent out. * This is similar to the regular data transmission case @@ -6171,7 +6177,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; - req = tp->fastopen_rsk; + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); if (req) { bool req_stolen; @@ -6211,7 +6218,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bf124b1742df..6be568334848 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) * without appearing to create any others. */ if (likely(!tp->repair)) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + u32 seq = tcptw->tw_snd_nxt + 65535 + 2; + + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } @@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; @@ -291,10 +293,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port); + WRITE_ONCE(tp->write_seq, + secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); @@ -478,7 +481,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -1644,7 +1647,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { - u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; + u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf); struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -2121,7 +2124,7 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - BUG_ON(tp->fastopen_rsk); + BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -2455,12 +2458,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index bb140a5db8c0..c802bc80c400 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -462,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk; struct tcp_sock *oldtp, *newtp; + u32 seq; if (!newsk) return NULL; @@ -475,12 +476,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, /* Now setup tcp_sock */ newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = - newtp->rcv_nxt = treq->rcv_isn + 1; + seq = treq->rcv_isn + 1; + newtp->rcv_wup = seq; + WRITE_ONCE(newtp->copied_seq, seq); + WRITE_ONCE(newtp->rcv_nxt, seq); newtp->segs_in = 1; - newtp->snd_sml = newtp->snd_una = - newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; + seq = treq->snt_isn + 1; + newtp->snd_sml = newtp->snd_una = seq; + WRITE_ONCE(newtp->snd_nxt, seq); + newtp->snd_up = seq; INIT_LIST_HEAD(&newtp->tsq_node); INIT_LIST_HEAD(&newtp->tsorted_sent_queue); @@ -495,7 +500,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1); if (sock_flag(newsk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(newsk, @@ -541,7 +546,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); newtp->fastopen_req = NULL; - newtp->fastopen_rsk = NULL; + RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fec6d67bfd14..0488607c5cd3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -67,7 +67,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); @@ -1196,10 +1196,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ - tp->write_seq = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } @@ -1333,7 +1333,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; @@ -1443,7 +1443,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; - sk->sk_wmem_queued -= delta_truesize; + sk_wmem_queued_add(sk, -delta_truesize); sk_mem_uncharge(sk, delta_truesize); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); } @@ -1888,7 +1888,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, return -ENOMEM; skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; @@ -2152,7 +2152,7 @@ static int tcp_mtu_probe(struct sock *sk) nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); @@ -2482,7 +2482,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; @@ -3142,7 +3142,7 @@ void tcp_send_fin(struct sock *sk) * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ - tp->snd_nxt++; + WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { @@ -3222,7 +3222,7 @@ int tcp_send_synack(struct sock *sk) tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } @@ -3426,14 +3426,14 @@ static void tcp_connect_init(struct sock *sk) tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; @@ -3447,9 +3447,9 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); - tp->write_seq = tcb->end_seq; + WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } @@ -3586,11 +3586,11 @@ int tcp_connect(struct sock *sk) /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { - tp->snd_nxt = TCP_SKB_CB(buff)->seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 05be564414e9..dd5a6317a801 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -386,15 +386,13 @@ abort: tcp_write_err(sk); * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ -static void tcp_fastopen_synack_timer(struct sock *sk) +static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); int max_retries = icsk->icsk_syn_retries ? : sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req; - req = tcp_sk(sk)->fastopen_rsk; req->rsk_ops->syn_ack_timeout(req); if (req->num_timeout >= max_retries) { @@ -435,11 +433,14 @@ void tcp_retransmit_timer(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; - if (tp->fastopen_rsk) { + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - tcp_fastopen_synack_timer(sk); + tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d5779d6a6065..787d9f2a6e99 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2192,6 +2192,7 @@ static void ip6erspan_tap_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &ip6erspan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index edadee4a7e76..71827b56c006 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -768,6 +768,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, inet6_sk(skb->sk) : NULL; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; + ktime_t tstamp = skb->tstamp; int hroom, err = 0; __be32 frag_id; u8 *prevhdr, nexthdr = 0; @@ -855,6 +856,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); + skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), @@ -913,6 +915,7 @@ slow_path: /* * Put this fragment into the sending queue. */ + frag->tstamp = tstamp; err = output(net, sk, frag); if (err) goto fail; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index a9bff556d3b2..409e79b84a83 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -119,6 +119,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; + ktime_t tstamp = skb->tstamp; struct ip6_frag_state state; u8 *prevhdr, nexthdr = 0; unsigned int mtu, hlen; @@ -183,6 +184,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); + skb->tstamp = tstamp; err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -215,6 +217,7 @@ slow_path: goto blackhole; } + skb2->tstamp = tstamp; err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e3d9f4559c99..4804b6dc5e65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; @@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport); + WRITE_ONCE(tp->write_seq, + secure_tcpv6_seq(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); @@ -406,7 +407,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -1895,7 +1896,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " @@ -1906,7 +1908,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2017b7d780f5..c74f44dfaa22 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -113,22 +113,26 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) * * Send data via reliable llc2 connection. * Returns 0 upon success, non-zero if action did not succeed. + * + * This function always consumes a reference to the skb. */ static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock) { struct llc_sock* llc = llc_sk(sk); - int rc = 0; if (unlikely(llc_data_accept_state(llc->state) || llc->remote_busy_flag || llc->p_flag)) { long timeout = sock_sndtimeo(sk, noblock); + int rc; rc = llc_ui_wait_for_busy_core(sk, timeout); + if (rc) { + kfree_skb(skb); + return rc; + } } - if (unlikely(!rc)) - rc = llc_build_and_send_pkt(sk, skb); - return rc; + return llc_build_and_send_pkt(sk, skb); } static void llc_ui_sk_init(struct socket *sock, struct sock *sk) @@ -899,7 +903,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; - struct sk_buff *skb; + struct sk_buff *skb = NULL; size_t size = 0; int rc = -EINVAL, copied = 0, hdrlen; @@ -908,10 +912,10 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) lock_sock(sk); if (addr) { if (msg->msg_namelen < sizeof(*addr)) - goto release; + goto out; } else { if (llc_ui_addr_null(&llc->addr)) - goto release; + goto out; addr = &llc->addr; } /* must bind connection to sap if user hasn't done it. */ @@ -919,7 +923,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* bind to sap with null dev, exclusive. */ rc = llc_ui_autobind(sock, addr); if (rc) - goto release; + goto out; } hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); size = hdrlen + len; @@ -928,12 +932,12 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) copied = size - hdrlen; rc = -EINVAL; if (copied < 0) - goto release; + goto out; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); if (!skb) - goto release; + goto out; skb->dev = llc->dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); skb_reserve(skb, hdrlen); @@ -943,29 +947,31 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) { llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } if (addr->sllc_test) { llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } if (addr->sllc_xid) { llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } rc = -ENOPROTOOPT; if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua)) goto out; rc = llc_ui_send_data(sk, skb, noblock); + skb = NULL; out: - if (rc) { - kfree_skb(skb); -release: + kfree_skb(skb); + if (rc) dprintk("%s: failed sending from %02X to %02X: %d\n", __func__, llc->laddr.lsap, llc->daddr.lsap, rc); - } release_sock(sk); return rc ? : copied; } diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 4d78375f9872..647c0554d04c 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -372,6 +372,7 @@ int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -389,7 +390,8 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; @@ -406,6 +408,7 @@ int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -916,7 +919,8 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk, llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 4ff89cb7c86f..7b620acaca9e 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -30,7 +30,7 @@ #endif static int llc_find_offset(int state, int ev_type); -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb); +static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, struct llc_conn_state_trans *trans, @@ -55,6 +55,8 @@ int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ; * (executing it's actions and changing state), upper layer will be * indicated or confirmed, if needed. Returns 0 for success, 1 for * failure. The socket lock has to be held before calling this function. + * + * This function always consumes a reference to the skb. */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) { @@ -62,12 +64,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) struct llc_sock *llc = llc_sk(skb->sk); struct llc_conn_state_ev *ev = llc_conn_ev(skb); - /* - * We have to hold the skb, because llc_conn_service will kfree it in - * the sending path and we need to look at the skb->cb, where we encode - * llc_conn_state_ev. - */ - skb_get(skb); ev->ind_prim = ev->cfm_prim = 0; /* * Send event to state machine @@ -75,21 +71,12 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) rc = llc_conn_service(skb->sk, skb); if (unlikely(rc != 0)) { printk(KERN_ERR "%s: llc_conn_service failed\n", __func__); - goto out_kfree_skb; - } - - if (unlikely(!ev->ind_prim && !ev->cfm_prim)) { - /* indicate or confirm not required */ - if (!skb->next) - goto out_kfree_skb; goto out_skb_put; } - if (unlikely(ev->ind_prim && ev->cfm_prim)) /* Paranoia */ - skb_get(skb); - switch (ev->ind_prim) { case LLC_DATA_PRIM: + skb_get(skb); llc_save_primitive(sk, skb, LLC_DATA_PRIM); if (unlikely(sock_queue_rcv_skb(sk, skb))) { /* @@ -106,6 +93,7 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) * skb->sk pointing to the newly created struct sock in * llc_conn_handler. -acme */ + skb_get(skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_state_change(sk); break; @@ -121,7 +109,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) sk->sk_state_change(sk); } } - kfree_skb(skb); sock_put(sk); break; case LLC_RESET_PRIM: @@ -130,14 +117,11 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) * RESET is not being notified to upper layers for now */ printk(KERN_INFO "%s: received a reset ind!\n", __func__); - kfree_skb(skb); break; default: - if (ev->ind_prim) { + if (ev->ind_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->ind_prim); - kfree_skb(skb); - } /* No indication */ break; } @@ -179,25 +163,22 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) printk(KERN_INFO "%s: received a reset conf!\n", __func__); break; default: - if (ev->cfm_prim) { + if (ev->cfm_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->cfm_prim); - break; - } - goto out_skb_put; /* No confirmation */ + /* No confirmation */ + break; } -out_kfree_skb: - kfree_skb(skb); out_skb_put: kfree_skb(skb); return rc; } -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) { /* queue PDU to send to MAC layer */ skb_queue_tail(&sk->sk_write_queue, skb); - return llc_conn_send_pdus(sk, skb); + llc_conn_send_pdus(sk); } /** @@ -255,7 +236,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -296,7 +277,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -340,16 +321,12 @@ out: /** * llc_conn_send_pdus - Sends queued PDUs * @sk: active connection - * @hold_skb: the skb held by caller, or NULL if does not care * - * Sends queued pdus to MAC layer for transmission. When @hold_skb is - * NULL, always return 0. Otherwise, return 0 if @hold_skb is sent - * successfully, or 1 for failure. + * Sends queued pdus to MAC layer for transmission. */ -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) +static void llc_conn_send_pdus(struct sock *sk) { struct sk_buff *skb; - int ret = 0; while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); @@ -361,20 +338,10 @@ static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb); if (!skb2) break; - dev_queue_xmit(skb2); - } else { - bool is_target = skb == hold_skb; - int rc; - - if (is_target) - skb_get(skb); - rc = dev_queue_xmit(skb); - if (is_target) - ret = rc; + skb = skb2; } + dev_queue_xmit(skb); } - - return ret; } /** @@ -846,7 +813,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) else { dprintk("%s: adding to backlog...\n", __func__); llc_set_backlog_type(skb, LLC_PACKET); - if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) + if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) goto drop_unlock; } out: diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index 8db03c2d5440..ad6547736c21 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -38,6 +38,8 @@ * closed and -EBUSY when sending data is not permitted in this state or * LLC has send an I pdu with p bit set to 1 and is waiting for it's * response. + * + * This function always consumes a reference to the skb. */ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb) { @@ -46,20 +48,22 @@ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb) struct llc_sock *llc = llc_sk(sk); if (unlikely(llc->state == LLC_CONN_STATE_ADM)) - goto out; + goto out_free; rc = -EBUSY; if (unlikely(llc_data_accept_state(llc->state) || /* data_conn_refuse */ llc->p_flag)) { llc->failed_data_req = 1; - goto out; + goto out_free; } ev = llc_conn_ev(skb); ev->type = LLC_CONN_EV_TYPE_PRIM; ev->prim = LLC_DATA_PRIM; ev->prim_type = LLC_PRIM_TYPE_REQ; skb->dev = llc->dev; - rc = llc_conn_state_process(sk, skb); -out: + return llc_conn_state_process(sk, skb); + +out_free: + kfree_skb(skb); return rc; } diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index a94bd56bcac6..7ae4cc684d3a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -58,8 +58,10 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -81,8 +83,10 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -135,8 +139,10 @@ int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_test_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index a7f7b8ff4729..be419062e19a 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -197,29 +197,22 @@ out: * After executing actions of the event, upper layer will be indicated * if needed(on receiving an UI frame). sk can be null for the * datalink_proto case. + * + * This function always consumes a reference to the skb. */ static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); - /* - * We have to hold the skb, because llc_sap_next_state - * will kfree it in the sending path and we need to - * look at the skb->cb, where we encode llc_sap_state_ev. - */ - skb_get(skb); ev->ind_cfm_flag = 0; llc_sap_next_state(sap, skb); - if (ev->ind_cfm_flag == LLC_IND) { - if (skb->sk->sk_state == TCP_LISTEN) - kfree_skb(skb); - else { - llc_save_primitive(skb->sk, skb, ev->prim); - /* queue skb to the user. */ - if (sock_queue_rcv_skb(skb->sk, skb)) - kfree_skb(skb); - } + if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) { + llc_save_primitive(skb->sk, skb, ev->prim); + + /* queue skb to the user. */ + if (sock_queue_rcv_skb(skb->sk, skb) == 0) + return; } kfree_skb(skb); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 26a2f49208b6..54dd8849d1cc 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2633,7 +2633,8 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, rcu_read_lock(); ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID); - if (WARN_ON_ONCE(ssid == NULL)) + if (WARN_ONCE(!ssid || ssid[1] > IEEE80211_MAX_SSID_LEN, + "invalid SSID element (len=%d)", ssid ? ssid[1] : -1)) ssid_len = 0; else ssid_len = ssid[1]; @@ -5233,7 +5234,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); - if (!ssidie) { + if (!ssidie || ssidie[1] > sizeof(assoc_data->ssid)) { rcu_read_unlock(); kfree(assoc_data); return -EINVAL; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 768d14c9a716..0e05ff037672 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3467,9 +3467,18 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) case cpu_to_le16(IEEE80211_STYPE_PROBE_RESP): /* process for all: mesh, mlme, ibss */ break; + case cpu_to_le16(IEEE80211_STYPE_DEAUTH): + if (is_multicast_ether_addr(mgmt->da) && + !is_broadcast_ether_addr(mgmt->da)) + return RX_DROP_MONITOR; + + /* process only for station/IBSS */ + if (sdata->vif.type != NL80211_IFTYPE_STATION && + sdata->vif.type != NL80211_IFTYPE_ADHOC) + return RX_DROP_MONITOR; + break; case cpu_to_le16(IEEE80211_STYPE_ASSOC_RESP): case cpu_to_le16(IEEE80211_STYPE_REASSOC_RESP): - case cpu_to_le16(IEEE80211_STYPE_DEAUTH): case cpu_to_le16(IEEE80211_STYPE_DISASSOC): if (is_multicast_ether_addr(mgmt->da) && !is_broadcast_ether_addr(mgmt->da)) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index adf94ba1ed77..4d31d9688dc2 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -520,10 +520,33 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local, return 0; } +static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *sdata_iter; + + if (!ieee80211_is_radar_required(local)) + return true; + + if (!regulatory_pre_cac_allowed(local->hw.wiphy)) + return false; + + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata_iter, &local->interfaces, list) { + if (sdata_iter->wdev.cac_started) { + mutex_unlock(&local->iflist_mtx); + return false; + } + } + mutex_unlock(&local->iflist_mtx); + + return true; +} + static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { - if (ieee80211_is_radar_required(local)) + if (!__ieee80211_can_leave_ch(sdata)) return false; if (!list_empty(&local->roc_list)) @@ -630,7 +653,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, lockdep_assert_held(&local->mtx); - if (local->scan_req || ieee80211_is_radar_required(local)) + if (local->scan_req) + return -EBUSY; + + if (!__ieee80211_can_leave_ch(sdata)) return -EBUSY; if (!ieee80211_can_scan(local, sdata)) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0c63120b2db2..5cd610b547e0 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1792,8 +1792,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) extra_jiffies += nfct_time_stamp; - if (ct->timeout != extra_jiffies) - ct->timeout = extra_jiffies; + if (READ_ONCE(ct->timeout) != extra_jiffies) + WRITE_ONCE(ct->timeout, extra_jiffies); acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 3572e11b6f21..1c77f520f474 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -165,7 +165,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype); + err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, + skb->mac_len); if (err) return err; @@ -178,7 +179,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_pop(skb, ethertype); + err = skb_mpls_pop(skb, ethertype, skb->mac_len); if (err) return err; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1091bf35a199..ecc17dabec8f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -556,6 +556,7 @@ struct rxrpc_call { struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ + const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ unsigned long ack_at; /* When deferred ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 00c095d74145..135bf5cd8dd5 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -84,7 +84,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, smp_store_release(&b->conn_backlog_head, (head + 1) & (size - 1)); - trace_rxrpc_conn(conn, rxrpc_conn_new_service, + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, atomic_read(&conn->usage), here); } @@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; - trace_rxrpc_call(call, rxrpc_call_new_service, + trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, atomic_read(&call->usage), here, (const void *)user_call_ID); @@ -307,6 +307,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_see_call(call); call->conn = conn; + call->security = conn->security; call->peer = rxrpc_get_peer(conn->params.peer); call->cong_cwnd = call->peer->cong_cwnd; return call; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 32d8dc677142..a31c18c09894 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -240,7 +240,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (p->intr) __set_bit(RXRPC_CALL_IS_INTR, &call->flags); call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, + atomic_read(&call->usage), here, (const void *)p->user_call_ID); /* We need to protect a partially set up call against the user as we @@ -290,8 +291,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (ret < 0) goto error; - trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), - here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_connected, + atomic_read(&call->usage), here, NULL); rxrpc_start_call_timer(call); @@ -313,8 +314,8 @@ error_dup_user_ID: error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, ret); - trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), - here, ERR_PTR(ret)); + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); @@ -376,7 +377,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call) if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -391,7 +393,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call) int n = atomic_read(&call->usage); ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -406,7 +409,8 @@ void rxrpc_see_call(struct rxrpc_call *call) if (call) { int n = atomic_read(&call->usage); - trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, + here, NULL); } } @@ -418,7 +422,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(call->debug_id, op, n, here, NULL); } /* @@ -445,7 +449,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_release, + atomic_read(&call->usage), here, (const void *)call->flags); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -488,10 +493,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn) { + if (conn) rxrpc_disconnect_call(call); - conn->security->free_call_crypto(call); - } + if (call->security) + call->security->free_call_crypto(call); rxrpc_cleanup_ring(call); _leave(""); @@ -534,12 +539,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { struct rxrpc_net *rxnet = call->rxnet; const void *here = __builtin_return_address(0); + unsigned int debug_id = call->debug_id; int n; ASSERT(call != NULL); n = atomic_dec_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(debug_id, op, n, here, NULL); ASSERTCMP(n, >=, 0); if (n == 0) { _debug("call %d dead", call->debug_id); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3f1da1b49f69..376370cd9285 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -212,7 +212,8 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) rxrpc_get_local(conn->params.local); key_get(conn->params.key); - trace_rxrpc_conn(conn, rxrpc_conn_new_client, atomic_read(&conn->usage), + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, + atomic_read(&conn->usage), __builtin_return_address(0)); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); _leave(" = %p", conn); @@ -352,6 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, if (cp->exclusive) { call->conn = candidate; + call->security = candidate->security; call->security_ix = candidate->security_ix; call->service_id = candidate->service_id; _leave(" = 0 [exclusive %d]", candidate->debug_id); @@ -403,6 +405,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, candidate_published: set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); call->conn = candidate; + call->security = candidate->security; call->security_ix = candidate->security_ix; call->service_id = candidate->service_id; spin_unlock(&local->client_conns_lock); @@ -425,6 +428,7 @@ found_extant_conn: spin_lock(&conn->channel_lock); call->conn = conn; + call->security = conn->security; call->security_ix = conn->security_ix; call->service_id = conn->service_id; list_add_tail(&call->chan_wait_link, &conn->waiting_calls); @@ -985,11 +989,12 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn) void rxrpc_put_client_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); + unsigned int debug_id = conn->debug_id; int n; do { n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_put_client, n, here); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); if (n > 0) return; ASSERTCMP(n, >=, 0); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index ed05b6922132..38d718e90dc6 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -269,7 +269,7 @@ bool rxrpc_queue_conn(struct rxrpc_connection *conn) if (n == 0) return false; if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn, rxrpc_conn_queued, n + 1, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, n + 1, here); else rxrpc_put_connection(conn); return true; @@ -284,7 +284,7 @@ void rxrpc_see_connection(struct rxrpc_connection *conn) if (conn) { int n = atomic_read(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_seen, n, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here); } } @@ -296,7 +296,7 @@ void rxrpc_get_connection(struct rxrpc_connection *conn) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_got, n, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here); } /* @@ -310,7 +310,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn) if (conn) { int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n > 0) - trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n + 1, here); else conn = NULL; } @@ -333,10 +333,11 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, void rxrpc_put_service_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); + unsigned int debug_id = conn->debug_id; int n; n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, n, here); ASSERTCMP(n, >=, 0); if (n == 1) rxrpc_set_service_reap_timer(conn->params.local->rxnet, @@ -420,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) */ if (atomic_cmpxchg(&conn->usage, 1, 0) != 1) continue; - trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, NULL); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL); if (rxrpc_conn_is_client(conn)) BUG(); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index b30e13f6d95f..123d6ceab15c 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -134,7 +134,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - trace_rxrpc_conn(conn, rxrpc_conn_new_service, + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, atomic_read(&conn->usage), __builtin_return_address(0)); } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index c97ebdc043e4..48f67a9b1037 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -147,10 +147,16 @@ void rxrpc_error_report(struct sock *sk) { struct sock_exterr_skb *serr; struct sockaddr_rxrpc srx; - struct rxrpc_local *local = sk->sk_user_data; + struct rxrpc_local *local; struct rxrpc_peer *peer; struct sk_buff *skb; + rcu_read_lock(); + local = rcu_dereference_sk_user_data(sk); + if (unlikely(!local)) { + rcu_read_unlock(); + return; + } _enter("%p{%d}", sk, local->debug_id); /* Clear the outstanding error value on the socket so that it doesn't @@ -160,6 +166,7 @@ void rxrpc_error_report(struct sock *sk) skb = sock_dequeue_err_skb(sk); if (!skb) { + rcu_read_unlock(); _leave("UDP socket errqueue empty"); return; } @@ -167,11 +174,11 @@ void rxrpc_error_report(struct sock *sk) serr = SKB_EXT_ERR(skb); if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); + rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_freed); return; } - rcu_read_lock(); peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9c3ac96f71cb..64830d8c1fdb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { atomic_set(&peer->usage, 1); - peer->local = local; + peer->local = rxrpc_get_local(local); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); @@ -307,7 +307,6 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); - peer->local = local; rxrpc_init_peer(rx, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); @@ -382,7 +381,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) int n; n = atomic_inc_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_got, n, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here); return peer; } @@ -396,7 +395,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) if (peer) { int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) - trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here); else peer = NULL; } @@ -417,6 +416,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } @@ -426,11 +426,13 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id; int n; if (peer) { + debug_id = peer->debug_id; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) __rxrpc_put_peer(peer); } @@ -443,13 +445,15 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer_locked(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id = peer->debug_id; int n; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 3b0becb12041..a4090797c9b2 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -251,8 +251,8 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, seq += subpacket; } - return call->conn->security->verify_packet(call, skb, offset, len, - seq, cksum); + return call->security->verify_packet(call, skb, offset, len, + seq, cksum); } /* @@ -291,7 +291,7 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, *_offset = offset; *_len = len; - call->conn->security->locate_data(call, skb, _offset, _len); + call->security->locate_data(call, skb, _offset, _len); return 0; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6a1547b270fe..813fd6888142 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -419,7 +419,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, call->tx_winsize) sp->hdr.flags |= RXRPC_MORE_PACKETS; - ret = conn->security->secure_packet( + ret = call->security->secure_packet( call, skb, skb->mark, skb->head); if (ret < 0) goto out; @@ -661,6 +661,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: case RXRPC_CALL_SERVER_ACCEPTING: + rxrpc_put_call(call, rxrpc_call_put); ret = -EBUSY; goto error_release_sock; default: diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2558f00f6b3e..69d4676a402f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -832,8 +832,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) } static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { - [TCA_ACT_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_ACT_KIND] = { .type = NLA_STRING }, [TCA_ACT_INDEX] = { .type = NLA_U32 }, [TCA_ACT_COOKIE] = { .type = NLA_BINARY, .len = TC_COOKIE_MAX_SIZE }, @@ -865,8 +864,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, NL_SET_ERR_MSG(extack, "TC action kind must be specified"); goto err_out; } - nla_strlcpy(act_name, kind, IFNAMSIZ); - + if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + goto err_out; + } if (tb[TCA_ACT_COOKIE]) { cookie = nla_memdup_cookie(tb); if (!cookie) { @@ -1352,11 +1353,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { size_t attr_size = 0; - int ret = 0; + int loop, ret; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions, - &attr_size, true, extack); + for (loop = 0; loop < 10; loop++) { + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, + actions, &attr_size, true, extack); + if (ret != -EAGAIN) + break; + } + if (ret < 0) return ret; ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); @@ -1406,11 +1412,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, */ if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; -replay: ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr, extack); - if (ret == -EAGAIN) - goto replay; break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 9ce073a05414..08923b21e566 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -484,7 +484,11 @@ static int __init mirred_init_module(void) return err; pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops, &mirred_net_ops); + err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); + if (err) + unregister_netdevice_notifier(&mirred_device_notifier); + + return err; } static void __exit mirred_cleanup_module(void) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index e168df0e008a..4cf6c553bb0b 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -55,7 +55,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; __be32 new_lse; - int ret; + int ret, mac_len; tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); @@ -63,8 +63,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, /* Ensure 'data' points at mac_header prior calling mpls manipulating * functions. */ - if (skb_at_tc_ingress(skb)) + if (skb_at_tc_ingress(skb)) { skb_push_rcsum(skb, skb->mac_len); + mac_len = skb->mac_len; + } else { + mac_len = skb_network_header(skb) - skb_mac_header(skb); + } ret = READ_ONCE(m->tcf_action); @@ -72,12 +76,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: - if (skb_mpls_pop(skb, p->tcfm_proto)) + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len)) goto drop; break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); - if (skb_mpls_push(skb, new_lse, p->tcfm_proto)) + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len)) goto drop; break; case TCA_MPLS_ACT_MODIFY: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 64584a1df425..8717c0b26c90 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -162,11 +162,22 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_check_kind(struct nlattr *kind, char *name) +{ + if (kind) + return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ; + memset(name, 0, IFNAMSIZ); + return false; +} + static bool tcf_proto_is_unlocked(const char *kind) { const struct tcf_proto_ops *ops; bool ret; + if (strlen(kind) == 0) + return false; + ops = tcf_proto_lookup_ops(kind, false, NULL); /* On error return false to take rtnl lock. Proto lookup/create * functions will perform lookup again and properly handle errors. @@ -1843,6 +1854,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -1899,13 +1911,19 @@ replay: if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, * block is shared (no qdisc found), qdisc is not unlocked, classifier * type is not specified, classifier is not unlocked. */ if (rtnl_held || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2063,6 +2081,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2102,13 +2121,18 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc * found), qdisc is not unlocked, classifier type is not specified, * classifier is not unlocked. */ if (!prio || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2216,6 +2240,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2252,12 +2277,17 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not * unlocked, classifier type is not specified, classifier is not * unlocked. */ if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 82bd14e7ac93..3177dcb17316 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued) *err = -1; return; } - dst->value = sk->sk_wmem_queued; + dst->value = READ_ONCE(sk->sk_wmem_queued); } META_COLLECTOR(int_sk_fwd_alloc) @@ -554,7 +554,7 @@ META_COLLECTOR(int_sk_rcvlowat) *err = -1; return; } - dst->value = sk->sk_rcvlowat; + dst->value = READ_ONCE(sk->sk_rcvlowat); } META_COLLECTOR(int_sk_rcvtimeo) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 81d58b280612..1047825d9f48 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1390,8 +1390,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { - [TCA_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index cebfb65d8556..b1da5589a0c6 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -177,7 +177,7 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, parent = *p; skb = rb_to_skb(parent); - if (ktime_after(txtime, skb->tstamp)) { + if (ktime_compare(txtime, skb->tstamp) >= 0) { p = &parent->rb_right; leftmost = false; } else { diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 0e44039e729c..42e557d48e4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -509,6 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) { qdisc_drop(skb, sch, to_free); + skb = NULL; goto finish_segs; } @@ -593,9 +594,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, finish_segs: if (segs) { unsigned int len, last_len; - int nb = 0; + int nb; - len = skb->len; + len = skb ? skb->len : 0; + nb = skb ? 1 : 0; while (segs) { skb2 = segs->next; @@ -612,7 +614,10 @@ finish_segs: } segs = skb2; } - qdisc_tree_reduce_backlog(sch, -nb, prev_len - len); + /* Parent qdiscs accounted for 1 skb of size @prev_len */ + qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); + } else if (!skb) { + return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 68b543f85a96..6719a65169d4 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1341,6 +1341,10 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); goto out; } + + /* Everything went ok, return success. */ + err = 0; + out: return err; } diff --git a/net/sctp/diag.c b/net/sctp/diag.c index fc9a4c6629ce..0851166b9175 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -175,7 +175,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0) diff --git a/net/sctp/input.c b/net/sctp/input.c index 5a070fb5b278..2277981559d0 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -243,7 +243,7 @@ int sctp_rcv(struct sk_buff *skb) bh_lock_sock(sk); } - if (sock_owned_by_user(sk)) { + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sctp_add_backlog(sk, skb)) { bh_unlock_sock(sk); sctp_chunk_free(chunk); @@ -321,8 +321,8 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) local_bh_disable(); bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { + if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) sctp_chunk_free(chunk); else backloged = 1; @@ -336,7 +336,13 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) if (backloged) return 0; } else { - sctp_inq_push(inqueue, chunk); + if (!sctp_newsk_ready(sk)) { + if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) + return 0; + sctp_chunk_free(chunk); + } else { + sctp_inq_push(inqueue, chunk); + } } done: @@ -358,7 +364,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) struct sctp_ep_common *rcvr = chunk->rcvr; int ret; - ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf); + ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); if (!ret) { /* Hold the assoc/ep while hanging on the backlog queue. * This way, we know structures we need will not disappear diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 939b8d2595bc..5ca0ec0e823c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9500,7 +9500,7 @@ struct proto sctp_prot = { .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, - .get_port = sctp_get_port, + .no_autobind = true, .obj_size = sizeof(struct sctp_sock), .useroffset = offsetof(struct sctp_sock, subscribe), .usersize = offsetof(struct sctp_sock, initmsg) - @@ -9542,7 +9542,7 @@ struct proto sctpv6_prot = { .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, - .get_port = sctp_get_port, + .no_autobind = true, .obj_size = sizeof(struct sctp6_sock), .useroffset = offsetof(struct sctp6_sock, sctp.subscribe), .usersize = offsetof(struct sctp6_sock, sctp.initmsg) - diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 4ca50ddf8d16..88556f0251ab 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -213,7 +213,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = SMC_CLC_DECL_MEM; - goto out; + goto ism_put_vlan; } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; @@ -289,6 +289,9 @@ clear_llc_lnk: smc_llc_link_clear(lnk); free_lgr: kfree(lgr); +ism_put_vlan: + if (ini->is_smcd && ini->vlan_id) + smc_ism_put_vlan(ini->ism_dev, ini->vlan_id); out: if (rc < 0) { if (rc == -ENOMEM) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 413a6abf227e..97e8369002d7 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -211,8 +211,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, rc = sk_wait_event(sk, timeo, sk->sk_err || sk->sk_shutdown & RCV_SHUTDOWN || - fcrit(conn) || - smc_cdc_rxed_any_close_or_senddone(conn), + fcrit(conn), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); @@ -262,6 +261,18 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, return -EAGAIN; } +static bool smc_rx_recvmsg_data_available(struct smc_sock *smc) +{ + struct smc_connection *conn = &smc->conn; + + if (smc_rx_data_available(conn)) + return true; + else if (conn->urg_state == SMC_URG_VALID) + /* we received a single urgent Byte - skip */ + smc_rx_update_cons(smc, 0); + return false; +} + /* smc_rx_recvmsg - receive data from RMBE * @msg: copy data to receive buffer * @pipe: copy data to pipe if set - indicates splice() call @@ -303,16 +314,18 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, if (read_done >= target || (pipe && read_done)) break; - if (atomic_read(&conn->bytes_to_rcv)) + if (smc_rx_recvmsg_data_available(smc)) goto copy; - else if (conn->urg_state == SMC_URG_VALID) - /* we received a single urgent Byte - skip */ - smc_rx_update_cons(smc, 0); if (sk->sk_shutdown & RCV_SHUTDOWN || - smc_cdc_rxed_any_close_or_senddone(conn) || - conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) + conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) { + /* smc_cdc_msg_recv_action() could have run after + * above smc_rx_recvmsg_data_available() + */ + if (smc_rx_recvmsg_data_available(smc)) + goto copy; break; + } if (read_done) { if (sk->sk_err || diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3b9f8cc328f5..f8bbc4aab213 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2119,13 +2119,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) struct tipc_msg *hdr = buf_msg(skb); if (unlikely(msg_in_group(hdr))) - return sk->sk_rcvbuf; + return READ_ONCE(sk->sk_rcvbuf); if (unlikely(!msg_connected(hdr))) - return sk->sk_rcvbuf << msg_importance(hdr); + return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr); if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL)) - return sk->sk_rcvbuf; + return READ_ONCE(sk->sk_rcvbuf); return FLOWCTL_MSG_LIM; } @@ -3790,7 +3790,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf); i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk)); i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf); - i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len); + i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len)); if (dqueues & TIPC_DUMP_SK_SNDQ) { i += scnprintf(buf + i, sz - i, "sk_write_queue: "); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a666ef8fc54e..481f7f8a1655 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -204,10 +204,14 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, return virtio_transport_get_ops()->send_pkt(pkt); } -static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, +static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { + if (vvs->rx_bytes + pkt->len > vvs->buf_alloc) + return false; + vvs->rx_bytes += pkt->len; + return true; } static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, @@ -458,6 +462,9 @@ void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) vvs->buf_size_max = val; vvs->buf_size = val; vvs->buf_alloc = val; + + virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, + NULL); } EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size); @@ -876,14 +883,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt) { struct virtio_vsock_sock *vvs = vsk->trans; - bool free_pkt = false; + bool can_enqueue, free_pkt = false; pkt->len = le32_to_cpu(pkt->hdr.len); pkt->off = 0; spin_lock_bh(&vvs->rx_lock); - virtio_transport_inc_rx_pkt(vvs, pkt); + can_enqueue = virtio_transport_inc_rx_pkt(vvs, pkt); + if (!can_enqueue) { + free_pkt = true; + goto out; + } /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 141cdb171665..4453dd375de9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13682,7 +13682,7 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb, hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_GET_FTM_RESPONDER_STATS); if (!hdr) - return -ENOBUFS; + goto nla_put_failure; if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 420c4207ab59..446c76d44e65 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3883,6 +3883,7 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy) return pre_cac_allowed; } +EXPORT_SYMBOL(regulatory_pre_cac_allowed); void regulatory_propagate_dfs_state(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 504133d76de4..dc8f689bd469 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -156,14 +156,6 @@ bool regulatory_indoor_allowed(void); #define REG_PRE_CAC_EXPIRY_GRACE_MS 2000 /** - * regulatory_pre_cac_allowed - if pre-CAC allowed in the current dfs domain - * @wiphy: wiphy for which pre-CAC capability is checked. - - * Pre-CAC is allowed only in ETSI domain. - */ -bool regulatory_pre_cac_allowed(struct wiphy *wiphy); - -/** * regulatory_propagate_dfs_state - Propagate DFS channel state to other wiphys * @wiphy - wiphy on which radar is detected and the event will be propagated * to other available wiphys having the same DFS domain diff --git a/net/wireless/scan.c b/net/wireless/scan.c index ff1016607f0b..aef240fdf8df 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1703,8 +1703,7 @@ cfg80211_parse_mbssid_frame_data(struct wiphy *wiphy, static void cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, struct cfg80211_bss *nontrans_bss, - struct ieee80211_mgmt *mgmt, size_t len, - gfp_t gfp) + struct ieee80211_mgmt *mgmt, size_t len) { u8 *ie, *new_ie, *pos; const u8 *nontrans_ssid, *trans_ssid, *mbssid; @@ -1715,6 +1714,8 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, const struct cfg80211_bss_ies *old; u8 cpy_len; + lockdep_assert_held(&wiphy_to_rdev(wiphy)->bss_lock); + ie = mgmt->u.probe_resp.variable; new_ie_len = ielen; @@ -1731,23 +1732,22 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, if (!mbssid || mbssid < trans_ssid) return; new_ie_len -= mbssid[1]; - rcu_read_lock(); + nontrans_ssid = ieee80211_bss_get_ie(nontrans_bss, WLAN_EID_SSID); - if (!nontrans_ssid) { - rcu_read_unlock(); + if (!nontrans_ssid) return; - } + new_ie_len += nontrans_ssid[1]; - rcu_read_unlock(); /* generate new ie for nontrans BSS * 1. replace SSID with nontrans BSS' SSID * 2. skip MBSSID IE */ - new_ie = kzalloc(new_ie_len, gfp); + new_ie = kzalloc(new_ie_len, GFP_ATOMIC); if (!new_ie) return; - new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, gfp); + + new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, GFP_ATOMIC); if (!new_ies) goto out_free; @@ -1901,6 +1901,8 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, cfg80211_parse_mbssid_frame_data(wiphy, data, mgmt, len, &non_tx_data, gfp); + spin_lock_bh(&wiphy_to_rdev(wiphy)->bss_lock); + /* check if the res has other nontransmitting bss which is not * in MBSSID IE */ @@ -1915,8 +1917,9 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, ies2 = rcu_access_pointer(tmp_bss->ies); if (ies2->tsf < ies1->tsf) cfg80211_update_notlisted_nontrans(wiphy, tmp_bss, - mgmt, len, gfp); + mgmt, len); } + spin_unlock_bh(&wiphy_to_rdev(wiphy)->bss_lock); return res; } diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index c67d7a82ab13..73fd0eae08ca 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -202,6 +202,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + int ret = 0; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) @@ -219,7 +220,10 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, if (ie) { data->flags = 1; data->length = ie[1]; - memcpy(ssid, ie + 2, data->length); + if (data->length > IW_ESSID_MAX_SIZE) + ret = -EINVAL; + else + memcpy(ssid, ie + 2, data->length); } rcu_read_unlock(); } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { @@ -229,7 +233,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, } wdev_unlock(wdev); - return 0; + return ret; } int cfg80211_mgd_wext_siwap(struct net_device *dev, diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 5c111bc3c8ea..00e782335cb0 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -55,7 +55,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) if (!sock_owned_by_user(sk)) { queued = x25_process_rx_frame(sk, skb); } else { - queued = !sk_add_backlog(sk, skb, sk->sk_rcvbuf); + queued = !sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); } bh_unlock_sock(sk); sock_put(sk); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index fa8fbb8fa3c8..9044073fbf22 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -305,9 +305,8 @@ out: } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct sock *sk) +static int xsk_zc_xmit(struct xdp_sock *xs) { - struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev = xs->dev; return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, @@ -327,11 +326,10 @@ static void xsk_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, - size_t total_len) +static int xsk_generic_xmit(struct sock *sk) { - u32 max_batch = TX_BATCH_SIZE; struct xdp_sock *xs = xdp_sk(sk); + u32 max_batch = TX_BATCH_SIZE; bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; @@ -394,6 +392,18 @@ out: return err; } +static int __xsk_sendmsg(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (unlikely(!(xs->dev->flags & IFF_UP))) + return -ENETDOWN; + if (unlikely(!xs->tx)) + return -ENOBUFS; + + return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk); +} + static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { bool need_wait = !(m->msg_flags & MSG_DONTWAIT); @@ -402,21 +412,18 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) if (unlikely(!xsk_is_bound(xs))) return -ENXIO; - if (unlikely(!(xs->dev->flags & IFF_UP))) - return -ENETDOWN; - if (unlikely(!xs->tx)) - return -ENOBUFS; - if (need_wait) + if (unlikely(need_wait)) return -EOPNOTSUPP; - return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len); + return __xsk_sendmsg(sk); } static unsigned int xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { unsigned int mask = datagram_poll(file, sock, wait); - struct xdp_sock *xs = xdp_sk(sock->sk); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; struct xdp_umem *umem; @@ -426,9 +433,14 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock, dev = xs->dev; umem = xs->umem; - if (umem->need_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (umem->need_wakeup) { + if (dev->netdev_ops->ndo_xsk_wakeup) + dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, + umem->need_wakeup); + else + /* Poll needs to drive Tx also in copy mode */ + __xsk_sendmsg(sk); + } if (xs->rx && !xskq_empty_desc(xs->rx)) mask |= POLLIN | POLLRDNORM; diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h index 7409722727ca..7048bb3594d6 100644 --- a/samples/bpf/asm_goto_workaround.h +++ b/samples/bpf/asm_goto_workaround.h @@ -3,7 +3,8 @@ #ifndef __ASM_GOTO_WORKAROUND_H #define __ASM_GOTO_WORKAROUND_H -/* this will bring in asm_volatile_goto macro definition +/* + * This will bring in asm_volatile_goto and asm_inline macro definitions * if enabled by compiler and config options. */ #include <linux/types.h> @@ -13,5 +14,15 @@ #define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") #endif +/* + * asm_inline is defined as asm __inline in "include/linux/compiler_types.h" + * if supported by the kernel's CC (i.e CONFIG_CC_HAS_ASM_INLINE) which is not + * supported by CLANG. + */ +#ifdef asm_inline +#undef asm_inline +#define asm_inline asm +#endif + #define volatile(x...) volatile("") #endif diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index e39938058223..4c31b305e6ef 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -13,6 +13,7 @@ #include <sys/resource.h> #include <sys/types.h> #include <sys/stat.h> +#include <linux/perf_event.h> #include "libbpf.h" #include "bpf_load.h" diff --git a/scripts/coccinelle/api/devm_platform_ioremap_resource.cocci b/scripts/coccinelle/api/devm_platform_ioremap_resource.cocci deleted file mode 100644 index 56a2e261d61d..000000000000 --- a/scripts/coccinelle/api/devm_platform_ioremap_resource.cocci +++ /dev/null @@ -1,60 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/// Use devm_platform_ioremap_resource helper which wraps -/// platform_get_resource() and devm_ioremap_resource() together. -/// -// Confidence: High -// Copyright: (C) 2019 Himanshu Jha GPLv2. -// Copyright: (C) 2019 Julia Lawall, Inria/LIP6. GPLv2. -// Keywords: platform_get_resource, devm_ioremap_resource, -// Keywords: devm_platform_ioremap_resource - -virtual patch -virtual report - -@r depends on patch && !report@ -expression e1, e2, arg1, arg2, arg3; -identifier id; -@@ - -( -- id = platform_get_resource(arg1, IORESOURCE_MEM, arg2); -| -- struct resource *id = platform_get_resource(arg1, IORESOURCE_MEM, arg2); -) - ... when != id -- e1 = devm_ioremap_resource(arg3, id); -+ e1 = devm_platform_ioremap_resource(arg1, arg2); - ... when != id -? id = e2 - -@r1 depends on patch && !report@ -identifier r.id; -type T; -@@ - -- T *id; - ...when != id - -@r2 depends on report && !patch@ -identifier id; -expression e1, e2, arg1, arg2, arg3; -position j0; -@@ - -( - id = platform_get_resource(arg1, IORESOURCE_MEM, arg2); -| - struct resource *id = platform_get_resource(arg1, IORESOURCE_MEM, arg2); -) - ... when != id - e1@j0 = devm_ioremap_resource(arg3, id); - ... when != id -? id = e2 - -@script:python depends on report && !patch@ -e1 << r2.e1; -j0 << r2.j0; -@@ - -msg = "WARNING: Use devm_platform_ioremap_resource for %s" % (e1) -coccilib.report.print_report(j0[0], msg) diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index 6d2e09a2ad2f..2fa7bb83885f 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -16,6 +16,8 @@ import sys from linux import utils +printk_log_type = utils.CachedType("struct printk_log") + class LxDmesg(gdb.Command): """Print Linux kernel log buffer.""" @@ -42,9 +44,14 @@ class LxDmesg(gdb.Command): b = utils.read_memoryview(inf, log_buf_addr, log_next_idx) log_buf = a.tobytes() + b.tobytes() + length_offset = printk_log_type.get_type()['len'].bitpos // 8 + text_len_offset = printk_log_type.get_type()['text_len'].bitpos // 8 + time_stamp_offset = printk_log_type.get_type()['ts_nsec'].bitpos // 8 + text_offset = printk_log_type.get_type().sizeof + pos = 0 while pos < log_buf.__len__(): - length = utils.read_u16(log_buf[pos + 8:pos + 10]) + length = utils.read_u16(log_buf, pos + length_offset) if length == 0: if log_buf_2nd_half == -1: gdb.write("Corrupted log buffer!\n") @@ -52,10 +59,11 @@ class LxDmesg(gdb.Command): pos = log_buf_2nd_half continue - text_len = utils.read_u16(log_buf[pos + 10:pos + 12]) - text = log_buf[pos + 16:pos + 16 + text_len].decode( + text_len = utils.read_u16(log_buf, pos + text_len_offset) + text_start = pos + text_offset + text = log_buf[text_start:text_start + text_len].decode( encoding='utf8', errors='replace') - time_stamp = utils.read_u64(log_buf[pos:pos + 8]) + time_stamp = utils.read_u64(log_buf, pos + time_stamp_offset) for line in text.splitlines(): msg = u"[{time:12.6f}] {line}\n".format( diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 34e40e96dee2..7b7c2fafbc68 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -15,7 +15,7 @@ import gdb import os import re -from linux import modules +from linux import modules, utils if hasattr(gdb, 'Breakpoint'): @@ -116,6 +116,12 @@ lx-symbols command.""" module_file = self._get_module_file(module_name) if module_file: + if utils.is_target_arch('s390'): + # Module text is preceded by PLT stubs on s390. + module_arch = module['arch'] + plt_offset = int(module_arch['plt_offset']) + plt_size = int(module_arch['plt_size']) + module_addr = hex(int(module_addr, 0) + plt_offset + plt_size) gdb.write("loading @{addr}: {filename}\n".format( addr=module_addr, filename=module_file)) cmdline = "add-symbol-file {filename} {addr}{sections}".format( diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index bc67126118c4..ea94221dbd39 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -92,15 +92,16 @@ def read_memoryview(inf, start, length): return memoryview(inf.read_memory(start, length)) -def read_u16(buffer): +def read_u16(buffer, offset): + buffer_val = buffer[offset:offset + 2] value = [0, 0] - if type(buffer[0]) is str: - value[0] = ord(buffer[0]) - value[1] = ord(buffer[1]) + if type(buffer_val[0]) is str: + value[0] = ord(buffer_val[0]) + value[1] = ord(buffer_val[1]) else: - value[0] = buffer[0] - value[1] = buffer[1] + value[0] = buffer_val[0] + value[1] = buffer_val[1] if get_target_endianness() == LITTLE_ENDIAN: return value[0] + (value[1] << 8) @@ -108,18 +109,18 @@ def read_u16(buffer): return value[1] + (value[0] << 8) -def read_u32(buffer): +def read_u32(buffer, offset): if get_target_endianness() == LITTLE_ENDIAN: - return read_u16(buffer[0:2]) + (read_u16(buffer[2:4]) << 16) + return read_u16(buffer, offset) + (read_u16(buffer, offset + 2) << 16) else: - return read_u16(buffer[2:4]) + (read_u16(buffer[0:2]) << 16) + return read_u16(buffer, offset + 2) + (read_u16(buffer, offset) << 16) -def read_u64(buffer): +def read_u64(buffer, offset): if get_target_endianness() == LITTLE_ENDIAN: - return read_u32(buffer[0:4]) + (read_u32(buffer[4:8]) << 32) + return read_u32(buffer, offset) + (read_u32(buffer, offset + 4) << 32) else: - return read_u32(buffer[4:8]) + (read_u32(buffer[0:4]) << 32) + return read_u32(buffer, offset + 4) + (read_u32(buffer, offset) << 32) target_arch = None diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 220dae0db3f1..a2998b118ef9 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -93,7 +93,7 @@ scm_version() # Check for mercurial and a mercurial repo. if test -d .hg && hgid=`hg id 2>/dev/null`; then # Do we have an tagged version? If so, latesttagdistance == 1 - if [ "`hg log -r . --template '{latesttagdistance}'`" == "1" ]; then + if [ "`hg log -r . --template '{latesttagdistance}'`" = "1" ]; then id=`hg log -r . --template '{latesttag}'` printf '%s%s' -hg "$id" else diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c index 211ca85acd8c..cfab60d88c92 100644 --- a/sound/hda/ext/hdac_ext_controller.c +++ b/sound/hda/ext/hdac_ext_controller.c @@ -271,6 +271,11 @@ int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, ret = snd_hdac_ext_bus_link_power_up(link); /* + * clear the register to invalidate all the output streams + */ + snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV, + ML_LOSIDV_STREAM_MASK, 0); + /* * wait for 521usec for codec to report status * HDA spec section 4.3 - Codec Discovery */ diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index bca5de78e9ad..795cbda32cbb 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -3474,6 +3474,8 @@ static int patch_nvhdmi(struct hda_codec *codec) nvhdmi_chmap_cea_alloc_validate_get_type; spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate; + codec->link_down_at_suspend = 1; + generic_acomp_init(codec, &nvhdmi_audio_ops, nvhdmi_port2pin); return 0; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b000b36ac3c6..ce4f11659765 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5358,6 +5358,17 @@ static void alc271_hp_gate_mic_jack(struct hda_codec *codec, } } +static void alc256_fixup_dell_xps_13_headphone_noise2(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + snd_hda_codec_amp_stereo(codec, 0x1a, HDA_INPUT, 0, HDA_AMP_VOLMASK, 1); + snd_hda_override_wcaps(codec, 0x1a, get_wcaps(codec, 0x1a) & ~AC_WCAP_IN_AMP); +} + static void alc269_fixup_limit_int_mic_boost(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -5822,6 +5833,7 @@ enum { ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, ALC275_FIXUP_DELL_XPS, ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, + ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2, ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, ALC255_FIXUP_DELL_SPK_NOISE, @@ -5869,6 +5881,7 @@ enum { ALC225_FIXUP_WYSE_AUTO_MUTE, ALC225_FIXUP_WYSE_DISABLE_MIC_VREF, ALC286_FIXUP_ACER_AIO_HEADSET_MIC, + ALC256_FIXUP_ASUS_HEADSET_MIC, ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, ALC299_FIXUP_PREDATOR_SPK, ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC, @@ -6558,6 +6571,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE }, + [ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc256_fixup_dell_xps_13_headphone_noise2, + .chained = true, + .chain_id = ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE + }, [ALC293_FIXUP_LENOVO_SPK_NOISE] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_disable_aamix, @@ -6912,6 +6931,15 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE }, + [ALC256_FIXUP_ASUS_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11020 }, /* headset mic with jack detect */ + { } + }, + .chained = true, + .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE + }, [ALC256_FIXUP_ASUS_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -7001,17 +7029,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), - SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2), SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x0738, "Dell Precision 5820", ALC269_FIXUP_NO_SHUTUP), - SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2), SND_PCI_QUIRK(0x1028, 0x075c, "Dell XPS 27 7760", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), SND_PCI_QUIRK(0x1028, 0x080c, "Dell WYSE", ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE), - SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2), SND_PCI_QUIRK(0x1028, 0x084b, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x084e, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), @@ -7108,6 +7136,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 33cd26763c0e..ff5ab24f3bd1 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -348,6 +348,9 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ep = 0x84; ifnum = 0; goto add_sync_ep_from_ifnum; + case USB_ID(0x0582, 0x01d8): /* BOSS Katana */ + /* BOSS Katana amplifiers do not need quirks */ + return 0; } if (attr == USB_ENDPOINT_SYNC_ASYNC && diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index fbf5e4a0cb9c..5d1995fd369c 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -12,7 +12,11 @@ INSTALL ?= install CFLAGS += -Wall -O2 CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include -ifeq ($(srctree),) +# This will work when bpf is built in tools env. where srctree +# isn't set and when invoked from selftests build, where srctree +# is set to ".". building_out_of_srctree is undefined for in srctree +# builds +ifndef building_out_of_srctree srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index c6f94cffe06e..56ce6292071b 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -8,7 +8,11 @@ LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) MAKEFLAGS += --no-print-directory -ifeq ($(srctree),) +# This will work when bpf is built in tools env. where srctree +# isn't set and when invoked from selftests build, where srctree +# is a ".". building_out_of_srctree is undefined for in srctree +# builds +ifndef building_out_of_srctree srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) srctree := $(patsubst %/,%,$(dir $(srctree))) @@ -110,6 +114,9 @@ override CFLAGS += $(INCLUDES) override CFLAGS += -fvisibility=hidden override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +# flags specific for shared library +SHLIB_FLAGS := -DSHARED + ifeq ($(VERBOSE),1) Q = else @@ -126,14 +133,17 @@ all: export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include -BPF_IN := $(OUTPUT)libbpf-in.o +SHARED_OBJDIR := $(OUTPUT)sharedobjs/ +STATIC_OBJDIR := $(OUTPUT)staticobjs/ +BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o +BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o VERSION_SCRIPT := libbpf.map LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) -GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ +GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \ sort -u | wc -l) @@ -155,7 +165,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN): force elfdep bpfdep +$(BPF_IN_SHARED): force elfdep bpfdep @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -171,17 +181,20 @@ $(BPF_IN): force elfdep bpfdep @(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \ (diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true - $(Q)$(MAKE) $(build)=libbpf + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" + +$(BPF_IN_STATIC): force elfdep bpfdep + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) -$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN) +$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) -$(OUTPUT)libbpf.a: $(BPF_IN) +$(OUTPUT)libbpf.a: $(BPF_IN_STATIC) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a @@ -197,7 +210,7 @@ check: check_abi check_abi: $(OUTPUT)libbpf.so @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ - echo "Warning: Num of global symbols in $(BPF_IN)" \ + echo "Warning: Num of global symbols in $(BPF_IN_SHARED)" \ "($(GLOBAL_SYM_COUNT)) does NOT match with num of" \ "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \ "Please make sure all LIBBPF_API symbols are" \ @@ -255,9 +268,9 @@ config-clean: $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: - $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ + $(call QUIET_CLEAN, libbpf) $(RM) -rf $(TARGETS) $(CXX_TEST_TARGET) \ *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ - *.pc LIBBPF-CFLAGS + *.pc LIBBPF-CFLAGS $(SHARED_OBJDIR) $(STATIC_OBJDIR) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 2e83a34f8c79..98216a69c32f 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -34,6 +34,22 @@ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +/* Symbol versioning is different between static and shared library. + * Properly versioned symbols are needed for shared library, but + * only the symbol of the new version is needed for static library. + */ +#ifdef SHARED +# define COMPAT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@" #version); +# define DEFAULT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@@" #version); +#else +# define COMPAT_VERSION(internal_name, api_name, version) +# define DEFAULT_VERSION(internal_name, api_name, version) \ + extern typeof(internal_name) api_name \ + __attribute__((alias(#internal_name))); +#endif + extern void libbpf_print(enum libbpf_print_level level, const char *format, ...) __attribute__((format(printf, 2, 3))); diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 24fa313524fb..a902838f9fcc 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -261,8 +261,8 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, &config); } -asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2"); -asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4"); +COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) +DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) static int xsk_load_xdp_prog(struct xsk_socket *xsk) { diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 6cbeea7b4bf1..8547ecbdc61f 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -195,7 +195,7 @@ static void run_test(int cgroup_fd) if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, (void *)&server_fd))) - goto close_bpf_object; + goto close_server_fd; pthread_mutex_lock(&server_started_mtx); pthread_cond_wait(&server_started, &server_started_mtx); diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index a82da555b1b0..f4cd60d6fba2 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -260,13 +260,14 @@ void test_tcp_rtt(void) if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread, (void *)&server_fd))) - goto close_cgroup_fd; + goto close_server_fd; pthread_mutex_lock(&server_started_mtx); pthread_cond_wait(&server_started, &server_started_mtx); pthread_mutex_unlock(&server_started_mtx); CHECK_FAIL(run_test(cgroup_fd, server_fd)); +close_server_fd: close(server_fd); close_cgroup_fd: close(cgroup_fd); diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh index d23d4da66b83..e2d06191bd35 100755 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ b/tools/testing/selftests/bpf/test_flow_dissector.sh @@ -63,6 +63,9 @@ fi # Setup tc qdisc add dev lo ingress +echo 0 > /proc/sys/net/ipv4/conf/default/rp_filter +echo 0 > /proc/sys/net/ipv4/conf/all/rp_filter +echo 0 > /proc/sys/net/ipv4/conf/lo/rp_filter echo "Testing IPv4..." # Drops all IP/UDP packets coming from port 9 diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index acf7a74f97cd..59ea56945e6c 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -314,15 +314,15 @@ test_gso() command -v nc >/dev/null 2>&1 || \ { echo >&2 "nc is not available: skipping TSO tests"; return; } - # listen on IPv*_DST, capture TCP into $TMPFILE + # listen on port 9000, capture TCP into $TMPFILE if [ "${PROTO}" == "IPv4" ] ; then IP_DST=${IPv4_DST} ip netns exec ${NS3} bash -c \ - "nc -4 -l -s ${IPv4_DST} -p 9000 > ${TMPFILE} &" + "nc -4 -l -p 9000 > ${TMPFILE} &" elif [ "${PROTO}" == "IPv6" ] ; then IP_DST=${IPv6_DST} ip netns exec ${NS3} bash -c \ - "nc -6 -l -s ${IPv6_DST} -p 9000 > ${TMPFILE} &" + "nc -6 -l -p 9000 > ${TMPFILE} &" RET=$? else echo " test_gso: unknown PROTO: ${PROTO}" diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index b35da375530a..30072c3f52fb 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,4 +1,5 @@ /s390x/sync_regs_test +/s390x/memop /x86_64/cr4_cpuid_sync_test /x86_64/evmcs_test /x86_64/hyperv_cpuid @@ -9,8 +10,10 @@ /x86_64/state_test /x86_64/sync_regs_test /x86_64/vmx_close_while_nested_test +/x86_64/vmx_dirty_log_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test +/x86_64/xss_msr_test /clear_dirty_log_test /dirty_log_test /kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index c5ec868fa1e5..3138a916574a 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -25,6 +25,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test +TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index ff234018219c..635ee6c33ad2 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -308,6 +308,8 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state); +struct kvm_msr_list *kvm_get_msr_index_list(void); + struct kvm_cpuid2 *kvm_get_supported_cpuid(void); void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid); @@ -322,10 +324,13 @@ kvm_get_supported_cpuid_entry(uint32_t function) } uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index); +int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value); void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, uint64_t msr_value); -uint32_t kvm_get_cpuid_max(void); +uint32_t kvm_get_cpuid_max_basic(void); +uint32_t kvm_get_cpuid_max_extended(void); void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); /* diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 6ae5a47fe067..f52e0ba84fed 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -580,6 +580,8 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx); void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); bool load_vmcs(struct vmx_pages *vmx); +void nested_vmx_check_supported(void); + void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot); void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index 231d79e57774..6f38c3dc0d56 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -29,12 +29,9 @@ void test_vcpu_creation(int first_vcpu_id, int num_vcpus) vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - for (i = 0; i < num_vcpus; i++) { - int vcpu_id = first_vcpu_id + i; - + for (i = first_vcpu_id; i < first_vcpu_id + num_vcpus; i++) /* This asserts that the vCPU was created. */ - vm_vcpu_add(vm, vcpu_id); - } + vm_vcpu_add(vm, i); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 6698cb741e10..683d3bdb8f6a 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -869,7 +869,7 @@ uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) return buffer.entry.data; } -/* VCPU Set MSR +/* _VCPU Set MSR * * Input Args: * vm - Virtual Machine @@ -879,12 +879,12 @@ uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) * * Output Args: None * - * Return: On success, nothing. On failure a TEST_ASSERT is produced. + * Return: The result of KVM_SET_MSRS. * - * Set value of MSR for VCPU. + * Sets the value of an MSR for the given VCPU. */ -void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, - uint64_t msr_value) +int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); struct { @@ -899,6 +899,29 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, buffer.entry.index = msr_index; buffer.entry.data = msr_value; r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header); + return r; +} + +/* VCPU Set MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * msr_value - New value of MSR + * + * Output Args: None + * + * Return: On success, nothing. On failure a TEST_ASSERT is produced. + * + * Set value of MSR for VCPU. + */ +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value) +{ + int r; + + r = _vcpu_set_msr(vm, vcpuid, msr_index, msr_value); TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n" " rc: %i errno: %i", r, errno); } @@ -1000,19 +1023,45 @@ struct kvm_x86_state { struct kvm_msrs msrs; }; -static int kvm_get_num_msrs(struct kvm_vm *vm) +static int kvm_get_num_msrs_fd(int kvm_fd) { struct kvm_msr_list nmsrs; int r; nmsrs.nmsrs = 0; - r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs); + r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs); TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i", r); return nmsrs.nmsrs; } +static int kvm_get_num_msrs(struct kvm_vm *vm) +{ + return kvm_get_num_msrs_fd(vm->kvm_fd); +} + +struct kvm_msr_list *kvm_get_msr_index_list(void) +{ + struct kvm_msr_list *list; + int nmsrs, r, kvm_fd; + + kvm_fd = open(KVM_DEV_PATH, O_RDONLY); + if (kvm_fd < 0) + exit(KSFT_SKIP); + + nmsrs = kvm_get_num_msrs_fd(kvm_fd); + list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); + list->nmsrs = nmsrs; + r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list); + close(kvm_fd); + + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i", + r); + + return list; +} + struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); @@ -1158,7 +1207,12 @@ bool is_intel_cpu(void) return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); } -uint32_t kvm_get_cpuid_max(void) +uint32_t kvm_get_cpuid_max_basic(void) +{ + return kvm_get_supported_cpuid_entry(0)->eax; +} + +uint32_t kvm_get_cpuid_max_extended(void) { return kvm_get_supported_cpuid_entry(0x80000000)->eax; } @@ -1169,7 +1223,7 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) bool pae; /* SDM 4.1.4 */ - if (kvm_get_cpuid_max() < 0x80000008) { + if (kvm_get_cpuid_max_extended() < 0x80000008) { pae = kvm_get_supported_cpuid_entry(1)->edx & (1 << 6); *pa_bits = pae ? 36 : 32; *va_bits = 32; diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index fab8f6b0bf52..f6ec97b7eaef 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -376,6 +376,16 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp) init_vmcs_guest_state(guest_rip, guest_rsp); } +void nested_vmx_check_supported(void) +{ + struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + + if (!(entry->ecx & CPUID_VMX)) { + fprintf(stderr, "nested VMX not enabled, skipping test\n"); + exit(KSFT_SKIP); + } +} + void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot) { diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c index d5290b4ad636..b705637ca14b 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -25,12 +25,15 @@ static void guest_code(void) { - register u64 stage asm("11") = 0; - - for (;;) { - GUEST_SYNC(0); - asm volatile ("ahi %0,1" : : "r"(stage)); - } + /* + * We embed diag 501 here instead of doing a ucall to avoid that + * the compiler has messed with r11 at the time of the ucall. + */ + asm volatile ( + "0: diag 0,0,0x501\n" + " ahi 11,1\n" + " j 0b\n" + ); } #define REG_COMPARE(reg) \ diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index 11c2a70a7b87..5c8224256294 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -22,18 +22,19 @@ #define VCPU_ID 5 +#define UCALL_PIO_PORT ((uint16_t)0x1000) + +/* + * ucall is embedded here to protect against compiler reshuffling registers + * before calling a function. In this test we only need to get KVM_EXIT_IO + * vmexit and preserve RBX, no additional information is needed. + */ void guest_code(void) { - /* - * use a callee-save register, otherwise the compiler - * saves it around the call to GUEST_SYNC. - */ - register u32 stage asm("rbx"); - for (;;) { - GUEST_SYNC(0); - stage++; - asm volatile ("" : : "r" (stage)); - } + asm volatile("1: in %[port], %%al\n" + "add $0x1, %%rbx\n" + "jmp 1b" + : : [port] "d" (UCALL_PIO_PORT) : "rax", "rbx"); } static void compare_regs(struct kvm_regs *left, struct kvm_regs *right) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index 3b0ffe01dacd..5dfb53546a26 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -53,12 +53,8 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - if (!(entry->ecx & CPUID_VMX)) { - fprintf(stderr, "nested VMX not enabled, skipping test\n"); - exit(KSFT_SKIP); - } + nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 0bca1cfe2c1e..a223a6401258 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -78,6 +78,8 @@ int main(int argc, char *argv[]) struct ucall uc; bool done = false; + nested_vmx_check_supported(); + /* Create VM */ vm = vm_create_default(VCPU_ID, 0, l1_guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 853e370e8a39..9ef7fab39d48 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -224,7 +224,6 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_nested_state state; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); @@ -237,10 +236,7 @@ int main(int argc, char *argv[]) * AMD currently does not implement set_nested_state, so for now we * just early out. */ - if (!(entry->ecx & CPUID_VMX)) { - fprintf(stderr, "nested VMX not enabled, skipping test\n"); - exit(KSFT_SKIP); - } + nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, 0); @@ -271,12 +267,7 @@ int main(int argc, char *argv[]) state.flags = KVM_STATE_NESTED_RUN_PENDING; test_nested_state_expect_einval(vm, &state); - /* - * TODO: When SVM support is added for KVM_SET_NESTED_STATE - * add tests here to support it like VMX. - */ - if (entry->ecx & CPUID_VMX) - test_vmx_nested_state(vm); + test_vmx_nested_state(vm); kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index f36c10eba71e..5590fd2bcf87 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -128,12 +128,8 @@ static void report(int64_t val) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - if (!(entry->ecx & CPUID_VMX)) { - fprintf(stderr, "nested VMX not enabled, skipping test\n"); - exit(KSFT_SKIP); - } + nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c new file mode 100644 index 000000000000..851ea81b9d9f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019, Google LLC. + * + * Tests for the IA32_XSS MSR. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "vmx.h" + +#define VCPU_ID 1 +#define MSR_BITS 64 + +#define X86_FEATURE_XSAVES (1<<3) + +bool is_supported_msr(u32 msr_index) +{ + struct kvm_msr_list *list; + bool found = false; + int i; + + list = kvm_get_msr_index_list(); + for (i = 0; i < list->nmsrs; ++i) { + if (list->indices[i] == msr_index) { + found = true; + break; + } + } + + free(list); + return found; +} + +int main(int argc, char *argv[]) +{ + struct kvm_cpuid_entry2 *entry; + bool xss_supported = false; + struct kvm_vm *vm; + uint64_t xss_val; + int i, r; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, 0); + + if (kvm_get_cpuid_max_basic() >= 0xd) { + entry = kvm_get_supported_cpuid_index(0xd, 1); + xss_supported = entry && !!(entry->eax & X86_FEATURE_XSAVES); + } + if (!xss_supported) { + printf("IA32_XSS is not supported by the vCPU.\n"); + exit(KSFT_SKIP); + } + + xss_val = vcpu_get_msr(vm, VCPU_ID, MSR_IA32_XSS); + TEST_ASSERT(xss_val == 0, + "MSR_IA32_XSS should be initialized to zero\n"); + + vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, xss_val); + /* + * At present, KVM only supports a guest IA32_XSS value of 0. Verify + * that trying to set the guest IA32_XSS to an unsupported value fails. + * Also, in the future when a non-zero value succeeds check that + * IA32_XSS is in the KVM_GET_MSR_INDEX_LIST. + */ + for (i = 0; i < MSR_BITS; ++i) { + r = _vcpu_set_msr(vm, VCPU_ID, MSR_IA32_XSS, 1ull << i); + TEST_ASSERT(r == 0 || is_supported_msr(MSR_IA32_XSS), + "IA32_XSS was able to be set, but was not found in KVM_GET_MSR_INDEX_LIST.\n"); + } + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index c0534e298b51..cb3fc09645c4 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -37,7 +37,7 @@ int main(int argc, char **argv) char *file = "/dev/zero"; char *p; - while ((opt = getopt(argc, argv, "m:r:n:f:tTLUSH")) != -1) { + while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) { switch (opt) { case 'm': size = atoi(optarg) * MB; diff --git a/tools/virtio/crypto/hash.h b/tools/virtio/crypto/hash.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/virtio/crypto/hash.h diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index f91aeb5fe571..8f41cd6bd5c0 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -29,4 +29,6 @@ enum dma_data_direction { #define dma_unmap_single(...) do { } while (0) #define dma_unmap_page(...) do { } while (0) +#define dma_max_mapping_size(...) SIZE_MAX + #endif diff --git a/tools/virtio/xen/xen.h b/tools/virtio/xen/xen.h new file mode 100644 index 000000000000..f569387d1403 --- /dev/null +++ b/tools/virtio/xen/xen.h @@ -0,0 +1,6 @@ +#ifndef XEN_XEN_STUB_H +#define XEN_XEN_STUB_H + +#define xen_domain() 0 + +#endif diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c index 362a01886bab..8731dfeced8b 100644 --- a/virt/kvm/arm/pmu.c +++ b/virt/kvm/arm/pmu.c @@ -8,6 +8,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> +#include <linux/perf/arm_pmu.h> #include <linux/uaccess.h> #include <asm/kvm_emulate.h> #include <kvm/arm_pmu.h> @@ -146,8 +147,7 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) if (kvm_pmu_pmc_is_chained(pmc) && kvm_pmu_idx_is_high_counter(select_idx)) counter = upper_32_bits(counter); - - else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx)) + else if (select_idx != ARMV8_PMU_CYCLE_IDX) counter = lower_32_bits(counter); return counter; @@ -193,7 +193,7 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) */ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc) { - u64 counter, reg; + u64 counter, reg, val; pmc = kvm_pmu_get_canonical_pmc(pmc); if (!pmc->perf_event) @@ -201,16 +201,19 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc) counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); - if (kvm_pmu_pmc_is_chained(pmc)) { - reg = PMEVCNTR0_EL0 + pmc->idx; - __vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter); - __vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter); + if (pmc->idx == ARMV8_PMU_CYCLE_IDX) { + reg = PMCCNTR_EL0; + val = counter; } else { - reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX) - ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx; - __vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter); + reg = PMEVCNTR0_EL0 + pmc->idx; + val = lower_32_bits(counter); } + __vcpu_sys_reg(vcpu, reg) = val; + + if (kvm_pmu_pmc_is_chained(pmc)) + __vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter); + kvm_pmu_release_perf_event(pmc); } @@ -440,8 +443,25 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); int idx = pmc->idx; + u64 period; + + cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE); + + /* + * Reset the sample period to the architectural limit, + * i.e. the point where the counter overflows. + */ + period = -(local64_read(&perf_event->count)); + + if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) + period &= GENMASK(31, 0); + + local64_set(&perf_event->hw.period_left, 0); + perf_event->attr.sample_period = period; + perf_event->hw.sample_period = period; __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx); @@ -449,6 +469,8 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); } + + cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD); } /** @@ -567,12 +589,12 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx) * high counter. */ attr.sample_period = (-counter) & GENMASK(63, 0); + if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1)) + attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED; + event = perf_event_create_kernel_counter(&attr, -1, current, kvm_pmu_perf_overflow, pmc + 1); - - if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1)) - attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED; } else { /* The initial sample period (overflow count) of an event. */ if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 8ffd07e2a160..00c747dbc82e 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -110,14 +110,11 @@ static const struct kvm_io_device_ops coalesced_mmio_ops = { int kvm_coalesced_mmio_init(struct kvm *kvm) { struct page *page; - int ret; - ret = -ENOMEM; page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) - goto out_err; + return -ENOMEM; - ret = 0; kvm->coalesced_mmio_ring = page_address(page); /* @@ -128,8 +125,7 @@ int kvm_coalesced_mmio_init(struct kvm *kvm) spin_lock_init(&kvm->ring_lock); INIT_LIST_HEAD(&kvm->coalesced_zones); -out_err: - return ret; + return 0; } void kvm_coalesced_mmio_free(struct kvm *kvm) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 66a977472a1c..5f8b89f8d915 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -772,6 +772,18 @@ void kvm_put_kvm(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_put_kvm); +/* + * Used to put a reference that was taken on behalf of an object associated + * with a user-visible file descriptor, e.g. a vcpu or device, if installation + * of the new file descriptor fails and the reference cannot be transferred to + * its final owner. In such cases, the caller is still actively using @kvm and + * will fail miserably if the refcount unexpectedly hits zero. + */ +void kvm_put_kvm_no_destroy(struct kvm *kvm) +{ + WARN_ON(refcount_dec_and_test(&kvm->users_count)); +} +EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy); static int kvm_vm_release(struct inode *inode, struct file *filp) { @@ -2360,20 +2372,23 @@ out: kvm_arch_vcpu_unblocking(vcpu); block_ns = ktime_to_ns(cur) - ktime_to_ns(start); - if (!vcpu_valid_wakeup(vcpu)) - shrink_halt_poll_ns(vcpu); - else if (halt_poll_ns) { - if (block_ns <= vcpu->halt_poll_ns) - ; - /* we had a long block, shrink polling */ - else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + if (!kvm_arch_no_poll(vcpu)) { + if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); - /* we had a short halt and our poll time is too small */ - else if (vcpu->halt_poll_ns < halt_poll_ns && - block_ns < halt_poll_ns) - grow_halt_poll_ns(vcpu); - } else - vcpu->halt_poll_ns = 0; + } else if (halt_poll_ns) { + if (block_ns <= vcpu->halt_poll_ns) + ; + /* we had a long block, shrink polling */ + else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + shrink_halt_poll_ns(vcpu); + /* we had a short halt and our poll time is too small */ + else if (vcpu->halt_poll_ns < halt_poll_ns && + block_ns < halt_poll_ns) + grow_halt_poll_ns(vcpu); + } else { + vcpu->halt_poll_ns = 0; + } + } trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu)); kvm_arch_vcpu_block_finish(vcpu); @@ -2670,17 +2685,18 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) goto unlock_vcpu_destroy; } - BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]); + vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); + BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } - kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu; + kvm->vcpus[vcpu->vcpu_idx] = vcpu; /* * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus @@ -3114,7 +3130,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); |