diff options
592 files changed, 14507 insertions, 4535 deletions
diff --git a/Documentation/DocBook/media/v4l/media-types.xml b/Documentation/DocBook/media/v4l/media-types.xml index 1af384250910..0ee0f3386cdf 100644 --- a/Documentation/DocBook/media/v4l/media-types.xml +++ b/Documentation/DocBook/media/v4l/media-types.xml @@ -57,10 +57,6 @@ <entry>Connector for a RGB composite signal.</entry> </row> <row> - <entry><constant>MEDIA_ENT_F_CONN_TEST</constant></entry> - <entry>Connector for a test generator.</entry> - </row> - <row> <entry><constant>MEDIA_ENT_F_CAM_SENSOR</constant></entry> <entry>Camera video sensor entity.</entry> </row> diff --git a/Documentation/devicetree/bindings/net/can/rcar_can.txt b/Documentation/devicetree/bindings/net/can/rcar_can.txt index 65edc055722f..8d40ab27bc8c 100644 --- a/Documentation/devicetree/bindings/net/can/rcar_can.txt +++ b/Documentation/devicetree/bindings/net/can/rcar_can.txt @@ -9,8 +9,10 @@ Required properties: "renesas,can-r8a7792" if CAN controller is a part of R8A7792 SoC. "renesas,can-r8a7793" if CAN controller is a part of R8A7793 SoC. "renesas,can-r8a7794" if CAN controller is a part of R8A7794 SoC. + "renesas,can-r8a7795" if CAN controller is a part of R8A7795 SoC. "renesas,rcar-gen1-can" for a generic R-Car Gen1 compatible device. "renesas,rcar-gen2-can" for a generic R-Car Gen2 compatible device. + "renesas,rcar-gen3-can" for a generic R-Car Gen3 compatible device. When compatible with the generic version, nodes must list the SoC-specific version corresponding to the platform first followed by the generic version. @@ -22,6 +24,15 @@ Required properties: - pinctrl-0: pin control group to be used for this controller. - pinctrl-names: must be "default". +Required properties for "renesas,can-r8a7795" compatible: +In R8A7795 SoC, "clkp2" can be CANFD clock. This is a div6 clock and can be +used by both CAN and CAN FD controller at the same time. It needs to be scaled +to maximum frequency if any of these controllers use it. This is done using +the below properties. + +- assigned-clocks: phandle of clkp2(CANFD) clock. +- assigned-clock-rates: maximum frequency of this clock. + Optional properties: - renesas,can-clock-select: R-Car CAN Clock Source Select. Valid values are: <0x0> (default) : Peripheral clock (clkp1) diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt index a4799fff0d1f..b037a9d78d93 100644 --- a/Documentation/devicetree/bindings/net/fsl-fec.txt +++ b/Documentation/devicetree/bindings/net/fsl-fec.txt @@ -12,7 +12,7 @@ Optional properties: only if property "phy-reset-gpios" is available. Missing the property will have the duration be 1 millisecond. Numbers greater than 1000 are invalid and 1 millisecond will be used instead. -- phy-reset-active-low : If present then the reset sequence using the GPIO +- phy-reset-active-high : If present then the reset sequence using the GPIO specified in the "phy-reset-gpios" property is reversed (H=reset state, L=operation state). - phy-supply : regulator that powers the Ethernet PHY. diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt new file mode 100644 index 000000000000..5ca79290eabf --- /dev/null +++ b/Documentation/devicetree/bindings/net/mediatek-net.txt @@ -0,0 +1,77 @@ +MediaTek Frame Engine Ethernet controller +========================================= + +The frame engine ethernet controller can be found on MediaTek SoCs. These SoCs +have dual GMAC each represented by a child node.. + +* Ethernet controller node + +Required properties: +- compatible: Should be "mediatek,mt7623-eth" +- reg: Address and length of the register set for the device +- interrupts: Should contain the frame engines interrupt +- clocks: the clock used by the core +- clock-names: the names of the clock listed in the clocks property. These are + "ethif", "esw", "gp2", "gp1" +- power-domains: phandle to the power domain that the ethernet is part of +- resets: Should contain a phandle to the ethsys reset signal +- reset-names: Should contain the reset signal name "eth" +- mediatek,ethsys: phandle to the syscon node that handles the port setup +- mediatek,pctl: phandle to the syscon node that handles the ports slew rate + and driver current + +Optional properties: +- interrupt-parent: Should be the phandle for the interrupt controller + that services interrupts for this device + + +* Ethernet MAC node + +Required properties: +- compatible: Should be "mediatek,eth-mac" +- reg: The number of the MAC +- phy-handle: see ethernet.txt file in the same directory. + +Example: + +eth: ethernet@1b100000 { + compatible = "mediatek,mt7623-eth"; + reg = <0 0x1b100000 0 0x20000>; + clocks = <&topckgen CLK_TOP_ETHIF_SEL>, + <ðsys CLK_ETHSYS_ESW>, + <ðsys CLK_ETHSYS_GP2>, + <ðsys CLK_ETHSYS_GP1>; + clock-names = "ethif", "esw", "gp2", "gp1"; + interrupts = <GIC_SPI 200 IRQ_TYPE_LEVEL_LOW>; + power-domains = <&scpsys MT2701_POWER_DOMAIN_ETH>; + resets = <ðsys MT2701_ETHSYS_ETH_RST>; + reset-names = "eth"; + mediatek,ethsys = <ðsys>; + mediatek,pctl = <&syscfg_pctl_a>; + #address-cells = <1>; + #size-cells = <0>; + + gmac1: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-handle = <&phy0>; + }; + + gmac2: mac@1 { + compatible = "mediatek,eth-mac"; + reg = <1>; + phy-handle = <&phy1>; + }; + + mdio-bus { + phy0: ethernet-phy@0 { + reg = <0>; + phy-mode = "rgmii"; + }; + + phy1: ethernet-phy@1 { + reg = <1>; + phy-mode = "rgmii"; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/regulator/tps65217.txt b/Documentation/devicetree/bindings/regulator/tps65217.txt index d18109657da6..4f05d208c95c 100644 --- a/Documentation/devicetree/bindings/regulator/tps65217.txt +++ b/Documentation/devicetree/bindings/regulator/tps65217.txt @@ -26,11 +26,7 @@ Example: ti,pmic-shutdown-controller; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: dcdc1 { - reg = <0>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1800000>; regulator-boot-on; @@ -38,7 +34,6 @@ Example: }; dcdc2_reg: dcdc2 { - reg = <1>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -46,7 +41,6 @@ Example: }; dcdc3_reg: dcc3 { - reg = <2>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1500000>; regulator-boot-on; @@ -54,7 +48,6 @@ Example: }; ldo1_reg: ldo1 { - reg = <3>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -62,7 +55,6 @@ Example: }; ldo2_reg: ldo2 { - reg = <4>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -70,7 +62,6 @@ Example: }; ldo3_reg: ldo3 { - reg = <5>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -78,7 +69,6 @@ Example: }; ldo4_reg: ldo4 { - reg = <6>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; diff --git a/Documentation/networking/kcm.txt b/Documentation/networking/kcm.txt new file mode 100644 index 000000000000..3476ede5bc2c --- /dev/null +++ b/Documentation/networking/kcm.txt @@ -0,0 +1,285 @@ +Kernel Connection Mulitplexor +----------------------------- + +Kernel Connection Multiplexor (KCM) is a mechanism that provides a message based +interface over TCP for generic application protocols. With KCM an application +can efficiently send and receive application protocol messages over TCP using +datagram sockets. + +KCM implements an NxM multiplexor in the kernel as diagrammed below: + ++------------+ +------------+ +------------+ +------------+ +| KCM socket | | KCM socket | | KCM socket | | KCM socket | ++------------+ +------------+ +------------+ +------------+ + | | | | + +-----------+ | | +----------+ + | | | | + +----------------------------------+ + | Multiplexor | + +----------------------------------+ + | | | | | + +---------+ | | | ------------+ + | | | | | ++----------+ +----------+ +----------+ +----------+ +----------+ +| Psock | | Psock | | Psock | | Psock | | Psock | ++----------+ +----------+ +----------+ +----------+ +----------+ + | | | | | ++----------+ +----------+ +----------+ +----------+ +----------+ +| TCP sock | | TCP sock | | TCP sock | | TCP sock | | TCP sock | ++----------+ +----------+ +----------+ +----------+ +----------+ + +KCM sockets +----------- + +The KCM sockets provide the user interface to the muliplexor. All the KCM sockets +bound to a multiplexor are considered to have equivalent function, and I/O +operations in different sockets may be done in parallel without the need for +synchronization between threads in userspace. + +Multiplexor +----------- + +The multiplexor provides the message steering. In the transmit path, messages +written on a KCM socket are sent atomically on an appropriate TCP socket. +Similarly, in the receive path, messages are constructed on each TCP socket +(Psock) and complete messages are steered to a KCM socket. + +TCP sockets & Psocks +-------------------- + +TCP sockets may be bound to a KCM multiplexor. A Psock structure is allocated +for each bound TCP socket, this structure holds the state for constructing +messages on receive as well as other connection specific information for KCM. + +Connected mode semantics +------------------------ + +Each multiplexor assumes that all attached TCP connections are to the same +destination and can use the different connections for load balancing when +transmitting. The normal send and recv calls (include sendmmsg and recvmmsg) +can be used to send and receive messages from the KCM socket. + +Socket types +------------ + +KCM supports SOCK_DGRAM and SOCK_SEQPACKET socket types. + +Message delineation +------------------- + +Messages are sent over a TCP stream with some application protocol message +format that typically includes a header which frames the messages. The length +of a received message can be deduced from the application protocol header +(often just a simple length field). + +A TCP stream must be parsed to determine message boundaries. Berkeley Packet +Filter (BPF) is used for this. When attaching a TCP socket to a multiplexor a +BPF program must be specified. The program is called at the start of receiving +a new message and is given an skbuff that contains the bytes received so far. +It parses the message header and returns the length of the message. Given this +information, KCM will construct the message of the stated length and deliver it +to a KCM socket. + +TCP socket management +--------------------- + +When a TCP socket is attached to a KCM multiplexor data ready (POLLIN) and +write space available (POLLOUT) events are handled by the multiplexor. If there +is a state change (disconnection) or other error on a TCP socket, an error is +posted on the TCP socket so that a POLLERR event happens and KCM discontinues +using the socket. When the application gets the error notification for a +TCP socket, it should unattach the socket from KCM and then handle the error +condition (the typical response is to close the socket and create a new +connection if necessary). + +KCM limits the maximum receive message size to be the size of the receive +socket buffer on the attached TCP socket (the socket buffer size can be set by +SO_RCVBUF). If the length of a new message reported by the BPF program is +greater than this limit a corresponding error (EMSGSIZE) is posted on the TCP +socket. The BPF program may also enforce a maximum messages size and report an +error when it is exceeded. + +A timeout may be set for assembling messages on a receive socket. The timeout +value is taken from the receive timeout of the attached TCP socket (this is set +by SO_RCVTIMEO). If the timer expires before assembly is complete an error +(ETIMEDOUT) is posted on the socket. + +User interface +============== + +Creating a multiplexor +---------------------- + +A new multiplexor and initial KCM socket is created by a socket call: + + socket(AF_KCM, type, protocol) + + - type is either SOCK_DGRAM or SOCK_SEQPACKET + - protocol is KCMPROTO_CONNECTED + +Cloning KCM sockets +------------------- + +After the first KCM socket is created using the socket call as described +above, additional sockets for the multiplexor can be created by cloning +a KCM socket. This is accomplished by an ioctl on a KCM socket: + + /* From linux/kcm.h */ + struct kcm_clone { + int fd; + }; + + struct kcm_clone info; + + memset(&info, 0, sizeof(info)); + + err = ioctl(kcmfd, SIOCKCMCLONE, &info); + + if (!err) + newkcmfd = info.fd; + +Attach transport sockets +------------------------ + +Attaching of transport sockets to a multiplexor is performed by calling an +ioctl on a KCM socket for the multiplexor. e.g.: + + /* From linux/kcm.h */ + struct kcm_attach { + int fd; + int bpf_fd; + }; + + struct kcm_attach info; + + memset(&info, 0, sizeof(info)); + + info.fd = tcpfd; + info.bpf_fd = bpf_prog_fd; + + ioctl(kcmfd, SIOCKCMATTACH, &info); + +The kcm_attach structure contains: + fd: file descriptor for TCP socket being attached + bpf_prog_fd: file descriptor for compiled BPF program downloaded + +Unattach transport sockets +-------------------------- + +Unattaching a transport socket from a multiplexor is straightforward. An +"unattach" ioctl is done with the kcm_unattach structure as the argument: + + /* From linux/kcm.h */ + struct kcm_unattach { + int fd; + }; + + struct kcm_unattach info; + + memset(&info, 0, sizeof(info)); + + info.fd = cfd; + + ioctl(fd, SIOCKCMUNATTACH, &info); + +Disabling receive on KCM socket +------------------------------- + +A setsockopt is used to disable or enable receiving on a KCM socket. +When receive is disabled, any pending messages in the socket's +receive buffer are moved to other sockets. This feature is useful +if an application thread knows that it will be doing a lot of +work on a request and won't be able to service new messages for a +while. Example use: + + int val = 1; + + setsockopt(kcmfd, SOL_KCM, KCM_RECV_DISABLE, &val, sizeof(val)) + +BFP programs for message delineation +------------------------------------ + +BPF programs can be compiled using the BPF LLVM backend. For exmple, +the BPF program for parsing Thrift is: + + #include "bpf.h" /* for __sk_buff */ + #include "bpf_helpers.h" /* for load_word intrinsic */ + + SEC("socket_kcm") + int bpf_prog1(struct __sk_buff *skb) + { + return load_word(skb, 0) + 4; + } + + char _license[] SEC("license") = "GPL"; + +Use in applications +=================== + +KCM accelerates application layer protocols. Specifically, it allows +applications to use a message based interface for sending and receiving +messages. The kernel provides necessary assurances that messages are sent +and received atomically. This relieves much of the burden applications have +in mapping a message based protocol onto the TCP stream. KCM also make +application layer messages a unit of work in the kernel for the purposes of +steerng and scheduling, which in turn allows a simpler networking model in +multithreaded applications. + +Configurations +-------------- + +In an Nx1 configuration, KCM logically provides multiple socket handles +to the same TCP connection. This allows parallelism between in I/O +operations on the TCP socket (for instance copyin and copyout of data is +parallelized). In an application, a KCM socket can be opened for each +processing thread and inserted into the epoll (similar to how SO_REUSEPORT +is used to allow multiple listener sockets on the same port). + +In a MxN configuration, multiple connections are established to the +same destination. These are used for simple load balancing. + +Message batching +---------------- + +The primary purpose of KCM is load balancing between KCM sockets and hence +threads in a nominal use case. Perfect load balancing, that is steering +each received message to a different KCM socket or steering each sent +message to a different TCP socket, can negatively impact performance +since this doesn't allow for affinities to be established. Balancing +based on groups, or batches of messages, can be beneficial for performance. + +On transmit, there are three ways an application can batch (pipeline) +messages on a KCM socket. + 1) Send multiple messages in a single sendmmsg. + 2) Send a group of messages each with a sendmsg call, where all messages + except the last have MSG_BATCH in the flags of sendmsg call. + 3) Create "super message" composed of multiple messages and send this + with a single sendmsg. + +On receive, the KCM module attempts to queue messages received on the +same KCM socket during each TCP ready callback. The targeted KCM socket +changes at each receive ready callback on the KCM socket. The application +does not need to configure this. + +Error handling +-------------- + +An application should include a thread to monitor errors raised on +the TCP connection. Normally, this will be done by placing each +TCP socket attached to a KCM multiplexor in epoll set for POLLERR +event. If an error occurs on an attached TCP socket, KCM sets an EPIPE +on the socket thus waking up the application thread. When the application +sees the error (which may just be a disconnect) it should unattach the +socket from KCM and then close it. It is assumed that once an error is +posted on the TCP socket the data stream is unrecoverable (i.e. an error +may have occurred in in the middle of receiving a messssge). + +TCP connection monitoring +------------------------- + +In KCM there is no means to correlate a message to the TCP socket that +was used to send or receive the message (except in the case there is +only one attached TCP socket). However, the application does retain +an open file descriptor to the socket so it will be able to get statistics +from the socket which can be used in detecting issues (such as high +retransmissions on the socket). diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt index 9f9ec9f76039..4e4b6f10d841 100644 --- a/Documentation/watchdog/watchdog-parameters.txt +++ b/Documentation/watchdog/watchdog-parameters.txt @@ -400,3 +400,7 @@ wm8350_wdt: nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) ------------------------------------------------- +sun4v_wdt: +timeout_ms: Watchdog timeout in milliseconds 1..180000, default=60000) +nowayout: Watchdog cannot be stopped once started +------------------------------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index be0b56b38720..1663ad41803c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -920,17 +920,24 @@ M: Emilio López <emilio@elopez.com.ar> S: Maintained F: drivers/clk/sunxi/ -ARM/Amlogic MesonX SoC support +ARM/Amlogic Meson SoC support M: Carlo Caione <carlo@caione.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-meson@googlegroups.com +W: http://linux-meson.com/ S: Maintained -F: drivers/media/rc/meson-ir.c -N: meson[x68] +F: arch/arm/mach-meson/ +F: arch/arm/boot/dts/meson* +N: meson ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg <tsahee@annapurnalabs.com> +M: Antoine Tenart <antoine.tenart@free-electrons.com> S: Maintained F: arch/arm/mach-alpine/ +F: arch/arm/boot/dts/alpine* +F: arch/arm64/boot/dts/al/ +F: drivers/*/*alpine* ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT M: Nicolas Ferre <nicolas.ferre@atmel.com> @@ -3446,7 +3453,6 @@ F: drivers/usb/dwc2/ DESIGNWARE USB3 DRD IP DRIVER M: Felipe Balbi <balbi@kernel.org> L: linux-usb@vger.kernel.org -L: linux-omap@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git S: Maintained F: drivers/usb/dwc3/ @@ -4522,6 +4528,12 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/dma/fsldma.* +FREESCALE GPMI NAND DRIVER +M: Han Xu <han.xu@nxp.com> +L: linux-mtd@lists.infradead.org +S: Maintained +F: drivers/mtd/nand/gpmi-nand/* + FREESCALE I2C CPM DRIVER M: Jochen Friedrich <jochen@scram.de> L: linuxppc-dev@lists.ozlabs.org @@ -4538,7 +4550,7 @@ F: include/linux/platform_data/video-imxfb.h F: drivers/video/fbdev/imxfb.c FREESCALE QUAD SPI DRIVER -M: Han Xu <han.xu@freescale.com> +M: Han Xu <han.xu@nxp.com> L: linux-mtd@lists.infradead.org S: Maintained F: drivers/mtd/spi-nor/fsl-quadspi.c @@ -4552,6 +4564,15 @@ S: Maintained F: drivers/net/ethernet/freescale/fs_enet/ F: include/linux/fs_enet_pd.h +FREESCALE IMX / MXC FEC DRIVER +M: Fugang Duan <fugang.duan@nxp.com> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/fec_main.c +F: drivers/net/ethernet/freescale/fec_ptp.c +F: drivers/net/ethernet/freescale/fec.h +F: Documentation/devicetree/bindings/net/fsl-fec.txt + FREESCALE QUICC ENGINE LIBRARY L: linuxppc-dev@lists.ozlabs.org S: Orphan @@ -6769,6 +6790,7 @@ S: Maintained F: Documentation/networking/mac80211-injection.txt F: include/net/mac80211.h F: net/mac80211/ +F: drivers/net/wireless/mac80211_hwsim.[ch] MACVLAN DRIVER M: Patrick McHardy <kaber@trash.net> @@ -7013,6 +7035,13 @@ F: include/uapi/linux/meye.h F: include/uapi/linux/ivtv* F: include/uapi/linux/uvcvideo.h +MEDIATEK ETHERNET DRIVER +M: Felix Fietkau <nbd@openwrt.org> +M: John Crispin <blogic@openwrt.org> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/mediatek/ + MEDIATEK MT7601U WIRELESS LAN DRIVER M: Jakub Kicinski <kubakici@wp.pl> L: linux-wireless@vger.kernel.org @@ -7365,7 +7394,7 @@ F: drivers/tty/isicom.c F: include/linux/isicom.h MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER -M: Felipe Balbi <balbi@kernel.org> +M: Bin Liu <b-liu@ti.com> L: linux-usb@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git S: Maintained @@ -7696,13 +7725,13 @@ S: Maintained F: arch/nios2/ NOKIA N900 POWER SUPPLY DRIVERS -M: Pali Rohár <pali.rohar@gmail.com> -S: Maintained +R: Pali Rohár <pali.rohar@gmail.com> F: include/linux/power/bq2415x_charger.h F: include/linux/power/bq27xxx_battery.h F: include/linux/power/isp1704_charger.h F: drivers/power/bq2415x_charger.c F: drivers/power/bq27xxx_battery.c +F: drivers/power/bq27xxx_battery_i2c.c F: drivers/power/isp1704_charger.c F: drivers/power/rx51_battery.c @@ -7933,11 +7962,9 @@ F: drivers/media/platform/omap3isp/ F: drivers/staging/media/omap4iss/ OMAP USB SUPPORT -M: Felipe Balbi <balbi@kernel.org> L: linux-usb@vger.kernel.org L: linux-omap@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git -S: Maintained +S: Orphan F: drivers/usb/*/*omap* F: arch/arm/*omap*/usb* @@ -9572,6 +9599,12 @@ M: Andreas Noever <andreas.noever@gmail.com> S: Maintained F: drivers/thunderbolt/ +TI BQ27XXX POWER SUPPLY DRIVER +R: Andrew F. Davis <afd@ti.com> +F: include/linux/power/bq27xxx_battery.h +F: drivers/power/bq27xxx_battery.c +F: drivers/power/bq27xxx_battery_i2c.c + TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER M: John Stultz <john.stultz@linaro.org> M: Thomas Gleixner <tglx@linutronix.de> @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc7 NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0655495470ad..8a188bc1786a 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -12,8 +12,6 @@ config ARC select BUILDTIME_EXTABLE_SORT select COMMON_CLK select CLONE_BACKWARDS - # ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev - select DEVTMPFS if !INITRAMFS_SOURCE="" select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS select GENERIC_FIND_FIRST_BIT @@ -275,14 +273,6 @@ config ARC_DCCM_BASE default "0xA0000000" depends on ARC_HAS_DCCM -config ARC_HAS_HW_MPY - bool "Use Hardware Multiplier (Normal or Faster XMAC)" - default y - help - Influences how gcc generates code for MPY operations. - If enabled, MPYxx insns are generated, provided by Standard/XMAC - Multipler. Otherwise software multipy lib is used - choice prompt "MMU Version" default ARC_MMU_V3 if ARC_CPU_770 @@ -542,14 +532,6 @@ config ARC_DBG_TLB_MISS_COUNT Counts number of I and D TLB Misses and exports them via Debugfs The counters can be cleared via Debugfs as well -if SMP - -config ARC_IPI_DBG - bool "Debug Inter Core interrupts" - default n - -endif - endif config ARC_UBOOT_SUPPORT diff --git a/arch/arc/Makefile b/arch/arc/Makefile index aeb19021099e..c8230f3395f2 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -74,10 +74,6 @@ ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB # --build-id w/o "-marclinux". Default arc-elf32-ld is OK ldflags-$(upto_gcc44) += -marclinux -ifndef CONFIG_ARC_HAS_HW_MPY - cflags-y += -mno-mpy -endif - LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index f1ac9818b751..5d4e2a07ad3e 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -39,6 +39,7 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -73,7 +74,6 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y @@ -91,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 323486d6ee83..87ee46b237ef 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -39,14 +39,10 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_AXS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -78,14 +74,12 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set # CONFIG_LOGO_LINUX_CLUT224 is not set -CONFIG_USB=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y @@ -97,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 66191cd0447e..d80daf4f7e73 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -40,14 +40,10 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_AXS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -79,14 +75,12 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set # CONFIG_LOGO_LINUX_CLUT224 is not set -CONFIG_USB=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y @@ -98,12 +92,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 138f9d887957..f41095340b6a 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -4,6 +4,7 @@ CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -26,7 +27,6 @@ CONFIG_ARC_PLAT_SIM=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -34,6 +34,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -51,7 +52,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -63,4 +63,3 @@ CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_PREEMPT is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index f68838e8068a..cfaa33cb5921 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -35,6 +35,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -49,7 +50,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -61,4 +61,3 @@ CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_PREEMPT is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 96bd1c20fb0b..bb2a8dc778b5 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -21,13 +22,11 @@ CONFIG_MODULES=y # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_SIM=y -CONFIG_ARC_BOARD_ML509=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -35,6 +34,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -49,7 +49,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -60,4 +59,3 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 31e1d95764ff..646182e93753 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -33,6 +33,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -58,7 +59,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index fcae66683ca0..ceca2541950d 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -34,12 +34,12 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set # CONFIG_BLK_DEV is not set CONFIG_NETDEVICES=y -CONFIG_NET_OSCI_LAN=y CONFIG_INPUT_EVDEV=y # CONFIG_MOUSE_PS2_ALPS is not set # CONFIG_MOUSE_PS2_LOGIPS2PP is not set @@ -58,7 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index b01b659168ea..4b6da90f6f26 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -18,15 +19,11 @@ CONFIG_MODULES=y # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_SIM=y -CONFIG_ARC_BOARD_ML509=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y -CONFIG_ARC_HAS_LL64=y -# CONFIG_ARC_HAS_RTSC is not set CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=y @@ -40,6 +37,7 @@ CONFIG_INET=y # CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -56,14 +54,11 @@ CONFIG_NETDEVICES=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -CONFIG_NET_OSCI_LAN=y # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set -CONFIG_SERIO_LIBPS2=y CONFIG_SERIO_ARC_PS2=y -CONFIG_VT_HW_CONSOLE_BINDING=y # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y @@ -75,9 +70,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_ARCPGU_RGB888=y -CONFIG_ARCPGU_DISPTYPE=0 -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 3b4dc9cebcf1..9b342eaf95ae 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -3,6 +3,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="tb10x" CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y @@ -26,12 +27,10 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLOCK is not set CONFIG_ARC_PLAT_TB10X=y CONFIG_ARC_CACHE_LINE_SHIFT=5 -CONFIG_ARC_STACK_NONEXEC=y CONFIG_HZ=250 CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk" CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -44,8 +43,8 @@ CONFIG_IP_MULTICAST=y # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_PROC_DEVICETREE=y CONFIG_NETDEVICES=y # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set @@ -55,9 +54,6 @@ CONFIG_NETDEVICES=y # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_SEEQ is not set CONFIG_STMMAC_ETH=y -CONFIG_STMMAC_DEBUG_FS=y -CONFIG_STMMAC_DA=y -CONFIG_STMMAC_CHAINED=y # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_WLAN is not set # CONFIG_INPUT is not set @@ -91,7 +87,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_LEDS_TRIGGER_TRANSIENT=y CONFIG_DMADEVICES=y CONFIG_DW_DMAC=y -CONFIG_NET_DMA=y CONFIG_ASYNC_TX_DMA=y # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set @@ -100,17 +95,16 @@ CONFIG_TMPFS=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_DEBUG_INFO=y # CONFIG_ENABLE_WARN_DEPRECATED is not set -CONFIG_MAGIC_SYSRQ=y CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_DETECT_HUNG_TASK=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_DEBUG_STACKOVERFLOW=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index fdc5be5b1029..f9f4c6f59fdb 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -10,7 +10,8 @@ #define _ASM_ARC_ARCREGS_H /* Build Configuration Registers */ -#define ARC_REG_DCCMBASE_BCR 0x61 /* DCCM Base Addr */ +#define ARC_REG_AUX_DCCM 0x18 /* DCCM Base Addr ARCv2 */ +#define ARC_REG_DCCM_BASE_BUILD 0x61 /* DCCM Base Addr ARCompact */ #define ARC_REG_CRC_BCR 0x62 #define ARC_REG_VECBASE_BCR 0x68 #define ARC_REG_PERIBASE_BCR 0x69 @@ -18,10 +19,10 @@ #define ARC_REG_DPFP_BCR 0x6C /* ARCompact: Dbl Precision FPU */ #define ARC_REG_FP_V2_BCR 0xc8 /* ARCv2 FPU */ #define ARC_REG_SLC_BCR 0xce -#define ARC_REG_DCCM_BCR 0x74 /* DCCM Present + SZ */ +#define ARC_REG_DCCM_BUILD 0x74 /* DCCM size (common) */ #define ARC_REG_TIMERS_BCR 0x75 #define ARC_REG_AP_BCR 0x76 -#define ARC_REG_ICCM_BCR 0x78 +#define ARC_REG_ICCM_BUILD 0x78 /* ICCM size (common) */ #define ARC_REG_XY_MEM_BCR 0x79 #define ARC_REG_MAC_BCR 0x7a #define ARC_REG_MUL_BCR 0x7b @@ -36,6 +37,7 @@ #define ARC_REG_IRQ_BCR 0xF3 #define ARC_REG_SMART_BCR 0xFF #define ARC_REG_CLUSTER_BCR 0xcf +#define ARC_REG_AUX_ICCM 0x208 /* ICCM Base Addr (ARCv2) */ /* status32 Bits Positions */ #define STATUS_AE_BIT 5 /* Exception active */ @@ -246,7 +248,7 @@ struct bcr_perip { #endif }; -struct bcr_iccm { +struct bcr_iccm_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int base:16, pad:5, sz:3, ver:8; #else @@ -254,17 +256,15 @@ struct bcr_iccm { #endif }; -/* DCCM Base Address Register: ARC_REG_DCCMBASE_BCR */ -struct bcr_dccm_base { +struct bcr_iccm_arcv2 { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int addr:24, ver:8; + unsigned int pad:8, sz11:4, sz01:4, sz10:4, sz00:4, ver:8; #else - unsigned int ver:8, addr:24; + unsigned int ver:8, sz00:4, sz10:4, sz01:4, sz11:4, pad:8; #endif }; -/* DCCM RAM Configuration Register: ARC_REG_DCCM_BCR */ -struct bcr_dccm { +struct bcr_dccm_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int res:21, sz:3, ver:8; #else @@ -272,6 +272,14 @@ struct bcr_dccm { #endif }; +struct bcr_dccm_arcv2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad2:12, cyc:3, pad1:1, sz1:4, sz0:4, ver:8; +#else + unsigned int ver:8, sz0:4, sz1:4, pad1:1, cyc:3, pad2:12; +#endif +}; + /* ARCompact: Both SP and DP FPU BCRs have same format */ struct bcr_fp_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN @@ -315,9 +323,9 @@ struct bcr_bpu_arcv2 { struct bcr_generic { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad:24, ver:8; + unsigned int info:24, ver:8; #else - unsigned int ver:8, pad:24; + unsigned int ver:8, info:24; #endif }; diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index 4fd7d62a6e30..49014f0ef36d 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -16,11 +16,9 @@ #ifdef CONFIG_ISA_ARCOMPACT #define TIMER0_IRQ 3 #define TIMER1_IRQ 4 -#define IPI_IRQ (NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */ #else #define TIMER0_IRQ 16 #define TIMER1_IRQ 17 -#define IPI_IRQ 19 #endif #include <linux/interrupt.h> diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 1fc18ee06cf2..37c2f751eebf 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -22,6 +22,7 @@ #define AUX_IRQ_CTRL 0x00E #define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ #define AUX_IRQ_LVL_PEND 0x200 /* Pending Intr across all levels */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ #define AUX_IRQ_PRIORITY 0x206 #define ICAUSE 0x40a #define AUX_IRQ_SELECT 0x40b @@ -115,6 +116,16 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +static inline void arc_softirq_trigger(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, irq); +} + +static inline void arc_softirq_clear(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, 0); +} + #else .macro IRQ_DISABLE scratch diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index b17830294706..c1264607bbff 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -45,11 +45,12 @@ VECTOR reserved ; Reserved slots VECTOR handle_interrupt ; (16) Timer0 VECTOR handle_interrupt ; unused (Timer1) VECTOR handle_interrupt ; unused (WDT) -VECTOR handle_interrupt ; (19) ICI (inter core interrupt) -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt ; (23) End of fixed IRQs +VECTOR handle_interrupt ; (19) Inter core Interrupt (IPI) +VECTOR handle_interrupt ; (20) perf Interrupt +VECTOR handle_interrupt ; (21) Software Triggered Intr (Self IPI) +VECTOR handle_interrupt ; unused +VECTOR handle_interrupt ; (23) unused +# End of fixed IRQs .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8 VECTOR handle_interrupt diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index 06bcedf19b62..224d1c3aa9c4 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -81,9 +81,6 @@ static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq, { switch (irq) { case TIMER0_IRQ: -#ifdef CONFIG_SMP - case IPI_IRQ: -#endif irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq); break; default: diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index bc771f58fefb..c41c364b926c 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -11,9 +11,13 @@ #include <linux/smp.h> #include <linux/irq.h> #include <linux/spinlock.h> +#include <asm/irqflags-arcv2.h> #include <asm/mcip.h> #include <asm/setup.h> +#define IPI_IRQ 19 +#define SOFTIRQ_IRQ 21 + static char smp_cpuinfo_buf[128]; static int idu_detected; @@ -22,6 +26,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static void mcip_setup_per_cpu(int cpu) { smp_ipi_irq_setup(cpu, IPI_IRQ); + smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); } static void mcip_ipi_send(int cpu) @@ -29,46 +34,44 @@ static void mcip_ipi_send(int cpu) unsigned long flags; int ipi_was_pending; + /* ARConnect can only send IPI to others */ + if (unlikely(cpu == raw_smp_processor_id())) { + arc_softirq_trigger(SOFTIRQ_IRQ); + return; + } + + raw_spin_lock_irqsave(&mcip_lock, flags); + /* - * NOTE: We must spin here if the other cpu hasn't yet - * serviced a previous message. This can burn lots - * of time, but we MUST follows this protocol or - * ipi messages can be lost!!! - * Also, we must release the lock in this loop because - * the other side may get to this same loop and not - * be able to ack -- thus causing deadlock. + * If receiver already has a pending interrupt, elide sending this one. + * Linux cross core calling works well with concurrent IPIs + * coalesced into one + * see arch/arc/kernel/smp.c: ipi_send_msg_one() */ + __mcip_cmd(CMD_INTRPT_READ_STATUS, cpu); + ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK); + if (!ipi_was_pending) + __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); - do { - raw_spin_lock_irqsave(&mcip_lock, flags); - __mcip_cmd(CMD_INTRPT_READ_STATUS, cpu); - ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK); - if (ipi_was_pending == 0) - break; /* break out but keep lock */ - raw_spin_unlock_irqrestore(&mcip_lock, flags); - } while (1); - - __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); - -#ifdef CONFIG_ARC_IPI_DBG - if (ipi_was_pending) - pr_info("IPI ACK delayed from cpu %d\n", cpu); -#endif } static void mcip_ipi_clear(int irq) { unsigned int cpu, c; unsigned long flags; - unsigned int __maybe_unused copy; + + if (unlikely(irq == SOFTIRQ_IRQ)) { + arc_softirq_clear(irq); + return; + } raw_spin_lock_irqsave(&mcip_lock, flags); /* Who sent the IPI */ __mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0); - copy = cpu = read_aux_reg(ARC_REG_MCIP_READBACK); /* 1,2,4,8... */ + cpu = read_aux_reg(ARC_REG_MCIP_READBACK); /* 1,2,4,8... */ /* * In rare case, multiple concurrent IPIs sent to same target can @@ -82,12 +85,6 @@ static void mcip_ipi_clear(int irq) } while (cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); - -#ifdef CONFIG_ARC_IPI_DBG - if (c != __ffs(copy)) - pr_info("IPIs from %x coalesced to %x\n", - copy, raw_smp_processor_id()); -#endif } static void mcip_probe_n_setup(void) @@ -111,10 +108,11 @@ static void mcip_probe_n_setup(void) READ_BCR(ARC_REG_MCIP_BCR, mp); sprintf(smp_cpuinfo_buf, - "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n", + "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n", mp.ver, mp.num_cores, IS_AVAIL1(mp.ipi, "IPI "), IS_AVAIL1(mp.idu, "IDU "), + IS_AVAIL1(mp.llm, "LLM "), IS_AVAIL1(mp.dbg, "DEBUG "), IS_AVAIL1(mp.gfrc, "GFRC")); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a7edceba5f84..cdc821df1809 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -42,6 +42,53 @@ struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; +static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu) +{ + if (is_isa_arcompact()) { + struct bcr_iccm_arcompact iccm; + struct bcr_dccm_arcompact dccm; + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + cpu->iccm.sz = 4096 << iccm.sz; /* 8K to 512K */ + cpu->iccm.base_addr = iccm.base << 16; + } + + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + unsigned long base; + cpu->dccm.sz = 2048 << dccm.sz; /* 2K to 256K */ + + base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD); + cpu->dccm.base_addr = base & ~0xF; + } + } else { + struct bcr_iccm_arcv2 iccm; + struct bcr_dccm_arcv2 dccm; + unsigned long region; + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + cpu->iccm.sz = 256 << iccm.sz00; /* 512B to 16M */ + if (iccm.sz00 == 0xF && iccm.sz01 > 0) + cpu->iccm.sz <<= iccm.sz01; + + region = read_aux_reg(ARC_REG_AUX_ICCM); + cpu->iccm.base_addr = region & 0xF0000000; + } + + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + cpu->dccm.sz = 256 << dccm.sz0; + if (dccm.sz0 == 0xF && dccm.sz1 > 0) + cpu->dccm.sz <<= dccm.sz1; + + region = read_aux_reg(ARC_REG_AUX_DCCM); + cpu->dccm.base_addr = region & 0xF0000000; + } + } +} + static void read_arc_build_cfg_regs(void) { struct bcr_perip uncached_space; @@ -76,36 +123,11 @@ static void read_arc_build_cfg_regs(void) cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0; /* 1,3 */ cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0; cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */ - - /* Note that we read the CCM BCRs independent of kernel config - * This is to catch the cases where user doesn't know that - * CCMs are present in hardware build - */ - { - struct bcr_iccm iccm; - struct bcr_dccm dccm; - struct bcr_dccm_base dccm_base; - unsigned int bcr_32bit_val; - - bcr_32bit_val = read_aux_reg(ARC_REG_ICCM_BCR); - if (bcr_32bit_val) { - iccm = *((struct bcr_iccm *)&bcr_32bit_val); - cpu->iccm.base_addr = iccm.base << 16; - cpu->iccm.sz = 0x2000 << (iccm.sz - 1); - } - - bcr_32bit_val = read_aux_reg(ARC_REG_DCCM_BCR); - if (bcr_32bit_val) { - dccm = *((struct bcr_dccm *)&bcr_32bit_val); - cpu->dccm.sz = 0x800 << (dccm.sz); - - READ_BCR(ARC_REG_DCCMBASE_BCR, dccm_base); - cpu->dccm.base_addr = dccm_base.addr << 8; - } - } - READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem); + /* Read CCM BCRs for boot reporting even if not enabled in Kconfig */ + read_decode_ccm_bcr(cpu); + read_decode_mmu_bcr(); read_decode_cache_bcr(); @@ -237,8 +259,6 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt); } - n += scnprintf(buf + n, len - n, "%s", - IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY)); } n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index ef6e9e15b82a..424e937da5c8 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -336,11 +336,8 @@ irqreturn_t do_IPI(int irq, void *dev_id) int rc; rc = __do_IPI(msg); -#ifdef CONFIG_ARC_IPI_DBG - /* IPI received but no valid @msg */ if (rc) pr_info("IPI with bogus msg %ld in %ld\n", msg, copy); -#endif pending &= ~(1U << msg); } while (pending); diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 7a6a58ef8aaf..43788b1a1ac5 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -195,5 +195,7 @@ CFLAGS_font.o := -Dstatic= $(obj)/font.c: $(FONTC) $(call cmd,shipped) +AFLAGS_hyp-stub.o := -Wa,-march=armv7-a + $(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S $(call cmd,shipped) diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index f3db13d2d90e..0cc150b87b86 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -285,8 +285,10 @@ }; }; + +/include/ "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; /* * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only * mode") at poweroff. Most BeagleBone versions do not support RTC-only @@ -307,17 +309,12 @@ ti,pmic-shutdown-controller; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; regulator-name = "vdds_dpr"; regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -327,7 +324,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -337,25 +333,21 @@ }; ldo1_reg: regulator@3 { - reg = <3>; regulator-name = "vio,vrtc,vdds"; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; regulator-name = "vdd_3v3aux"; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; regulator-name = "vdd_1v8"; regulator-always-on; }; ldo4_reg: regulator@6 { - reg = <6>; regulator-name = "vdd_3v3a"; regulator-always-on; }; diff --git a/arch/arm/boot/dts/am335x-chilisom.dtsi b/arch/arm/boot/dts/am335x-chilisom.dtsi index fda457b07e15..857d9894103a 100644 --- a/arch/arm/boot/dts/am335x-chilisom.dtsi +++ b/arch/arm/boot/dts/am335x-chilisom.dtsi @@ -128,21 +128,16 @@ }; -&tps { - compatible = "ti,tps65217"; +/include/ "tps65217.dtsi" +&tps { regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; regulator-name = "vdds_dpr"; regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -152,7 +147,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -162,28 +156,24 @@ }; ldo1_reg: regulator@3 { - reg = <3>; regulator-name = "vio,vrtc,vdds"; regulator-boot-on; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; regulator-name = "vdd_3v3aux"; regulator-boot-on; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; regulator-name = "vdd_1v8"; regulator-boot-on; regulator-always-on; }; ldo4_reg: regulator@6 { - reg = <6>; regulator-name = "vdd_3v3d"; regulator-boot-on; regulator-always-on; diff --git a/arch/arm/boot/dts/am335x-nano.dts b/arch/arm/boot/dts/am335x-nano.dts index 77559a1ded60..f313999c503e 100644 --- a/arch/arm/boot/dts/am335x-nano.dts +++ b/arch/arm/boot/dts/am335x-nano.dts @@ -375,15 +375,11 @@ wp-gpios = <&gpio3 18 0>; }; -&tps { - compatible = "ti,tps65217"; +#include "tps65217.dtsi" +&tps { regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* +1.5V voltage with ±4% tolerance */ regulator-min-microvolt = <1450000>; regulator-max-microvolt = <1550000>; @@ -392,7 +388,6 @@ }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.1V with ±4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <915000>; @@ -402,7 +397,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with ±4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <915000>; @@ -412,7 +406,6 @@ }; ldo1_reg: regulator@3 { - reg = <3>; /* +1.8V voltage with ±4% tolerance */ regulator-min-microvolt = <1750000>; regulator-max-microvolt = <1870000>; @@ -421,7 +414,6 @@ }; ldo2_reg: regulator@4 { - reg = <4>; /* +3.3V voltage with ±4% tolerance */ regulator-min-microvolt = <3175000>; regulator-max-microvolt = <3430000>; @@ -430,7 +422,6 @@ }; ldo3_reg: regulator@5 { - reg = <5>; /* +1.8V voltage with ±4% tolerance */ regulator-min-microvolt = <1750000>; regulator-max-microvolt = <1870000>; @@ -439,7 +430,6 @@ }; ldo4_reg: regulator@6 { - reg = <6>; /* +3.3V voltage with ±4% tolerance */ regulator-min-microvolt = <3175000>; regulator-max-microvolt = <3430000>; diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts index 471a3a70ea1f..8867aaaec54d 100644 --- a/arch/arm/boot/dts/am335x-pepper.dts +++ b/arch/arm/boot/dts/am335x-pepper.dts @@ -420,9 +420,9 @@ vin-supply = <&vbat>; }; -&tps { - compatible = "ti,tps65217"; +/include/ "tps65217.dtsi" +&tps { backlight { isel = <1>; /* ISET1 */ fdim = <200>; /* TPS65217_BL_FDIM_200HZ */ @@ -430,17 +430,12 @@ }; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* VDD_1V8 system supply */ regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_CORE voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -450,7 +445,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_MPU voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -460,21 +454,18 @@ }; ldo1_reg: regulator@3 { - reg = <3>; /* VRTC 1.8V always-on supply */ regulator-name = "vrtc,vdds"; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; /* 3.3V rail */ regulator-name = "vdd_3v3aux"; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; /* VDD_3V3A 3.3V rail */ regulator-name = "vdd_3v3a"; regulator-min-microvolt = <3300000>; @@ -482,7 +473,6 @@ }; ldo4_reg: regulator@6 { - reg = <6>; /* VDD_3V3B 3.3V rail */ regulator-name = "vdd_3v3b"; regulator-always-on; diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts index 1b5b044fcd91..865de8500f1c 100644 --- a/arch/arm/boot/dts/am335x-shc.dts +++ b/arch/arm/boot/dts/am335x-shc.dts @@ -46,7 +46,7 @@ gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>; linux,code = <KEY_BACK>; debounce-interval = <1000>; - gpio-key,wakeup; + wakeup-source; }; front_button { @@ -54,7 +54,7 @@ gpios = <&gpio1 25 GPIO_ACTIVE_HIGH>; linux,code = <KEY_FRONT>; debounce-interval = <1000>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/am335x-sl50.dts b/arch/arm/boot/dts/am335x-sl50.dts index d38edfa53bb9..3303c281697b 100644 --- a/arch/arm/boot/dts/am335x-sl50.dts +++ b/arch/arm/boot/dts/am335x-sl50.dts @@ -375,19 +375,16 @@ pinctrl-0 = <&uart4_pins>; }; +#include "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; ti,pmic-shutdown-controller; interrupt-parent = <&intc>; interrupts = <7>; /* NNMI */ regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* VDDS_DDR */ regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; @@ -395,7 +392,6 @@ }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -405,7 +401,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -415,7 +410,6 @@ }; ldo1_reg: regulator@3 { - reg = <3>; /* VRTC / VIO / VDDS*/ regulator-always-on; regulator-min-microvolt = <1800000>; @@ -423,7 +417,6 @@ }; ldo2_reg: regulator@4 { - reg = <4>; /* VDD_3V3AUX */ regulator-always-on; regulator-min-microvolt = <3300000>; @@ -431,7 +424,6 @@ }; ldo3_reg: regulator@5 { - reg = <5>; /* VDD_1V8 */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -439,7 +431,6 @@ }; ldo4_reg: regulator@6 { - reg = <6>; /* VDD_3V3A */ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 36c0fa6c362a..a0986c65be0c 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -173,6 +173,8 @@ sound0_master: simple-audio-card,codec { sound-dai = <&tlv320aic3104>; + assigned-clocks = <&clkoutmux2_clk_mux>; + assigned-clock-parents = <&sys_clk2_dclk_div>; clocks = <&clkout2_clk>; }; }; @@ -796,6 +798,8 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <&mcasp3_pins_default>; pinctrl-1 = <&mcasp3_pins_sleep>; + assigned-clocks = <&mcasp3_ahclkx_mux>; + assigned-clock-parents = <&sys_clkin2>; status = "okay"; op-mode = <0>; /* MCASP_IIS_MODE */ diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts index 8d93882dc8d5..1c06cb76da07 100644 --- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts +++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts @@ -545,7 +545,7 @@ ti,debounce-tol = /bits/ 16 <10>; ti,debounce-rep = /bits/ 16 <1>; - linux,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 4f6ae921656f..f74d3db4846d 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -896,7 +896,6 @@ #size-cells = <1>; reg = <0x2100000 0x10000>; ranges = <0 0x2100000 0x10000>; - interrupt-parent = <&intc>; clocks = <&clks IMX6QDL_CLK_CAAM_MEM>, <&clks IMX6QDL_CLK_CAAM_ACLK>, <&clks IMX6QDL_CLK_CAAM_IPG>, diff --git a/arch/arm/boot/dts/kirkwood-ds112.dts b/arch/arm/boot/dts/kirkwood-ds112.dts index bf4143c6cb8f..b84af3da8c84 100644 --- a/arch/arm/boot/dts/kirkwood-ds112.dts +++ b/arch/arm/boot/dts/kirkwood-ds112.dts @@ -14,7 +14,7 @@ #include "kirkwood-synology.dtsi" / { - model = "Synology DS111"; + model = "Synology DS112"; compatible = "synology,ds111", "marvell,kirkwood"; memory { diff --git a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts index 420788229e6f..aae8a7aceab7 100644 --- a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts +++ b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts @@ -228,6 +228,37 @@ }; }; +&devbus_bootcs { + status = "okay"; + devbus,keep-config; + + flash@0 { + compatible = "jedec-flash"; + reg = <0 0x40000>; + bank-width = <1>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + header@0 { + reg = <0 0x30000>; + read-only; + }; + + uboot@30000 { + reg = <0x30000 0xF000>; + read-only; + }; + + uboot_env@3F000 { + reg = <0x3F000 0x1000>; + }; + }; + }; +}; + &mdio { status = "okay"; diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts index 6713b1ea732b..01d239c3eaaa 100644 --- a/arch/arm/boot/dts/r8a7791-porter.dts +++ b/arch/arm/boot/dts/r8a7791-porter.dts @@ -283,7 +283,6 @@ pinctrl-names = "default"; status = "okay"; - renesas,enable-gpio = <&gpio5 31 GPIO_ACTIVE_HIGH>; }; &usbphy { diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h index 1afe24629d1f..b0c912feaa2f 100644 --- a/arch/arm/boot/dts/sama5d2-pinfunc.h +++ b/arch/arm/boot/dts/sama5d2-pinfunc.h @@ -90,7 +90,7 @@ #define PIN_PA14__I2SC1_MCK PINMUX_PIN(PIN_PA14, 4, 2) #define PIN_PA14__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA14, 5, 1) #define PIN_PA14__D9 PINMUX_PIN(PIN_PA14, 6, 2) -#define PIN_PA15 14 +#define PIN_PA15 15 #define PIN_PA15__GPIO PINMUX_PIN(PIN_PA15, 0, 0) #define PIN_PA15__SPI0_MOSI PINMUX_PIN(PIN_PA15, 1, 1) #define PIN_PA15__TF1 PINMUX_PIN(PIN_PA15, 2, 1) diff --git a/arch/arm/boot/dts/tps65217.dtsi b/arch/arm/boot/dts/tps65217.dtsi new file mode 100644 index 000000000000..a63272422d76 --- /dev/null +++ b/arch/arm/boot/dts/tps65217.dtsi @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Integrated Power Management Chip + * http://www.ti.com/lit/ds/symlink/tps65217.pdf + */ + +&tps { + compatible = "ti,tps65217"; + + regulators { + #address-cells = <1>; + #size-cells = <0>; + + dcdc1_reg: regulator@0 { + reg = <0>; + regulator-compatible = "dcdc1"; + }; + + dcdc2_reg: regulator@1 { + reg = <1>; + regulator-compatible = "dcdc2"; + }; + + dcdc3_reg: regulator@2 { + reg = <2>; + regulator-compatible = "dcdc3"; + }; + + ldo1_reg: regulator@3 { + reg = <3>; + regulator-compatible = "ldo1"; + }; + + ldo2_reg: regulator@4 { + reg = <4>; + regulator-compatible = "ldo2"; + }; + + ldo3_reg: regulator@5 { + reg = <5>; + regulator-compatible = "ldo3"; + }; + + ldo4_reg: regulator@6 { + reg = <6>; + regulator-compatible = "ldo4"; + }; + }; +}; diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 7da5503c0591..e08d15184056 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void) u32 irqstat; asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat)); + dsb(sy); return irqstat; } diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 0375c8caa061..9408a994cc91 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<<compound_order(page)) * XEN_PFN_PER_PAGE; + bool local = (page_pfn <= dev_pfn) && + (dev_pfn - page_pfn < compound_pages); + /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. So if the first xen_pfn == mfn the page is local - * otherwise it's a foreign page grant-mapped in dom0. If the page is - * local we can safely call the native dma_ops function, otherwise we - * call the xen specific function. + * Dom0 is mapped 1:1, while the Linux page can span across + * multiple Xen pages, it's not possible for it to contain a + * mix of local and foreign Xen pages. So if the first xen_pfn + * == mfn the page is local otherwise it's a foreign page + * grant-mapped in dom0. If the page is local we can safely + * call the native dma_ops function, otherwise we call the xen + * specific function. */ if (local) __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 2c5f160be65e..ad325a8c7e1e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -88,6 +88,7 @@ obj-$(CONFIG_DEBUG_LL) += debug.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o +AFLAGS_hyp-stub.o :=-Wa,-march=armv7-a ifeq ($(CONFIG_ARM_PSCI),y) obj-$(CONFIG_SMP) += psci_smp.o endif diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 5fa69d7bae58..99361f11354a 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -161,7 +161,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_core_regs(void) diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 7f33b2056ae6..0f6600f05137 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -206,7 +206,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, run->mmio.is_write = is_write; run->mmio.phys_addr = fault_ipa; run->mmio.len = len; - memcpy(run->mmio.data, data_buf, len); + if (is_write) + memcpy(run->mmio.data, data_buf, len); if (!ret) { /* We handled the access successfully in the kernel. */ diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 809827265fb3..bab814d2f37d 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -18,6 +18,7 @@ #include <asm/setup.h> #include <asm/mach/arch.h> +#include <asm/system_info.h> #include "common.h" @@ -77,12 +78,31 @@ static const char *const n900_boards_compat[] __initconst = { NULL, }; +/* Set system_rev from atags */ +static void __init rx51_set_system_rev(const struct tag *tags) +{ + const struct tag *tag; + + if (tags->hdr.tag != ATAG_CORE) + return; + + for_each_tag(tag, tags) { + if (tag->hdr.tag == ATAG_REVISION) { + system_rev = tag->u.revision.rev; + break; + } + } +} + /* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags, * save them while the data is still not overwritten */ static void __init rx51_reserve(void) { - save_atags((const struct tag *)(PAGE_OFFSET + 0x100)); + const struct tag *tags = (const struct tag *)(PAGE_OFFSET + 0x100); + + save_atags(tags); + rx51_set_system_rev(tags); omap_reserve(); } diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 7b76ce01c21d..8633c703546a 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base) static void set_onenand_cfg(void __iomem *onenand_base) { - u32 reg; + u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT; - reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); - reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9)); reg |= (latency << ONENAND_SYS_CFG1_BRL_SHIFT) | ONENAND_SYS_CFG1_BL_16; if (onenand_flags & ONENAND_FLAG_SYNCREAD) @@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base) reg |= ONENAND_SYS_CFG1_VHF; else reg &= ~ONENAND_SYS_CFG1_VHF; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); } @@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) } } + onenand_async.sync_write = true; omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 0437537751bc..f7ff3b9dad87 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -191,12 +191,22 @@ static int _omap_device_notifier_call(struct notifier_block *nb, { struct platform_device *pdev = to_platform_device(dev); struct omap_device *od; + int err; switch (event) { case BUS_NOTIFY_DEL_DEVICE: if (pdev->archdata.od) omap_device_delete(pdev->archdata.od); break; + case BUS_NOTIFY_UNBOUND_DRIVER: + od = to_omap_device(pdev); + if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED)) { + dev_info(dev, "enabled after unload, idling\n"); + err = omap_device_idle(pdev); + if (err) + dev_err(dev, "failed to idle\n"); + } + break; case BUS_NOTIFY_ADD_DEVICE: if (pdev->dev.of_node) omap_device_build_from_dt(pdev); @@ -602,8 +612,10 @@ static int _od_runtime_resume(struct device *dev) int ret; ret = omap_device_enable(pdev); - if (ret) + if (ret) { + dev_err(dev, "use pm_runtime_put_sync_suspend() in driver?\n"); return ret; + } return pm_generic_runtime_resume(dev); } diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h index 9cb11215ceba..b3a4ed5289ec 100644 --- a/arch/arm/mach-shmobile/common.h +++ b/arch/arm/mach-shmobile/common.h @@ -4,7 +4,6 @@ extern void shmobile_init_delay(void); extern void shmobile_boot_vector(void); extern unsigned long shmobile_boot_fn; -extern unsigned long shmobile_boot_arg; extern unsigned long shmobile_boot_size; extern void shmobile_smp_boot(void); extern void shmobile_smp_sleep(void); diff --git a/arch/arm/mach-shmobile/headsmp-scu.S b/arch/arm/mach-shmobile/headsmp-scu.S index fa5248c52399..5e503d91ad70 100644 --- a/arch/arm/mach-shmobile/headsmp-scu.S +++ b/arch/arm/mach-shmobile/headsmp-scu.S @@ -38,9 +38,3 @@ ENTRY(shmobile_boot_scu) b secondary_startup ENDPROC(shmobile_boot_scu) - - .text - .align 2 - .globl shmobile_scu_base -shmobile_scu_base: - .space 4 diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S index 330c1fc63197..32e0bf6e3ccb 100644 --- a/arch/arm/mach-shmobile/headsmp.S +++ b/arch/arm/mach-shmobile/headsmp.S @@ -24,7 +24,6 @@ .arm .align 12 ENTRY(shmobile_boot_vector) - ldr r0, 2f ldr r1, 1f bx r1 @@ -34,9 +33,6 @@ ENDPROC(shmobile_boot_vector) .globl shmobile_boot_fn shmobile_boot_fn: 1: .space 4 - .globl shmobile_boot_arg -shmobile_boot_arg: -2: .space 4 .globl shmobile_boot_size shmobile_boot_size: .long . - shmobile_boot_vector @@ -46,13 +42,15 @@ shmobile_boot_size: */ ENTRY(shmobile_smp_boot) - @ r0 = MPIDR_HWID_BITMASK mrc p15, 0, r1, c0, c0, 5 @ r1 = MPIDR - and r0, r1, r0 @ r0 = cpu_logical_map() value + and r0, r1, #0xffffff @ MPIDR_HWID_BITMASK + @ r0 = cpu_logical_map() value mov r1, #0 @ r1 = CPU index - adr r5, 1f @ array of per-cpu mpidr values - adr r6, 2f @ array of per-cpu functions - adr r7, 3f @ array of per-cpu arguments + adr r2, 1f + ldmia r2, {r5, r6, r7} + add r5, r5, r2 @ array of per-cpu mpidr values + add r6, r6, r2 @ array of per-cpu functions + add r7, r7, r2 @ array of per-cpu arguments shmobile_smp_boot_find_mpidr: ldr r8, [r5, r1, lsl #2] @@ -80,12 +78,18 @@ ENTRY(shmobile_smp_sleep) b shmobile_smp_boot ENDPROC(shmobile_smp_sleep) + .align 2 +1: .long shmobile_smp_mpidr - . + .long shmobile_smp_fn - 1b + .long shmobile_smp_arg - 1b + + .bss .globl shmobile_smp_mpidr shmobile_smp_mpidr: -1: .space NR_CPUS * 4 + .space NR_CPUS * 4 .globl shmobile_smp_fn shmobile_smp_fn: -2: .space NR_CPUS * 4 + .space NR_CPUS * 4 .globl shmobile_smp_arg shmobile_smp_arg: -3: .space NR_CPUS * 4 + .space NR_CPUS * 4 diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c index 911884f7e28b..aba75c89f9c1 100644 --- a/arch/arm/mach-shmobile/platsmp-apmu.c +++ b/arch/arm/mach-shmobile/platsmp-apmu.c @@ -123,7 +123,6 @@ void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus, { /* install boot code shared by all CPUs */ shmobile_boot_fn = virt_to_phys(shmobile_smp_boot); - shmobile_boot_arg = MPIDR_HWID_BITMASK; /* perform per-cpu setup */ apmu_parse_cfg(apmu_init_cpu, apmu_config, num); diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c index 64663110ab6c..081a097c9219 100644 --- a/arch/arm/mach-shmobile/platsmp-scu.c +++ b/arch/arm/mach-shmobile/platsmp-scu.c @@ -17,6 +17,9 @@ #include <asm/smp_scu.h> #include "common.h" + +void __iomem *shmobile_scu_base; + static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -41,7 +44,6 @@ void __init shmobile_smp_scu_prepare_cpus(unsigned int max_cpus) { /* install boot code shared by all CPUs */ shmobile_boot_fn = virt_to_phys(shmobile_smp_boot); - shmobile_boot_arg = MPIDR_HWID_BITMASK; /* enable SCU and cache coherency on booting CPU */ scu_enable(shmobile_scu_base); diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c index b854fe2095ad..0b024a9dbd43 100644 --- a/arch/arm/mach-shmobile/smp-r8a7779.c +++ b/arch/arm/mach-shmobile/smp-r8a7779.c @@ -92,8 +92,6 @@ static void __init r8a7779_smp_prepare_cpus(unsigned int max_cpus) { /* Map the reset vector (in headsmp-scu.S, headsmp.S) */ __raw_writel(__pa(shmobile_boot_vector), AVECR); - shmobile_boot_fn = virt_to_phys(shmobile_boot_scu); - shmobile_boot_arg = (unsigned long)shmobile_scu_base; /* setup r8a7779 specific SCU bits */ shmobile_scu_base = IOMEM(R8A7779_SCU_BASE); diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 4b4058db0781..66353caa35b9 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -173,7 +173,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c index cf30daff8932..d19b1ad29b07 100644 --- a/arch/arm/mm/pageattr.c +++ b/arch/arm/mm/pageattr.c @@ -49,6 +49,9 @@ static int change_memory_common(unsigned long addr, int numpages, WARN_ON_ONCE(1); } + if (!numpages) + return 0; + if (start < MODULES_VADDR || start >= MODULES_END) return -EINVAL; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bf464de33f52..f50608674580 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,13 +34,13 @@ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. * - * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). * VMALLOC_START: beginning of the kernel VA space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ -#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) +#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT - 1)) * sizeof(struct page), PUD_SIZE) #ifndef CONFIG_KASAN #define VMALLOC_START (VA_START) @@ -51,7 +51,8 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index fcb778899a38..9e54ad7c240a 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -194,7 +194,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } /** diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 9142e082f5f3..5dd2a26444ec 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -149,16 +149,6 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) switch (nr_pri_bits) { case 7: - write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); - write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); - case 6: - write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); - default: - write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); - } - - switch (nr_pri_bits) { - case 7: write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2); write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2); case 6: @@ -167,6 +157,16 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2); } + switch (nr_pri_bits) { + case 7: + write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); + write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); + case 6: + write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); + default: + write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); + } + switch (max_lr_idx) { case 15: write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index f3b061e67bfe..7802f216a67a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -319,8 +319,8 @@ void __init mem_init(void) #endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG((unsigned long)vmemmap, - (unsigned long)vmemmap + VMEMMAP_SIZE), + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), MLM((unsigned long)virt_to_page(PAGE_OFFSET), (unsigned long)virt_to_page(high_memory)), #endif diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 4c893b5189dd..232f787a088a 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -53,10 +53,10 @@ unsigned long arch_mmap_rnd(void) #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_32BIT)) - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c index 8c6d76c9b2d6..d9907e57e9b9 100644 --- a/arch/mips/jz4740/gpio.c +++ b/arch/mips/jz4740/gpio.c @@ -270,7 +270,7 @@ uint32_t jz_gpio_port_get_value(int port, uint32_t mask) } EXPORT_SYMBOL(jz_gpio_port_get_value); -#define IRQ_TO_BIT(irq) BIT(irq_to_gpio(irq) & 0x1f) +#define IRQ_TO_BIT(irq) BIT((irq - JZ4740_IRQ_GPIO(0)) & 0x1f) static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int irq) { diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S index 5ce3b746cedc..b4ac6374a38f 100644 --- a/arch/mips/kernel/r2300_fpu.S +++ b/arch/mips/kernel/r2300_fpu.S @@ -125,7 +125,7 @@ LEAF(_restore_fp_context) END(_restore_fp_context) .set reorder - .type fault@function + .type fault, @function .ent fault fault: li v0, -EFAULT jr ra diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index f09546ee2cdc..17732f876eff 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -358,7 +358,7 @@ LEAF(_restore_msa_all_upper) .set reorder - .type fault@function + .type fault, @function .ent fault fault: li v0, -EFAULT # failure jr ra diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index ae790c575d4f..bf14da9f3e33 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode) asmlinkage void do_ov(struct pt_regs *regs) { enum ctx_state prev_state; - siginfo_t info; + siginfo_t info = { + .si_signo = SIGFPE, + .si_code = FPE_INTOVF, + .si_addr = (void __user *)regs->cp0_epc, + }; prev_state = exception_enter(); die_if_kernel("Integer overflow", regs); - info.si_code = FPE_INTOVF; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); exception_exit(prev_state); } @@ -874,7 +874,7 @@ out: void do_trap_or_bp(struct pt_regs *regs, unsigned int code, const char *str) { - siginfo_t info; + siginfo_t info = { 0 }; char b[40]; #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, else info.si_code = FPE_INTOVF; info.si_signo = SIGFPE; - info.si_errno = 0; info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); break; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 8bc3977576e6..3110447ab1e9 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_to_user(uaddr, vs, 16); + return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_from_user(vs, uaddr, 16); + return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0; } else { return -EINVAL; } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 5c81fdd032c3..353037699512 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -146,7 +146,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int(); + rnd = get_random_long(); rnd <<= PAGE_SHIFT; if (TASK_IS_32BIT_ADDR) rnd &= 0xfffffful; @@ -174,7 +174,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) static inline unsigned long brk_rnd(void) { - unsigned long rnd = get_random_int(); + unsigned long rnd = get_random_long(); rnd = rnd << PAGE_SHIFT; /* 8MB for 32bit, 256MB for 64bit */ diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 249647578e58..91dec32c77b7 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void) sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK; sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF; - c->scache.sets = 64 << sets; + if (sets) + c->scache.sets = 64 << sets; line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK; line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF; - c->scache.linesz = 2 << line_sz; + if (line_sz) + c->scache.linesz = 2 << line_sz; assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK; assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF; @@ -176,9 +178,12 @@ static int __init mips_sc_probe_cm3(void) c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize); - c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + if (c->scache.linesz) { + c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + return 1; + } - return 1; + return 0; } static inline int __init mips_sc_probe(void) diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h index f84ff12574b7..6d8276cd25ca 100644 --- a/arch/parisc/include/asm/floppy.h +++ b/arch/parisc/include/asm/floppy.h @@ -33,7 +33,7 @@ * floppy accesses go through the track buffer. */ #define _CROSS_64KB(a,s,vdma) \ -(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) +(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) #define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1) diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 35bdccbb2036..b75039f92116 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -361,8 +361,9 @@ #define __NR_membarrier (__NR_Linux + 343) #define __NR_userfaultfd (__NR_Linux + 344) #define __NR_mlock2 (__NR_Linux + 345) +#define __NR_copy_file_range (__NR_Linux + 346) -#define __NR_Linux_syscalls (__NR_mlock2 + 1) +#define __NR_Linux_syscalls (__NR_copy_file_range + 1) #define __IGNORE_select /* newselect */ diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9585c81f755f..ce0b2b4075c7 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - /* Do the secure computing check first. */ secure_computing_strict(regs->gr[20]); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - ret = -1L; + tracehook_report_syscall_entry(regs)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + regs->gr[20] = -1UL; + goto out; + } #ifdef CONFIG_64BIT if (!is_compat_task()) @@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); - return ret ? : regs->gr[20]; +out: + return regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 3fbd7252a4b2..fbafa0d0e2bf 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -343,7 +343,7 @@ tracesys_next: #endif comiclr,>>= __NR_Linux_syscalls, %r20, %r0 - b,n .Lsyscall_nosys + b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 @@ -359,6 +359,9 @@ tracesys_next: be 0(%sr7,%r19) ldo R%tracesys_exit(%r2),%r2 +.Ltracesys_nosys: + ldo -ENOSYS(%r0),%r28 /* set errno */ + /* Do *not* call this function on the gateway page, because it makes a direct call to syscall_trace. */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index d4ffcfbc9885..585d50fc75c0 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -441,6 +441,7 @@ ENTRY_SAME(membarrier) ENTRY_SAME(userfaultfd) ENTRY_SAME(mlock2) /* 345 */ + ENTRY_SAME(copy_file_range) .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 301be3126ae3..650cfb31ea3d 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata) eeh_pcid_put(dev); if (driver->err_handler && driver->err_handler->error_detected && - driver->err_handler->slot_reset && - driver->err_handler->resume) + driver->err_handler->slot_reset) return NULL; } diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 05e804cdecaa..aec9a1b1d25b 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -109,8 +109,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp) * If the breakpoint is unregistered between a hw_breakpoint_handler() * and the single_step_dabr_instruction(), then cleanup the breakpoint * restoration variables to prevent dangling pointers. + * FIXME, this should not be using bp->ctx at all! Sayeth peterz. */ - if (bp->ctx && bp->ctx->task) + if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) bp->ctx->task->thread.last_hit_ubp = NULL; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index dccc87e8fee5..3c5736e52a14 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1768,9 +1768,9 @@ static inline unsigned long brk_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT))); else - rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT))); return rnd << PAGE_SHIFT; } diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 0762c1e08c88..edb09912f0c9 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -111,7 +111,13 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, */ if (!(old_pte & _PAGE_COMBO)) { flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags); - old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND; + /* + * clear the old slot details from the old and new pte. + * On hash insert failure we use old pte value and we don't + * want slot information there if we have a insert failure. + */ + old_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND); + new_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND); goto htab_insert_hpte; } /* diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 49b152b0f926..eb2accdd76fd 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -78,9 +78,19 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * base page size. This is because demote_segment won't flush * hash page table entries. */ - if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) + if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) { flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K, ssize, flags); + /* + * With THP, we also clear the slot information with + * respect to all the 64K hash pte mapping the 16MB + * page. They are all invalid now. This make sure we + * don't find the slot valid when we fault with 4k + * base page size. + * + */ + memset(hpte_slot_array, 0, PTE_FRAG_SIZE); + } } valid = hpte_valid(hpte_slot_array, index); diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c index 7e6d0880813f..83a8be791e06 100644 --- a/arch/powerpc/mm/hugetlbpage-book3e.c +++ b/arch/powerpc/mm/hugetlbpage-book3e.c @@ -8,6 +8,8 @@ #include <linux/mm.h> #include <linux/hugetlb.h> +#include <asm/mmu.h> + #ifdef CONFIG_PPC_FSL_BOOK3E #ifdef CONFIG_PPC64 static inline int tlb1_next(void) @@ -60,6 +62,14 @@ static inline void book3e_tlb_lock(void) unsigned long tmp; int token = smp_processor_id() + 1; + /* + * Besides being unnecessary in the absence of SMT, this + * check prevents trying to do lbarx/stbcx. on e5500 which + * doesn't implement either feature. + */ + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + asm volatile("1: lbarx %0, 0, %1;" "cmpwi %0, 0;" "bne 2f;" @@ -80,6 +90,9 @@ static inline void book3e_tlb_unlock(void) { struct paca_struct *paca = get_paca(); + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + isync(); paca->tcd_ptr->lock = 0; } diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 0f0502e12f6c..4087705ba90f 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -59,9 +59,9 @@ unsigned long arch_mmap_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT)); + rnd = get_random_long() % (1<<(23-PAGE_SHIFT)); else - rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT)); + rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT)); return rnd << PAGE_SHIFT; } diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index ea91ddfe54eb..629c90865a07 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -40,6 +40,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) { fpregs->pad = 0; + fpregs->fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); else @@ -49,6 +50,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) { + fpu->fpc = fpregs->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); else diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 66c94417c0ba..4af60374eba0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs, /* Restore high gprs from signal stack */ if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high, - sizeof(&sregs_ext->gprs_high))) + sizeof(sregs_ext->gprs_high))) return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index eaee14637d93..8496a074bd0e 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -24,7 +24,13 @@ LDFLAGS := -m elf32_sparc export BITS := 32 UTS_MACHINE := sparc +# We are adding -Wa,-Av8 to KBUILD_CFLAGS to deal with a specs bug in some +# versions of gcc. Some gcc versions won't pass -Av8 to binutils when you +# give -mcpu=v8. This silently worked with older bintutils versions but +# does not any more. KBUILD_CFLAGS += -m32 -mcpu=v8 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7 +KBUILD_CFLAGS += -Wa,-Av8 + KBUILD_AFLAGS += -m32 -Wa,-Av8 else diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index 1c26d440d288..b6de8b10a55b 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -422,8 +422,9 @@ #define __NR_listen 354 #define __NR_setsockopt 355 #define __NR_mlock2 356 +#define __NR_copy_file_range 357 -#define NR_syscalls 357 +#define NR_syscalls 358 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 33c02b15f478..a83707c83be8 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -948,7 +948,24 @@ linux_syscall_trace: cmp %o0, 0 bne 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ld [%sp + STACKFRAME_SZ + PT_G1], %g1 + sethi %hi(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I0], %i0 + or %l7, %lo(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I1], %i1 + ld [%sp + STACKFRAME_SZ + PT_I2], %i2 + ld [%sp + STACKFRAME_SZ + PT_I3], %i3 + ld [%sp + STACKFRAME_SZ + PT_I4], %i4 + ld [%sp + STACKFRAME_SZ + PT_I5], %i5 + cmp %g1, NR_syscalls + bgeu 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + ld [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index afbaba52d2f1..d127130bf424 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -338,8 +338,9 @@ ENTRY(sun4v_mach_set_watchdog) mov %o1, %o4 mov HV_FAST_MACH_SET_WATCHDOG, %o5 ta HV_FAST_TRAP + brnz,a,pn %o4, 0f stx %o1, [%o4] - retl +0: retl nop ENDPROC(sun4v_mach_set_watchdog) diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index d88beff47bab..39aaec173f66 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) unsigned char fenab; int err; - flush_user_windows(); + synchronize_user_stack(); if (get_thread_wsaved() || (((unsigned long)ucp) & (sizeof(unsigned long)-1)) || (!__access_ok(ucp, sizeof(*ucp)))) diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index a92d5d2c46a3..9e034f29dcc5 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -37,6 +37,7 @@ EXPORT_SYMBOL(sun4v_niagara_getperf); EXPORT_SYMBOL(sun4v_niagara_setperf); EXPORT_SYMBOL(sun4v_niagara2_getperf); EXPORT_SYMBOL(sun4v_niagara2_setperf); +EXPORT_SYMBOL(sun4v_mach_set_watchdog); /* from hweight.S */ EXPORT_SYMBOL(__arch_hweight8); diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index c690c8e16a96..b489e9759518 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -264,7 +264,7 @@ static unsigned long mmap_rnd(void) unsigned long rnd = 0UL; if (current->flags & PF_RANDOMIZE) { - unsigned long val = get_random_int(); + unsigned long val = get_random_long(); if (test_thread_flag(TIF_32BIT)) rnd = (val % (1UL << (23UL-PAGE_SHIFT))); else diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index bb0008927598..c4a1b5c40e4e 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -158,7 +158,25 @@ linux_syscall_trace32: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 srl %i0, 0, %o0 + lduw [%l7 + %l4], %l7 srl %i4, 0, %o4 srl %i1, 0, %o1 srl %i2, 0, %o2 @@ -170,7 +188,25 @@ linux_syscall_trace: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + lduw [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index e663b6c78de2..6c3dd6c52f8b 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -88,4 +88,4 @@ sys_call_table: /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen -/*355*/ .long sys_setsockopt, sys_mlock2 +/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 1557121f4cdc..12b524cfcfa0 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -89,7 +89,7 @@ sys_call_table32: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word compat_sys_setsockopt, sys_mlock2 + .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range #endif /* CONFIG_COMPAT */ @@ -170,4 +170,4 @@ sys_call_table: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word sys_setsockopt, sys_mlock2 + .word sys_setsockopt, sys_mlock2, sys_copy_file_range diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 9bdf67a092a5..b60a9f8cda75 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -12,6 +12,7 @@ #include <skas.h> void (*pm_power_off)(void); +EXPORT_SYMBOL(pm_power_off); static void kill_off_processes(void) { diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index fc8be0e3a4ff..57acbd67d85d 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs) struct ksignal ksig; int handled_sig = 0; - if (get_signal(&ksig)) { + while (get_signal(&ksig)) { handled_sig = 1; /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 77d8c5112900..bb3e376d0f33 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -294,6 +294,7 @@ sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ + ASM_CLAC /* Clear AC after saving FLAGS */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index ff1c6d61f332..3c990eeee40b 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -261,6 +261,7 @@ ENTRY(entry_INT80_compat) * Interrupts are off on entry. */ PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ SWAPGS /* diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 46873fbd44e1..d08eacd298c2 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); +extern bool mp_should_keep_irq(struct device *dev); + struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index f5dcb5204dcd..3fe0eac59462 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4); + __uaccess_end(); return ret; case 8: + __uaccess_begin(); __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret, 8); + __uaccess_end(); return ret; } } @@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to, switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 968d57dd54c9..f320ee32d5a1 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -57,7 +57,7 @@ static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msi) return xen_pci_frontend->enable_msi(dev, vectors); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev) { @@ -69,7 +69,7 @@ static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msix) return xen_pci_frontend->enable_msix(dev, vectors, nvec); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index d1daead5fcdd..adb3eaf8fe2a 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include <asm/cacheflush.h> #include <asm/realmode.h> +#include <linux/ftrace.h> #include "../../realmode/rm/wakeup.h" #include "sleep.h" @@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + /* + * Pause/unpause graph tracing around do_suspend_lowlevel as it has + * inconsistent call/return info after it jumps to the wakeup vector. + */ + pause_graph_tracing(); do_suspend_lowlevel(); + unpause_graph_tracing(); return 0; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1505587d06e9..b9b09fec173b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, u16 sel; la = seg_base(ctxt, addr.seg) + addr.ea; - *linear = la; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: + *linear = la; if (is_noncanonical_address(la)) goto bad; @@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; break; default: + *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) @@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (size > *max_size) goto bad; } - la &= (u32)-1; break; } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6c9fed957cce..2ce4f05e81d3 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, return ret; kvm_vcpu_mark_page_dirty(vcpu, table_gfn); - walker->ptes[level] = pte; + walker->ptes[level - 1] = pte; } return 0; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e2951b6edbbc..0ff453749a90 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -596,6 +596,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -2127,14 +2129,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - /* Setup TSC multiplier */ - if (cpu_has_vmx_tsc_scaling()) - vmcs_write64(TSC_MULTIPLIER, - vcpu->arch.tsc_scaling_ratio); - vmx->loaded_vmcs->cpu = cpu; } + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + vmx_vcpu_pi_load(vcpu, cpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4244c2baf57d..eaf6ee8c28b8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6618,12 +6618,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { - int i; - WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops->sync_dirty_debug_regs(vcpu); - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + kvm_update_dr0123(vcpu); + kvm_update_dr6(vcpu); + kvm_update_dr7(vcpu); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 96bd1e2bffaf..72bb52f93c3d 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -71,12 +71,12 @@ unsigned long arch_mmap_rnd(void) if (mmap_is_ia32()) #ifdef CONFIG_COMPAT - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); #else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); #endif else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b2fd67da1701..ef05755a1900 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 2440814b0069..9cf96d82147a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -419,24 +419,30 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - unsigned long phys_addr, offset; + phys_addr_t phys_addr; + unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ switch (level) { case PG_LEVEL_1G: - phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_PAGE_MASK; break; case PG_LEVEL_2M: - phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_PAGE_MASK; break; default: - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 2879efc73a96..d34b5118b4e8 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -711,28 +711,22 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) +int pcibios_enable_device(struct pci_dev *dev, int mask) { - /* - * If the PCI device was already claimed by core code and has - * MSI enabled, probing of the pcibios IRQ will overwrite - * dev->irq. So bail out if MSI is already enabled. - */ - if (pci_dev_msi_enabled(dev)) - return -EBUSY; + int err; - return pcibios_enable_irq(dev); -} + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; } -int pcibios_enable_device(struct pci_dev *dev, int mask) +void pcibios_disable_device (struct pci_dev *dev) { - return pci_enable_resources(dev, mask); + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10145..8b93e634af84 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e6fd..9bd115484745 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index ff31ab464213..beac4dfdade6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -196,7 +196,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 0; error: - dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + if (ret == -ENOSYS) + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + else if (ret) + dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret); free: kfree(v); return ret; diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index c61b6c332e97..bfadcd0f4944 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -592,14 +592,14 @@ static void __init imr_fixup_memmap(struct imr_device *idev) end = (unsigned long)__end_rodata - 1; /* - * Setup a locked IMR around the physical extent of the kernel + * Setup an unlocked IMR around the physical extent of the kernel * from the beginning of the .text secton to the end of the * .rodata section as one physically contiguous block. * * We don't round up @size since it is already PAGE_SIZE aligned. * See vmlinux.lds.S for details. */ - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); if (ret < 0) { pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n", size / 1024, start, end); diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c index 8502ad30e61b..5adb6a2fd117 100644 --- a/arch/x86/um/os-Linux/task_size.c +++ b/arch/x86/um/os-Linux/task_size.c @@ -109,7 +109,7 @@ unsigned long os_get_top_address(void) exit(1); } - printf("0x%x\n", bottom << UM_KERN_PAGE_SHIFT); + printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT); printf("Locating the top of the address space ... "); fflush(stdout); @@ -134,7 +134,7 @@ out: exit(1); } top <<= UM_KERN_PAGE_SHIFT; - printf("0x%x\n", top); + printf("0x%lx\n", top); return top; } diff --git a/block/Kconfig b/block/Kconfig index 161491d0a879..0363cd731320 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_DAX + bool "Block device DAX support" + depends on FS_DAX + depends on BROKEN + help + When DAX support is available (CONFIG_FS_DAX) raw block + devices can also support direct userspace access to the + storage capacity via MMAP(2) similar to a file on a + DAX-enabled filesystem. However, the DAX I/O-path disables + some standard I/O-statistics, and the MMAP(2) path has some + operational differences due to bypassing the page + cache. If in doubt, say N. + config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y diff --git a/block/blk-map.c b/block/blk-map.c index f565e11f465a..a54f0543b956 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -57,6 +57,49 @@ static int __blk_rq_unmap_user(struct bio *bio) return ret; } +static int __blk_rq_map_user_iov(struct request *rq, + struct rq_map_data *map_data, struct iov_iter *iter, + gfp_t gfp_mask, bool copy) +{ + struct request_queue *q = rq->q; + struct bio *bio, *orig_bio; + int ret; + + if (copy) + bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); + else + bio = bio_map_user_iov(q, iter, gfp_mask); + + if (IS_ERR(bio)) + return PTR_ERR(bio); + + if (map_data && map_data->null_mapped) + bio_set_flag(bio, BIO_NULL_MAPPED); + + iov_iter_advance(iter, bio->bi_iter.bi_size); + if (map_data) + map_data->offset += bio->bi_iter.bi_size; + + orig_bio = bio; + blk_queue_bounce(q, &bio); + + /* + * We link the bounce buffer in and could have to traverse it + * later so we have to get a ref to prevent it from being freed + */ + bio_get(bio); + + ret = blk_rq_append_bio(q, rq, bio); + if (ret) { + bio_endio(bio); + __blk_rq_unmap_user(orig_bio); + bio_put(bio); + return ret; + } + + return 0; +} + /** * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage * @q: request queue where request should be inserted @@ -82,10 +125,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { - struct bio *bio; - int unaligned = 0; - struct iov_iter i; struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0}; + bool copy = (q->dma_pad_mask & iter->count) || map_data; + struct bio *bio = NULL; + struct iov_iter i; + int ret; if (!iter || !iter->count) return -EINVAL; @@ -101,42 +145,29 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, */ if ((uaddr & queue_dma_alignment(q)) || iovec_gap_to_prv(q, &prv, &iov)) - unaligned = 1; + copy = true; prv.iov_base = iov.iov_base; prv.iov_len = iov.iov_len; } - if (unaligned || (q->dma_pad_mask & iter->count) || map_data) - bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); - else - bio = bio_map_user_iov(q, iter, gfp_mask); - - if (IS_ERR(bio)) - return PTR_ERR(bio); - - if (map_data && map_data->null_mapped) - bio_set_flag(bio, BIO_NULL_MAPPED); - - if (bio->bi_iter.bi_size != iter->count) { - /* - * Grab an extra reference to this bio, as bio_unmap_user() - * expects to be able to drop it twice as it happens on the - * normal IO completion path - */ - bio_get(bio); - bio_endio(bio); - __blk_rq_unmap_user(bio); - return -EINVAL; - } + i = *iter; + do { + ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy); + if (ret) + goto unmap_rq; + if (!bio) + bio = rq->bio; + } while (iov_iter_count(&i)); if (!bio_flagged(bio, BIO_USER_MAPPED)) rq->cmd_flags |= REQ_COPY_USER; - - blk_queue_bounce(q, &bio); - bio_get(bio); - blk_rq_bio_prep(q, rq, bio); return 0; + +unmap_rq: + __blk_rq_unmap_user(bio); + rq->bio = NULL; + return -EINVAL; } EXPORT_SYMBOL(blk_rq_map_user_iov); diff --git a/block/blk-merge.c b/block/blk-merge.c index 888a7fec81f7..261353166dcf 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -304,7 +304,6 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { struct bio_vec end_bv = { NULL }, nxt_bv; - struct bvec_iter iter; if (!blk_queue_cluster(q)) return 0; @@ -316,11 +315,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, if (!bio_has_data(bio)) return 1; - bio_for_each_segment(end_bv, bio, iter) - if (end_bv.bv_len == iter.bi_size) - break; - - nxt_bv = bio_iovec(nxt); + bio_get_last_bvec(bio, &end_bv); + bio_get_first_bvec(nxt, &nxt_bv); if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv)) return 0; diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index ad6d8c6b777e..35947ac87644 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -469,37 +469,16 @@ static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc, nfit_mem->bdw = NULL; } -static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, +static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) { u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; struct nfit_memdev *nfit_memdev; struct nfit_flush *nfit_flush; - struct nfit_dcr *nfit_dcr; struct nfit_bdw *nfit_bdw; struct nfit_idt *nfit_idt; u16 idt_idx, range_index; - list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { - if (nfit_dcr->dcr->region_index != dcr) - continue; - nfit_mem->dcr = nfit_dcr->dcr; - break; - } - - if (!nfit_mem->dcr) { - dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n", - spa->range_index, __to_nfit_memdev(nfit_mem) - ? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR"); - return -ENODEV; - } - - /* - * We've found enough to create an nvdimm, optionally - * find an associated BDW - */ - list_add(&nfit_mem->list, &acpi_desc->dimms); - list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) { if (nfit_bdw->bdw->region_index != dcr) continue; @@ -508,12 +487,12 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } if (!nfit_mem->bdw) - return 0; + return; nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); if (!nfit_mem->spa_bdw) - return 0; + return; range_index = nfit_mem->spa_bdw->range_index; list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { @@ -538,8 +517,6 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } break; } - - return 0; } static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, @@ -548,7 +525,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, *found; struct nfit_memdev *nfit_memdev; int type = nfit_spa_type(spa); - u16 dcr; switch (type) { case NFIT_SPA_DCR: @@ -559,14 +535,18 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, } list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { - int rc; + struct nfit_dcr *nfit_dcr; + u32 device_handle; + u16 dcr; if (nfit_memdev->memdev->range_index != spa->range_index) continue; found = NULL; dcr = nfit_memdev->memdev->region_index; + device_handle = nfit_memdev->memdev->device_handle; list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) - if (__to_nfit_memdev(nfit_mem)->region_index == dcr) { + if (__to_nfit_memdev(nfit_mem)->device_handle + == device_handle) { found = nfit_mem; break; } @@ -579,6 +559,31 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, if (!nfit_mem) return -ENOMEM; INIT_LIST_HEAD(&nfit_mem->list); + list_add(&nfit_mem->list, &acpi_desc->dimms); + } + + list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { + if (nfit_dcr->dcr->region_index != dcr) + continue; + /* + * Record the control region for the dimm. For + * the ACPI 6.1 case, where there are separate + * control regions for the pmem vs blk + * interfaces, be sure to record the extended + * blk details. + */ + if (!nfit_mem->dcr) + nfit_mem->dcr = nfit_dcr->dcr; + else if (nfit_mem->dcr->windows == 0 + && nfit_dcr->dcr->windows) + nfit_mem->dcr = nfit_dcr->dcr; + break; + } + + if (dcr && !nfit_mem->dcr) { + dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n", + spa->range_index, dcr); + return -ENODEV; } if (type == NFIT_SPA_DCR) { @@ -595,6 +600,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, nfit_mem->idt_dcr = nfit_idt->idt; break; } + nfit_mem_init_bdw(acpi_desc, nfit_mem, spa); } else { /* * A single dimm may belong to multiple SPA-PM @@ -603,13 +609,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, */ nfit_mem->memdev_pmem = nfit_memdev->memdev; } - - if (found) - continue; - - rc = nfit_mem_add(acpi_desc, nfit_mem, spa); - if (rc) - return rc; } return 0; @@ -1504,9 +1503,7 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, case 1: /* ARS unsupported, but we should never get here */ return 0; - case 2: - return -EINVAL; - case 3: + case 6: /* ARS is in progress */ msleep(1000); break; @@ -1517,13 +1514,13 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, } static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, - struct nd_cmd_ars_status *cmd) + struct nd_cmd_ars_status *cmd, u32 size) { int rc; while (1) { rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd, - sizeof(*cmd)); + size); if (rc || cmd->status & 0xffff) return -ENXIO; @@ -1538,6 +1535,8 @@ static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, case 2: /* No ARS performed for the current boot */ return 0; + case 3: + /* TODO: error list overflow support */ default: return -ENXIO; } @@ -1581,6 +1580,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, struct nd_cmd_ars_start *ars_start = NULL; struct nd_cmd_ars_cap *ars_cap = NULL; u64 start, len, cur, remaining; + u32 ars_status_size; int rc; ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL); @@ -1590,14 +1590,21 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, start = ndr_desc->res->start; len = ndr_desc->res->end - ndr_desc->res->start + 1; + /* + * If ARS is unimplemented, unsupported, or if the 'Persistent Memory + * Scrub' flag in extended status is not set, skip this but continue + * initialization + */ rc = ars_get_cap(nd_desc, ars_cap, start, len); + if (rc == -ENOTTY) { + dev_dbg(acpi_desc->dev, + "Address Range Scrub is not implemented, won't create an error list\n"); + rc = 0; + goto out; + } if (rc) goto out; - /* - * If ARS is unsupported, or if the 'Persistent Memory Scrub' flag in - * extended status is not set, skip this but continue initialization - */ if ((ars_cap->status & 0xffff) || !(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) { dev_warn(acpi_desc->dev, @@ -1610,14 +1617,14 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, * Check if a full-range ARS has been run. If so, use those results * without having to start a new ARS. */ - ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status), - GFP_KERNEL); + ars_status_size = ars_cap->max_ars_out; + ars_status = kzalloc(ars_status_size, GFP_KERNEL); if (!ars_status) { rc = -ENOMEM; goto out; } - rc = ars_get_status(nd_desc, ars_status); + rc = ars_get_status(nd_desc, ars_status, ars_status_size); if (rc) goto out; @@ -1647,7 +1654,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, if (rc) goto out; - rc = ars_get_status(nd_desc, ars_status); + rc = ars_get_status(nd_desc, ars_status, ars_status_size); if (rc) goto out; diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index d30184c7f3bc..c8e169e46673 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -406,7 +406,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev) return 0; } - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; entry = acpi_pci_irq_lookup(dev, pin); @@ -451,7 +451,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev) kfree(entry); return rc; } - pci_set_managed_irq(dev, rc); + dev->irq = rc; + dev->irq_managed = 1; if (link) snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link); @@ -474,9 +475,17 @@ void acpi_pci_irq_disable(struct pci_dev *dev) u8 pin; pin = dev->pin; - if (!pin || !pci_has_managed_irq(dev)) + if (!pin || !dev->irq_managed || dev->irq <= 0) return; + /* Keep IOAPIC pin configuration when suspending */ + if (dev->dev.power.is_prepared) + return; +#ifdef CONFIG_PM + if (dev->dev.power.runtime_status == RPM_SUSPENDING) + return; +#endif + entry = acpi_pci_irq_lookup(dev, pin); if (!entry) return; @@ -496,6 +505,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev) dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin)); if (gsi >= 0) { acpi_unregister_gsi(gsi); - pci_reset_managed_irq(dev); + dev->irq_managed = 0; } } diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index fa2863567eed..ededa909df2f 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -4,7 +4,6 @@ * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2002 Dominik Brodowski <devel@brodo.de> - * Copyright (c) 2015, The Linux Foundation. All rights reserved. * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -438,6 +437,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) * enabled system. */ +#define ACPI_MAX_IRQS 256 #define ACPI_MAX_ISA_IRQ 16 #define PIRQ_PENALTY_PCI_AVAILABLE (0) @@ -447,7 +447,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) #define PIRQ_PENALTY_ISA_USED (16*16*16*16*16) #define PIRQ_PENALTY_ISA_ALWAYS (16*16*16*16*16*16) -static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = { +static int acpi_irq_penalty[ACPI_MAX_IRQS] = { PIRQ_PENALTY_ISA_ALWAYS, /* IRQ0 timer */ PIRQ_PENALTY_ISA_ALWAYS, /* IRQ1 keyboard */ PIRQ_PENALTY_ISA_ALWAYS, /* IRQ2 cascade */ @@ -464,68 +464,9 @@ static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = { PIRQ_PENALTY_ISA_USED, /* IRQ13 fpe, sometimes */ PIRQ_PENALTY_ISA_USED, /* IRQ14 ide0 */ PIRQ_PENALTY_ISA_USED, /* IRQ15 ide1 */ + /* >IRQ15 */ }; -struct irq_penalty_info { - int irq; - int penalty; - struct list_head node; -}; - -static LIST_HEAD(acpi_irq_penalty_list); - -static int acpi_irq_get_penalty(int irq) -{ - struct irq_penalty_info *irq_info; - - if (irq < ACPI_MAX_ISA_IRQ) - return acpi_irq_isa_penalty[irq]; - - list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) { - if (irq_info->irq == irq) - return irq_info->penalty; - } - - return 0; -} - -static int acpi_irq_set_penalty(int irq, int new_penalty) -{ - struct irq_penalty_info *irq_info; - - /* see if this is a ISA IRQ */ - if (irq < ACPI_MAX_ISA_IRQ) { - acpi_irq_isa_penalty[irq] = new_penalty; - return 0; - } - - /* next, try to locate from the dynamic list */ - list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) { - if (irq_info->irq == irq) { - irq_info->penalty = new_penalty; - return 0; - } - } - - /* nope, let's allocate a slot for this IRQ */ - irq_info = kzalloc(sizeof(*irq_info), GFP_KERNEL); - if (!irq_info) - return -ENOMEM; - - irq_info->irq = irq; - irq_info->penalty = new_penalty; - list_add_tail(&irq_info->node, &acpi_irq_penalty_list); - - return 0; -} - -static void acpi_irq_add_penalty(int irq, int penalty) -{ - int curpen = acpi_irq_get_penalty(irq); - - acpi_irq_set_penalty(irq, curpen + penalty); -} - int __init acpi_irq_penalty_init(void) { struct acpi_pci_link *link; @@ -546,16 +487,15 @@ int __init acpi_irq_penalty_init(void) link->irq.possible_count; for (i = 0; i < link->irq.possible_count; i++) { - if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) { - int irqpos = link->irq.possible[i]; - - acpi_irq_add_penalty(irqpos, penalty); - } + if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) + acpi_irq_penalty[link->irq. + possible[i]] += + penalty; } } else if (link->irq.active) { - acpi_irq_add_penalty(link->irq.active, - PIRQ_PENALTY_PCI_POSSIBLE); + acpi_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_POSSIBLE; } } @@ -607,12 +547,12 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) * the use of IRQs 9, 10, 11, and >15. */ for (i = (link->irq.possible_count - 1); i >= 0; i--) { - if (acpi_irq_get_penalty(irq) > - acpi_irq_get_penalty(link->irq.possible[i])) + if (acpi_irq_penalty[irq] > + acpi_irq_penalty[link->irq.possible[i]]) irq = link->irq.possible[i]; } } - if (acpi_irq_get_penalty(irq) >= PIRQ_PENALTY_ISA_ALWAYS) { + if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) { printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. " "Try pci=noacpi or acpi=off\n", acpi_device_name(link->device), @@ -628,8 +568,7 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) acpi_device_bid(link->device)); return -ENODEV; } else { - acpi_irq_add_penalty(link->irq.active, PIRQ_PENALTY_PCI_USING); - + acpi_irq_penalty[link->irq.active] += PIRQ_PENALTY_PCI_USING; printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n", acpi_device_name(link->device), acpi_device_bid(link->device), link->irq.active); @@ -839,7 +778,7 @@ static void acpi_pci_link_remove(struct acpi_device *device) } /* - * modify penalty from cmdline + * modify acpi_irq_penalty[] from cmdline */ static int __init acpi_irq_penalty_update(char *str, int used) { @@ -857,10 +796,13 @@ static int __init acpi_irq_penalty_update(char *str, int used) if (irq < 0) continue; + if (irq >= ARRAY_SIZE(acpi_irq_penalty)) + continue; + if (used) - acpi_irq_add_penalty(irq, PIRQ_PENALTY_ISA_USED); + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED; else - acpi_irq_set_penalty(irq, PIRQ_PENALTY_PCI_AVAILABLE); + acpi_irq_penalty[irq] = PIRQ_PENALTY_PCI_AVAILABLE; if (retval != 2) /* no next number */ break; @@ -877,15 +819,18 @@ static int __init acpi_irq_penalty_update(char *str, int used) */ void acpi_penalize_isa_irq(int irq, int active) { - if (irq >= 0) - acpi_irq_add_penalty(irq, active ? - PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING); + if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) { + if (active) + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED; + else + acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING; + } } bool acpi_isa_irq_available(int irq) { - return irq >= 0 && - (acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS); + return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) || + acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS); } /* @@ -895,18 +840,13 @@ bool acpi_isa_irq_available(int irq) */ void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { - int penalty; - - if (irq < 0) - return; - - if (trigger != ACPI_MADT_TRIGGER_LEVEL || - polarity != ACPI_MADT_POLARITY_ACTIVE_LOW) - penalty = PIRQ_PENALTY_ISA_ALWAYS; - else - penalty = PIRQ_PENALTY_PCI_USING; - - acpi_irq_add_penalty(irq, penalty); + if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) { + if (trigger != ACPI_MADT_TRIGGER_LEVEL || + polarity != ACPI_MADT_POLARITY_ACTIVE_LOW) + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_ALWAYS; + else + acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING; + } } /* diff --git a/drivers/android/binder.c b/drivers/android/binder.c index a39e85f9efa9..7d00b7a015ea 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2074,7 +2074,7 @@ static int binder_thread_write(struct binder_proc *proc, if (get_user(cookie, (binder_uintptr_t __user *)ptr)) return -EFAULT; - ptr += sizeof(void *); + ptr += sizeof(cookie); list_for_each_entry(w, &proc->delivered_death, entry) { struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work); diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 546a3692774f..146dc0b8ec61 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -367,15 +367,21 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d2), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d6), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -1325,6 +1331,44 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host) {} #endif +#ifdef CONFIG_ARM64 +/* + * Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently. + * Workaround is to make sure all pending IRQs are served before leaving + * handler. + */ +static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv; + unsigned int rc = 0; + void __iomem *mmio; + u32 irq_stat, irq_masked; + unsigned int handled = 1; + + VPRINTK("ENTER\n"); + hpriv = host->private_data; + mmio = hpriv->mmio; + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + do { + irq_masked = irq_stat & hpriv->port_map; + spin_lock(&host->lock); + rc = ahci_handle_port_intr(host, irq_masked); + if (!rc) + handled = 0; + writel(irq_stat, mmio + HOST_IRQ_STAT); + irq_stat = readl(mmio + HOST_IRQ_STAT); + spin_unlock(&host->lock); + } while (irq_stat); + VPRINTK("EXIT\n"); + + return IRQ_RETVAL(handled); +} +#endif + /* * ahci_init_msix() - optionally enable per-port MSI-X otherwise defer * to single msi. @@ -1560,6 +1604,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ahci_broken_devslp(pdev)) hpriv->flags |= AHCI_HFLAG_NO_DEVSLP; +#ifdef CONFIG_ARM64 + if (pdev->vendor == 0x177d && pdev->device == 0xa01c) + hpriv->irq_handler = ahci_thunderx_irq_handler; +#endif + /* save initial config */ ahci_pci_save_initial_config(pdev, hpriv); diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index a44c75d4c284..167ba7e3b92e 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -240,8 +240,7 @@ enum { error-handling stage) */ AHCI_HFLAG_NO_DEVSLP = (1 << 17), /* no device sleep */ AHCI_HFLAG_NO_FBS = (1 << 18), /* no FBS */ - AHCI_HFLAG_EDGE_IRQ = (1 << 19), /* HOST_IRQ_STAT behaves as - Edge Triggered */ + #ifdef CONFIG_PCI_MSI AHCI_HFLAG_MULTI_MSI = (1 << 20), /* multiple PCI MSIs */ AHCI_HFLAG_MULTI_MSIX = (1 << 21), /* per-port MSI-X */ @@ -361,6 +360,7 @@ struct ahci_host_priv { * be overridden anytime before the host is activated. */ void (*start_engine)(struct ata_port *ap); + irqreturn_t (*irq_handler)(int irq, void *dev_instance); }; #ifdef CONFIG_PCI_MSI @@ -424,6 +424,7 @@ int ahci_reset_em(struct ata_host *host); void ahci_print_info(struct ata_host *host, const char *scc_s); int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht); void ahci_error_handler(struct ata_port *ap); +u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked); static inline void __iomem *__ahci_port_base(struct ata_host *host, unsigned int port_no) diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index e2c6d9e0c5ac..8e3f7faf00d3 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -548,6 +548,88 @@ softreset_retry: return rc; } +/** + * xgene_ahci_handle_broken_edge_irq - Handle the broken irq. + * @ata_host: Host that recieved the irq + * @irq_masked: HOST_IRQ_STAT value + * + * For hardware with broken edge trigger latch + * the HOST_IRQ_STAT register misses the edge interrupt + * when clearing of HOST_IRQ_STAT register and hardware + * reporting the PORT_IRQ_STAT register at the + * same clock cycle. + * As such, the algorithm below outlines the workaround. + * + * 1. Read HOST_IRQ_STAT register and save the state. + * 2. Clear the HOST_IRQ_STAT register. + * 3. Read back the HOST_IRQ_STAT register. + * 4. If HOST_IRQ_STAT register equals to zero, then + * traverse the rest of port's PORT_IRQ_STAT register + * to check if an interrupt is triggered at that point else + * go to step 6. + * 5. If PORT_IRQ_STAT register of rest ports is not equal to zero + * then update the state of HOST_IRQ_STAT saved in step 1. + * 6. Handle port interrupts. + * 7. Exit + */ +static int xgene_ahci_handle_broken_edge_irq(struct ata_host *host, + u32 irq_masked) +{ + struct ahci_host_priv *hpriv = host->private_data; + void __iomem *port_mmio; + int i; + + if (!readl(hpriv->mmio + HOST_IRQ_STAT)) { + for (i = 0; i < host->n_ports; i++) { + if (irq_masked & (1 << i)) + continue; + + port_mmio = ahci_port_base(host->ports[i]); + if (readl(port_mmio + PORT_IRQ_STAT)) + irq_masked |= (1 << i); + } + } + + return ahci_handle_port_intr(host, irq_masked); +} + +static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv; + unsigned int rc = 0; + void __iomem *mmio; + u32 irq_stat, irq_masked; + + VPRINTK("ENTER\n"); + + hpriv = host->private_data; + mmio = hpriv->mmio; + + /* sigh. 0xffffffff is a valid return from h/w */ + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + irq_masked = irq_stat & hpriv->port_map; + + spin_lock(&host->lock); + + /* + * HOST_IRQ_STAT behaves as edge triggered latch meaning that + * it should be cleared before all the port events are cleared. + */ + writel(irq_stat, mmio + HOST_IRQ_STAT); + + rc = xgene_ahci_handle_broken_edge_irq(host, irq_masked); + + spin_unlock(&host->lock); + + VPRINTK("EXIT\n"); + + return IRQ_RETVAL(rc); +} + static struct ata_port_operations xgene_ahci_v1_ops = { .inherits = &ahci_ops, .host_stop = xgene_ahci_host_stop, @@ -779,7 +861,8 @@ skip_clk_phy: hpriv->flags = AHCI_HFLAG_NO_NCQ; break; case XGENE_AHCI_V2: - hpriv->flags |= AHCI_HFLAG_YES_FBS | AHCI_HFLAG_EDGE_IRQ; + hpriv->flags |= AHCI_HFLAG_YES_FBS; + hpriv->irq_handler = xgene_ahci_irq_intr; break; default: break; diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 402967902cbe..85ea5142a095 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -113,6 +113,7 @@ static ssize_t ahci_store_em_buffer(struct device *dev, const char *buf, size_t size); static ssize_t ahci_show_em_supported(struct device *dev, struct device_attribute *attr, char *buf); +static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance); static DEVICE_ATTR(ahci_host_caps, S_IRUGO, ahci_show_host_caps, NULL); static DEVICE_ATTR(ahci_host_cap2, S_IRUGO, ahci_show_host_cap2, NULL); @@ -512,6 +513,9 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) if (!hpriv->start_engine) hpriv->start_engine = ahci_start_engine; + + if (!hpriv->irq_handler) + hpriv->irq_handler = ahci_single_level_irq_intr; } EXPORT_SYMBOL_GPL(ahci_save_initial_config); @@ -1164,8 +1168,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); - if ((tmp & PORT_CMD_HPCP) || - ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS))) + if ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)) ap->pflags |= ATA_PFLAG_EXTERNAL; } @@ -1846,7 +1849,7 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance) return IRQ_HANDLED; } -static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) +u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) { unsigned int i, handled = 0; @@ -1872,43 +1875,7 @@ static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) return handled; } - -static irqreturn_t ahci_single_edge_irq_intr(int irq, void *dev_instance) -{ - struct ata_host *host = dev_instance; - struct ahci_host_priv *hpriv; - unsigned int rc = 0; - void __iomem *mmio; - u32 irq_stat, irq_masked; - - VPRINTK("ENTER\n"); - - hpriv = host->private_data; - mmio = hpriv->mmio; - - /* sigh. 0xffffffff is a valid return from h/w */ - irq_stat = readl(mmio + HOST_IRQ_STAT); - if (!irq_stat) - return IRQ_NONE; - - irq_masked = irq_stat & hpriv->port_map; - - spin_lock(&host->lock); - - /* - * HOST_IRQ_STAT behaves as edge triggered latch meaning that - * it should be cleared before all the port events are cleared. - */ - writel(irq_stat, mmio + HOST_IRQ_STAT); - - rc = ahci_handle_port_intr(host, irq_masked); - - spin_unlock(&host->lock); - - VPRINTK("EXIT\n"); - - return IRQ_RETVAL(rc); -} +EXPORT_SYMBOL_GPL(ahci_handle_port_intr); static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance) { @@ -2535,14 +2502,18 @@ int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht) int irq = hpriv->irq; int rc; - if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) + if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) { + if (hpriv->irq_handler) + dev_warn(host->dev, "both AHCI_HFLAG_MULTI_MSI flag set \ + and custom irq handler implemented\n"); + rc = ahci_host_activate_multi_irqs(host, sht); - else if (hpriv->flags & AHCI_HFLAG_EDGE_IRQ) - rc = ata_host_activate(host, irq, ahci_single_edge_irq_intr, - IRQF_SHARED, sht); - else - rc = ata_host_activate(host, irq, ahci_single_level_irq_intr, + } else { + rc = ata_host_activate(host, irq, hpriv->irq_handler, IRQF_SHARED, sht); + } + + return rc; } EXPORT_SYMBOL_GPL(ahci_host_activate); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7e959f90c020..e417e1a1d02c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -675,19 +675,18 @@ static int ata_ioc32(struct ata_port *ap) int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev, int cmd, void __user *arg) { - int val = -EINVAL, rc = -EINVAL; + unsigned long val; + int rc = -EINVAL; unsigned long flags; switch (cmd) { - case ATA_IOC_GET_IO32: + case HDIO_GET_32BIT: spin_lock_irqsave(ap->lock, flags); val = ata_ioc32(ap); spin_unlock_irqrestore(ap->lock, flags); - if (copy_to_user(arg, &val, 1)) - return -EFAULT; - return 0; + return put_user(val, (unsigned long __user *)arg); - case ATA_IOC_SET_IO32: + case HDIO_SET_32BIT: val = (unsigned long) arg; rc = 0; spin_lock_irqsave(ap->lock, flags); diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c index 12fe0f3bb7e9..c8b6a780a290 100644 --- a/drivers/ata/pata_rb532_cf.c +++ b/drivers/ata/pata_rb532_cf.c @@ -32,6 +32,8 @@ #include <linux/libata.h> #include <scsi/scsi_host.h> +#include <asm/mach-rc32434/rb.h> + #define DRV_NAME "pata-rb532-cf" #define DRV_VERSION "0.1.0" #define DRV_DESC "PATA driver for RouterBOARD 532 Compact Flash" @@ -107,6 +109,7 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) int gpio; struct resource *res; struct ata_host *ah; + struct cf_device *pdata; struct rb532_cf_info *info; int ret; @@ -122,7 +125,13 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) return -ENOENT; } - gpio = irq_to_gpio(irq); + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + dev_err(&pdev->dev, "no platform data specified\n"); + return -EINVAL; + } + + gpio = pdata->gpio_pin; if (gpio < 0) { dev_err(&pdev->dev, "no GPIO found for irq%d\n", irq); return -ENOENT; diff --git a/drivers/char/random.c b/drivers/char/random.c index d0da5d852d41..b583e5336630 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1819,6 +1819,28 @@ unsigned int get_random_int(void) EXPORT_SYMBOL(get_random_int); /* + * Same as get_random_int(), but returns unsigned long. + */ +unsigned long get_random_long(void) +{ + __u32 *hash; + unsigned long ret; + + if (arch_get_random_long(&ret)) + return ret; + + hash = get_cpu_var(get_random_int_hash); + + hash[0] += current->pid + jiffies + random_get_entropy(); + md5_transform(hash, random_int_secret); + ret = *(unsigned long *)hash; + put_cpu_var(get_random_int_hash); + + return ret; +} +EXPORT_SYMBOL(get_random_long); + +/* * randomize_range() returns a start address such that * * [...... <range> .....] diff --git a/drivers/clk/ti/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c index 1c300388782b..cc739291a3ce 100644 --- a/drivers/clk/ti/dpll3xxx.c +++ b/drivers/clk/ti/dpll3xxx.c @@ -460,7 +460,8 @@ int omap3_noncore_dpll_enable(struct clk_hw *hw) parent = clk_hw_get_parent(hw); - if (clk_hw_get_rate(hw) == clk_get_rate(dd->clk_bypass)) { + if (clk_hw_get_rate(hw) == + clk_hw_get_rate(__clk_get_hw(dd->clk_bypass))) { WARN_ON(parent != __clk_get_hw(dd->clk_bypass)); r = _omap3_noncore_dpll_bypass(clk); } else { diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 659879a56dba..f93511031177 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -296,6 +296,7 @@ endif config QORIQ_CPUFREQ tristate "CPU frequency scaling driver for Freescale QorIQ SoCs" depends on OF && COMMON_CLK && (PPC_E500MC || ARM) + depends on !CPU_THERMAL || THERMAL select CLK_QORIQ help This adds the CPUFreq driver support for Freescale QorIQ SoCs diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 0031069b64c9..14b1f9393b05 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -84,10 +84,10 @@ config ARM_KIRKWOOD_CPUFREQ SoCs. config ARM_MT8173_CPUFREQ - bool "Mediatek MT8173 CPUFreq support" + tristate "Mediatek MT8173 CPUFreq support" depends on ARCH_MEDIATEK && REGULATOR depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST) - depends on !CPU_THERMAL || THERMAL=y + depends on !CPU_THERMAL || THERMAL select PM_OPP help This adds the CPUFreq driver support for Mediatek MT8173 SoC. diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c index 1efba340456d..2058e6d292ce 100644 --- a/drivers/cpufreq/mt8173-cpufreq.c +++ b/drivers/cpufreq/mt8173-cpufreq.c @@ -17,6 +17,7 @@ #include <linux/cpu_cooling.h> #include <linux/cpufreq.h> #include <linux/cpumask.h> +#include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> #include <linux/pm_opp.h> diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c index 848b93ee930f..fe9dce0245bf 100644 --- a/drivers/devfreq/tegra-devfreq.c +++ b/drivers/devfreq/tegra-devfreq.c @@ -500,6 +500,8 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq, clk_set_min_rate(tegra->emc_clock, rate); clk_set_rate(tegra->emc_clock, 0); + *freq = rate; + return 0; } diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index f2a0310ae771..debca824bed6 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -583,6 +583,8 @@ static void set_updater_desc(struct pxad_desc_sw *sw_desc, (PXA_DCMD_LENGTH & sizeof(u32)); if (flags & DMA_PREP_INTERRUPT) updater->dcmd |= PXA_DCMD_ENDIRQEN; + if (sw_desc->cyclic) + sw_desc->hw_desc[sw_desc->nb_desc - 2]->ddadr = sw_desc->first; } static bool is_desc_completed(struct virt_dma_desc *vd) @@ -673,6 +675,10 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id) dev_dbg(&chan->vc.chan.dev->device, "%s(): checking txd %p[%x]: completed=%d\n", __func__, vd, vd->tx.cookie, is_desc_completed(vd)); + if (to_pxad_sw_desc(vd)->cyclic) { + vchan_cyclic_callback(vd); + break; + } if (is_desc_completed(vd)) { list_del(&vd->node); vchan_cookie_complete(vd); @@ -1080,7 +1086,7 @@ pxad_prep_dma_cyclic(struct dma_chan *dchan, return NULL; pxad_get_config(chan, dir, &dcmd, &dsadr, &dtadr); - dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH | period_len); + dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH & period_len); dev_dbg(&chan->vc.chan.dev->device, "%s(): buf_addr=0x%lx len=%zu period=%zu dir=%d flags=%lx\n", __func__, (unsigned long)buf_addr, len, period_len, dir, flags); diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index cf41440aff91..d9ab0cd1d205 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -196,6 +196,44 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) return 0; } +static void gpio_rcar_irq_bus_lock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_get_sync(&p->pdev->dev); +} + +static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_put(&p->pdev->dev); +} + + +static int gpio_rcar_irq_request_resources(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + int error; + + error = pm_runtime_get_sync(&p->pdev->dev); + if (error < 0) + return error; + + return 0; +} + +static void gpio_rcar_irq_release_resources(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_put(&p->pdev->dev); +} + static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id) { struct gpio_rcar_priv *p = dev_id; @@ -450,6 +488,10 @@ static int gpio_rcar_probe(struct platform_device *pdev) irq_chip->irq_unmask = gpio_rcar_irq_enable; irq_chip->irq_set_type = gpio_rcar_irq_set_type; irq_chip->irq_set_wake = gpio_rcar_irq_set_wake; + irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock; + irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock; + irq_chip->irq_request_resources = gpio_rcar_irq_request_resources; + irq_chip->irq_release_resources = gpio_rcar_irq_release_resources; irq_chip->flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND; ret = gpiochip_add_data(gpio_chip, p); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 89c3dd62ba21..119cdc2c43e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -77,7 +77,7 @@ void amdgpu_connector_hotplug(struct drm_connector *connector) } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { /* Don't try to start link training before we * have the dpcd */ - if (!amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) + if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) return; /* set it to OFF so that drm_helper_connector_dpms() diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index acd066d0a805..8297bc319369 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &amdgpuCrtc->base; unsigned long flags; - unsigned i; - int vpos, hpos, stat, min_udelay; + unsigned i, repcnt = 4; + int vpos, hpos, stat, min_udelay = 0; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; amdgpu_flip_wait_fence(adev, &work->excl); @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (amdgpuCrtc->enabled && repcnt--) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -114,10 +114,22 @@ static void amdgpu_flip_work_func(struct work_struct *__work) /* Sleep at least until estimated real start of hw vblank */ spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 7380f782cd14..d20c2a8929cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -596,7 +596,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, break; } ttm_eu_backoff_reservation(&ticket, &list); - if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE)) + if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && + !amdgpu_vm_debug) amdgpu_gem_va_update_vm(adev, bo_va, args->operation); drm_gem_object_unreference_unlocked(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 7d8d84eaea4a..95a4a25d8df9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -113,6 +113,10 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = ddev->dev_private; + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return snprintf(buf, PAGE_SIZE, "off\n"); + if (adev->pp_enabled) { enum amd_dpm_forced_level level; @@ -140,6 +144,11 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, enum amdgpu_dpm_forced_level level; int ret = 0; + /* Can't force performance level when the card is off */ + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + if (strncmp("low", buf, strlen("low")) == 0) { level = AMDGPU_DPM_FORCED_LEVEL_LOW; } else if (strncmp("high", buf, strlen("high")) == 0) { @@ -157,6 +166,7 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, mutex_lock(&adev->pm.mutex); if (adev->pm.dpm.thermal_active) { count = -EINVAL; + mutex_unlock(&adev->pm.mutex); goto fail; } ret = amdgpu_dpm_force_performance_level(adev, level); @@ -167,8 +177,6 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, mutex_unlock(&adev->pm.mutex); } fail: - mutex_unlock(&adev->pm.mutex); - return count; } @@ -182,8 +190,14 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev, char *buf) { struct amdgpu_device *adev = dev_get_drvdata(dev); + struct drm_device *ddev = adev->ddev; int temp; + /* Can't get temperature when the card is off */ + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + if (!adev->pp_enabled && !adev->pm.funcs->get_temperature) temp = 0; else @@ -634,11 +648,6 @@ force: /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - /* update displays */ - amdgpu_dpm_display_configuration_changed(adev); - - adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; - adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; /* wait for the rings to drain */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { @@ -655,6 +664,12 @@ force: amdgpu_dpm_post_set_power_state(adev); + /* update displays */ + amdgpu_dpm_display_configuration_changed(adev); + + adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; + adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; @@ -847,12 +862,16 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data) struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; struct amdgpu_device *adev = dev->dev_private; + struct drm_device *ddev = adev->ddev; if (!adev->pm.dpm_enabled) { seq_printf(m, "dpm not enabled\n"); return 0; } - if (adev->pp_enabled) { + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) { + seq_printf(m, "PX asic powered off\n"); + } else if (adev->pp_enabled) { amdgpu_dpm_debugfs_print_current_performance_level(adev, m); } else { mutex_lock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c index b9d0d55f6b47..3cb6d6c413c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c @@ -143,8 +143,10 @@ static int amdgpu_pp_late_init(void *handle) adev->powerplay.pp_handle); #ifdef CONFIG_DRM_AMD_POWERPLAY - if (adev->pp_enabled) + if (adev->pp_enabled) { amdgpu_pm_sysfs_init(adev); + amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_COMPLETE_INIT, NULL, NULL); + } #endif return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 9056355309d1..e7ef2261ff4a 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -2202,8 +2202,7 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) AMD_PG_STATE_GATE); cz_enable_vce_dpm(adev, false); - /* TODO: to figure out why vce can't be poweroff. */ - /* cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF); */ + cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF); pi->vce_power_gated = true; } else { cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerON); @@ -2226,10 +2225,8 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) } } else { /*pi->caps_vce_pg*/ cz_update_vce_dpm(adev); - cz_enable_vce_dpm(adev, true); + cz_enable_vce_dpm(adev, !gate); } - - return; } const struct amd_ip_funcs cz_dpm_ip_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 7732059ae30f..06602df707f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3628,6 +3628,19 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr) { int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX); + uint32_t seq = ring->fence_drv.sync_seq; + uint64_t addr = ring->fence_drv.gpu_addr; + + amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); + amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); + amdgpu_ring_write(ring, seq); + amdgpu_ring_write(ring, 0xffffffff); + amdgpu_ring_write(ring, 4); /* poll interval */ + if (usepfp) { /* synce CE with ME to prevent CE fetch CEIB before context switch done */ amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 8f8ec37ecd88..7086ac17abee 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4809,7 +4809,8 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ - WAIT_REG_MEM_FUNCTION(3))); /* equal */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); @@ -4995,7 +4996,7 @@ static int gfx_v8_0_set_priv_reg_fault_state(struct amdgpu_device *adev, case AMDGPU_IRQ_STATE_ENABLE: cp_int_cntl = RREG32(mmCP_INT_CNTL_RING0); cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0, - PRIV_REG_INT_ENABLE, 0); + PRIV_REG_INT_ENABLE, 1); WREG32(mmCP_INT_CNTL_RING0, cp_int_cntl); break; default: diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index aa67244a77ae..589599f66fcc 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -402,8 +402,11 @@ int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_event event_id, void *input, data.requested_ui_label = power_state_convert(ps); ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); + break; } - break; + case AMD_PP_EVENT_COMPLETE_INIT: + ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); + break; default: break; } diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c index 83be3cf210e0..6b52c78cb404 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c @@ -165,6 +165,7 @@ const struct action_chain resume_action_chain = { }; static const pem_event_action *complete_init_event[] = { + unblock_adjust_power_state_tasks, adjust_power_state_tasks, enable_gfx_clock_gating_tasks, enable_gfx_voltage_island_power_gating_tasks, diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c index 52a3efc97f05..46410e3c7349 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c @@ -31,7 +31,7 @@ static int pem_init(struct pp_eventmgr *eventmgr) { int result = 0; - struct pem_event_data event_data; + struct pem_event_data event_data = { {0} }; /* Initialize PowerPlay feature info */ pem_init_feature_info(eventmgr); @@ -52,7 +52,7 @@ static int pem_init(struct pp_eventmgr *eventmgr) static void pem_fini(struct pp_eventmgr *eventmgr) { - struct pem_event_data event_data; + struct pem_event_data event_data = { {0} }; pem_uninit_featureInfo(eventmgr); pem_unregister_interrupts(eventmgr); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c index ad7700822a1c..ff08ce41bde9 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c @@ -226,7 +226,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) } } else { cz_dpm_update_vce_dpm(hwmgr); - cz_enable_disable_vce_dpm(hwmgr, true); + cz_enable_disable_vce_dpm(hwmgr, !bgate); return 0; } diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 9759009d1da3..b1480acbb3c3 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -227,7 +227,7 @@ static int ast_get_dram_info(struct drm_device *dev) } while (ast_read32(ast, 0x10000) != 0x01); data = ast_read32(ast, 0x10004); - if (data & 0x400) + if (data & 0x40) ast->dram_bus_width = 16; else ast->dram_bus_width = 32; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 0fc38bb7276c..cf39ed3133d6 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -825,8 +825,11 @@ static int i915_interrupt_info(struct seq_file *m, void *data) } for_each_pipe(dev_priv, pipe) { - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(pipe))) { + enum intel_display_power_domain power_domain; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, + power_domain)) { seq_printf(m, "Pipe %c power disabled\n", pipe_name(pipe)); continue; @@ -840,6 +843,8 @@ static int i915_interrupt_info(struct seq_file *m, void *data) seq_printf(m, "Pipe %c IER:\t%08x\n", pipe_name(pipe), I915_READ(GEN8_DE_PIPE_IER(pipe))); + + intel_display_power_put(dev_priv, power_domain); } seq_printf(m, "Display Engine port interrupt mask:\t%08x\n", @@ -3985,6 +3990,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe]; struct intel_crtc *crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe)); + enum intel_display_power_domain power_domain; u32 val = 0; /* shut up gcc */ int ret; @@ -3995,7 +4001,8 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, if (pipe_crc->source && source) return -EINVAL; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) { + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) { DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n"); return -EIO; } @@ -4012,7 +4019,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, ret = ivb_pipe_crc_ctl_reg(dev, pipe, &source, &val); if (ret != 0) - return ret; + goto out; /* none -> real source transition */ if (source) { @@ -4024,8 +4031,10 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR, sizeof(pipe_crc->entries[0]), GFP_KERNEL); - if (!entries) - return -ENOMEM; + if (!entries) { + ret = -ENOMEM; + goto out; + } /* * When IPS gets enabled, the pipe CRC changes. Since IPS gets @@ -4081,7 +4090,12 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, hsw_enable_ips(crtc); } - return 0; + ret = 0; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } /* diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e7cd311e9fbb..b0847b915545 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -751,6 +751,7 @@ struct intel_csr { uint32_t mmio_count; i915_reg_t mmioaddr[8]; uint32_t mmiodata[8]; + uint32_t dc_state; }; #define DEV_INFO_FOR_EACH_FLAG(func, sep) \ diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 9c89df1af036..a7b4a524fadd 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -71,22 +71,29 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder, struct intel_crt *crt = intel_encoder_to_crt(encoder); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(crt->adpa_reg); if (!(tmp & ADPA_DAC_ENABLE)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static unsigned int intel_crt_get_flags(struct intel_encoder *encoder) diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 9bb63a85997a..647d85e77c2f 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -240,6 +240,8 @@ void intel_csr_load_program(struct drm_i915_private *dev_priv) I915_WRITE(dev_priv->csr.mmioaddr[i], dev_priv->csr.mmiodata[i]); } + + dev_priv->csr.dc_state = 0; } static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 54a165b9c92d..0f3df2c39f7c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1969,13 +1969,16 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) enum transcoder cpu_transcoder; enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; power_domain = intel_display_port_power_domain(intel_encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) - return false; + if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) { + ret = false; + goto out; + } if (port == PORT_A) cpu_transcoder = TRANSCODER_EDP; @@ -1987,23 +1990,33 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) switch (tmp & TRANS_DDI_MODE_SELECT_MASK) { case TRANS_DDI_MODE_SELECT_HDMI: case TRANS_DDI_MODE_SELECT_DVI: - return (type == DRM_MODE_CONNECTOR_HDMIA); + ret = type == DRM_MODE_CONNECTOR_HDMIA; + break; case TRANS_DDI_MODE_SELECT_DP_SST: - if (type == DRM_MODE_CONNECTOR_eDP) - return true; - return (type == DRM_MODE_CONNECTOR_DisplayPort); + ret = type == DRM_MODE_CONNECTOR_eDP || + type == DRM_MODE_CONNECTOR_DisplayPort; + break; + case TRANS_DDI_MODE_SELECT_DP_MST: /* if the transcoder is in MST state then * connector isn't connected */ - return false; + ret = false; + break; case TRANS_DDI_MODE_SELECT_FDI: - return (type == DRM_MODE_CONNECTOR_VGA); + ret = type == DRM_MODE_CONNECTOR_VGA; + break; default: - return false; + ret = false; + break; } + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } bool intel_ddi_get_hw_state(struct intel_encoder *encoder, @@ -2015,15 +2028,18 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum intel_display_power_domain power_domain; u32 tmp; int i; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(DDI_BUF_CTL(port)); if (!(tmp & DDI_BUF_CTL_ENABLE)) - return false; + goto out; if (port == PORT_A) { tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)); @@ -2041,25 +2057,32 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, break; } - return true; - } else { - for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) { - tmp = I915_READ(TRANS_DDI_FUNC_CTL(i)); + ret = true; - if ((tmp & TRANS_DDI_PORT_MASK) - == TRANS_DDI_SELECT_PORT(port)) { - if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == TRANS_DDI_MODE_SELECT_DP_MST) - return false; + goto out; + } - *pipe = i; - return true; - } + for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) { + tmp = I915_READ(TRANS_DDI_FUNC_CTL(i)); + + if ((tmp & TRANS_DDI_PORT_MASK) == TRANS_DDI_SELECT_PORT(port)) { + if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == + TRANS_DDI_MODE_SELECT_DP_MST) + goto out; + + *pipe = i; + ret = true; + + goto out; } } DRM_DEBUG_KMS("No pipe for ddi port %c found\n", port_name(port)); - return false; +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc) @@ -2508,12 +2531,14 @@ static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(WRPLL_CTL(pll->id)); hw_state->wrpll = val; + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & WRPLL_PLL_ENABLE; } @@ -2523,12 +2548,14 @@ static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(SPLL_CTL); hw_state->spll = val; + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & SPLL_PLL_ENABLE; } @@ -2645,16 +2672,19 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, uint32_t val; unsigned int dpll; const struct skl_dpll_regs *regs = skl_dpll_regs; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; + ret = false; + /* DPLL0 is not part of the shared DPLLs, so pll->id is 0 for DPLL1 */ dpll = pll->id + 1; val = I915_READ(regs[pll->id].ctl); if (!(val & LCPLL_PLL_ENABLE)) - return false; + goto out; val = I915_READ(DPLL_CTRL1); hw_state->ctrl1 = (val >> (dpll * 6)) & 0x3f; @@ -2664,8 +2694,12 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->cfgcr1 = I915_READ(regs[pll->id].cfgcr1); hw_state->cfgcr2 = I915_READ(regs[pll->id].cfgcr2); } + ret = true; - return true; +out: + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + + return ret; } static void skl_shared_dplls_init(struct drm_i915_private *dev_priv) @@ -2932,13 +2966,16 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, { enum port port = (enum port)pll->id; /* 1:1 port->PLL mapping */ uint32_t val; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; + ret = false; + val = I915_READ(BXT_PORT_PLL_ENABLE(port)); if (!(val & PORT_PLL_ENABLE)) - return false; + goto out; hw_state->ebb0 = I915_READ(BXT_PORT_PLL_EBB_0(port)); hw_state->ebb0 &= PORT_PLL_P1_MASK | PORT_PLL_P2_MASK; @@ -2985,7 +3022,12 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, I915_READ(BXT_PORT_PCS_DW12_LN23(port))); hw_state->pcsdw12 &= LANE_STAGGER_MASK | LANESTAGGER_STRAP_OVRD; - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + + return ret; } static void bxt_shared_dplls_init(struct drm_i915_private *dev_priv) @@ -3120,11 +3162,15 @@ bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv, { u32 temp; - if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { + if (intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + + intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); + if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe)) return true; } + return false; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 5feb65725c04..46947fffd599 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1351,18 +1351,21 @@ void assert_pipe(struct drm_i915_private *dev_priv, bool cur_state; enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv, pipe); + enum intel_display_power_domain power_domain; /* if we need the pipe quirk it must be always on */ if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) || (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE)) state = true; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_TRANSCODER(cpu_transcoder))) { - cur_state = false; - } else { + power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); + if (intel_display_power_get_if_enabled(dev_priv, power_domain)) { u32 val = I915_READ(PIPECONF(cpu_transcoder)); cur_state = !!(val & PIPECONF_ENABLE); + + intel_display_power_put(dev_priv, power_domain); + } else { + cur_state = false; } I915_STATE_WARN(cur_state != state, @@ -8171,18 +8174,22 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; + ret = false; + tmp = I915_READ(PIPECONF(crtc->pipe)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; if (IS_G4X(dev) || IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { switch (tmp & PIPECONF_BPC_MASK) { @@ -8262,7 +8269,12 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock / pipe_config->pixel_multiplier; - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void ironlake_init_pch_refclk(struct drm_device *dev) @@ -9366,18 +9378,21 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; + ret = false; tmp = I915_READ(PIPECONF(crtc->pipe)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; switch (tmp & PIPECONF_BPC_MASK) { case PIPECONF_6BPC: @@ -9440,7 +9455,12 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, ironlake_get_pfit_config(crtc, pipe_config); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) @@ -9950,12 +9970,17 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - enum intel_display_power_domain pfit_domain; + enum intel_display_power_domain power_domain; + unsigned long power_domain_mask; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + power_domain_mask = BIT(power_domain); + + ret = false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; @@ -9982,13 +10007,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, pipe_config->cpu_transcoder = TRANSCODER_EDP; } - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder))) - return false; + power_domain = POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + goto out; + power_domain_mask |= BIT(power_domain); tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; haswell_get_ddi_port_state(crtc, pipe_config); @@ -9998,14 +10024,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, skl_init_scalers(dev, crtc, pipe_config); } - pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe); - if (INTEL_INFO(dev)->gen >= 9) { pipe_config->scaler_state.scaler_id = -1; pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX); } - if (intel_display_power_is_enabled(dev_priv, pfit_domain)) { + power_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe); + if (intel_display_power_get_if_enabled(dev_priv, power_domain)) { + power_domain_mask |= BIT(power_domain); if (INTEL_INFO(dev)->gen >= 9) skylake_get_pfit_config(crtc, pipe_config); else @@ -10023,7 +10049,13 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, pipe_config->pixel_multiplier = 1; } - return true; + ret = true; + +out: + for_each_power_domain(power_domain, power_domain_mask) + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on) @@ -13630,7 +13662,7 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(PCH_DPLL(pll->id)); @@ -13638,6 +13670,8 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->fp0 = I915_READ(PCH_FP0(pll->id)); hw_state->fp1 = I915_READ(PCH_FP1(pll->id)); + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & DPLL_VCO_ENABLE; } @@ -15568,10 +15602,12 @@ void i915_redisable_vga(struct drm_device *dev) * level, just check if the power well is enabled instead of trying to * follow the "don't touch the power well if we don't need it" policy * the rest of the driver uses. */ - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_VGA)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_VGA)) return; i915_redisable_vga_power_on(dev); + + intel_display_power_put(dev_priv, POWER_DOMAIN_VGA); } static bool primary_get_hw_state(struct intel_plane *plane) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 1bbd67b046da..1d8de43bed56 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -2362,15 +2362,18 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = dev->dev_private; enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(intel_dp->output_reg); if (!(tmp & DP_PORT_EN)) - return false; + goto out; if (IS_GEN7(dev) && port == PORT_A) { *pipe = PORT_TO_PIPE_CPT(tmp); @@ -2381,7 +2384,9 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, u32 trans_dp = I915_READ(TRANS_DP_CTL(p)); if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) { *pipe = p; - return true; + ret = true; + + goto out; } } @@ -2393,7 +2398,12 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, *pipe = PORT_TO_PIPE(tmp); } - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_dp_get_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index ea5415851c6e..df7f3cb66056 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1428,6 +1428,8 @@ bool __intel_display_power_is_enabled(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); +bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain); void intel_display_power_put(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); @@ -1514,6 +1516,7 @@ enable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv) enable_rpm_wakeref_asserts(dev_priv) void intel_runtime_pm_get(struct drm_i915_private *dev_priv); +bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv); void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv); void intel_runtime_pm_put(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 44742fa2f616..0193c62a53ef 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -664,13 +664,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, struct drm_device *dev = encoder->base.dev; enum intel_display_power_domain power_domain; enum port port; + bool ret; DRM_DEBUG_KMS("\n"); power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + /* XXX: this only works for one DSI output */ for_each_dsi_port(port, intel_dsi->ports) { i915_reg_t ctrl_reg = IS_BROXTON(dev) ? @@ -691,12 +694,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, if (dpi_enabled || (func & CMD_MODE_DATA_WIDTH_MASK)) { if (I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY) { *pipe = port == PORT_A ? PIPE_A : PIPE_B; - return true; + ret = true; + + goto out; } } } +out: + intel_display_power_put(dev_priv, power_domain); - return false; + return ret; } static void intel_dsi_get_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 4a77639a489d..cb5d1b15755c 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -880,15 +880,18 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(intel_hdmi->hdmi_reg); if (!(tmp & SDVO_ENABLE)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); @@ -897,7 +900,12 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_hdmi_get_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 0da0240caf81..bc04d8d29acb 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -75,22 +75,30 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder, struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(lvds_encoder->reg); if (!(tmp & LVDS_PORT_EN)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_lvds_get_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a234687792f0..b28c29f20e75 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2829,7 +2829,10 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, memset(ddb, 0, sizeof(*ddb)); for_each_pipe(dev_priv, pipe) { - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) + enum intel_display_power_domain power_domain; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) continue; for_each_plane(dev_priv, pipe, plane) { @@ -2841,6 +2844,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, val = I915_READ(CUR_BUF_CFG(pipe)); skl_ddb_entry_init_from_hw(&ddb->plane[pipe][PLANE_CURSOR], val); + + intel_display_power_put(dev_priv, power_domain); } } diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index ddbdbffe829a..4f43d9b32e66 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -470,6 +470,43 @@ static void gen9_set_dc_state_debugmask_memory_up( } } +static void gen9_write_dc_state(struct drm_i915_private *dev_priv, + u32 state) +{ + int rewrites = 0; + int rereads = 0; + u32 v; + + I915_WRITE(DC_STATE_EN, state); + + /* It has been observed that disabling the dc6 state sometimes + * doesn't stick and dmc keeps returning old value. Make sure + * the write really sticks enough times and also force rewrite until + * we are confident that state is exactly what we want. + */ + do { + v = I915_READ(DC_STATE_EN); + + if (v != state) { + I915_WRITE(DC_STATE_EN, state); + rewrites++; + rereads = 0; + } else if (rereads++ > 5) { + break; + } + + } while (rewrites < 100); + + if (v != state) + DRM_ERROR("Writing dc state to 0x%x failed, now 0x%x\n", + state, v); + + /* Most of the times we need one retry, avoid spam */ + if (rewrites > 1) + DRM_DEBUG_KMS("Rewrote dc state to 0x%x %d times\n", + state, rewrites); +} + static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) { uint32_t val; @@ -494,10 +531,18 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) val = I915_READ(DC_STATE_EN); DRM_DEBUG_KMS("Setting DC state from %02x to %02x\n", val & mask, state); + + /* Check if DMC is ignoring our DC state requests */ + if ((val & mask) != dev_priv->csr.dc_state) + DRM_ERROR("DC state mismatch (0x%x -> 0x%x)\n", + dev_priv->csr.dc_state, val & mask); + val &= ~mask; val |= state; - I915_WRITE(DC_STATE_EN, val); - POSTING_READ(DC_STATE_EN); + + gen9_write_dc_state(dev_priv, val); + + dev_priv->csr.dc_state = val & mask; } void bxt_enable_dc9(struct drm_i915_private *dev_priv) @@ -1442,6 +1487,22 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv, chv_set_pipe_power_well(dev_priv, power_well, false); } +static void +__intel_display_power_get_domain(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_well *power_well; + int i; + + for_each_power_well(i, power_well, BIT(domain), power_domains) { + if (!power_well->count++) + intel_power_well_enable(dev_priv, power_well); + } + + power_domains->domain_use_count[domain]++; +} + /** * intel_display_power_get - grab a power domain reference * @dev_priv: i915 device instance @@ -1457,24 +1518,53 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv, void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains; - struct i915_power_well *power_well; - int i; + struct i915_power_domains *power_domains = &dev_priv->power_domains; intel_runtime_pm_get(dev_priv); - power_domains = &dev_priv->power_domains; + mutex_lock(&power_domains->lock); + + __intel_display_power_get_domain(dev_priv, domain); + + mutex_unlock(&power_domains->lock); +} + +/** + * intel_display_power_get_if_enabled - grab a reference for an enabled display power domain + * @dev_priv: i915 device instance + * @domain: power domain to reference + * + * This function grabs a power domain reference for @domain and ensures that the + * power domain and all its parents are powered up. Therefore users should only + * grab a reference to the innermost power domain they need. + * + * Any power domain reference obtained by this function must have a symmetric + * call to intel_display_power_put() to release the reference again. + */ +bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + bool is_enabled; + + if (!intel_runtime_pm_get_if_in_use(dev_priv)) + return false; mutex_lock(&power_domains->lock); - for_each_power_well(i, power_well, BIT(domain), power_domains) { - if (!power_well->count++) - intel_power_well_enable(dev_priv, power_well); + if (__intel_display_power_is_enabled(dev_priv, domain)) { + __intel_display_power_get_domain(dev_priv, domain); + is_enabled = true; + } else { + is_enabled = false; } - power_domains->domain_use_count[domain]++; - mutex_unlock(&power_domains->lock); + + if (!is_enabled) + intel_runtime_pm_put(dev_priv); + + return is_enabled; } /** @@ -2213,15 +2303,15 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume) */ void intel_power_domains_suspend(struct drm_i915_private *dev_priv) { - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) - skl_display_core_uninit(dev_priv); - /* * Even if power well support was disabled we still want to disable * power wells while we are system suspended. */ if (!i915.disable_power_well) intel_display_power_put(dev_priv, POWER_DOMAIN_INIT); + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + skl_display_core_uninit(dev_priv); } /** @@ -2246,6 +2336,41 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv) } /** + * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use + * @dev_priv: i915 device instance + * + * This function grabs a device-level runtime pm reference if the device is + * already in use and ensures that it is powered up. + * + * Any runtime pm reference obtained by this function must have a symmetric + * call to intel_runtime_pm_put() to release the reference again. + */ +bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + struct device *device = &dev->pdev->dev; + + if (IS_ENABLED(CONFIG_PM)) { + int ret = pm_runtime_get_if_in_use(device); + + /* + * In cases runtime PM is disabled by the RPM core and we get + * an -EINVAL return value we are not supposed to call this + * function, since the power state is undefined. This applies + * atm to the late/early system suspend/resume handlers. + */ + WARN_ON_ONCE(ret < 0); + if (ret <= 0) + return false; + } + + atomic_inc(&dev_priv->pm.wakeref_count); + assert_rpm_wakelock_held(dev_priv); + + return true; +} + +/** * intel_runtime_pm_get_noresume - grab a runtime pm reference * @dev_priv: i915 device instance * diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c index 8a70cec59bcd..2dfe58af12e4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_platform.c +++ b/drivers/gpu/drm/nouveau/nouveau_platform.c @@ -24,7 +24,7 @@ static int nouveau_platform_probe(struct platform_device *pdev) { const struct nvkm_device_tegra_func *func; - struct nvkm_device *device; + struct nvkm_device *device = NULL; struct drm_device *drm; int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index 7f8a42721eb2..e7e581d6a8ff 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -252,32 +252,40 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL))) return -ENOMEM; - *pdevice = &tdev->device; + tdev->func = func; tdev->pdev = pdev; tdev->irq = -1; tdev->vdd = devm_regulator_get(&pdev->dev, "vdd"); - if (IS_ERR(tdev->vdd)) - return PTR_ERR(tdev->vdd); + if (IS_ERR(tdev->vdd)) { + ret = PTR_ERR(tdev->vdd); + goto free; + } tdev->rst = devm_reset_control_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->rst)) - return PTR_ERR(tdev->rst); + if (IS_ERR(tdev->rst)) { + ret = PTR_ERR(tdev->rst); + goto free; + } tdev->clk = devm_clk_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->clk)) - return PTR_ERR(tdev->clk); + if (IS_ERR(tdev->clk)) { + ret = PTR_ERR(tdev->clk); + goto free; + } tdev->clk_pwr = devm_clk_get(&pdev->dev, "pwr"); - if (IS_ERR(tdev->clk_pwr)) - return PTR_ERR(tdev->clk_pwr); + if (IS_ERR(tdev->clk_pwr)) { + ret = PTR_ERR(tdev->clk_pwr); + goto free; + } nvkm_device_tegra_probe_iommu(tdev); ret = nvkm_device_tegra_power_up(tdev); if (ret) - return ret; + goto remove; tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value; ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev, @@ -285,9 +293,19 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, cfg, dbg, detect, mmio, subdev_mask, &tdev->device); if (ret) - return ret; + goto powerdown; + + *pdevice = &tdev->device; return 0; + +powerdown: + nvkm_device_tegra_power_down(tdev); +remove: + nvkm_device_tegra_remove_iommu(tdev); +free: + kfree(tdev); + return ret; } #else int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c index 74e2f7c6c07e..9688970eca47 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c @@ -328,6 +328,7 @@ nvkm_dp_train(struct work_struct *w) .outp = outp, }, *dp = &_dp; u32 datarate = 0; + u8 pwr; int ret; if (!outp->base.info.location && disp->func->sor.magic) @@ -355,6 +356,15 @@ nvkm_dp_train(struct work_struct *w) /* disable link interrupt handling during link training */ nvkm_notify_put(&outp->irq); + /* ensure sink is not in a low-power state */ + if (!nvkm_rdaux(outp->aux, DPCD_SC00, &pwr, 1)) { + if ((pwr & DPCD_SC00_SET_POWER) != DPCD_SC00_SET_POWER_D0) { + pwr &= ~DPCD_SC00_SET_POWER; + pwr |= DPCD_SC00_SET_POWER_D0; + nvkm_wraux(outp->aux, DPCD_SC00, &pwr, 1); + } + } + /* enable down-spreading and execute pre-train script from vbios */ dp_link_train_init(dp, outp->dpcd[3] & 0x01); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h index 9596290329c7..6e10c5e0ef11 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h @@ -71,5 +71,11 @@ #define DPCD_LS0C_LANE1_POST_CURSOR2 0x0c #define DPCD_LS0C_LANE0_POST_CURSOR2 0x03 +/* DPCD Sink Control */ +#define DPCD_SC00 0x00600 +#define DPCD_SC00_SET_POWER 0x03 +#define DPCD_SC00_SET_POWER_D0 0x01 +#define DPCD_SC00_SET_POWER_D3 0x03 + void nvkm_dp_train(struct work_struct *); #endif diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 902b59cebac5..4197ca1bb1e4 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1744,7 +1744,6 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } drm_kms_helper_poll_enable(dev); - drm_helper_hpd_irq_event(dev); /* set the power state here in case we are a PX system or headless */ if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 298ea1c453c3..2b9ba03a7c1a 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -403,7 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &radeon_crtc->base; unsigned long flags; int r; - int vpos, hpos, stat, min_udelay; + int vpos, hpos, stat, min_udelay = 0; + unsigned repcnt = 4; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; down_read(&rdev->exclusive_lock); @@ -454,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (radeon_crtc->enabled && repcnt--) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -472,10 +473,22 @@ static void radeon_flip_work_func(struct work_struct *__work) /* Sleep at least until estimated real start of hw vblank */ spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 248c5a9fb0b6..0f14d897baf9 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1079,12 +1079,6 @@ force: /* update display watermarks based on new power state */ radeon_bandwidth_update(rdev); - /* update displays */ - radeon_dpm_display_configuration_changed(rdev); - - rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; - rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; - rdev->pm.dpm.single_display = single_display; /* wait for the rings to drain */ for (i = 0; i < RADEON_NUM_RINGS; i++) { @@ -1101,6 +1095,13 @@ force: radeon_dpm_post_set_power_state(rdev); + /* update displays */ + radeon_dpm_display_configuration_changed(rdev); + + rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; + rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; + rdev->pm.dpm.single_display = single_display; + if (rdev->asic->dpm.force_performance_level) { if (rdev->pm.dpm.thermal_active) { enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level; diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index da462afcb225..dd2dbb9746ce 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -18,6 +18,7 @@ #include <linux/host1x.h> #include <linux/of.h> #include <linux/slab.h> +#include <linux/of_device.h> #include "bus.h" #include "dev.h" @@ -394,6 +395,7 @@ static int host1x_device_add(struct host1x *host1x, device->dev.coherent_dma_mask = host1x->dev->coherent_dma_mask; device->dev.dma_mask = &device->dev.coherent_dma_mask; dev_set_name(&device->dev, "%s", driver->driver.name); + of_dma_configure(&device->dev, host1x->dev->of_node); device->dev.release = host1x_device_release; device->dev.bus = &host1x_bus_type; device->dev.parent = host1x->dev; diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 314bf3718cc7..ff348690df94 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -23,6 +23,7 @@ #include <linux/of_device.h> #include <linux/clk.h> #include <linux/io.h> +#include <linux/dma-mapping.h> #define CREATE_TRACE_POINTS #include <trace/events/host1x.h> @@ -68,6 +69,7 @@ static const struct host1x_info host1x01_info = { .nb_bases = 8, .init = host1x01_init, .sync_offset = 0x3000, + .dma_mask = DMA_BIT_MASK(32), }; static const struct host1x_info host1x02_info = { @@ -77,6 +79,7 @@ static const struct host1x_info host1x02_info = { .nb_bases = 12, .init = host1x02_init, .sync_offset = 0x3000, + .dma_mask = DMA_BIT_MASK(32), }; static const struct host1x_info host1x04_info = { @@ -86,6 +89,7 @@ static const struct host1x_info host1x04_info = { .nb_bases = 64, .init = host1x04_init, .sync_offset = 0x2100, + .dma_mask = DMA_BIT_MASK(34), }; static const struct host1x_info host1x05_info = { @@ -95,6 +99,7 @@ static const struct host1x_info host1x05_info = { .nb_bases = 64, .init = host1x05_init, .sync_offset = 0x2100, + .dma_mask = DMA_BIT_MASK(34), }; static struct of_device_id host1x_of_match[] = { @@ -148,6 +153,8 @@ static int host1x_probe(struct platform_device *pdev) if (IS_ERR(host->regs)) return PTR_ERR(host->regs); + dma_set_mask_and_coherent(host->dev, host->info->dma_mask); + if (host->info->init) { err = host->info->init(host); if (err) diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index 0b6e8e9629c5..dace124994bb 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -96,6 +96,7 @@ struct host1x_info { int nb_mlocks; /* host1x: number of mlocks */ int (*init)(struct host1x *); /* initialize per SoC ops */ int sync_offset; + u64 dma_mask; /* mask of addressable memory */ }; struct host1x { diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 3711df1d4526..4a45408dd820 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -586,8 +586,7 @@ static int brcmstb_i2c_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; - dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(struct bsc_regs *), - GFP_KERNEL); + dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(*dev->bsc_regmap), GFP_KERNEL); if (!dev->bsc_regmap) return -ENOMEM; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 00da80e02154..94b80a51ab68 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -358,6 +358,7 @@ int ib_register_device(struct ib_device *device, ret = device->query_device(device, &device->attrs, &uhw); if (ret) { printk(KERN_WARNING "Couldn't query the device attributes\n"); + ib_cache_cleanup_one(device); goto out; } diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index f334090bb612..1e37f3515d98 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1071,7 +1071,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num, } } - if (rec->hop_limit > 1 || use_roce) { + if (rec->hop_limit > 0 || use_roce) { ah_attr->ah_flags = IB_AH_GRH; ah_attr->grh.dgid = rec->dgid; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 6ffc9c4e93af..6c6fbff19752 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1970,7 +1970,8 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, resp_size); INIT_UDATA(&uhw, buf + sizeof(cmd), (unsigned long)cmd.response + resp_size, - in_len - sizeof(cmd), out_len - resp_size); + in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), + out_len - resp_size); memset(&cmd_ex, 0, sizeof(cmd_ex)); cmd_ex.user_handle = cmd.user_handle; @@ -3413,7 +3414,8 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file, INIT_UDATA(&udata, buf + sizeof cmd, (unsigned long) cmd.response + sizeof resp, - in_len - sizeof cmd, out_len - sizeof resp); + in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr), + out_len - sizeof resp); ret = __uverbs_create_xsrq(file, ib_dev, &xcmd, &udata); if (ret) @@ -3439,7 +3441,8 @@ ssize_t ib_uverbs_create_xsrq(struct ib_uverbs_file *file, INIT_UDATA(&udata, buf + sizeof cmd, (unsigned long) cmd.response + sizeof resp, - in_len - sizeof cmd, out_len - sizeof resp); + in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr), + out_len - sizeof resp); ret = __uverbs_create_xsrq(file, ib_dev, &cmd, &udata); if (ret) diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 4659256cd95e..3b2ddd64a371 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -75,7 +75,8 @@ static void mlx5_ib_srq_event(struct mlx5_core_srq *srq, enum mlx5_event type) static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, struct mlx5_create_srq_mbox_in **in, - struct ib_udata *udata, int buf_size, int *inlen) + struct ib_udata *udata, int buf_size, int *inlen, + int is_xrc) { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_ib_create_srq ucmd = {}; @@ -87,13 +88,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, int ncont; u32 offset; u32 uidx = MLX5_IB_DEFAULT_UIDX; - int drv_data = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr); - if (drv_data < 0) - return -EINVAL; - - ucmdlen = (drv_data < sizeof(ucmd)) ? - drv_data : sizeof(ucmd); + ucmdlen = min(udata->inlen, sizeof(ucmd)); if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) { mlx5_ib_dbg(dev, "failed copy udata\n"); @@ -103,15 +99,17 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, if (ucmd.reserved0 || ucmd.reserved1) return -EINVAL; - if (drv_data > sizeof(ucmd) && + if (udata->inlen > sizeof(ucmd) && !ib_is_udata_cleared(udata, sizeof(ucmd), - drv_data - sizeof(ucmd))) + udata->inlen - sizeof(ucmd))) return -EINVAL; - err = get_srq_user_index(to_mucontext(pd->uobject->context), - &ucmd, udata->inlen, &uidx); - if (err) - return err; + if (is_xrc) { + err = get_srq_user_index(to_mucontext(pd->uobject->context), + &ucmd, udata->inlen, &uidx); + if (err) + return err; + } srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE); @@ -151,7 +149,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT; (*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26); - if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) { + if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) && + is_xrc){ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in, xrc_srq_context_entry); MLX5_SET(xrc_srqc, xsrqc, user_index, uidx); @@ -170,7 +169,7 @@ err_umem: static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, struct mlx5_create_srq_mbox_in **in, int buf_size, - int *inlen) + int *inlen, int is_xrc) { int err; int i; @@ -224,7 +223,8 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT; - if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) { + if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) && + is_xrc){ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in, xrc_srq_context_entry); /* 0xffffff means we ask to work with cqe version 0 */ @@ -302,10 +302,14 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs, srq->msrq.max_avail_gather); + is_xrc = (init_attr->srq_type == IB_SRQT_XRC); + if (pd->uobject) - err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen); + err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen, + is_xrc); else - err = create_srq_kernel(dev, srq, &in, buf_size, &inlen); + err = create_srq_kernel(dev, srq, &in, buf_size, &inlen, + is_xrc); if (err) { mlx5_ib_warn(dev, "create srq %s failed, err %d\n", @@ -313,7 +317,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, goto err_srq; } - is_xrc = (init_attr->srq_type == IB_SRQT_XRC); in->ctx.state_log_sz = ilog2(srq->msrq.max); flgs = ((srq->msrq.wqe_shift - 4) | (is_xrc << 5) | (srq->wq_sig << 7)) << 24; xrcdn = 0; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index e5e223938eec..374c129219ef 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -114,6 +114,7 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); +static void detach_device(struct device *dev); /* * For dynamic growth the aperture size is split into ranges of 128MB of @@ -384,6 +385,9 @@ static void iommu_uninit_device(struct device *dev) if (!dev_data) return; + if (dev_data->domain) + detach_device(dev); + iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev, dev); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 013bdfff2d4d..bf4959f4225b 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -228,6 +228,10 @@ static int amd_iommu_enable_interrupts(void); static int __init iommu_go_to_state(enum iommu_init_state state); static void init_device_table_dma(void); +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write); + static inline void update_last_devid(u16 devid) { if (devid > amd_iommu_last_bdf) @@ -1016,6 +1020,34 @@ static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) } /* + * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission) + * Workaround: + * BIOS should enable ATS write permission check by setting + * L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b + */ +static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu) +{ + u32 value; + + if ((boot_cpu_data.x86 != 0x15) || + (boot_cpu_data.x86_model < 0x30) || + (boot_cpu_data.x86_model > 0x3f)) + return; + + /* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */ + value = iommu_read_l2(iommu, 0x47); + + if (value & BIT(0)) + return; + + /* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */ + iommu_write_l2(iommu, 0x47, value | BIT(0)); + + pr_info("AMD-Vi: Applying ATS write check workaround for IOMMU at %s\n", + dev_name(&iommu->dev->dev)); +} + +/* * This function clues the initialization function for one IOMMU * together and also allocates the command buffer and programs the * hardware. It does NOT enable the IOMMU. This is done afterwards. @@ -1142,8 +1174,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu) amd_iommu_pc_present = true; /* Check if the performance counters can be written to */ - if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) || - (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) || + if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) || + (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) || (val != val2)) { pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n"); amd_iommu_pc_present = false; @@ -1284,6 +1316,7 @@ static int iommu_init_pci(struct amd_iommu *iommu) } amd_iommu_erratum_746_workaround(iommu); + amd_iommu_ats_write_check_workaround(iommu); iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu, amd_iommu_groups, "ivhd%d", @@ -2283,22 +2316,15 @@ u8 amd_iommu_pc_get_max_counters(u16 devid) } EXPORT_SYMBOL(amd_iommu_pc_get_max_counters); -int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, u64 *value, bool is_write) { - struct amd_iommu *iommu; u32 offset; u32 max_offset_lim; - /* Make sure the IOMMU PC resource is available */ - if (!amd_iommu_pc_present) - return -ENODEV; - - /* Locate the iommu associated with the device ID */ - iommu = amd_iommu_rlookup_table[devid]; - /* Check for valid iommu and pc register indexing */ - if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7))) + if (WARN_ON((fxn > 0x28) || (fxn & 7))) return -ENODEV; offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn); @@ -2322,3 +2348,16 @@ int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, return 0; } EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val); + +int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write) +{ + struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; + + /* Make sure the IOMMU PC resource is available */ + if (!amd_iommu_pc_present || iommu == NULL) + return -ENODEV; + + return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn, + value, is_write); +} diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index fb092f3f11cb..8ffd7568fc91 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -329,7 +329,8 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, /* Only care about add/remove events for physical functions */ if (pdev->is_virtfn) return NOTIFY_DONE; - if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE) + if (action != BUS_NOTIFY_ADD_DEVICE && + action != BUS_NOTIFY_REMOVED_DEVICE) return NOTIFY_DONE; info = dmar_alloc_pci_notify_info(pdev, action); @@ -339,7 +340,7 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, down_write(&dmar_global_lock); if (action == BUS_NOTIFY_ADD_DEVICE) dmar_pci_bus_add_dev(info); - else if (action == BUS_NOTIFY_DEL_DEVICE) + else if (action == BUS_NOTIFY_REMOVED_DEVICE) dmar_pci_bus_del_dev(info); up_write(&dmar_global_lock); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 986a53e3eb96..a2e1b7f14df2 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4367,7 +4367,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) rmrru->devices_cnt); if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { dmar_remove_dev_scope(info, rmrr->segment, rmrru->devices, rmrru->devices_cnt); } @@ -4387,7 +4387,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) break; else if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { if (dmar_remove_dev_scope(info, atsr->segment, atsru->devices, atsru->devices_cnt)) break; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 0a73632b28d5..43dfd15c1dd2 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -78,6 +78,9 @@ struct its_node { #define ITS_ITT_ALIGN SZ_256 +/* Convert page order to size in bytes */ +#define PAGE_ORDER_TO_SIZE(o) (PAGE_SIZE << (o)) + struct event_lpi_map { unsigned long *lpi_map; u16 *col_map; @@ -600,11 +603,6 @@ static void its_unmask_irq(struct irq_data *d) lpi_set_config(d, true); } -static void its_eoi_irq(struct irq_data *d) -{ - gic_write_eoir(d->hwirq); -} - static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { @@ -641,7 +639,7 @@ static struct irq_chip its_irq_chip = { .name = "ITS", .irq_mask = its_mask_irq, .irq_unmask = its_unmask_irq, - .irq_eoi = its_eoi_irq, + .irq_eoi = irq_chip_eoi_parent, .irq_set_affinity = its_set_affinity, .irq_compose_msi_msg = its_irq_compose_msi_msg, }; @@ -846,7 +844,6 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) u64 type = GITS_BASER_TYPE(val); u64 entry_size = GITS_BASER_ENTRY_SIZE(val); int order = get_order(psz); - int alloc_size; int alloc_pages; u64 tmp; void *base; @@ -878,9 +875,8 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) } } - alloc_size = (1 << order) * PAGE_SIZE; retry_alloc_baser: - alloc_pages = (alloc_size / psz); + alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); if (alloc_pages > GITS_BASER_PAGES_MAX) { alloc_pages = GITS_BASER_PAGES_MAX; order = get_order(GITS_BASER_PAGES_MAX * psz); @@ -933,7 +929,7 @@ retry_baser: shr = tmp & GITS_BASER_SHAREABILITY_MASK; if (!shr) { cache = GITS_BASER_nC; - __flush_dcache_area(base, alloc_size); + __flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order)); } goto retry_baser; } @@ -966,7 +962,7 @@ retry_baser: } pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n", - (int)(alloc_size / entry_size), + (int)(PAGE_ORDER_TO_SIZE(order) / entry_size), its_base_type_string[type], (unsigned long)virt_to_phys(base), psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 5df40480228b..dd834927bc66 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1191,6 +1191,8 @@ static void dm_unprep_request(struct request *rq) if (clone) free_rq_clone(clone); + else if (!tio->md->queue->mq_ops) + free_rq_tio(tio); } /* diff --git a/drivers/media/i2c/adp1653.c b/drivers/media/i2c/adp1653.c index 7e9cbf757e95..fb7ed730d932 100644 --- a/drivers/media/i2c/adp1653.c +++ b/drivers/media/i2c/adp1653.c @@ -497,7 +497,7 @@ static int adp1653_probe(struct i2c_client *client, if (!client->dev.platform_data) { dev_err(&client->dev, "Neither DT not platform data provided\n"); - return EINVAL; + return -EINVAL; } flash->platform_data = client->dev.platform_data; } diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index f8dd7505b529..e1719ffdfb3d 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -1960,10 +1960,9 @@ static int adv76xx_isr(struct v4l2_subdev *sd, u32 status, bool *handled) } /* tx 5v detect */ - tx_5v = io_read(sd, 0x70) & info->cable_det_mask; + tx_5v = irq_reg_0x70 & info->cable_det_mask; if (tx_5v) { v4l2_dbg(1, debug, sd, "%s: tx_5v: 0x%x\n", __func__, tx_5v); - io_write(sd, 0x71, tx_5v); adv76xx_s_detect_tx_5v_ctrl(sd); if (handled) *handled = true; diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index 8c54fd21022e..a13625722848 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -1843,8 +1843,7 @@ static void au0828_analog_create_entities(struct au0828_dev *dev) ent->function = MEDIA_ENT_F_CONN_RF; break; default: /* AU0828_VMUX_DEBUG */ - ent->function = MEDIA_ENT_F_CONN_TEST; - break; + continue; } ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]); diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 4c1903f781fc..0c6c17a1c59e 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -415,7 +415,7 @@ static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev) delta = mftb() - psl_tb; if (delta < 0) delta = -delta; - } while (cputime_to_usecs(delta) > 16); + } while (tb_to_ns(delta) > 16000); return 0; } diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index b6639ea0bf18..f6e4d9718035 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -2232,6 +2232,7 @@ err_irq: dma_release_channel(host->tx_chan); if (host->rx_chan) dma_release_channel(host->rx_chan); + pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); if (host->dbclk) @@ -2253,6 +2254,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev) dma_release_channel(host->tx_chan); dma_release_channel(host->rx_chan); + pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); device_init_wakeup(&pdev->dev, false); diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 2a1b6e037e1a..0134ba32a057 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -193,7 +193,7 @@ int ubi_start_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, vol->changing_leb = 1; vol->ch_lnum = req->lnum; - vol->upd_buf = vmalloc(req->bytes); + vol->upd_buf = vmalloc(ALIGN((int)req->bytes, ubi->min_io_size)); if (!vol->upd_buf) return -ENOMEM; diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 164ccdeca663..0d40aef928e2 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -106,7 +106,7 @@ config CAN_JANZ_ICAN3 config CAN_RCAR tristate "Renesas R-Car CAN controller" - depends on ARM + depends on ARCH_RENESAS || ARM ---help--- Say Y here if you want to use CAN controller found on Renesas R-Car SoCs. diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c index 0d1c164374b7..a1bd54ffd31e 100644 --- a/drivers/net/can/ifi_canfd/ifi_canfd.c +++ b/drivers/net/can/ifi_canfd/ifi_canfd.c @@ -135,8 +135,12 @@ #define IFI_CANFD_RXFIFO_ID 0x6c #define IFI_CANFD_RXFIFO_ID_ID_OFFSET 0 -#define IFI_CANFD_RXFIFO_ID_ID_STD_MASK 0x3ff -#define IFI_CANFD_RXFIFO_ID_ID_XTD_MASK 0x1fffffff +#define IFI_CANFD_RXFIFO_ID_ID_STD_MASK CAN_SFF_MASK +#define IFI_CANFD_RXFIFO_ID_ID_STD_OFFSET 0 +#define IFI_CANFD_RXFIFO_ID_ID_STD_WIDTH 10 +#define IFI_CANFD_RXFIFO_ID_ID_XTD_MASK CAN_EFF_MASK +#define IFI_CANFD_RXFIFO_ID_ID_XTD_OFFSET 11 +#define IFI_CANFD_RXFIFO_ID_ID_XTD_WIDTH 18 #define IFI_CANFD_RXFIFO_ID_IDE BIT(29) #define IFI_CANFD_RXFIFO_DATA 0x70 /* 0x70..0xac */ @@ -156,8 +160,12 @@ #define IFI_CANFD_TXFIFO_ID 0xbc #define IFI_CANFD_TXFIFO_ID_ID_OFFSET 0 -#define IFI_CANFD_TXFIFO_ID_ID_STD_MASK 0x3ff -#define IFI_CANFD_TXFIFO_ID_ID_XTD_MASK 0x1fffffff +#define IFI_CANFD_TXFIFO_ID_ID_STD_MASK CAN_SFF_MASK +#define IFI_CANFD_TXFIFO_ID_ID_STD_OFFSET 0 +#define IFI_CANFD_TXFIFO_ID_ID_STD_WIDTH 10 +#define IFI_CANFD_TXFIFO_ID_ID_XTD_MASK CAN_EFF_MASK +#define IFI_CANFD_TXFIFO_ID_ID_XTD_OFFSET 11 +#define IFI_CANFD_TXFIFO_ID_ID_XTD_WIDTH 18 #define IFI_CANFD_TXFIFO_ID_IDE BIT(29) #define IFI_CANFD_TXFIFO_DATA 0xc0 /* 0xb0..0xfc */ @@ -229,10 +237,20 @@ static void ifi_canfd_read_fifo(struct net_device *ndev) rxid = readl(priv->base + IFI_CANFD_RXFIFO_ID); id = (rxid >> IFI_CANFD_RXFIFO_ID_ID_OFFSET); - if (id & IFI_CANFD_RXFIFO_ID_IDE) + if (id & IFI_CANFD_RXFIFO_ID_IDE) { id &= IFI_CANFD_RXFIFO_ID_ID_XTD_MASK; - else + /* + * In case the Extended ID frame is received, the standard + * and extended part of the ID are swapped in the register, + * so swap them back to obtain the correct ID. + */ + id = (id >> IFI_CANFD_RXFIFO_ID_ID_XTD_OFFSET) | + ((id & IFI_CANFD_RXFIFO_ID_ID_STD_MASK) << + IFI_CANFD_RXFIFO_ID_ID_XTD_WIDTH); + id |= CAN_EFF_FLAG; + } else { id &= IFI_CANFD_RXFIFO_ID_ID_STD_MASK; + } cf->can_id = id; if (rxdlc & IFI_CANFD_RXFIFO_DLC_ESI) { @@ -514,25 +532,25 @@ static irqreturn_t ifi_canfd_isr(int irq, void *dev_id) static const struct can_bittiming_const ifi_canfd_bittiming_const = { .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ + .tseg1_min = 1, /* Time segment 1 = prop_seg + phase_seg1 */ .tseg1_max = 64, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 16, + .tseg2_min = 2, /* Time segment 2 = phase_seg2 */ + .tseg2_max = 64, .sjw_max = 16, - .brp_min = 1, - .brp_max = 1024, + .brp_min = 2, + .brp_max = 256, .brp_inc = 1, }; static const struct can_bittiming_const ifi_canfd_data_bittiming_const = { .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ - .tseg1_max = 16, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 8, - .sjw_max = 4, - .brp_min = 1, - .brp_max = 32, + .tseg1_min = 1, /* Time segment 1 = prop_seg + phase_seg1 */ + .tseg1_max = 64, + .tseg2_min = 2, /* Time segment 2 = phase_seg2 */ + .tseg2_max = 64, + .sjw_max = 16, + .brp_min = 2, + .brp_max = 256, .brp_inc = 1, }; @@ -545,32 +563,34 @@ static void ifi_canfd_set_bittiming(struct net_device *ndev) u32 noniso_arg = 0; u32 time_off; - if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) { + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) && + !(priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)) { + time_off = IFI_CANFD_TIME_SJW_OFF_ISO; + } else { noniso_arg = IFI_CANFD_TIME_SET_TIMEB_BOSCH | IFI_CANFD_TIME_SET_TIMEA_BOSCH | IFI_CANFD_TIME_SET_PRESC_BOSCH | IFI_CANFD_TIME_SET_SJW_BOSCH; time_off = IFI_CANFD_TIME_SJW_OFF_BOSCH; - } else { - time_off = IFI_CANFD_TIME_SJW_OFF_ISO; } /* Configure bit timing */ - brp = bt->brp - 1; + brp = bt->brp - 2; sjw = bt->sjw - 1; tseg1 = bt->prop_seg + bt->phase_seg1 - 1; - tseg2 = bt->phase_seg2 - 1; + tseg2 = bt->phase_seg2 - 2; writel((tseg2 << IFI_CANFD_TIME_TIMEB_OFF) | (tseg1 << IFI_CANFD_TIME_TIMEA_OFF) | (brp << IFI_CANFD_TIME_PRESCALE_OFF) | - (sjw << time_off), + (sjw << time_off) | + noniso_arg, priv->base + IFI_CANFD_TIME); /* Configure data bit timing */ - brp = dbt->brp - 1; + brp = dbt->brp - 2; sjw = dbt->sjw - 1; tseg1 = dbt->prop_seg + dbt->phase_seg1 - 1; - tseg2 = dbt->phase_seg2 - 1; + tseg2 = dbt->phase_seg2 - 2; writel((tseg2 << IFI_CANFD_TIME_TIMEB_OFF) | (tseg1 << IFI_CANFD_TIME_TIMEA_OFF) | (brp << IFI_CANFD_TIME_PRESCALE_OFF) | @@ -747,8 +767,7 @@ static netdev_tx_t ifi_canfd_start_xmit(struct sk_buff *skb, { struct ifi_canfd_priv *priv = netdev_priv(ndev); struct canfd_frame *cf = (struct canfd_frame *)skb->data; - u32 txst, txid; - u32 txdlc = 0; + u32 txst, txid, txdlc; int i; if (can_dropped_invalid_skb(ndev, skb)) @@ -766,17 +785,25 @@ static netdev_tx_t ifi_canfd_start_xmit(struct sk_buff *skb, if (cf->can_id & CAN_EFF_FLAG) { txid = cf->can_id & CAN_EFF_MASK; + /* + * In case the Extended ID frame is transmitted, the + * standard and extended part of the ID are swapped + * in the register, so swap them back to send the + * correct ID. + */ + txid = (txid >> IFI_CANFD_TXFIFO_ID_ID_XTD_WIDTH) | + ((txid & IFI_CANFD_TXFIFO_ID_ID_XTD_MASK) << + IFI_CANFD_TXFIFO_ID_ID_XTD_OFFSET); txid |= IFI_CANFD_TXFIFO_ID_IDE; } else { txid = cf->can_id & CAN_SFF_MASK; } - if (priv->can.ctrlmode & (CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO)) { - if (can_is_canfd_skb(skb)) { - txdlc |= IFI_CANFD_TXFIFO_DLC_EDL; - if (cf->flags & CANFD_BRS) - txdlc |= IFI_CANFD_TXFIFO_DLC_BRS; - } + txdlc = can_len2dlc(cf->len); + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) && can_is_canfd_skb(skb)) { + txdlc |= IFI_CANFD_TXFIFO_DLC_EDL; + if (cf->flags & CANFD_BRS) + txdlc |= IFI_CANFD_TXFIFO_DLC_BRS; } if (cf->can_id & CAN_RTR_FLAG) @@ -847,7 +874,7 @@ static int ifi_canfd_plat_probe(struct platform_device *pdev) priv->can.state = CAN_STATE_STOPPED; - priv->can.clock.freq = readl(addr + IFI_CANFD_SYSCLOCK); + priv->can.clock.freq = readl(addr + IFI_CANFD_CANCLOCK); priv->can.bittiming_const = &ifi_canfd_bittiming_const; priv->can.data_bittiming_const = &ifi_canfd_data_bittiming_const; diff --git a/drivers/net/can/rcar_can.c b/drivers/net/can/rcar_can.c index ad3d2e0cb191..788459f6bf5c 100644 --- a/drivers/net/can/rcar_can.c +++ b/drivers/net/can/rcar_can.c @@ -906,6 +906,7 @@ static const struct of_device_id rcar_can_of_table[] __maybe_unused = { { .compatible = "renesas,can-r8a7791" }, { .compatible = "renesas,rcar-gen1-can" }, { .compatible = "renesas,rcar-gen2-can" }, + { .compatible = "renesas,rcar-gen3-can" }, { } }; MODULE_DEVICE_TABLE(of, rcar_can_of_table); diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 575790e8a75a..74a7dfecee27 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -843,7 +843,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id) if (clear_intf) mcp251x_write_bits(spi, CANINTF, clear_intf, 0x00); - if (eflag) + if (eflag & (EFLG_RX0OVR | EFLG_RX1OVR)) mcp251x_write_bits(spi, EFLG, eflag, 0x00); /* Update can state */ diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 5eee62badf45..cbc99d5649af 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -826,9 +826,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface static void gs_destroy_candev(struct gs_can *dev) { unregister_candev(dev->netdev); - free_candev(dev->netdev); usb_kill_anchored_urbs(&dev->tx_submitted); - kfree(dev); + free_candev(dev->netdev); } static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -913,12 +912,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id * for (i = 0; i < icount; i++) { dev->canch[i] = gs_make_candev(i, intf); if (IS_ERR_OR_NULL(dev->canch[i])) { + /* save error code to return later */ + rc = PTR_ERR(dev->canch[i]); + /* on failure destroy previously created candevs */ icount = i; - for (i = 0; i < icount; i++) { + for (i = 0; i < icount; i++) gs_destroy_candev(dev->canch[i]); - dev->canch[i] = NULL; - } + + usb_kill_anchored_urbs(&dev->rx_submitted); kfree(dev); return rc; } @@ -939,16 +941,12 @@ static void gs_usb_disconnect(struct usb_interface *intf) return; } - for (i = 0; i < GS_MAX_INTF; i++) { - struct gs_can *can = dev->canch[i]; - - if (!can) - continue; - - gs_destroy_candev(can); - } + for (i = 0; i < GS_MAX_INTF; i++) + if (dev->canch[i]) + gs_destroy_candev(dev->canch[i]); usb_kill_anchored_urbs(&dev->rx_submitted); + kfree(dev); } static const struct usb_device_id gs_usb_table[] = { diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index d11c9d58cf10..5f07524083c3 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1051,39 +1051,49 @@ static int _mv88e6xxx_atu_remove(struct dsa_switch *ds, u16 fid, int port, return _mv88e6xxx_atu_move(ds, fid, port, 0x0f, static_too); } -static int mv88e6xxx_set_port_state(struct dsa_switch *ds, int port, u8 state) +static const char * const mv88e6xxx_port_state_names[] = { + [PORT_CONTROL_STATE_DISABLED] = "Disabled", + [PORT_CONTROL_STATE_BLOCKING] = "Blocking/Listening", + [PORT_CONTROL_STATE_LEARNING] = "Learning", + [PORT_CONTROL_STATE_FORWARDING] = "Forwarding", +}; + +static int _mv88e6xxx_port_state(struct dsa_switch *ds, int port, u8 state) { - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); int reg, ret = 0; u8 oldstate; - mutex_lock(&ps->smi_mutex); - reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_CONTROL); - if (reg < 0) { - ret = reg; - goto abort; - } + if (reg < 0) + return reg; oldstate = reg & PORT_CONTROL_STATE_MASK; + if (oldstate != state) { /* Flush forwarding database if we're moving a port * from Learning or Forwarding state to Disabled or * Blocking or Listening state. */ - if (oldstate >= PORT_CONTROL_STATE_LEARNING && - state <= PORT_CONTROL_STATE_BLOCKING) { + if ((oldstate == PORT_CONTROL_STATE_LEARNING || + oldstate == PORT_CONTROL_STATE_FORWARDING) + && (state == PORT_CONTROL_STATE_DISABLED || + state == PORT_CONTROL_STATE_BLOCKING)) { ret = _mv88e6xxx_atu_remove(ds, 0, port, false); if (ret) - goto abort; + return ret; } + reg = (reg & ~PORT_CONTROL_STATE_MASK) | state; ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_CONTROL, reg); + if (ret) + return ret; + + netdev_dbg(ds->ports[port], "PortState %s (was %s)\n", + mv88e6xxx_port_state_names[state], + mv88e6xxx_port_state_names[oldstate]); } -abort: - mutex_unlock(&ps->smi_mutex); return ret; } @@ -1146,35 +1156,55 @@ int mv88e6xxx_port_stp_update(struct dsa_switch *ds, int port, u8 state) break; } - netdev_dbg(ds->ports[port], "port state %d [%d]\n", state, stp_state); - /* mv88e6xxx_port_stp_update may be called with softirqs disabled, * so we can not update the port state directly but need to schedule it. */ ps->ports[port].state = stp_state; - set_bit(port, &ps->port_state_update_mask); + set_bit(port, ps->port_state_update_mask); schedule_work(&ps->bridge_work); return 0; } -static int _mv88e6xxx_port_pvid_get(struct dsa_switch *ds, int port, u16 *pvid) +static int _mv88e6xxx_port_pvid(struct dsa_switch *ds, int port, u16 *new, + u16 *old) { + u16 pvid; int ret; ret = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_DEFAULT_VLAN); if (ret < 0) return ret; - *pvid = ret & PORT_DEFAULT_VLAN_MASK; + pvid = ret & PORT_DEFAULT_VLAN_MASK; + + if (new) { + ret &= ~PORT_DEFAULT_VLAN_MASK; + ret |= *new & PORT_DEFAULT_VLAN_MASK; + + ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), + PORT_DEFAULT_VLAN, ret); + if (ret < 0) + return ret; + + netdev_dbg(ds->ports[port], "DefaultVID %d (was %d)\n", *new, + pvid); + } + + if (old) + *old = pvid; return 0; } +static int _mv88e6xxx_port_pvid_get(struct dsa_switch *ds, int port, u16 *pvid) +{ + return _mv88e6xxx_port_pvid(ds, port, NULL, pvid); +} + static int _mv88e6xxx_port_pvid_set(struct dsa_switch *ds, int port, u16 pvid) { - return _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_DEFAULT_VLAN, - pvid & PORT_DEFAULT_VLAN_MASK); + return _mv88e6xxx_port_pvid(ds, port, &pvid, NULL); } static int _mv88e6xxx_vtu_wait(struct dsa_switch *ds) @@ -1735,16 +1765,21 @@ int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port, old = ret & PORT_CONTROL_2_8021Q_MASK; - ret &= ~PORT_CONTROL_2_8021Q_MASK; - ret |= new & PORT_CONTROL_2_8021Q_MASK; + if (new != old) { + ret &= ~PORT_CONTROL_2_8021Q_MASK; + ret |= new & PORT_CONTROL_2_8021Q_MASK; - ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_CONTROL_2, ret); - if (ret < 0) - goto unlock; + ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_CONTROL_2, + ret); + if (ret < 0) + goto unlock; + + netdev_dbg(ds->ports[port], "802.1Q Mode %s (was %s)\n", + mv88e6xxx_port_8021q_mode_names[new], + mv88e6xxx_port_8021q_mode_names[old]); + } - netdev_dbg(ds->ports[port], "802.1Q Mode: %s (was %s)\n", - mv88e6xxx_port_8021q_mode_names[new], - mv88e6xxx_port_8021q_mode_names[old]); + ret = 0; unlock: mutex_unlock(&ps->smi_mutex); @@ -2228,11 +2263,15 @@ static void mv88e6xxx_bridge_work(struct work_struct *work) ps = container_of(work, struct mv88e6xxx_priv_state, bridge_work); ds = ((struct dsa_switch *)ps) - 1; - while (ps->port_state_update_mask) { - port = __ffs(ps->port_state_update_mask); - clear_bit(port, &ps->port_state_update_mask); - mv88e6xxx_set_port_state(ds, port, ps->ports[port].state); - } + mutex_lock(&ps->smi_mutex); + + for (port = 0; port < ps->num_ports; ++port) + if (test_and_clear_bit(port, ps->port_state_update_mask) && + _mv88e6xxx_port_state(ds, port, ps->ports[port].state)) + netdev_warn(ds->ports[port], "failed to update state to %s\n", + mv88e6xxx_port_state_names[ps->ports[port].state]); + + mutex_unlock(&ps->smi_mutex); } static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index d7b088dd8e16..3425616987ed 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -426,7 +426,7 @@ struct mv88e6xxx_priv_state { struct mv88e6xxx_priv_port ports[DSA_MAX_PORTS]; - unsigned long port_state_update_mask; + DECLARE_BITMAP(port_state_update_mask, DSA_MAX_PORTS); struct work_struct bridge_work; }; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 7b881edc0b0a..d81fceddbe0e 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -2455,7 +2455,7 @@ boomerang_interrupt(int irq, void *dev_id) int i; pci_unmap_single(VORTEX_PCI(vp), le32_to_cpu(vp->tx_ring[entry].frag[0].addr), - le32_to_cpu(vp->tx_ring[entry].frag[0].length), + le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF, PCI_DMA_TODEVICE); for (i=1; i<=skb_shinfo(skb)->nr_frags; i++) diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 0b13af8e4070..be67a19e01b9 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -106,6 +106,7 @@ config LANTIQ_ETOP Support for the MII0 inside the Lantiq SoC source "drivers/net/ethernet/marvell/Kconfig" +source "drivers/net/ethernet/mediatek/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" source "drivers/net/ethernet/micrel/Kconfig" source "drivers/net/ethernet/microchip/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 38dc1a776a2b..6ffcc801d37e 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_JME) += jme.o obj-$(CONFIG_KORINA) += korina.o obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o obj-$(CONFIG_NET_VENDOR_MARVELL) += marvell/ +obj-$(CONFIG_NET_VENDOR_MEDIATEK) += mediatek/ obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/ obj-$(CONFIG_NET_VENDOR_MICREL) += micrel/ obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/ diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 17472851674f..f749e4d389eb 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -193,7 +193,6 @@ static void altera_tse_mdio_destroy(struct net_device *dev) priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); priv->mdio = NULL; } diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index f71ab2647a3b..08a23e6b60e9 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1460,7 +1460,19 @@ static int nb8800_probe(struct platform_device *pdev) goto err_disable_clk; } - priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + if (of_phy_is_fixed_link(pdev->dev.of_node)) { + ret = of_phy_register_fixed_link(pdev->dev.of_node); + if (ret < 0) { + dev_err(&pdev->dev, "bad fixed-link spec\n"); + goto err_free_bus; + } + priv->phy_node = of_node_get(pdev->dev.of_node); + } + + if (!priv->phy_node) + priv->phy_node = of_parse_phandle(pdev->dev.of_node, + "phy-handle", 0); + if (!priv->phy_node) { dev_err(&pdev->dev, "no PHY specified\n"); ret = -ENODEV; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 04523d41b873..f8b810313094 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -4901,9 +4901,9 @@ struct c2s_pri_trans_table_entry { * cfc delete event data */ struct cfc_del_event_data { - u32 cid; - u32 reserved0; - u32 reserved1; + __le32 cid; + __le32 reserved0; + __le32 reserved1; }; @@ -5119,15 +5119,9 @@ struct vf_pf_channel_zone_trigger { * zone that triggers the in-bound interrupt */ struct trigger_vf_zone { -#if defined(__BIG_ENDIAN) - u16 reserved1; - u8 reserved0; - struct vf_pf_channel_zone_trigger vf_pf_channel; -#elif defined(__LITTLE_ENDIAN) struct vf_pf_channel_zone_trigger vf_pf_channel; u8 reserved0; u16 reserved1; -#endif u32 reserved2; }; @@ -5212,9 +5206,9 @@ struct e2_integ_data { * set mac event data */ struct eth_event_data { - u32 echo; - u32 reserved0; - u32 reserved1; + __le32 echo; + __le32 reserved0; + __le32 reserved1; }; @@ -5224,9 +5218,9 @@ struct eth_event_data { struct vf_pf_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 msg_addr_lo; - u32 msg_addr_hi; + __le16 reserved1; + __le32 msg_addr_lo; + __le32 msg_addr_hi; }; /* @@ -5235,9 +5229,9 @@ struct vf_pf_event_data { struct vf_flr_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* @@ -5246,9 +5240,9 @@ struct vf_flr_event_data { struct malicious_vf_event_data { u8 vf_id; u8 err_id; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 5c95d0c3b076..b597c32275aa 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -5282,14 +5282,14 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; - u32 cid = elem->message.data.eth_event.echo & BNX2X_SWCID_MASK; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); + u32 cid = echo & BNX2X_SWCID_MASK; struct bnx2x_vlan_mac_obj *vlan_mac_obj; /* Always push next commands out, don't wait here */ __set_bit(RAMROD_CONT, &ramrod_flags); - switch (le32_to_cpu((__force __le32)elem->message.data.eth_event.echo) - >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: DP(BNX2X_MSG_SP, "Got SETUP_MAC completions\n"); if (CNIC_LOADED(bp) && (cid == BNX2X_ISCSI_ETH_CID(bp))) @@ -5310,8 +5310,7 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, bnx2x_handle_mcast_eqe(bp); return; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } @@ -5480,9 +5479,6 @@ static void bnx2x_eq_int(struct bnx2x *bp) goto next_spqe; } - /* elem CID originates from FW; actually LE */ - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); opcode = elem->message.opcode; /* handle eq element */ @@ -5505,6 +5501,10 @@ static void bnx2x_eq_int(struct bnx2x *bp) * we may want to verify here that the bp state is * HALTING */ + + /* elem CID originates from FW; actually LE */ + cid = SW_CID(elem->message.data.cfc_del_event.cid); + DP(BNX2X_MSG_SP, "got delete ramrod for MULTI[%d]\n", cid); @@ -5598,10 +5598,8 @@ static void bnx2x_eq_int(struct bnx2x *bp) BNX2X_STATE_OPENING_WAIT4_PORT): case (EVENT_RING_OPCODE_RSS_UPDATE_RULES | BNX2X_STATE_CLOSING_WAIT4_HALT): - cid = elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK; DP(BNX2X_MSG_SP, "got RSS_UPDATE ramrod. CID %d\n", - cid); + SW_CID(elem->message.data.eth_event.echo)); rss_raw->clear_pending(rss_raw); break; @@ -5686,7 +5684,7 @@ static void bnx2x_sp_task(struct work_struct *work) if (status & BNX2X_DEF_SB_IDX) { struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp); - if (FCOE_INIT(bp) && + if (FCOE_INIT(bp) && (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) { /* Prevent local bottom-halves from running as * we are going to change the local NAPI list. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 9d027348cd09..632daff117d3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1672,11 +1672,12 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); /* Always push next commands out, don't wait here */ set_bit(RAMROD_CONT, &ramrod_flags); - switch (elem->message.data.eth_event.echo >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: rc = vfq->mac_obj.complete(bp, &vfq->mac_obj, elem, &ramrod_flags); @@ -1686,8 +1687,7 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, &ramrod_flags); break; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } if (rc < 0) @@ -1747,16 +1747,14 @@ int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem) switch (opcode) { case EVENT_RING_OPCODE_CFC_DEL: - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); + cid = SW_CID(elem->message.data.cfc_del_event.cid); DP(BNX2X_MSG_IOV, "checking cfc-del comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_CLASSIFICATION_RULES: case EVENT_RING_OPCODE_MULTICAST_RULES: case EVENT_RING_OPCODE_FILTERS_RULES: case EVENT_RING_OPCODE_RSS_UPDATE_RULES: - cid = (elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK); + cid = SW_CID(elem->message.data.eth_event.echo); DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_VF_FLR: diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 1374e5394a79..bfae300cf25f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -2187,8 +2187,10 @@ void bnx2x_vf_mbx_schedule(struct bnx2x *bp, /* Update VFDB with current message and schedule its handling */ mutex_lock(&BP_VFDB(bp)->event_mutex); - BP_VF_MBX(bp, vf_idx)->vf_addr_hi = vfpf_event->msg_addr_hi; - BP_VF_MBX(bp, vf_idx)->vf_addr_lo = vfpf_event->msg_addr_lo; + BP_VF_MBX(bp, vf_idx)->vf_addr_hi = + le32_to_cpu(vfpf_event->msg_addr_hi); + BP_VF_MBX(bp, vf_idx)->vf_addr_lo = + le32_to_cpu(vfpf_event->msg_addr_lo); BP_VFDB(bp)->event_occur |= (1ULL << vf_idx); mutex_unlock(&BP_VFDB(bp)->event_mutex); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ce6b075842ee..aabbd51db981 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -248,7 +248,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action); - end = PTR_ALIGN(pdata + length + 1, 8) - 1; + end = pdata + length; + end = PTR_ALIGN(end, 8) - 1; *end = 0; skb_copy_from_linear_data(skb, pdata, len); @@ -2361,6 +2362,14 @@ static void bnxt_free_stats(struct bnxt *bp) u32 size, i; struct pci_dev *pdev = bp->pdev; + if (bp->hw_rx_port_stats) { + dma_free_coherent(&pdev->dev, bp->hw_port_stats_size, + bp->hw_rx_port_stats, + bp->hw_rx_port_stats_map); + bp->hw_rx_port_stats = NULL; + bp->flags &= ~BNXT_FLAG_PORT_STATS; + } + if (!bp->bnapi) return; @@ -2397,6 +2406,24 @@ static int bnxt_alloc_stats(struct bnxt *bp) cpr->hw_stats_ctx_id = INVALID_STATS_CTX_ID; } + + if (BNXT_PF(bp)) { + bp->hw_port_stats_size = sizeof(struct rx_port_stats) + + sizeof(struct tx_port_stats) + 1024; + + bp->hw_rx_port_stats = + dma_alloc_coherent(&pdev->dev, bp->hw_port_stats_size, + &bp->hw_rx_port_stats_map, + GFP_KERNEL); + if (!bp->hw_rx_port_stats) + return -ENOMEM; + + bp->hw_tx_port_stats = (void *)(bp->hw_rx_port_stats + 1) + + 512; + bp->hw_tx_port_stats_map = bp->hw_rx_port_stats_map + + sizeof(struct rx_port_stats) + 512; + bp->flags |= BNXT_FLAG_PORT_STATS; + } return 0; } @@ -3833,6 +3860,23 @@ hwrm_ver_get_exit: return rc; } +static int bnxt_hwrm_port_qstats(struct bnxt *bp) +{ + int rc; + struct bnxt_pf_info *pf = &bp->pf; + struct hwrm_port_qstats_input req = {0}; + + if (!(bp->flags & BNXT_FLAG_PORT_STATS)) + return 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_QSTATS, -1, -1); + req.port_id = cpu_to_le16(pf->port_id); + req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_map); + req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_map); + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + return rc; +} + static void bnxt_hwrm_free_tunnel_ports(struct bnxt *bp) { if (bp->vxlan_port_cnt) { @@ -4467,6 +4511,7 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state) link_info->pause = resp->pause; link_info->auto_mode = resp->auto_mode; link_info->auto_pause_setting = resp->auto_pause; + link_info->lp_pause = resp->link_partner_adv_pause; link_info->force_pause_setting = resp->force_pause; link_info->duplex_setting = resp->duplex; if (link_info->phy_link_status == BNXT_LINK_LINK) @@ -4477,6 +4522,8 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state) link_info->auto_link_speed = le16_to_cpu(resp->auto_link_speed); link_info->support_speeds = le16_to_cpu(resp->support_speeds); link_info->auto_link_speeds = le16_to_cpu(resp->auto_link_speed_mask); + link_info->lp_auto_link_speeds = + le16_to_cpu(resp->link_partner_adv_speeds); link_info->preemphasis = le32_to_cpu(resp->preemphasis); link_info->phy_ver[0] = resp->phy_maj; link_info->phy_ver[1] = resp->phy_min; @@ -4888,6 +4935,22 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts); } + if (bp->flags & BNXT_FLAG_PORT_STATS) { + struct rx_port_stats *rx = bp->hw_rx_port_stats; + struct tx_port_stats *tx = bp->hw_tx_port_stats; + + stats->rx_crc_errors = le64_to_cpu(rx->rx_fcs_err_frames); + stats->rx_frame_errors = le64_to_cpu(rx->rx_align_err_frames); + stats->rx_length_errors = le64_to_cpu(rx->rx_undrsz_frames) + + le64_to_cpu(rx->rx_ovrsz_frames) + + le64_to_cpu(rx->rx_runt_frames); + stats->rx_errors = le64_to_cpu(rx->rx_false_carrier_frames) + + le64_to_cpu(rx->rx_jbr_frames); + stats->collisions = le64_to_cpu(tx->tx_total_collisions); + stats->tx_fifo_errors = le64_to_cpu(tx->tx_fifo_underruns); + stats->tx_errors = le64_to_cpu(tx->tx_err); + } + return stats; } @@ -5228,6 +5291,10 @@ static void bnxt_timer(unsigned long data) if (atomic_read(&bp->intr_sem) != 0) goto bnxt_restart_timer; + if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS)) { + set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event); + schedule_work(&bp->sp_task); + } bnxt_restart_timer: mod_timer(&bp->timer, jiffies + bp->current_interval); } @@ -5279,6 +5346,9 @@ static void bnxt_sp_task(struct work_struct *work) rtnl_unlock(); } + if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) + bnxt_hwrm_port_qstats(bp); + smp_mb__before_atomic(); clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); } @@ -5342,6 +5412,8 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) goto init_err_release; } + pci_enable_pcie_error_reporting(pdev); + INIT_WORK(&bp->sp_task, bnxt_sp_task); spin_lock_init(&bp->ntp_fltr_lock); @@ -5721,6 +5793,7 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); + pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); cancel_work_sync(&bp->sp_task); bp->sp_event = 0; @@ -5960,11 +6033,117 @@ init_err_free: return rc; } +/** + * bnxt_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + + netdev_info(netdev, "PCI I/O error detected\n"); + + rtnl_lock(); + netif_device_detach(netdev); + + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); + return PCI_ERS_RESULT_DISCONNECT; + } + + if (netif_running(netdev)) + bnxt_close(netdev); + + pci_disable_device(pdev); + rtnl_unlock(); + + /* Request a slot slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * bnxt_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. + * At this point, the card has exprienced a hard reset, + * followed by fixups by BIOS, and has its config space + * set up identically to what it was at cold boot. + */ +static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct bnxt *bp = netdev_priv(netdev); + int err = 0; + pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT; + + netdev_info(bp->dev, "PCI Slot Reset\n"); + + rtnl_lock(); + + if (pci_enable_device(pdev)) { + dev_err(&pdev->dev, + "Cannot re-enable PCI device after reset.\n"); + } else { + pci_set_master(pdev); + + if (netif_running(netdev)) + err = bnxt_open(netdev); + + if (!err) + result = PCI_ERS_RESULT_RECOVERED; + } + + if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev)) + dev_close(netdev); + + rtnl_unlock(); + + err = pci_cleanup_aer_uncorrect_error_status(pdev); + if (err) { + dev_err(&pdev->dev, + "pci_cleanup_aer_uncorrect_error_status failed 0x%0x\n", + err); /* non-fatal, continue */ + } + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * bnxt_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells + * us that its OK to resume normal operation. + */ +static void bnxt_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + + rtnl_lock(); + + netif_device_attach(netdev); + + rtnl_unlock(); +} + +static const struct pci_error_handlers bnxt_err_handler = { + .error_detected = bnxt_io_error_detected, + .slot_reset = bnxt_io_slot_reset, + .resume = bnxt_io_resume +}; + static struct pci_driver bnxt_pci_driver = { .name = DRV_MODULE_NAME, .id_table = bnxt_pci_tbl, .probe = bnxt_init_one, .remove = bnxt_remove_one, + .err_handler = &bnxt_err_handler, #if defined(CONFIG_BNXT_SRIOV) .sriov_configure = bnxt_sriov_configure, #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9aa38f57601b..ec04c47172b7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -757,10 +757,6 @@ struct bnxt_ntuple_filter { #define BNXT_FLTR_UPDATE 1 }; -#define BNXT_ALL_COPPER_ETHTOOL_SPEED \ - (ADVERTISED_100baseT_Full | ADVERTISED_1000baseT_Full | \ - ADVERTISED_10000baseT_Full) - struct bnxt_link_info { u8 media_type; u8 transceiver; @@ -780,6 +776,7 @@ struct bnxt_link_info { #define BNXT_LINK_PAUSE_RX PORT_PHY_QCFG_RESP_PAUSE_RX #define BNXT_LINK_PAUSE_BOTH (PORT_PHY_QCFG_RESP_PAUSE_RX | \ PORT_PHY_QCFG_RESP_PAUSE_TX) + u8 lp_pause; u8 auto_pause_setting; u8 force_pause_setting; u8 duplex_setting; @@ -814,6 +811,7 @@ struct bnxt_link_info { #define BNXT_LINK_SPEED_MSK_25GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB #define BNXT_LINK_SPEED_MSK_40GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB #define BNXT_LINK_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB + u16 lp_auto_link_speeds; u16 auto_link_speed; u16 force_link_speed; u32 preemphasis; @@ -875,6 +873,7 @@ struct bnxt { #define BNXT_FLAG_MSIX_CAP 0x80 #define BNXT_FLAG_RFS 0x100 #define BNXT_FLAG_SHARED_RINGS 0x200 + #define BNXT_FLAG_PORT_STATS 0x400 #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ BNXT_FLAG_RFS | \ @@ -927,7 +926,7 @@ struct bnxt { struct bnxt_queue_info q_info[BNXT_MAX_QUEUE]; unsigned int current_interval; -#define BNXT_TIMER_INTERVAL (HZ / 2) +#define BNXT_TIMER_INTERVAL HZ struct timer_list timer; @@ -947,6 +946,13 @@ struct bnxt { void *hwrm_dbg_resp_addr; dma_addr_t hwrm_dbg_resp_dma_addr; #define HWRM_DBG_REG_BUF_SIZE 128 + + struct rx_port_stats *hw_rx_port_stats; + struct tx_port_stats *hw_tx_port_stats; + dma_addr_t hw_rx_port_stats_map; + dma_addr_t hw_tx_port_stats_map; + int hw_port_stats_size; + int hwrm_cmd_timeout; struct mutex hwrm_cmd_lock; /* serialize hwrm messages */ struct hwrm_ver_get_output ver_resp; @@ -982,6 +988,7 @@ struct bnxt { #define BNXT_RESET_TASK_SP_EVENT 6 #define BNXT_RST_RING_SP_EVENT 7 #define BNXT_HWRM_PF_UNLOAD_SP_EVENT 8 +#define BNXT_PERIODIC_STATS_SP_EVENT 9 struct bnxt_pf_info pf; #ifdef CONFIG_BNXT_SRIOV diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 84ea26d6f3ff..9ada1662b651 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -8,6 +8,7 @@ */ #include <linux/ctype.h> +#include <linux/stringify.h> #include <linux/ethtool.h> #include <linux/interrupt.h> #include <linux/pci.h> @@ -83,13 +84,99 @@ static int bnxt_set_coalesce(struct net_device *dev, #define BNXT_NUM_STATS 21 +#define BNXT_RX_STATS_OFFSET(counter) \ + (offsetof(struct rx_port_stats, counter) / 8) + +#define BNXT_RX_STATS_ENTRY(counter) \ + { BNXT_RX_STATS_OFFSET(counter), __stringify(counter) } + +#define BNXT_TX_STATS_OFFSET(counter) \ + ((offsetof(struct tx_port_stats, counter) + \ + sizeof(struct rx_port_stats) + 512) / 8) + +#define BNXT_TX_STATS_ENTRY(counter) \ + { BNXT_TX_STATS_OFFSET(counter), __stringify(counter) } + +static const struct { + long offset; + char string[ETH_GSTRING_LEN]; +} bnxt_port_stats_arr[] = { + BNXT_RX_STATS_ENTRY(rx_64b_frames), + BNXT_RX_STATS_ENTRY(rx_65b_127b_frames), + BNXT_RX_STATS_ENTRY(rx_128b_255b_frames), + BNXT_RX_STATS_ENTRY(rx_256b_511b_frames), + BNXT_RX_STATS_ENTRY(rx_512b_1023b_frames), + BNXT_RX_STATS_ENTRY(rx_1024b_1518_frames), + BNXT_RX_STATS_ENTRY(rx_good_vlan_frames), + BNXT_RX_STATS_ENTRY(rx_1519b_2047b_frames), + BNXT_RX_STATS_ENTRY(rx_2048b_4095b_frames), + BNXT_RX_STATS_ENTRY(rx_4096b_9216b_frames), + BNXT_RX_STATS_ENTRY(rx_9217b_16383b_frames), + BNXT_RX_STATS_ENTRY(rx_total_frames), + BNXT_RX_STATS_ENTRY(rx_ucast_frames), + BNXT_RX_STATS_ENTRY(rx_mcast_frames), + BNXT_RX_STATS_ENTRY(rx_bcast_frames), + BNXT_RX_STATS_ENTRY(rx_fcs_err_frames), + BNXT_RX_STATS_ENTRY(rx_ctrl_frames), + BNXT_RX_STATS_ENTRY(rx_pause_frames), + BNXT_RX_STATS_ENTRY(rx_pfc_frames), + BNXT_RX_STATS_ENTRY(rx_align_err_frames), + BNXT_RX_STATS_ENTRY(rx_ovrsz_frames), + BNXT_RX_STATS_ENTRY(rx_jbr_frames), + BNXT_RX_STATS_ENTRY(rx_mtu_err_frames), + BNXT_RX_STATS_ENTRY(rx_tagged_frames), + BNXT_RX_STATS_ENTRY(rx_double_tagged_frames), + BNXT_RX_STATS_ENTRY(rx_good_frames), + BNXT_RX_STATS_ENTRY(rx_undrsz_frames), + BNXT_RX_STATS_ENTRY(rx_eee_lpi_events), + BNXT_RX_STATS_ENTRY(rx_eee_lpi_duration), + BNXT_RX_STATS_ENTRY(rx_bytes), + BNXT_RX_STATS_ENTRY(rx_runt_bytes), + BNXT_RX_STATS_ENTRY(rx_runt_frames), + + BNXT_TX_STATS_ENTRY(tx_64b_frames), + BNXT_TX_STATS_ENTRY(tx_65b_127b_frames), + BNXT_TX_STATS_ENTRY(tx_128b_255b_frames), + BNXT_TX_STATS_ENTRY(tx_256b_511b_frames), + BNXT_TX_STATS_ENTRY(tx_512b_1023b_frames), + BNXT_TX_STATS_ENTRY(tx_1024b_1518_frames), + BNXT_TX_STATS_ENTRY(tx_good_vlan_frames), + BNXT_TX_STATS_ENTRY(tx_1519b_2047_frames), + BNXT_TX_STATS_ENTRY(tx_2048b_4095b_frames), + BNXT_TX_STATS_ENTRY(tx_4096b_9216b_frames), + BNXT_TX_STATS_ENTRY(tx_9217b_16383b_frames), + BNXT_TX_STATS_ENTRY(tx_good_frames), + BNXT_TX_STATS_ENTRY(tx_total_frames), + BNXT_TX_STATS_ENTRY(tx_ucast_frames), + BNXT_TX_STATS_ENTRY(tx_mcast_frames), + BNXT_TX_STATS_ENTRY(tx_bcast_frames), + BNXT_TX_STATS_ENTRY(tx_pause_frames), + BNXT_TX_STATS_ENTRY(tx_pfc_frames), + BNXT_TX_STATS_ENTRY(tx_jabber_frames), + BNXT_TX_STATS_ENTRY(tx_fcs_err_frames), + BNXT_TX_STATS_ENTRY(tx_err), + BNXT_TX_STATS_ENTRY(tx_fifo_underruns), + BNXT_TX_STATS_ENTRY(tx_eee_lpi_events), + BNXT_TX_STATS_ENTRY(tx_eee_lpi_duration), + BNXT_TX_STATS_ENTRY(tx_total_collisions), + BNXT_TX_STATS_ENTRY(tx_bytes), +}; + +#define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr) + static int bnxt_get_sset_count(struct net_device *dev, int sset) { struct bnxt *bp = netdev_priv(dev); switch (sset) { - case ETH_SS_STATS: - return BNXT_NUM_STATS * bp->cp_nr_rings; + case ETH_SS_STATS: { + int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings; + + if (bp->flags & BNXT_FLAG_PORT_STATS) + num_stats += BNXT_NUM_PORT_STATS; + + return num_stats; + } default: return -EOPNOTSUPP; } @@ -118,6 +205,14 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, buf[j] = le64_to_cpu(hw_stats[k]); buf[j++] = cpr->rx_l4_csum_errors; } + if (bp->flags & BNXT_FLAG_PORT_STATS) { + __le64 *port_stats = (__le64 *)bp->hw_rx_port_stats; + + for (i = 0; i < BNXT_NUM_PORT_STATS; i++, j++) { + buf[j] = le64_to_cpu(*(port_stats + + bnxt_port_stats_arr[i].offset)); + } + } } static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) @@ -172,6 +267,12 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) sprintf(buf, "[%d]: rx_l4_csum_errors", i); buf += ETH_GSTRING_LEN; } + if (bp->flags & BNXT_FLAG_PORT_STATS) { + for (i = 0; i < BNXT_NUM_PORT_STATS; i++) { + strcpy(buf, bnxt_port_stats_arr[i].string); + buf += ETH_GSTRING_LEN; + } + } break; default: netdev_err(bp->dev, "bnxt_get_strings invalid request %x\n", @@ -496,28 +597,8 @@ static void bnxt_get_drvinfo(struct net_device *dev, kfree(pkglog); } -static u32 bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info) +static u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause) { - u16 fw_speeds = link_info->support_speeds; - u32 speed_mask = 0; - - if (fw_speeds & BNXT_LINK_SPEED_MSK_100MB) - speed_mask |= SUPPORTED_100baseT_Full; - if (fw_speeds & BNXT_LINK_SPEED_MSK_1GB) - speed_mask |= SUPPORTED_1000baseT_Full; - if (fw_speeds & BNXT_LINK_SPEED_MSK_2_5GB) - speed_mask |= SUPPORTED_2500baseX_Full; - if (fw_speeds & BNXT_LINK_SPEED_MSK_10GB) - speed_mask |= SUPPORTED_10000baseT_Full; - if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB) - speed_mask |= SUPPORTED_40000baseCR4_Full; - - return speed_mask; -} - -static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info) -{ - u16 fw_speeds = link_info->auto_link_speeds; u32 speed_mask = 0; /* TODO: support 25GB, 40GB, 50GB with different cable type */ @@ -532,9 +613,48 @@ static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info) speed_mask |= ADVERTISED_10000baseT_Full; if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB) speed_mask |= ADVERTISED_40000baseCR4_Full; + + if ((fw_pause & BNXT_LINK_PAUSE_BOTH) == BNXT_LINK_PAUSE_BOTH) + speed_mask |= ADVERTISED_Pause; + else if (fw_pause & BNXT_LINK_PAUSE_TX) + speed_mask |= ADVERTISED_Asym_Pause; + else if (fw_pause & BNXT_LINK_PAUSE_RX) + speed_mask |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; + return speed_mask; } +static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info) +{ + u16 fw_speeds = link_info->auto_link_speeds; + u8 fw_pause = 0; + + if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) + fw_pause = link_info->auto_pause_setting; + + return _bnxt_fw_to_ethtool_adv_spds(fw_speeds, fw_pause); +} + +static u32 bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info) +{ + u16 fw_speeds = link_info->lp_auto_link_speeds; + u8 fw_pause = 0; + + if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) + fw_pause = link_info->lp_pause; + + return _bnxt_fw_to_ethtool_adv_spds(fw_speeds, fw_pause); +} + +static u32 bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info) +{ + u16 fw_speeds = link_info->support_speeds; + u32 supported; + + supported = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0); + return supported | SUPPORTED_Pause | SUPPORTED_Asym_Pause; +} + u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed) { switch (fw_link_speed) { @@ -566,7 +686,6 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) u16 ethtool_speed; cmd->supported = bnxt_fw_to_ethtool_support_spds(link_info); - cmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; if (link_info->auto_link_speeds) cmd->supported |= SUPPORTED_Autoneg; @@ -576,21 +695,13 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) bnxt_fw_to_ethtool_advertised_spds(link_info); cmd->advertising |= ADVERTISED_Autoneg; cmd->autoneg = AUTONEG_ENABLE; + if (link_info->phy_link_status == BNXT_LINK_LINK) + cmd->lp_advertising = + bnxt_fw_to_ethtool_lp_adv(link_info); } else { cmd->autoneg = AUTONEG_DISABLE; cmd->advertising = 0; } - if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) { - if ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) == - BNXT_LINK_PAUSE_BOTH) { - cmd->advertising |= ADVERTISED_Pause; - } else { - cmd->advertising |= ADVERTISED_Asym_Pause; - if (link_info->auto_pause_setting & - BNXT_LINK_PAUSE_RX) - cmd->advertising |= ADVERTISED_Pause; - } - } cmd->port = PORT_NONE; if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) { @@ -686,16 +797,10 @@ static int bnxt_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) return rc; if (cmd->autoneg == AUTONEG_ENABLE) { - if (link_info->media_type != PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) { - netdev_err(dev, "Media type doesn't support autoneg\n"); - rc = -EINVAL; - goto set_setting_exit; - } - if (cmd->advertising & ~(BNXT_ALL_COPPER_ETHTOOL_SPEED | - ADVERTISED_Autoneg | - ADVERTISED_TP | - ADVERTISED_Pause | - ADVERTISED_Asym_Pause)) { + u32 supported_spds = bnxt_fw_to_ethtool_support_spds(link_info); + + if (cmd->advertising & ~(supported_spds | ADVERTISED_Autoneg | + ADVERTISED_TP | ADVERTISED_FIBRE)) { netdev_err(dev, "Unsupported advertising mask (adv: 0x%x)\n", cmd->advertising); rc = -EINVAL; @@ -750,8 +855,10 @@ static void bnxt_get_pauseparam(struct net_device *dev, if (BNXT_VF(bp)) return; epause->autoneg = !!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL); - epause->rx_pause = ((link_info->pause & BNXT_LINK_PAUSE_RX) != 0); - epause->tx_pause = ((link_info->pause & BNXT_LINK_PAUSE_TX) != 0); + epause->rx_pause = + ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_RX) != 0); + epause->tx_pause = + ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_TX) != 0); } static int bnxt_set_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c index 04b0d16b210e..95bc470ae441 100644 --- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c +++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c @@ -987,7 +987,7 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf) if (!list_empty(&rxf->ucast_pending_add_q)) { mac = list_first_entry(&rxf->ucast_pending_add_q, struct bna_mac, qe); - list_add_tail(&mac->qe, &rxf->ucast_active_q); + list_move_tail(&mac->qe, &rxf->ucast_active_q); bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_ADD_REQ); return 1; } diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 00cc9156abbb..092f097a5943 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -116,6 +116,15 @@ #define NIC_PF_INTR_ID_MBOX0 8 #define NIC_PF_INTR_ID_MBOX1 9 +/* Minimum FIFO level before all packets for the CQ are dropped + * + * This value ensures that once a packet has been "accepted" + * for reception it will not get dropped due to non-availability + * of CQ descriptor. An errata in HW mandates this value to be + * atleast 0x100. + */ +#define NICPF_CQM_MIN_DROP_LEVEL 0x100 + /* Global timer for CQ timer thresh interrupts * Calculated for SCLK of 700Mhz * value written should be a 1/16th of what is expected diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 4dded90076c8..95f17f8cadac 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -304,6 +304,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) static void nic_init_hw(struct nicpf *nic) { int i; + u64 cqm_cfg; /* Enable NIC HW block */ nic_reg_write(nic, NIC_PF_CFG, 0x3); @@ -340,6 +341,11 @@ static void nic_init_hw(struct nicpf *nic) /* Enable VLAN ethertype matching and stripping */ nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7, (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q); + + /* Check if HW expected value is higher (could be in future chips) */ + cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG); + if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL) + nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL); } /* Channel parse index configuration */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index dd536be20193..afb10e326b4f 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -21,7 +21,7 @@ #define NIC_PF_TCP_TIMER (0x0060) #define NIC_PF_BP_CFG (0x0080) #define NIC_PF_RRM_CFG (0x0088) -#define NIC_PF_CQM_CF (0x00A0) +#define NIC_PF_CQM_CFG (0x00A0) #define NIC_PF_CNM_CF (0x00A8) #define NIC_PF_CNM_STATUS (0x00B0) #define NIC_PF_CQ_AVG_CFG (0x00C0) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 91857b81009e..1cc8a7a69457 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -790,10 +790,6 @@ static int cxgb4vf_open(struct net_device *dev) /* * Note that this interface is up and start everything up ... */ - netif_set_real_num_tx_queues(dev, pi->nqsets); - err = netif_set_real_num_rx_queues(dev, pi->nqsets); - if (err) - goto err_unwind; err = link_start(dev); if (err) goto err_unwind; @@ -2176,6 +2172,73 @@ static void cleanup_debugfs(struct adapter *adapter) /* nothing to do */ } +/* Figure out how many Ports and Queue Sets we can support. This depends on + * knowing our Virtual Function Resources and may be called a second time if + * we fall back from MSI-X to MSI Interrupt Mode. + */ +static void size_nports_qsets(struct adapter *adapter) +{ + struct vf_resources *vfres = &adapter->params.vfres; + unsigned int ethqsets, pmask_nports; + + /* The number of "ports" which we support is equal to the number of + * Virtual Interfaces with which we've been provisioned. + */ + adapter->params.nports = vfres->nvi; + if (adapter->params.nports > MAX_NPORTS) { + dev_warn(adapter->pdev_dev, "only using %d of %d maximum" + " allowed virtual interfaces\n", MAX_NPORTS, + adapter->params.nports); + adapter->params.nports = MAX_NPORTS; + } + + /* We may have been provisioned with more VIs than the number of + * ports we're allowed to access (our Port Access Rights Mask). + * This is obviously a configuration conflict but we don't want to + * crash the kernel or anything silly just because of that. + */ + pmask_nports = hweight32(adapter->params.vfres.pmask); + if (pmask_nports < adapter->params.nports) { + dev_warn(adapter->pdev_dev, "only using %d of %d provissioned" + " virtual interfaces; limited by Port Access Rights" + " mask %#x\n", pmask_nports, adapter->params.nports, + adapter->params.vfres.pmask); + adapter->params.nports = pmask_nports; + } + + /* We need to reserve an Ingress Queue for the Asynchronous Firmware + * Event Queue. And if we're using MSI Interrupts, we'll also need to + * reserve an Ingress Queue for a Forwarded Interrupts. + * + * The rest of the FL/Intr-capable ingress queues will be matched up + * one-for-one with Ethernet/Control egress queues in order to form + * "Queue Sets" which will be aportioned between the "ports". For + * each Queue Set, we'll need the ability to allocate two Egress + * Contexts -- one for the Ingress Queue Free List and one for the TX + * Ethernet Queue. + * + * Note that even if we're currently configured to use MSI-X + * Interrupts (module variable msi == MSI_MSIX) we may get downgraded + * to MSI Interrupts if we can't get enough MSI-X Interrupts. If that + * happens we'll need to adjust things later. + */ + ethqsets = vfres->niqflint - 1 - (msi == MSI_MSI); + if (vfres->nethctrl != ethqsets) + ethqsets = min(vfres->nethctrl, ethqsets); + if (vfres->neq < ethqsets*2) + ethqsets = vfres->neq/2; + if (ethqsets > MAX_ETH_QSETS) + ethqsets = MAX_ETH_QSETS; + adapter->sge.max_ethqsets = ethqsets; + + if (adapter->sge.max_ethqsets < adapter->params.nports) { + dev_warn(adapter->pdev_dev, "only using %d of %d available" + " virtual interfaces (too few Queue Sets)\n", + adapter->sge.max_ethqsets, adapter->params.nports); + adapter->params.nports = adapter->sge.max_ethqsets; + } +} + /* * Perform early "adapter" initialization. This is where we discover what * adapter parameters we're going to be using and initialize basic adapter @@ -2183,10 +2246,8 @@ static void cleanup_debugfs(struct adapter *adapter) */ static int adap_init0(struct adapter *adapter) { - struct vf_resources *vfres = &adapter->params.vfres; struct sge_params *sge_params = &adapter->params.sge; struct sge *s = &adapter->sge; - unsigned int ethqsets; int err; u32 param, val = 0; @@ -2295,69 +2356,23 @@ static int adap_init0(struct adapter *adapter) return err; } - /* - * The number of "ports" which we support is equal to the number of - * Virtual Interfaces with which we've been provisioned. - */ - adapter->params.nports = vfres->nvi; - if (adapter->params.nports > MAX_NPORTS) { - dev_warn(adapter->pdev_dev, "only using %d of %d allowed" - " virtual interfaces\n", MAX_NPORTS, - adapter->params.nports); - adapter->params.nports = MAX_NPORTS; - } - - /* - * We need to reserve a number of the ingress queues with Free List - * and Interrupt capabilities for special interrupt purposes (like - * asynchronous firmware messages, or forwarded interrupts if we're - * using MSI). The rest of the FL/Intr-capable ingress queues will be - * matched up one-for-one with Ethernet/Control egress queues in order - * to form "Queue Sets" which will be aportioned between the "ports". - * For each Queue Set, we'll need the ability to allocate two Egress - * Contexts -- one for the Ingress Queue Free List and one for the TX - * Ethernet Queue. - */ - ethqsets = vfres->niqflint - INGQ_EXTRAS; - if (vfres->nethctrl != ethqsets) { - dev_warn(adapter->pdev_dev, "unequal number of [available]" - " ingress/egress queues (%d/%d); using minimum for" - " number of Queue Sets\n", ethqsets, vfres->nethctrl); - ethqsets = min(vfres->nethctrl, ethqsets); - } - if (vfres->neq < ethqsets*2) { - dev_warn(adapter->pdev_dev, "Not enough Egress Contexts (%d)" - " to support Queue Sets (%d); reducing allowed Queue" - " Sets\n", vfres->neq, ethqsets); - ethqsets = vfres->neq/2; - } - if (ethqsets > MAX_ETH_QSETS) { - dev_warn(adapter->pdev_dev, "only using %d of %d allowed Queue" - " Sets\n", MAX_ETH_QSETS, adapter->sge.max_ethqsets); - ethqsets = MAX_ETH_QSETS; - } - if (vfres->niq != 0 || vfres->neq > ethqsets*2) { - dev_warn(adapter->pdev_dev, "unused resources niq/neq (%d/%d)" - " ignored\n", vfres->niq, vfres->neq - ethqsets*2); - } - adapter->sge.max_ethqsets = ethqsets; - - /* - * Check for various parameter sanity issues. Most checks simply - * result in us using fewer resources than our provissioning but we - * do need at least one "port" with which to work ... - */ - if (adapter->sge.max_ethqsets < adapter->params.nports) { - dev_warn(adapter->pdev_dev, "only using %d of %d available" - " virtual interfaces (too few Queue Sets)\n", - adapter->sge.max_ethqsets, adapter->params.nports); - adapter->params.nports = adapter->sge.max_ethqsets; + /* Check for various parameter sanity issues */ + if (adapter->params.vfres.pmask == 0) { + dev_err(adapter->pdev_dev, "no port access configured\n" + "usable!\n"); + return -EINVAL; } - if (adapter->params.nports == 0) { + if (adapter->params.vfres.nvi == 0) { dev_err(adapter->pdev_dev, "no virtual interfaces configured/" "usable!\n"); return -EINVAL; } + + /* Initialize nports and max_ethqsets now that we have our Virtual + * Function Resources. + */ + size_nports_qsets(adapter); + return 0; } @@ -2771,6 +2786,40 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, } } + /* See what interrupts we'll be using. If we've been configured to + * use MSI-X interrupts, try to enable them but fall back to using + * MSI interrupts if we can't enable MSI-X interrupts. If we can't + * get MSI interrupts we bail with the error. + */ + if (msi == MSI_MSIX && enable_msix(adapter) == 0) + adapter->flags |= USING_MSIX; + else { + if (msi == MSI_MSIX) { + dev_info(adapter->pdev_dev, + "Unable to use MSI-X Interrupts; falling " + "back to MSI Interrupts\n"); + + /* We're going to need a Forwarded Interrupt Queue so + * that may cut into how many Queue Sets we can + * support. + */ + msi = MSI_MSI; + size_nports_qsets(adapter); + } + err = pci_enable_msi(pdev); + if (err) { + dev_err(&pdev->dev, "Unable to allocate MSI Interrupts;" + " err=%d\n", err); + goto err_free_dev; + } + adapter->flags |= USING_MSI; + } + + /* Now that we know how many "ports" we have and what interrupt + * mechanism we're going to use, we can configure our queue resources. + */ + cfg_queues(adapter); + /* * The "card" is now ready to go. If any errors occur during device * registration we do not fail the whole "card" but rather proceed @@ -2778,10 +2827,14 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, * must register at least one net device. */ for_each_port(adapter, pidx) { + struct port_info *pi = netdev_priv(adapter->port[pidx]); netdev = adapter->port[pidx]; if (netdev == NULL) continue; + netif_set_real_num_tx_queues(netdev, pi->nqsets); + netif_set_real_num_rx_queues(netdev, pi->nqsets); + err = register_netdev(netdev); if (err) { dev_warn(&pdev->dev, "cannot register net device %s," @@ -2793,7 +2846,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, } if (adapter->registered_device_map == 0) { dev_err(&pdev->dev, "could not register any net devices\n"); - goto err_free_dev; + goto err_disable_interrupts; } /* @@ -2811,32 +2864,6 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, } /* - * See what interrupts we'll be using. If we've been configured to - * use MSI-X interrupts, try to enable them but fall back to using - * MSI interrupts if we can't enable MSI-X interrupts. If we can't - * get MSI interrupts we bail with the error. - */ - if (msi == MSI_MSIX && enable_msix(adapter) == 0) - adapter->flags |= USING_MSIX; - else { - err = pci_enable_msi(pdev); - if (err) { - dev_err(&pdev->dev, "Unable to allocate %s interrupts;" - " err=%d\n", - msi == MSI_MSIX ? "MSI-X or MSI" : "MSI", err); - goto err_free_debugfs; - } - adapter->flags |= USING_MSI; - } - - /* - * Now that we know how many "ports" we have and what their types are, - * and how many Queue Sets we can support, we can configure our queue - * resources. - */ - cfg_queues(adapter); - - /* * Print a short notice on the existence and configuration of the new * VF network device ... */ @@ -2856,11 +2883,13 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, * Error recovery and exit code. Unwind state that's been created * so far and return the error. */ - -err_free_debugfs: - if (!IS_ERR_OR_NULL(adapter->debugfs_root)) { - cleanup_debugfs(adapter); - debugfs_remove_recursive(adapter->debugfs_root); +err_disable_interrupts: + if (adapter->flags & USING_MSIX) { + pci_disable_msix(adapter->pdev); + adapter->flags &= ~USING_MSIX; + } else if (adapter->flags & USING_MSI) { + pci_disable_msi(adapter->pdev); + adapter->flags &= ~USING_MSI; } err_free_dev: diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 7ba6d530b0c0..130f910e4785 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -201,16 +201,20 @@ static inline struct net_device *vnic_get_netdev(struct vnic_dev *vdev) } /* wrappers function for kernel log - * Make sure variable vdev of struct vnic_dev is available in the block where - * these macros are used */ -#define vdev_info(args...) dev_info(&vdev->pdev->dev, args) -#define vdev_warn(args...) dev_warn(&vdev->pdev->dev, args) -#define vdev_err(args...) dev_err(&vdev->pdev->dev, args) - -#define vdev_netinfo(args...) netdev_info(vnic_get_netdev(vdev), args) -#define vdev_netwarn(args...) netdev_warn(vnic_get_netdev(vdev), args) -#define vdev_neterr(args...) netdev_err(vnic_get_netdev(vdev), args) +#define vdev_err(vdev, fmt, ...) \ + dev_err(&(vdev)->pdev->dev, fmt, ##__VA_ARGS__) +#define vdev_warn(vdev, fmt, ...) \ + dev_warn(&(vdev)->pdev->dev, fmt, ##__VA_ARGS__) +#define vdev_info(vdev, fmt, ...) \ + dev_info(&(vdev)->pdev->dev, fmt, ##__VA_ARGS__) + +#define vdev_neterr(vdev, fmt, ...) \ + netdev_err(vnic_get_netdev(vdev), fmt, ##__VA_ARGS__) +#define vdev_netwarn(vdev, fmt, ...) \ + netdev_warn(vnic_get_netdev(vdev), fmt, ##__VA_ARGS__) +#define vdev_netinfo(vdev, fmt, ...) \ + netdev_info(vnic_get_netdev(vdev), fmt, ##__VA_ARGS__) static inline struct device *enic_get_dev(struct enic *enic) { diff --git a/drivers/net/ethernet/cisco/enic/vnic_cq.c b/drivers/net/ethernet/cisco/enic/vnic_cq.c index abeda2a9ea27..9c682aff3834 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_cq.c +++ b/drivers/net/ethernet/cisco/enic/vnic_cq.c @@ -43,7 +43,7 @@ int vnic_cq_alloc(struct vnic_dev *vdev, struct vnic_cq *cq, unsigned int index, cq->ctrl = vnic_dev_get_res(vdev, RES_TYPE_CQ, index); if (!cq->ctrl) { - vdev_err("Failed to hook CQ[%d] resource\n", index); + vdev_err(vdev, "Failed to hook CQ[%d] resource\n", index); return -EINVAL; } diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c index 1fdf5fe12a95..8f27df3207bc 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_dev.c +++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c @@ -53,14 +53,14 @@ static int vnic_dev_discover_res(struct vnic_dev *vdev, return -EINVAL; if (bar->len < VNIC_MAX_RES_HDR_SIZE) { - vdev_err("vNIC BAR0 res hdr length error\n"); + vdev_err(vdev, "vNIC BAR0 res hdr length error\n"); return -EINVAL; } rh = bar->vaddr; mrh = bar->vaddr; if (!rh) { - vdev_err("vNIC BAR0 res hdr not mem-mapped\n"); + vdev_err(vdev, "vNIC BAR0 res hdr not mem-mapped\n"); return -EINVAL; } @@ -69,7 +69,7 @@ static int vnic_dev_discover_res(struct vnic_dev *vdev, (ioread32(&rh->version) != VNIC_RES_VERSION)) { if ((ioread32(&mrh->magic) != MGMTVNIC_MAGIC) || (ioread32(&mrh->version) != MGMTVNIC_VERSION)) { - vdev_err("vNIC BAR0 res magic/version error exp (%lx/%lx) or (%lx/%lx), curr (%x/%x)\n", + vdev_err(vdev, "vNIC BAR0 res magic/version error exp (%lx/%lx) or (%lx/%lx), curr (%x/%x)\n", VNIC_RES_MAGIC, VNIC_RES_VERSION, MGMTVNIC_MAGIC, MGMTVNIC_VERSION, ioread32(&rh->magic), ioread32(&rh->version)); @@ -106,7 +106,7 @@ static int vnic_dev_discover_res(struct vnic_dev *vdev, /* each count is stride bytes long */ len = count * VNIC_RES_STRIDE; if (len + bar_offset > bar[bar_num].len) { - vdev_err("vNIC BAR0 resource %d out-of-bounds, offset 0x%x + size 0x%x > bar len 0x%lx\n", + vdev_err(vdev, "vNIC BAR0 resource %d out-of-bounds, offset 0x%x + size 0x%x > bar len 0x%lx\n", type, bar_offset, len, bar[bar_num].len); return -EINVAL; @@ -198,7 +198,7 @@ int vnic_dev_alloc_desc_ring(struct vnic_dev *vdev, struct vnic_dev_ring *ring, &ring->base_addr_unaligned); if (!ring->descs_unaligned) { - vdev_err("Failed to allocate ring (size=%d), aborting\n", + vdev_err(vdev, "Failed to allocate ring (size=%d), aborting\n", (int)ring->size); return -ENOMEM; } @@ -241,7 +241,7 @@ static int _vnic_dev_cmd(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, return -ENODEV; } if (status & STAT_BUSY) { - vdev_neterr("Busy devcmd %d\n", _CMD_N(cmd)); + vdev_neterr(vdev, "Busy devcmd %d\n", _CMD_N(cmd)); return -EBUSY; } @@ -275,7 +275,7 @@ static int _vnic_dev_cmd(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, return -err; if (err != ERR_ECMDUNKNOWN || cmd != CMD_CAPABILITY) - vdev_neterr("Error %d devcmd %d\n", + vdev_neterr(vdev, "Error %d devcmd %d\n", err, _CMD_N(cmd)); return -err; } @@ -290,7 +290,7 @@ static int _vnic_dev_cmd(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, } } - vdev_neterr("Timedout devcmd %d\n", _CMD_N(cmd)); + vdev_neterr(vdev, "Timedout devcmd %d\n", _CMD_N(cmd)); return -ETIMEDOUT; } @@ -313,7 +313,7 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, new_posted = (posted + 1) % DEVCMD2_RING_SIZE; if (new_posted == fetch_index) { - vdev_neterr("devcmd2 %d: wq is full. fetch index: %u, posted index: %u\n", + vdev_neterr(vdev, "devcmd2 %d: wq is full. fetch index: %u, posted index: %u\n", _CMD_N(cmd), fetch_index, posted); return -EBUSY; } @@ -352,7 +352,7 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, err = result->error; if (err != ERR_ECMDUNKNOWN || cmd != CMD_CAPABILITY) - vdev_neterr("Error %d devcmd %d\n", + vdev_neterr(vdev, "Error %d devcmd %d\n", err, _CMD_N(cmd)); return -err; } @@ -365,7 +365,7 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, udelay(100); } - vdev_neterr("devcmd %d timed out\n", _CMD_N(cmd)); + vdev_neterr(vdev, "devcmd %d timed out\n", _CMD_N(cmd)); return -ETIMEDOUT; } @@ -401,7 +401,7 @@ static int vnic_dev_init_devcmd2(struct vnic_dev *vdev) fetch_index = ioread32(&vdev->devcmd2->wq.ctrl->fetch_index); if (fetch_index == 0xFFFFFFFF) { /* check for hardware gone */ - vdev_err("Fatal error in devcmd2 init - hardware surprise removal"); + vdev_err(vdev, "Fatal error in devcmd2 init - hardware surprise removal\n"); return -ENODEV; } @@ -474,8 +474,8 @@ static int vnic_dev_cmd_proxy(struct vnic_dev *vdev, err = (int)vdev->args[1]; if (err != ERR_ECMDUNKNOWN || cmd != CMD_CAPABILITY) - vdev_neterr("Error %d proxy devcmd %d\n", err, - _CMD_N(cmd)); + vdev_neterr(vdev, "Error %d proxy devcmd %d\n", + err, _CMD_N(cmd)); return err; } @@ -768,7 +768,7 @@ int vnic_dev_packet_filter(struct vnic_dev *vdev, int directed, int multicast, err = vnic_dev_cmd(vdev, CMD_PACKET_FILTER, &a0, &a1, wait); if (err) - vdev_neterr("Can't set packet filter\n"); + vdev_neterr(vdev, "Can't set packet filter\n"); return err; } @@ -785,7 +785,7 @@ int vnic_dev_add_addr(struct vnic_dev *vdev, const u8 *addr) err = vnic_dev_cmd(vdev, CMD_ADDR_ADD, &a0, &a1, wait); if (err) - vdev_neterr("Can't add addr [%pM], %d\n", addr, err); + vdev_neterr(vdev, "Can't add addr [%pM], %d\n", addr, err); return err; } @@ -802,7 +802,7 @@ int vnic_dev_del_addr(struct vnic_dev *vdev, const u8 *addr) err = vnic_dev_cmd(vdev, CMD_ADDR_DEL, &a0, &a1, wait); if (err) - vdev_neterr("Can't del addr [%pM], %d\n", addr, err); + vdev_neterr(vdev, "Can't del addr [%pM], %d\n", addr, err); return err; } @@ -846,7 +846,8 @@ int vnic_dev_notify_set(struct vnic_dev *vdev, u16 intr) dma_addr_t notify_pa; if (vdev->notify || vdev->notify_pa) { - vdev_neterr("notify block %p still allocated", vdev->notify); + vdev_neterr(vdev, "notify block %p still allocated\n", + vdev->notify); return -EINVAL; } @@ -965,7 +966,7 @@ int vnic_dev_intr_coal_timer_info(struct vnic_dev *vdev) */ if ((err == ERR_ECMDUNKNOWN) || (!err && !(vdev->args[0] && vdev->args[1] && vdev->args[2]))) { - vdev_netwarn("Using default conversion factor for interrupt coalesce timer\n"); + vdev_netwarn(vdev, "Using default conversion factor for interrupt coalesce timer\n"); vnic_dev_intr_coal_timer_info_default(vdev); return 0; } @@ -1103,16 +1104,16 @@ int vnic_devcmd_init(struct vnic_dev *vdev) if (res) { err = vnic_dev_init_devcmd2(vdev); if (err) - vdev_warn("DEVCMD2 init failed: %d, Using DEVCMD1", + vdev_warn(vdev, "DEVCMD2 init failed: %d, Using DEVCMD1\n", err); else return 0; } else { - vdev_warn("DEVCMD2 resource not found (old firmware?) Using DEVCMD1\n"); + vdev_warn(vdev, "DEVCMD2 resource not found (old firmware?) Using DEVCMD1\n"); } err = vnic_dev_init_devcmd1(vdev); if (err) - vdev_err("DEVCMD1 initialization failed: %d", err); + vdev_err(vdev, "DEVCMD1 initialization failed: %d\n", err); return err; } diff --git a/drivers/net/ethernet/cisco/enic/vnic_intr.c b/drivers/net/ethernet/cisco/enic/vnic_intr.c index 942759d9cb3c..23604e3d4455 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_intr.c +++ b/drivers/net/ethernet/cisco/enic/vnic_intr.c @@ -40,7 +40,8 @@ int vnic_intr_alloc(struct vnic_dev *vdev, struct vnic_intr *intr, intr->ctrl = vnic_dev_get_res(vdev, RES_TYPE_INTR_CTRL, index); if (!intr->ctrl) { - vdev_err("Failed to hook INTR[%d].ctrl resource\n", index); + vdev_err(vdev, "Failed to hook INTR[%d].ctrl resource\n", + index); return -EINVAL; } diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c index cce2777dfc41..e572a527b18d 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_rq.c +++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c @@ -92,7 +92,7 @@ int vnic_rq_alloc(struct vnic_dev *vdev, struct vnic_rq *rq, unsigned int index, rq->ctrl = vnic_dev_get_res(vdev, RES_TYPE_RQ, index); if (!rq->ctrl) { - vdev_err("Failed to hook RQ[%d] resource\n", index); + vdev_err(vdev, "Failed to hook RQ[%d] resource\n", index); return -EINVAL; } @@ -179,7 +179,7 @@ int vnic_rq_disable(struct vnic_rq *rq) udelay(10); } - vdev_neterr("Failed to disable RQ[%d]\n", rq->index); + vdev_neterr(vdev, "Failed to disable RQ[%d]\n", rq->index); return -ETIMEDOUT; } diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.c b/drivers/net/ethernet/cisco/enic/vnic_wq.c index 05ad16a7e872..090cc65658a3 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_wq.c +++ b/drivers/net/ethernet/cisco/enic/vnic_wq.c @@ -95,7 +95,7 @@ int vnic_wq_alloc(struct vnic_dev *vdev, struct vnic_wq *wq, unsigned int index, wq->ctrl = vnic_dev_get_res(vdev, RES_TYPE_WQ, index); if (!wq->ctrl) { - vdev_err("Failed to hook WQ[%d] resource\n", index); + vdev_err(vdev, "Failed to hook WQ[%d] resource\n", index); return -EINVAL; } @@ -187,7 +187,7 @@ int vnic_wq_disable(struct vnic_wq *wq) udelay(10); } - vdev_neterr("Failed to disable WQ[%d]\n", wq->index); + vdev_neterr(vdev, "Failed to disable WQ[%d]\n", wq->index); return -ETIMEDOUT; } diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index ee584c59ff62..fe3763df3f13 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -545,6 +545,7 @@ struct be_adapter { struct delayed_work be_err_detection_work; u8 recovery_retries; u8 err_flags; + bool pcicfg_mapped; /* pcicfg obtained via pci_iomap() */ u32 flags; u32 cmd_privileges; /* Ethtool knobs and info */ diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 0b9f741f31af..d8540ae95e5a 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -666,10 +666,13 @@ enum be_if_flags { BE_IF_FLAGS_VLAN_PROMISCUOUS |\ BE_IF_FLAGS_MCAST_PROMISCUOUS) -#define BE_IF_EN_FLAGS (BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\ - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED) +#define BE_IF_FILT_FLAGS_BASIC (BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS | \ + BE_IF_FLAGS_UNTAGGED) -#define BE_IF_ALL_FILT_FLAGS (BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS) +#define BE_IF_ALL_FILT_FLAGS (BE_IF_FILT_FLAGS_BASIC | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_ALL_PROMISCUOUS) /* An RX interface is an object with one or more MAC addresses and * filtering capabilities. */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 17422b20a8ec..536686476369 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -125,6 +125,11 @@ static const char * const ue_status_hi_desc[] = { "Unknown" }; +#define BE_VF_IF_EN_FLAGS (BE_IF_FLAGS_UNTAGGED | \ + BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS) + static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q) { struct be_dma_mem *mem = &q->dma_mem; @@ -3558,7 +3563,7 @@ static int be_enable_if_filters(struct be_adapter *adapter) { int status; - status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON); + status = be_cmd_rx_filter(adapter, BE_IF_FILT_FLAGS_BASIC, ON); if (status) return status; @@ -3875,8 +3880,7 @@ static int be_vfs_if_create(struct be_adapter *adapter) int status; /* If a FW profile exists, then cap_flags are updated */ - cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS; + cap_flags = BE_VF_IF_EN_FLAGS; for_all_vfs(adapter, vf_cfg, vf) { if (!BE3_chip(adapter)) { @@ -3892,10 +3896,8 @@ static int be_vfs_if_create(struct be_adapter *adapter) } } - en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED | - BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | - BE_IF_FLAGS_PASS_L3L4_ERRORS); + /* PF should enable IF flags during proxy if_create call */ + en_flags = cap_flags & BE_VF_IF_EN_FLAGS; status = be_cmd_if_create(adapter, cap_flags, en_flags, &vf_cfg->if_handle, vf + 1); if (status) @@ -5040,6 +5042,8 @@ static void be_unmap_pci_bars(struct be_adapter *adapter) pci_iounmap(adapter->pdev, adapter->csr); if (adapter->db) pci_iounmap(adapter->pdev, adapter->db); + if (adapter->pcicfg && adapter->pcicfg_mapped) + pci_iounmap(adapter->pdev, adapter->pcicfg); } static int db_bar(struct be_adapter *adapter) @@ -5091,8 +5095,10 @@ static int be_map_pci_bars(struct be_adapter *adapter) if (!addr) goto pci_map_err; adapter->pcicfg = addr; + adapter->pcicfg_mapped = true; } else { adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET; + adapter->pcicfg_mapped = false; } } diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 62fa136554ac..41b010645100 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1265,7 +1265,6 @@ static int ethoc_remove(struct platform_device *pdev) if (priv->mdio) { mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } if (priv->clk) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index bad0ba29a94a..37c081583084 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3191,7 +3191,7 @@ static int fec_enet_init(struct net_device *ndev) static void fec_reset_phy(struct platform_device *pdev) { int err, phy_reset; - bool active_low = false; + bool active_high = false; int msec = 1; struct device_node *np = pdev->dev.of_node; @@ -3207,17 +3207,17 @@ static void fec_reset_phy(struct platform_device *pdev) if (!gpio_is_valid(phy_reset)) return; - active_low = of_property_read_bool(np, "phy-reset-active-low"); + active_high = of_property_read_bool(np, "phy-reset-active-high"); err = devm_gpio_request_one(&pdev->dev, phy_reset, - active_low ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW, + active_high ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW, "phy-reset"); if (err) { dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err); return; } msleep(msec); - gpio_set_value_cansleep(phy_reset, !active_low); + gpio_set_value_cansleep(phy_reset, !active_high); } #else /* CONFIG_OF */ static void fec_reset_phy(struct platform_device *pdev) diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 623aa1c8ebc6..79a210aaf0bb 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2791,6 +2791,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) goto fman_free; } + fman->dev = &of_dev->dev; + return fman; fman_node_put: @@ -2845,8 +2847,6 @@ static int fman_probe(struct platform_device *of_dev) dev_set_drvdata(dev, fman); - fman->dev = dev; - dev_dbg(dev, "FMan%d probed\n", fman->dts_params.id); return 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index a01e5a32b631..08c041548300 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1111,8 +1111,10 @@ static void __gfar_detect_errata_85xx(struct gfar_private *priv) if ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) == 0x20)) priv->errata |= GFAR_ERRATA_12; + /* P2020/P1010 Rev 1; MPC8548 Rev 2 */ if (((SVR_SOC_VER(svr) == SVR_P2020) && (SVR_REV(svr) < 0x20)) || - ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20))) + ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)) || + ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) < 0x31))) priv->errata |= GFAR_ERRATA_76; /* aka eTSEC 20 */ } #endif diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 74beb1867230..4ccc032633c4 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -25,6 +25,7 @@ config HIX5HD2_GMAC config HIP04_ETH tristate "HISILICON P04 Ethernet support" + depends on HAS_IOMEM # For MFD_SYSCON select MARVELL_PHY select MFD_SYSCON select HNS_MDIO diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index a0070d0e740d..d4f92ed322d6 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -675,8 +675,12 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, { int ret; struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); switch (loop) { + case MAC_INTERNALLOOP_PHY: + ret = 0; + break; case MAC_INTERNALLOOP_SERDES: ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en); break; @@ -686,6 +690,10 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, default: ret = -EINVAL; } + + if (!ret) + hns_dsaf_set_inner_lb(mac_cb->dsaf_dev, mac_cb->mac_id, en); + return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 9439f04962e1..38fc5be3870c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -230,6 +230,30 @@ static void hns_dsaf_mix_def_qid_cfg(struct dsaf_device *dsaf_dev) } } +static void hns_dsaf_inner_qid_cfg(struct dsaf_device *dsaf_dev) +{ + u16 max_q_per_vf, max_vfn; + u32 q_id, q_num_per_port; + u32 mac_id; + + if (AE_IS_VER1(dsaf_dev->dsaf_ver)) + return; + + hns_rcb_get_queue_mode(dsaf_dev->dsaf_mode, + HNS_DSAF_COMM_SERVICE_NW_IDX, + &max_vfn, &max_q_per_vf); + q_num_per_port = max_vfn * max_q_per_vf; + + for (mac_id = 0, q_id = 0; mac_id < DSAF_SERVICE_NW_NUM; mac_id++) { + dsaf_set_dev_field(dsaf_dev, + DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_QID_M, + DSAFV2_SERDES_LBK_QID_S, + q_id); + q_id += q_num_per_port; + } +} + /** * hns_dsaf_sw_port_type_cfg - cfg sw type * @dsaf_id: dsa fabric id @@ -691,6 +715,16 @@ void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en) dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_MIX_MODE_S, !!en); } +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en) +{ + if (AE_IS_VER1(dsaf_dev->dsaf_ver) || + dsaf_dev->mac_cb[mac_id].mac_type == HNAE_PORT_DEBUG) + return; + + dsaf_set_dev_bit(dsaf_dev, DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_EN_B, !!en); +} + /** * hns_dsaf_tbl_stat_en - tbl * @dsaf_id: dsa fabric id @@ -1022,6 +1056,9 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev) /* set promisc def queue id */ hns_dsaf_mix_def_qid_cfg(dsaf_dev); + /* set inner loopback queue id */ + hns_dsaf_inner_qid_cfg(dsaf_dev); + /* in non switch mode, set all port to access mode */ hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 40205b910f80..5fea226efaf3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -417,5 +417,6 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port); void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data); int hns_dsaf_get_regs_count(void); void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en); +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en); #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index f0c4f9b09d5b..60d695daa471 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -134,6 +134,7 @@ #define DSAF_XGE_INT_STS_0_REG 0x1C0 #define DSAF_PPE_INT_STS_0_REG 0x1E0 #define DSAF_ROCEE_INT_STS_0_REG 0x200 +#define DSAFV2_SERDES_LBK_0_REG 0x220 #define DSAF_PPE_QID_CFG_0_REG 0x300 #define DSAF_SW_PORT_TYPE_0_REG 0x320 #define DSAF_STP_PORT_TYPE_0_REG 0x340 @@ -857,6 +858,10 @@ #define PPEV2_CFG_RSS_TBL_4N3_S 24 #define PPEV2_CFG_RSS_TBL_4N3_M (((1UL << 5) - 1) << PPEV2_CFG_RSS_TBL_4N3_S) +#define DSAFV2_SERDES_LBK_EN_B 8 +#define DSAFV2_SERDES_LBK_QID_S 0 +#define DSAFV2_SERDES_LBK_QID_M (((1UL << 8) - 1) << DSAFV2_SERDES_LBK_QID_S) + #define PPE_CNT_CLR_CE_B 0 #define PPE_CNT_CLR_SNAP_EN_B 1 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 3df22840fcd1..3c4a3bc31a89 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -295,8 +295,10 @@ static int __lb_setup(struct net_device *ndev, switch (loop) { case MAC_INTERNALLOOP_PHY: - if ((phy_dev) && (!phy_dev->is_c45)) + if ((phy_dev) && (!phy_dev->is_c45)) { ret = hns_nic_config_phy_loopback(phy_dev, 0x1); + ret |= h->dev->ops->set_loopback(h, loop, 0x1); + } break; case MAC_INTERNALLOOP_MAC: if ((h->dev->ops->set_loopback) && @@ -376,6 +378,7 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, struct sk_buff *skb) { struct net_device *ndev; + struct hns_nic_priv *priv; struct hnae_ring *ring; struct netdev_queue *dev_queue; struct sk_buff *new_skb; @@ -385,8 +388,17 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, char buff[33]; /* 32B data and the last character '\0' */ if (!ring_data) { /* Just for doing create frame*/ + ndev = skb->dev; + priv = netdev_priv(ndev); + frame_size = skb->len; memset(skb->data, 0xFF, frame_size); + if ((!AE_IS_VER1(priv->enet_ver)) && + (priv->ae_handle->port_type == HNAE_PORT_SERVICE)) { + memcpy(skb->data, ndev->dev_addr, 6); + skb->data[5] += 0x1f; + } + frame_size &= ~1ul; memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); memset(&skb->data[frame_size / 2 + 10], 0xBE, @@ -486,6 +498,7 @@ static int __lb_run_test(struct net_device *ndev, /* place data into test skb */ (void)skb_put(skb, size); + skb->dev = ndev; __lb_other_process(NULL, skb); skb->queue_mapping = NIC_LB_TEST_RING_ID; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 335417b4756b..ebe60719e489 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1166,7 +1166,10 @@ map_failed: if (!firmware_has_feature(FW_FEATURE_CMO)) netdev_err(netdev, "tx: unable to map xmit buffer\n"); adapter->tx_map_failed++; - skb_linearize(skb); + if (skb_linearize(skb)) { + netdev->stats.tx_dropped++; + goto out; + } force_bounce = 1; goto retry_bounce; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7d6570843723..6e9e16eee5d0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1348,44 +1348,44 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) crq.request_capability.cmd = REQUEST_CAPABILITY; crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_tx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_add_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_tx_entries_per_subcrq); + cpu_to_be64(adapter->req_tx_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_rx_add_entries_per_subcrq); + cpu_to_be64(adapter->req_rx_add_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_MTU); - crq.request_capability.number = cpu_to_be32(adapter->req_mtu); + crq.request_capability.number = cpu_to_be64(adapter->req_mtu); ibmvnic_send_crq(adapter, &crq); if (adapter->netdev->flags & IFF_PROMISC) { if (adapter->promisc_supported) { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(1); + crq.request_capability.number = cpu_to_be64(1); ibmvnic_send_crq(adapter, &crq); } } else { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(0); + crq.request_capability.number = cpu_to_be64(0); ibmvnic_send_crq(adapter, &crq); } @@ -2312,93 +2312,93 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, switch (be16_to_cpu(crq->query_capability.capability)) { case MIN_TX_QUEUES: adapter->min_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_queues = %lld\n", adapter->min_tx_queues); break; case MIN_RX_QUEUES: adapter->min_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_queues = %lld\n", adapter->min_rx_queues); break; case MIN_RX_ADD_QUEUES: adapter->min_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_queues = %lld\n", adapter->min_rx_add_queues); break; case MAX_TX_QUEUES: adapter->max_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_queues = %lld\n", adapter->max_tx_queues); break; case MAX_RX_QUEUES: adapter->max_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_queues = %lld\n", adapter->max_rx_queues); break; case MAX_RX_ADD_QUEUES: adapter->max_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_queues = %lld\n", adapter->max_rx_add_queues); break; case MIN_TX_ENTRIES_PER_SUBCRQ: adapter->min_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n", adapter->min_tx_entries_per_subcrq); break; case MIN_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->min_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n", adapter->min_rx_add_entries_per_subcrq); break; case MAX_TX_ENTRIES_PER_SUBCRQ: adapter->max_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n", adapter->max_tx_entries_per_subcrq); break; case MAX_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->max_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n", adapter->max_rx_add_entries_per_subcrq); break; case TCP_IP_OFFLOAD: adapter->tcp_ip_offload = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "tcp_ip_offload = %lld\n", adapter->tcp_ip_offload); break; case PROMISC_SUPPORTED: adapter->promisc_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "promisc_supported = %lld\n", adapter->promisc_supported); break; case MIN_MTU: - adapter->min_mtu = be32_to_cpu(crq->query_capability.number); + adapter->min_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu); break; case MAX_MTU: - adapter->max_mtu = be32_to_cpu(crq->query_capability.number); + adapter->max_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu); break; case MAX_MULTICAST_FILTERS: adapter->max_multicast_filters = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_multicast_filters = %lld\n", adapter->max_multicast_filters); break; case VLAN_HEADER_INSERTION: adapter->vlan_header_insertion = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); if (adapter->vlan_header_insertion) netdev->features |= NETIF_F_HW_VLAN_STAG_TX; netdev_dbg(netdev, "vlan_header_insertion = %lld\n", @@ -2406,43 +2406,43 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, break; case MAX_TX_SG_ENTRIES: adapter->max_tx_sg_entries = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_sg_entries = %lld\n", adapter->max_tx_sg_entries); break; case RX_SG_SUPPORTED: adapter->rx_sg_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "rx_sg_supported = %lld\n", adapter->rx_sg_supported); break; case OPT_TX_COMP_SUB_QUEUES: adapter->opt_tx_comp_sub_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n", adapter->opt_tx_comp_sub_queues); break; case OPT_RX_COMP_QUEUES: adapter->opt_rx_comp_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n", adapter->opt_rx_comp_queues); break; case OPT_RX_BUFADD_Q_PER_RX_COMP_Q: adapter->opt_rx_bufadd_q_per_rx_comp_q = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n", adapter->opt_rx_bufadd_q_per_rx_comp_q); break; case OPT_TX_ENTRIES_PER_SUBCRQ: adapter->opt_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n", adapter->opt_tx_entries_per_subcrq); break; case OPT_RXBA_ENTRIES_PER_SUBCRQ: adapter->opt_rxba_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n", adapter->opt_rxba_entries_per_subcrq); break; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 1242925ad34c..1a9993cc79b5 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -319,10 +319,8 @@ struct ibmvnic_capability { u8 first; u8 cmd; __be16 capability; /* one of ibmvnic_capabilities */ + __be64 number; struct ibmvnic_rc rc; - __be32 number; /*FIX: should be __be64, but I'm getting the least - * significant word first - */ } __packed __aligned(8); struct ibmvnic_login { diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b1de7afd4116..3ddf657bc10b 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme) } static inline void -jme_clear_pm(struct jme_adapter *jme) +jme_clear_pm_enable_wol(struct jme_adapter *jme) { jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs); } +static inline void +jme_clear_pm_disable_wol(struct jme_adapter *jme) +{ + jwrite32(jme, JME_PMCS, PMCS_STMASK); +} + static int jme_reload_eeprom(struct jme_adapter *jme) { @@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev) struct jme_adapter *jme = netdev_priv(netdev); int rc; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); JME_NAPI_ENABLE(jme); tasklet_init(&jme->linkch_task, jme_link_change_tasklet, @@ -1925,11 +1931,11 @@ jme_wait_link(struct jme_adapter *jme) static void jme_powersave_phy(struct jme_adapter *jme) { - if (jme->reg_pmcs) { + if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) { jme_set_100m_half(jme); if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN)) jme_wait_link(jme); - jme_clear_pm(jme); + jme_clear_pm_enable_wol(jme); } else { jme_phy_off(jme); } @@ -2646,9 +2652,6 @@ jme_set_wol(struct net_device *netdev, if (wol->wolopts & WAKE_MAGIC) jme->reg_pmcs |= PMCS_MFEN; - jwrite32(jme, JME_PMCS, jme->reg_pmcs); - device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs)); - return 0; } @@ -3172,8 +3175,8 @@ jme_init_one(struct pci_dev *pdev, jme->mii_if.mdio_read = jme_mdio_read; jme->mii_if.mdio_write = jme_mdio_write; - jme_clear_pm(jme); - device_set_wakeup_enable(&pdev->dev, true); + jme_clear_pm_disable_wol(jme); + device_init_wakeup(&pdev->dev, true); jme_set_phyfifo_5level(jme); jme->pcirev = pdev->revision; @@ -3304,7 +3307,7 @@ jme_resume(struct device *dev) if (!netif_running(netdev)) return 0; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); jme_phy_on(jme); if (test_bit(JME_FLAG_SSET, &jme->flags)) jme_set_settings(netdev, &jme->old_ecmd); @@ -3312,13 +3315,14 @@ jme_resume(struct device *dev) jme_reset_phy_processor(jme); jme_phy_calibration(jme); jme_phy_setEA(jme); - jme_start_irq(jme); netif_device_attach(netdev); atomic_inc(&jme->link_changing); jme_reset_link(jme); + jme_start_irq(jme); + return 0; } diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig new file mode 100644 index 000000000000..698bb89aa901 --- /dev/null +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -0,0 +1,17 @@ +config NET_VENDOR_MEDIATEK + bool "MediaTek ethernet driver" + depends on ARCH_MEDIATEK + ---help--- + If you have a Mediatek SoC with ethernet, say Y. + +if NET_VENDOR_MEDIATEK + +config NET_MEDIATEK_SOC + tristate "MediaTek MT7623 Gigabit ethernet support" + depends on NET_VENDOR_MEDIATEK && (MACH_MT7623 || MACH_MT2701) + select PHYLIB + ---help--- + This driver supports the gigabit ethernet MACs in the + MediaTek MT2701/MT7623 chipset family. + +endif #NET_VENDOR_MEDIATEK diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile new file mode 100644 index 000000000000..aa3f1c8ccd4a --- /dev/null +++ b/drivers/net/ethernet/mediatek/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the Mediatek SoCs built-in ethernet macs +# + +obj-$(CONFIG_NET_MEDIATEK_SOC) += mtk_eth_soc.o diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c new file mode 100644 index 000000000000..ba3afa5d4640 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -0,0 +1,1807 @@ +/* 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 of the License + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> + * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> + * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> + */ + +#include <linux/of_device.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> +#include <linux/clk.h> +#include <linux/if_vlan.h> +#include <linux/reset.h> +#include <linux/tcp.h> + +#include "mtk_eth_soc.h" + +static int mtk_msg_level = -1; +module_param_named(msg_level, mtk_msg_level, int, 0); +MODULE_PARM_DESC(msg_level, "Message level (-1=defaults,0=none,...,16=all)"); + +#define MTK_ETHTOOL_STAT(x) { #x, \ + offsetof(struct mtk_hw_stats, x) / sizeof(u64) } + +/* strings used by ethtool */ +static const struct mtk_ethtool_stats { + char str[ETH_GSTRING_LEN]; + u32 offset; +} mtk_ethtool_stats[] = { + MTK_ETHTOOL_STAT(tx_bytes), + MTK_ETHTOOL_STAT(tx_packets), + MTK_ETHTOOL_STAT(tx_skip), + MTK_ETHTOOL_STAT(tx_collisions), + MTK_ETHTOOL_STAT(rx_bytes), + MTK_ETHTOOL_STAT(rx_packets), + MTK_ETHTOOL_STAT(rx_overflow), + MTK_ETHTOOL_STAT(rx_fcs_errors), + MTK_ETHTOOL_STAT(rx_short_errors), + MTK_ETHTOOL_STAT(rx_long_errors), + MTK_ETHTOOL_STAT(rx_checksum_errors), + MTK_ETHTOOL_STAT(rx_flow_control_packets), +}; + +void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg) +{ + __raw_writel(val, eth->base + reg); +} + +u32 mtk_r32(struct mtk_eth *eth, unsigned reg) +{ + return __raw_readl(eth->base + reg); +} + +static int mtk_mdio_busy_wait(struct mtk_eth *eth) +{ + unsigned long t_start = jiffies; + + while (1) { + if (!(mtk_r32(eth, MTK_PHY_IAC) & PHY_IAC_ACCESS)) + return 0; + if (time_after(jiffies, t_start + PHY_IAC_TIMEOUT)) + break; + usleep_range(10, 20); + } + + dev_err(eth->dev, "mdio: MDIO timeout\n"); + return -1; +} + +u32 _mtk_mdio_write(struct mtk_eth *eth, u32 phy_addr, + u32 phy_register, u32 write_data) +{ + if (mtk_mdio_busy_wait(eth)) + return -1; + + write_data &= 0xffff; + + mtk_w32(eth, PHY_IAC_ACCESS | PHY_IAC_START | PHY_IAC_WRITE | + (phy_register << PHY_IAC_REG_SHIFT) | + (phy_addr << PHY_IAC_ADDR_SHIFT) | write_data, + MTK_PHY_IAC); + + if (mtk_mdio_busy_wait(eth)) + return -1; + + return 0; +} + +u32 _mtk_mdio_read(struct mtk_eth *eth, int phy_addr, int phy_reg) +{ + u32 d; + + if (mtk_mdio_busy_wait(eth)) + return 0xffff; + + mtk_w32(eth, PHY_IAC_ACCESS | PHY_IAC_START | PHY_IAC_READ | + (phy_reg << PHY_IAC_REG_SHIFT) | + (phy_addr << PHY_IAC_ADDR_SHIFT), + MTK_PHY_IAC); + + if (mtk_mdio_busy_wait(eth)) + return 0xffff; + + d = mtk_r32(eth, MTK_PHY_IAC) & 0xffff; + + return d; +} + +static int mtk_mdio_write(struct mii_bus *bus, int phy_addr, + int phy_reg, u16 val) +{ + struct mtk_eth *eth = bus->priv; + + return _mtk_mdio_write(eth, phy_addr, phy_reg, val); +} + +static int mtk_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg) +{ + struct mtk_eth *eth = bus->priv; + + return _mtk_mdio_read(eth, phy_addr, phy_reg); +} + +static void mtk_phy_link_adjust(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + u32 mcr = MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG | + MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN | + MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN | + MAC_MCR_BACKPR_EN; + + switch (mac->phy_dev->speed) { + case SPEED_1000: + mcr |= MAC_MCR_SPEED_1000; + break; + case SPEED_100: + mcr |= MAC_MCR_SPEED_100; + break; + }; + + if (mac->phy_dev->link) + mcr |= MAC_MCR_FORCE_LINK; + + if (mac->phy_dev->duplex) + mcr |= MAC_MCR_FORCE_DPX; + + if (mac->phy_dev->pause) + mcr |= MAC_MCR_FORCE_RX_FC | MAC_MCR_FORCE_TX_FC; + + mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); + + if (mac->phy_dev->link) + netif_carrier_on(dev); + else + netif_carrier_off(dev); +} + +static int mtk_phy_connect_node(struct mtk_eth *eth, struct mtk_mac *mac, + struct device_node *phy_node) +{ + const __be32 *_addr = NULL; + struct phy_device *phydev; + int phy_mode, addr; + + _addr = of_get_property(phy_node, "reg", NULL); + + if (!_addr || (be32_to_cpu(*_addr) >= 0x20)) { + pr_err("%s: invalid phy address\n", phy_node->name); + return -EINVAL; + } + addr = be32_to_cpu(*_addr); + phy_mode = of_get_phy_mode(phy_node); + if (phy_mode < 0) { + dev_err(eth->dev, "incorrect phy-mode %d\n", phy_mode); + return -EINVAL; + } + + phydev = of_phy_connect(eth->netdev[mac->id], phy_node, + mtk_phy_link_adjust, 0, phy_mode); + if (IS_ERR(phydev)) { + dev_err(eth->dev, "could not connect to PHY\n"); + return PTR_ERR(phydev); + } + + dev_info(eth->dev, + "connected mac %d to PHY at %s [uid=%08x, driver=%s]\n", + mac->id, phydev_name(phydev), phydev->phy_id, + phydev->drv->name); + + mac->phy_dev = phydev; + + return 0; +} + +static int mtk_phy_connect(struct mtk_mac *mac) +{ + struct mtk_eth *eth = mac->hw; + struct device_node *np; + u32 val, ge_mode; + + np = of_parse_phandle(mac->of_node, "phy-handle", 0); + if (!np) + return -ENODEV; + + switch (of_get_phy_mode(np)) { + case PHY_INTERFACE_MODE_RGMII: + ge_mode = 0; + break; + case PHY_INTERFACE_MODE_MII: + ge_mode = 1; + break; + case PHY_INTERFACE_MODE_RMII: + ge_mode = 2; + break; + default: + dev_err(eth->dev, "invalid phy_mode\n"); + return -1; + } + + /* put the gmac into the right mode */ + regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); + val &= ~SYSCFG0_GE_MODE(SYSCFG0_GE_MASK, mac->id); + val |= SYSCFG0_GE_MODE(ge_mode, mac->id); + regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val); + + mtk_phy_connect_node(eth, mac, np); + mac->phy_dev->autoneg = AUTONEG_ENABLE; + mac->phy_dev->speed = 0; + mac->phy_dev->duplex = 0; + mac->phy_dev->supported &= PHY_BASIC_FEATURES; + mac->phy_dev->advertising = mac->phy_dev->supported | + ADVERTISED_Autoneg; + phy_start_aneg(mac->phy_dev); + + return 0; +} + +static int mtk_mdio_init(struct mtk_eth *eth) +{ + struct device_node *mii_np; + int err; + + mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus"); + if (!mii_np) { + dev_err(eth->dev, "no %s child node found", "mdio-bus"); + return -ENODEV; + } + + if (!of_device_is_available(mii_np)) { + err = 0; + goto err_put_node; + } + + eth->mii_bus = mdiobus_alloc(); + if (!eth->mii_bus) { + err = -ENOMEM; + goto err_put_node; + } + + eth->mii_bus->name = "mdio"; + eth->mii_bus->read = mtk_mdio_read; + eth->mii_bus->write = mtk_mdio_write; + eth->mii_bus->priv = eth; + eth->mii_bus->parent = eth->dev; + + snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%s", mii_np->name); + err = of_mdiobus_register(eth->mii_bus, mii_np); + if (err) + goto err_free_bus; + + return 0; + +err_free_bus: + kfree(eth->mii_bus); + +err_put_node: + of_node_put(mii_np); + eth->mii_bus = NULL; + return err; +} + +static void mtk_mdio_cleanup(struct mtk_eth *eth) +{ + if (!eth->mii_bus) + return; + + mdiobus_unregister(eth->mii_bus); + of_node_put(eth->mii_bus->dev.of_node); + kfree(eth->mii_bus); +} + +static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask) +{ + u32 val; + + val = mtk_r32(eth, MTK_QDMA_INT_MASK); + mtk_w32(eth, val & ~mask, MTK_QDMA_INT_MASK); + /* flush write */ + mtk_r32(eth, MTK_QDMA_INT_MASK); +} + +static inline void mtk_irq_enable(struct mtk_eth *eth, u32 mask) +{ + u32 val; + + val = mtk_r32(eth, MTK_QDMA_INT_MASK); + mtk_w32(eth, val | mask, MTK_QDMA_INT_MASK); + /* flush write */ + mtk_r32(eth, MTK_QDMA_INT_MASK); +} + +static int mtk_set_mac_address(struct net_device *dev, void *p) +{ + int ret = eth_mac_addr(dev, p); + struct mtk_mac *mac = netdev_priv(dev); + const char *macaddr = dev->dev_addr; + unsigned long flags; + + if (ret) + return ret; + + spin_lock_irqsave(&mac->hw->page_lock, flags); + mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], + MTK_GDMA_MAC_ADRH(mac->id)); + mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | + (macaddr[4] << 8) | macaddr[5], + MTK_GDMA_MAC_ADRL(mac->id)); + spin_unlock_irqrestore(&mac->hw->page_lock, flags); + + return 0; +} + +void mtk_stats_update_mac(struct mtk_mac *mac) +{ + struct mtk_hw_stats *hw_stats = mac->hw_stats; + unsigned int base = MTK_GDM1_TX_GBCNT; + u64 stats; + + base += hw_stats->reg_offset; + + u64_stats_update_begin(&hw_stats->syncp); + + hw_stats->rx_bytes += mtk_r32(mac->hw, base); + stats = mtk_r32(mac->hw, base + 0x04); + if (stats) + hw_stats->rx_bytes += (stats << 32); + hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x08); + hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x10); + hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x14); + hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x18); + hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x1c); + hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x20); + hw_stats->rx_flow_control_packets += + mtk_r32(mac->hw, base + 0x24); + hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x28); + hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x2c); + hw_stats->tx_bytes += mtk_r32(mac->hw, base + 0x30); + stats = mtk_r32(mac->hw, base + 0x34); + if (stats) + hw_stats->tx_bytes += (stats << 32); + hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x38); + u64_stats_update_end(&hw_stats->syncp); +} + +static void mtk_stats_update(struct mtk_eth *eth) +{ + int i; + + for (i = 0; i < MTK_MAC_COUNT; i++) { + if (!eth->mac[i] || !eth->mac[i]->hw_stats) + continue; + if (spin_trylock(ð->mac[i]->hw_stats->stats_lock)) { + mtk_stats_update_mac(eth->mac[i]); + spin_unlock(ð->mac[i]->hw_stats->stats_lock); + } + } +} + +static struct rtnl_link_stats64 *mtk_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *storage) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_hw_stats *hw_stats = mac->hw_stats; + unsigned int start; + + if (netif_running(dev) && netif_device_present(dev)) { + if (spin_trylock(&hw_stats->stats_lock)) { + mtk_stats_update_mac(mac); + spin_unlock(&hw_stats->stats_lock); + } + } + + do { + start = u64_stats_fetch_begin_irq(&hw_stats->syncp); + storage->rx_packets = hw_stats->rx_packets; + storage->tx_packets = hw_stats->tx_packets; + storage->rx_bytes = hw_stats->rx_bytes; + storage->tx_bytes = hw_stats->tx_bytes; + storage->collisions = hw_stats->tx_collisions; + storage->rx_length_errors = hw_stats->rx_short_errors + + hw_stats->rx_long_errors; + storage->rx_over_errors = hw_stats->rx_overflow; + storage->rx_crc_errors = hw_stats->rx_fcs_errors; + storage->rx_errors = hw_stats->rx_checksum_errors; + storage->tx_aborted_errors = hw_stats->tx_skip; + } while (u64_stats_fetch_retry_irq(&hw_stats->syncp, start)); + + storage->tx_errors = dev->stats.tx_errors; + storage->rx_dropped = dev->stats.rx_dropped; + storage->tx_dropped = dev->stats.tx_dropped; + + return storage; +} + +static inline int mtk_max_frag_size(int mtu) +{ + /* make sure buf_size will be at least MTK_MAX_RX_LENGTH */ + if (mtu + MTK_RX_ETH_HLEN < MTK_MAX_RX_LENGTH) + mtu = MTK_MAX_RX_LENGTH - MTK_RX_ETH_HLEN; + + return SKB_DATA_ALIGN(MTK_RX_HLEN + mtu) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); +} + +static inline int mtk_max_buf_size(int frag_size) +{ + int buf_size = frag_size - NET_SKB_PAD - NET_IP_ALIGN - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + WARN_ON(buf_size < MTK_MAX_RX_LENGTH); + + return buf_size; +} + +static inline void mtk_rx_get_desc(struct mtk_rx_dma *rxd, + struct mtk_rx_dma *dma_rxd) +{ + rxd->rxd1 = READ_ONCE(dma_rxd->rxd1); + rxd->rxd2 = READ_ONCE(dma_rxd->rxd2); + rxd->rxd3 = READ_ONCE(dma_rxd->rxd3); + rxd->rxd4 = READ_ONCE(dma_rxd->rxd4); +} + +/* the qdma core needs scratch memory to be setup */ +static int mtk_init_fq_dma(struct mtk_eth *eth) +{ + unsigned int phy_ring_head, phy_ring_tail; + int cnt = MTK_DMA_SIZE; + dma_addr_t dma_addr; + int i; + + eth->scratch_ring = dma_alloc_coherent(eth->dev, + cnt * sizeof(struct mtk_tx_dma), + &phy_ring_head, + GFP_ATOMIC | __GFP_ZERO); + if (unlikely(!eth->scratch_ring)) + return -ENOMEM; + + eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE, + GFP_KERNEL); + dma_addr = dma_map_single(eth->dev, + eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(eth->dev, dma_addr))) + return -ENOMEM; + + memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt); + phy_ring_tail = phy_ring_head + + (sizeof(struct mtk_tx_dma) * (cnt - 1)); + + for (i = 0; i < cnt; i++) { + eth->scratch_ring[i].txd1 = + (dma_addr + (i * MTK_QDMA_PAGE_SIZE)); + if (i < cnt - 1) + eth->scratch_ring[i].txd2 = (phy_ring_head + + ((i + 1) * sizeof(struct mtk_tx_dma))); + eth->scratch_ring[i].txd3 = TX_DMA_SDL(MTK_QDMA_PAGE_SIZE); + } + + mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD); + mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL); + mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT); + mtk_w32(eth, MTK_QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN); + + return 0; +} + +static inline void *mtk_qdma_phys_to_virt(struct mtk_tx_ring *ring, u32 desc) +{ + void *ret = ring->dma; + + return ret + (desc - ring->phys); +} + +static inline struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring, + struct mtk_tx_dma *txd) +{ + int idx = txd - ring->dma; + + return &ring->buf[idx]; +} + +static void mtk_tx_unmap(struct device *dev, struct mtk_tx_buf *tx_buf) +{ + if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { + dma_unmap_single(dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { + dma_unmap_page(dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } + tx_buf->flags = 0; + if (tx_buf->skb && + (tx_buf->skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC)) + dev_kfree_skb_any(tx_buf->skb); + tx_buf->skb = NULL; +} + +static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, + int tx_num, struct mtk_tx_ring *ring, bool gso) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + struct mtk_tx_dma *itxd, *txd; + struct mtk_tx_buf *tx_buf; + unsigned long flags; + dma_addr_t mapped_addr; + unsigned int nr_frags; + int i, n_desc = 1; + u32 txd4 = 0; + + itxd = ring->next_free; + if (itxd == ring->last_free) + return -ENOMEM; + + /* set the forward port */ + txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT; + + tx_buf = mtk_desc_to_tx_buf(ring, itxd); + memset(tx_buf, 0, sizeof(*tx_buf)); + + if (gso) + txd4 |= TX_DMA_TSO; + + /* TX Checksum offload */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + txd4 |= TX_DMA_CHKSUM; + + /* VLAN header offload */ + if (skb_vlan_tag_present(skb)) + txd4 |= TX_DMA_INS_VLAN | skb_vlan_tag_get(skb); + + mapped_addr = dma_map_single(&dev->dev, skb->data, + skb_headlen(skb), DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) + return -ENOMEM; + + /* normally we can rely on the stack not calling this more than once, + * however we have 2 queues running ont he same ring so we need to lock + * the ring access + */ + spin_lock_irqsave(ð->page_lock, flags); + WRITE_ONCE(itxd->txd1, mapped_addr); + tx_buf->flags |= MTK_TX_FLAGS_SINGLE0; + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb)); + + /* TX SG offload */ + txd = itxd; + nr_frags = skb_shinfo(skb)->nr_frags; + for (i = 0; i < nr_frags; i++) { + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + unsigned int offset = 0; + int frag_size = skb_frag_size(frag); + + while (frag_size) { + bool last_frag = false; + unsigned int frag_map_size; + + txd = mtk_qdma_phys_to_virt(ring, txd->txd2); + if (txd == ring->last_free) + goto err_dma; + + n_desc++; + frag_map_size = min(frag_size, MTK_TX_DMA_BUF_LEN); + mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset, + frag_map_size, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) + goto err_dma; + + if (i == nr_frags - 1 && + (frag_size - frag_map_size) == 0) + last_frag = true; + + WRITE_ONCE(txd->txd1, mapped_addr); + WRITE_ONCE(txd->txd3, (TX_DMA_SWC | + TX_DMA_PLEN0(frag_map_size) | + last_frag * TX_DMA_LS0) | + mac->id); + WRITE_ONCE(txd->txd4, 0); + + tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; + tx_buf = mtk_desc_to_tx_buf(ring, txd); + memset(tx_buf, 0, sizeof(*tx_buf)); + + tx_buf->flags |= MTK_TX_FLAGS_PAGE0; + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len0, frag_map_size); + frag_size -= frag_map_size; + offset += frag_map_size; + } + } + + /* store skb to cleanup */ + tx_buf->skb = skb; + + WRITE_ONCE(itxd->txd4, txd4); + WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) | + (!nr_frags * TX_DMA_LS0))); + + spin_unlock_irqrestore(ð->page_lock, flags); + + netdev_sent_queue(dev, skb->len); + skb_tx_timestamp(skb); + + ring->next_free = mtk_qdma_phys_to_virt(ring, txd->txd2); + atomic_sub(n_desc, &ring->free_count); + + /* make sure that all changes to the dma ring are flushed before we + * continue + */ + wmb(); + + if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more) + mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); + + return 0; + +err_dma: + do { + tx_buf = mtk_desc_to_tx_buf(ring, txd); + + /* unmap dma */ + mtk_tx_unmap(&dev->dev, tx_buf); + + itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; + itxd = mtk_qdma_phys_to_virt(ring, itxd->txd2); + } while (itxd != txd); + + return -ENOMEM; +} + +static inline int mtk_cal_txd_req(struct sk_buff *skb) +{ + int i, nfrags; + struct skb_frag_struct *frag; + + nfrags = 1; + if (skb_is_gso(skb)) { + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + frag = &skb_shinfo(skb)->frags[i]; + nfrags += DIV_ROUND_UP(frag->size, MTK_TX_DMA_BUF_LEN); + } + } else { + nfrags += skb_shinfo(skb)->nr_frags; + } + + return DIV_ROUND_UP(nfrags, 2); +} + +static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + struct mtk_tx_ring *ring = ð->tx_ring; + struct net_device_stats *stats = &dev->stats; + bool gso = false; + int tx_num; + + tx_num = mtk_cal_txd_req(skb); + if (unlikely(atomic_read(&ring->free_count) <= tx_num)) { + netif_stop_queue(dev); + netif_err(eth, tx_queued, dev, + "Tx Ring full when queue awake!\n"); + return NETDEV_TX_BUSY; + } + + /* TSO: fill MSS info in tcp checksum field */ + if (skb_is_gso(skb)) { + if (skb_cow_head(skb, 0)) { + netif_warn(eth, tx_err, dev, + "GSO expand head fail.\n"); + goto drop; + } + + if (skb_shinfo(skb)->gso_type & + (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { + gso = true; + tcp_hdr(skb)->check = htons(skb_shinfo(skb)->gso_size); + } + } + + if (mtk_tx_map(skb, dev, tx_num, ring, gso) < 0) + goto drop; + + if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) { + netif_stop_queue(dev); + if (unlikely(atomic_read(&ring->free_count) > + ring->thresh)) + netif_wake_queue(dev); + } + + return NETDEV_TX_OK; + +drop: + stats->tx_dropped++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; +} + +static int mtk_poll_rx(struct napi_struct *napi, int budget, + struct mtk_eth *eth, u32 rx_intr) +{ + struct mtk_rx_ring *ring = ð->rx_ring; + int idx = ring->calc_idx; + struct sk_buff *skb; + u8 *data, *new_data; + struct mtk_rx_dma *rxd, trxd; + int done = 0; + + while (done < budget) { + struct net_device *netdev; + unsigned int pktlen; + dma_addr_t dma_addr; + int mac = 0; + + idx = NEXT_RX_DESP_IDX(idx); + rxd = &ring->dma[idx]; + data = ring->data[idx]; + + mtk_rx_get_desc(&trxd, rxd); + if (!(trxd.rxd2 & RX_DMA_DONE)) + break; + + /* find out which mac the packet come from. values start at 1 */ + mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) & + RX_DMA_FPORT_MASK; + mac--; + + netdev = eth->netdev[mac]; + + /* alloc new buffer */ + new_data = napi_alloc_frag(ring->frag_size); + if (unlikely(!new_data)) { + netdev->stats.rx_dropped++; + goto release_desc; + } + dma_addr = dma_map_single(ð->netdev[mac]->dev, + new_data + NET_SKB_PAD, + ring->buf_size, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) { + skb_free_frag(new_data); + goto release_desc; + } + + /* receive data */ + skb = build_skb(data, ring->frag_size); + if (unlikely(!skb)) { + put_page(virt_to_head_page(new_data)); + goto release_desc; + } + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + + dma_unmap_single(&netdev->dev, trxd.rxd1, + ring->buf_size, DMA_FROM_DEVICE); + pktlen = RX_DMA_GET_PLEN0(trxd.rxd2); + skb->dev = netdev; + skb_put(skb, pktlen); + if (trxd.rxd4 & RX_DMA_L4_VALID) + skb->ip_summed = CHECKSUM_UNNECESSARY; + else + skb_checksum_none_assert(skb); + skb->protocol = eth_type_trans(skb, netdev); + + if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX && + RX_DMA_VID(trxd.rxd3)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + RX_DMA_VID(trxd.rxd3)); + napi_gro_receive(napi, skb); + + ring->data[idx] = new_data; + rxd->rxd1 = (unsigned int)dma_addr; + +release_desc: + rxd->rxd2 = RX_DMA_PLEN0(ring->buf_size); + + ring->calc_idx = idx; + /* make sure that all changes to the dma ring are flushed before + * we continue + */ + wmb(); + mtk_w32(eth, ring->calc_idx, MTK_QRX_CRX_IDX0); + done++; + } + + if (done < budget) + mtk_w32(eth, rx_intr, MTK_QMTK_INT_STATUS); + + return done; +} + +static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again) +{ + struct mtk_tx_ring *ring = ð->tx_ring; + struct mtk_tx_dma *desc; + struct sk_buff *skb; + struct mtk_tx_buf *tx_buf; + int total = 0, done[MTK_MAX_DEVS]; + unsigned int bytes[MTK_MAX_DEVS]; + u32 cpu, dma; + static int condition; + int i; + + memset(done, 0, sizeof(done)); + memset(bytes, 0, sizeof(bytes)); + + cpu = mtk_r32(eth, MTK_QTX_CRX_PTR); + dma = mtk_r32(eth, MTK_QTX_DRX_PTR); + + desc = mtk_qdma_phys_to_virt(ring, cpu); + + while ((cpu != dma) && budget) { + u32 next_cpu = desc->txd2; + int mac; + + desc = mtk_qdma_phys_to_virt(ring, desc->txd2); + if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0) + break; + + mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) & + TX_DMA_FPORT_MASK; + mac--; + + tx_buf = mtk_desc_to_tx_buf(ring, desc); + skb = tx_buf->skb; + if (!skb) { + condition = 1; + break; + } + + if (skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC) { + bytes[mac] += skb->len; + done[mac]++; + budget--; + } + mtk_tx_unmap(eth->dev, tx_buf); + + ring->last_free->txd2 = next_cpu; + ring->last_free = desc; + atomic_inc(&ring->free_count); + + cpu = next_cpu; + } + + mtk_w32(eth, cpu, MTK_QTX_CRX_PTR); + + for (i = 0; i < MTK_MAC_COUNT; i++) { + if (!eth->netdev[i] || !done[i]) + continue; + netdev_completed_queue(eth->netdev[i], done[i], bytes[i]); + total += done[i]; + } + + /* read hw index again make sure no new tx packet */ + if (cpu != dma || cpu != mtk_r32(eth, MTK_QTX_DRX_PTR)) + *tx_again = true; + else + mtk_w32(eth, MTK_TX_DONE_INT, MTK_QMTK_INT_STATUS); + + if (!total) + return 0; + + for (i = 0; i < MTK_MAC_COUNT; i++) { + if (!eth->netdev[i] || + unlikely(!netif_queue_stopped(eth->netdev[i]))) + continue; + if (atomic_read(&ring->free_count) > ring->thresh) + netif_wake_queue(eth->netdev[i]); + } + + return total; +} + +static int mtk_poll(struct napi_struct *napi, int budget) +{ + struct mtk_eth *eth = container_of(napi, struct mtk_eth, rx_napi); + u32 status, status2, mask, tx_intr, rx_intr, status_intr; + int tx_done, rx_done; + bool tx_again = false; + + status = mtk_r32(eth, MTK_QMTK_INT_STATUS); + status2 = mtk_r32(eth, MTK_INT_STATUS2); + tx_intr = MTK_TX_DONE_INT; + rx_intr = MTK_RX_DONE_INT; + status_intr = (MTK_GDM1_AF | MTK_GDM2_AF); + tx_done = 0; + rx_done = 0; + tx_again = 0; + + if (status & tx_intr) + tx_done = mtk_poll_tx(eth, budget, &tx_again); + + if (status & rx_intr) + rx_done = mtk_poll_rx(napi, budget, eth, rx_intr); + + if (unlikely(status2 & status_intr)) { + mtk_stats_update(eth); + mtk_w32(eth, status_intr, MTK_INT_STATUS2); + } + + if (unlikely(netif_msg_intr(eth))) { + mask = mtk_r32(eth, MTK_QDMA_INT_MASK); + netdev_info(eth->netdev[0], + "done tx %d, rx %d, intr 0x%08x/0x%x\n", + tx_done, rx_done, status, mask); + } + + if (tx_again || rx_done == budget) + return budget; + + status = mtk_r32(eth, MTK_QMTK_INT_STATUS); + if (status & (tx_intr | rx_intr)) + return budget; + + napi_complete(napi); + mtk_irq_enable(eth, tx_intr | rx_intr); + + return rx_done; +} + +static int mtk_tx_alloc(struct mtk_eth *eth) +{ + struct mtk_tx_ring *ring = ð->tx_ring; + int i, sz = sizeof(*ring->dma); + + ring->buf = kcalloc(MTK_DMA_SIZE, sizeof(*ring->buf), + GFP_KERNEL); + if (!ring->buf) + goto no_tx_mem; + + ring->dma = dma_alloc_coherent(eth->dev, + MTK_DMA_SIZE * sz, + &ring->phys, + GFP_ATOMIC | __GFP_ZERO); + if (!ring->dma) + goto no_tx_mem; + + memset(ring->dma, 0, MTK_DMA_SIZE * sz); + for (i = 0; i < MTK_DMA_SIZE; i++) { + int next = (i + 1) % MTK_DMA_SIZE; + u32 next_ptr = ring->phys + next * sz; + + ring->dma[i].txd2 = next_ptr; + ring->dma[i].txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; + } + + atomic_set(&ring->free_count, MTK_DMA_SIZE - 2); + ring->next_free = &ring->dma[0]; + ring->last_free = &ring->dma[MTK_DMA_SIZE - 2]; + ring->thresh = max((unsigned long)MTK_DMA_SIZE >> 2, + MAX_SKB_FRAGS); + + /* make sure that all changes to the dma ring are flushed before we + * continue + */ + wmb(); + + mtk_w32(eth, ring->phys, MTK_QTX_CTX_PTR); + mtk_w32(eth, ring->phys, MTK_QTX_DTX_PTR); + mtk_w32(eth, + ring->phys + ((MTK_DMA_SIZE - 1) * sz), + MTK_QTX_CRX_PTR); + mtk_w32(eth, + ring->phys + ((MTK_DMA_SIZE - 1) * sz), + MTK_QTX_DRX_PTR); + + return 0; + +no_tx_mem: + return -ENOMEM; +} + +static void mtk_tx_clean(struct mtk_eth *eth) +{ + struct mtk_tx_ring *ring = ð->tx_ring; + int i; + + if (ring->buf) { + for (i = 0; i < MTK_DMA_SIZE; i++) + mtk_tx_unmap(eth->dev, &ring->buf[i]); + kfree(ring->buf); + ring->buf = NULL; + } + + if (ring->dma) { + dma_free_coherent(eth->dev, + MTK_DMA_SIZE * sizeof(*ring->dma), + ring->dma, + ring->phys); + ring->dma = NULL; + } +} + +static int mtk_rx_alloc(struct mtk_eth *eth) +{ + struct mtk_rx_ring *ring = ð->rx_ring; + int i; + + ring->frag_size = mtk_max_frag_size(ETH_DATA_LEN); + ring->buf_size = mtk_max_buf_size(ring->frag_size); + ring->data = kcalloc(MTK_DMA_SIZE, sizeof(*ring->data), + GFP_KERNEL); + if (!ring->data) + return -ENOMEM; + + for (i = 0; i < MTK_DMA_SIZE; i++) { + ring->data[i] = netdev_alloc_frag(ring->frag_size); + if (!ring->data[i]) + return -ENOMEM; + } + + ring->dma = dma_alloc_coherent(eth->dev, + MTK_DMA_SIZE * sizeof(*ring->dma), + &ring->phys, + GFP_ATOMIC | __GFP_ZERO); + if (!ring->dma) + return -ENOMEM; + + for (i = 0; i < MTK_DMA_SIZE; i++) { + dma_addr_t dma_addr = dma_map_single(eth->dev, + ring->data[i] + NET_SKB_PAD, + ring->buf_size, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(eth->dev, dma_addr))) + return -ENOMEM; + ring->dma[i].rxd1 = (unsigned int)dma_addr; + + ring->dma[i].rxd2 = RX_DMA_PLEN0(ring->buf_size); + } + ring->calc_idx = MTK_DMA_SIZE - 1; + /* make sure that all changes to the dma ring are flushed before we + * continue + */ + wmb(); + + mtk_w32(eth, eth->rx_ring.phys, MTK_QRX_BASE_PTR0); + mtk_w32(eth, MTK_DMA_SIZE, MTK_QRX_MAX_CNT0); + mtk_w32(eth, eth->rx_ring.calc_idx, MTK_QRX_CRX_IDX0); + mtk_w32(eth, MTK_PST_DRX_IDX0, MTK_QDMA_RST_IDX); + mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0)); + + return 0; +} + +static void mtk_rx_clean(struct mtk_eth *eth) +{ + struct mtk_rx_ring *ring = ð->rx_ring; + int i; + + if (ring->data && ring->dma) { + for (i = 0; i < MTK_DMA_SIZE; i++) { + if (!ring->data[i]) + continue; + if (!ring->dma[i].rxd1) + continue; + dma_unmap_single(eth->dev, + ring->dma[i].rxd1, + ring->buf_size, + DMA_FROM_DEVICE); + skb_free_frag(ring->data[i]); + } + kfree(ring->data); + ring->data = NULL; + } + + if (ring->dma) { + dma_free_coherent(eth->dev, + MTK_DMA_SIZE * sizeof(*ring->dma), + ring->dma, + ring->phys); + ring->dma = NULL; + } +} + +/* wait for DMA to finish whatever it is doing before we start using it again */ +static int mtk_dma_busy_wait(struct mtk_eth *eth) +{ + unsigned long t_start = jiffies; + + while (1) { + if (!(mtk_r32(eth, MTK_QDMA_GLO_CFG) & + (MTK_RX_DMA_BUSY | MTK_TX_DMA_BUSY))) + return 0; + if (time_after(jiffies, t_start + MTK_DMA_BUSY_TIMEOUT)) + break; + } + + dev_err(eth->dev, "DMA init timeout\n"); + return -1; +} + +static int mtk_dma_init(struct mtk_eth *eth) +{ + int err; + + if (mtk_dma_busy_wait(eth)) + return -EBUSY; + + /* QDMA needs scratch memory for internal reordering of the + * descriptors + */ + err = mtk_init_fq_dma(eth); + if (err) + return err; + + err = mtk_tx_alloc(eth); + if (err) + return err; + + err = mtk_rx_alloc(eth); + if (err) + return err; + + /* Enable random early drop and set drop threshold automatically */ + mtk_w32(eth, FC_THRES_DROP_MODE | FC_THRES_DROP_EN | FC_THRES_MIN, + MTK_QDMA_FC_THRES); + mtk_w32(eth, 0x0, MTK_QDMA_HRED2); + + return 0; +} + +static void mtk_dma_free(struct mtk_eth *eth) +{ + int i; + + for (i = 0; i < MTK_MAC_COUNT; i++) + if (eth->netdev[i]) + netdev_reset_queue(eth->netdev[i]); + mtk_tx_clean(eth); + mtk_rx_clean(eth); + kfree(eth->scratch_head); +} + +static void mtk_tx_timeout(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + + eth->netdev[mac->id]->stats.tx_errors++; + netif_err(eth, tx_err, dev, + "transmit timed out\n"); + schedule_work(&mac->pending_work); +} + +static irqreturn_t mtk_handle_irq(int irq, void *_eth) +{ + struct mtk_eth *eth = _eth; + u32 status; + + status = mtk_r32(eth, MTK_QMTK_INT_STATUS); + if (unlikely(!status)) + return IRQ_NONE; + + if (likely(status & (MTK_RX_DONE_INT | MTK_TX_DONE_INT))) { + if (likely(napi_schedule_prep(ð->rx_napi))) + __napi_schedule(ð->rx_napi); + } else { + mtk_w32(eth, status, MTK_QMTK_INT_STATUS); + } + mtk_irq_disable(eth, (MTK_RX_DONE_INT | MTK_TX_DONE_INT)); + + return IRQ_HANDLED; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void mtk_poll_controller(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + u32 int_mask = MTK_TX_DONE_INT | MTK_RX_DONE_INT; + + mtk_irq_disable(eth, int_mask); + mtk_handle_irq(dev->irq, dev); + mtk_irq_enable(eth, int_mask); +} +#endif + +static int mtk_start_dma(struct mtk_eth *eth) +{ + int err; + + err = mtk_dma_init(eth); + if (err) { + mtk_dma_free(eth); + return err; + } + + mtk_w32(eth, + MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN | + MTK_RX_2B_OFFSET | MTK_DMA_SIZE_16DWORDS | + MTK_RX_BT_32DWORDS, + MTK_QDMA_GLO_CFG); + + return 0; +} + +static int mtk_open(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + + /* we run 2 netdevs on the same dma ring so we only bring it up once */ + if (!atomic_read(ð->dma_refcnt)) { + int err = mtk_start_dma(eth); + + if (err) + return err; + + napi_enable(ð->rx_napi); + mtk_irq_enable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT); + } + atomic_inc(ð->dma_refcnt); + + phy_start(mac->phy_dev); + netif_start_queue(dev); + + return 0; +} + +static void mtk_stop_dma(struct mtk_eth *eth, u32 glo_cfg) +{ + unsigned long flags; + u32 val; + int i; + + /* stop the dma engine */ + spin_lock_irqsave(ð->page_lock, flags); + val = mtk_r32(eth, glo_cfg); + mtk_w32(eth, val & ~(MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN), + glo_cfg); + spin_unlock_irqrestore(ð->page_lock, flags); + + /* wait for dma stop */ + for (i = 0; i < 10; i++) { + val = mtk_r32(eth, glo_cfg); + if (val & (MTK_TX_DMA_BUSY | MTK_RX_DMA_BUSY)) { + msleep(20); + continue; + } + break; + } +} + +static int mtk_stop(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + + netif_tx_disable(dev); + phy_stop(mac->phy_dev); + + /* only shutdown DMA if this is the last user */ + if (!atomic_dec_and_test(ð->dma_refcnt)) + return 0; + + mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT); + napi_disable(ð->rx_napi); + + mtk_stop_dma(eth, MTK_QDMA_GLO_CFG); + + mtk_dma_free(eth); + + return 0; +} + +static int __init mtk_hw_init(struct mtk_eth *eth) +{ + int err, i; + + /* reset the frame engine */ + reset_control_assert(eth->rstc); + usleep_range(10, 20); + reset_control_deassert(eth->rstc); + usleep_range(10, 20); + + /* Set GE2 driving and slew rate */ + regmap_write(eth->pctl, GPIO_DRV_SEL10, 0xa00); + + /* set GE2 TDSEL */ + regmap_write(eth->pctl, GPIO_OD33_CTRL8, 0x5); + + /* set GE2 TUNE */ + regmap_write(eth->pctl, GPIO_BIAS_CTRL, 0x0); + + /* GE1, Force 1000M/FD, FC ON */ + mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(0)); + + /* GE2, Force 1000M/FD, FC ON */ + mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(1)); + + /* Enable RX VLan Offloading */ + mtk_w32(eth, 1, MTK_CDMP_EG_CTRL); + + err = devm_request_irq(eth->dev, eth->irq, mtk_handle_irq, 0, + dev_name(eth->dev), eth); + if (err) + return err; + + err = mtk_mdio_init(eth); + if (err) + return err; + + /* disable delay and normal interrupt */ + mtk_w32(eth, 0, MTK_QDMA_DELAY_INT); + mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT); + mtk_w32(eth, RST_GL_PSE, MTK_RST_GL); + mtk_w32(eth, 0, MTK_RST_GL); + + /* FE int grouping */ + mtk_w32(eth, 0, MTK_FE_INT_GRP); + + for (i = 0; i < 2; i++) { + u32 val = mtk_r32(eth, MTK_GDMA_FWD_CFG(i)); + + /* setup the forward port to send frame to QDMA */ + val &= ~0xffff; + val |= 0x5555; + + /* Enable RX checksum */ + val |= MTK_GDMA_ICS_EN | MTK_GDMA_TCS_EN | MTK_GDMA_UCS_EN; + + /* setup the mac dma */ + mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i)); + } + + return 0; +} + +static int __init mtk_init(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + const char *mac_addr; + + mac_addr = of_get_mac_address(mac->of_node); + if (mac_addr) + ether_addr_copy(dev->dev_addr, mac_addr); + + /* If the mac address is invalid, use random mac address */ + if (!is_valid_ether_addr(dev->dev_addr)) { + random_ether_addr(dev->dev_addr); + dev_err(eth->dev, "generated random MAC address %pM\n", + dev->dev_addr); + dev->addr_assign_type = NET_ADDR_RANDOM; + } + + return mtk_phy_connect(mac); +} + +static void mtk_uninit(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; + + phy_disconnect(mac->phy_dev); + mtk_mdio_cleanup(eth); + mtk_irq_disable(eth, ~0); + free_irq(dev->irq, dev); +} + +static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct mtk_mac *mac = netdev_priv(dev); + + switch (cmd) { + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSMIIREG: + return phy_mii_ioctl(mac->phy_dev, ifr, cmd); + default: + break; + } + + return -EOPNOTSUPP; +} + +static void mtk_pending_work(struct work_struct *work) +{ + struct mtk_mac *mac = container_of(work, struct mtk_mac, pending_work); + struct mtk_eth *eth = mac->hw; + struct net_device *dev = eth->netdev[mac->id]; + int err; + + rtnl_lock(); + mtk_stop(dev); + + err = mtk_open(dev); + if (err) { + netif_alert(eth, ifup, dev, + "Driver up/down cycle failed, closing device.\n"); + dev_close(dev); + } + rtnl_unlock(); +} + +static int mtk_cleanup(struct mtk_eth *eth) +{ + int i; + + for (i = 0; i < MTK_MAC_COUNT; i++) { + struct mtk_mac *mac = netdev_priv(eth->netdev[i]); + + if (!eth->netdev[i]) + continue; + + unregister_netdev(eth->netdev[i]); + free_netdev(eth->netdev[i]); + cancel_work_sync(&mac->pending_work); + } + + return 0; +} + +static int mtk_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + struct mtk_mac *mac = netdev_priv(dev); + int err; + + err = phy_read_status(mac->phy_dev); + if (err) + return -ENODEV; + + return phy_ethtool_gset(mac->phy_dev, cmd); +} + +static int mtk_set_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + struct mtk_mac *mac = netdev_priv(dev); + + if (cmd->phy_address != mac->phy_dev->mdio.addr) { + mac->phy_dev = mdiobus_get_phy(mac->hw->mii_bus, + cmd->phy_address); + if (!mac->phy_dev) + return -ENODEV; + } + + return phy_ethtool_sset(mac->phy_dev, cmd); +} + +static void mtk_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + struct mtk_mac *mac = netdev_priv(dev); + + strlcpy(info->driver, mac->hw->dev->driver->name, sizeof(info->driver)); + strlcpy(info->bus_info, dev_name(mac->hw->dev), sizeof(info->bus_info)); + info->n_stats = ARRAY_SIZE(mtk_ethtool_stats); +} + +static u32 mtk_get_msglevel(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + + return mac->hw->msg_enable; +} + +static void mtk_set_msglevel(struct net_device *dev, u32 value) +{ + struct mtk_mac *mac = netdev_priv(dev); + + mac->hw->msg_enable = value; +} + +static int mtk_nway_reset(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + + return genphy_restart_aneg(mac->phy_dev); +} + +static u32 mtk_get_link(struct net_device *dev) +{ + struct mtk_mac *mac = netdev_priv(dev); + int err; + + err = genphy_update_link(mac->phy_dev); + if (err) + return ethtool_op_get_link(dev); + + return mac->phy_dev->link; +} + +static void mtk_get_strings(struct net_device *dev, u32 stringset, u8 *data) +{ + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < ARRAY_SIZE(mtk_ethtool_stats); i++) { + memcpy(data, mtk_ethtool_stats[i].str, ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + break; + } +} + +static int mtk_get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ARRAY_SIZE(mtk_ethtool_stats); + default: + return -EOPNOTSUPP; + } +} + +static void mtk_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct mtk_mac *mac = netdev_priv(dev); + struct mtk_hw_stats *hwstats = mac->hw_stats; + u64 *data_src, *data_dst; + unsigned int start; + int i; + + if (netif_running(dev) && netif_device_present(dev)) { + if (spin_trylock(&hwstats->stats_lock)) { + mtk_stats_update_mac(mac); + spin_unlock(&hwstats->stats_lock); + } + } + + do { + data_src = (u64*)hwstats; + data_dst = data; + start = u64_stats_fetch_begin_irq(&hwstats->syncp); + + for (i = 0; i < ARRAY_SIZE(mtk_ethtool_stats); i++) + *data_dst++ = *(data_src + mtk_ethtool_stats[i].offset); + } while (u64_stats_fetch_retry_irq(&hwstats->syncp, start)); +} + +static struct ethtool_ops mtk_ethtool_ops = { + .get_settings = mtk_get_settings, + .set_settings = mtk_set_settings, + .get_drvinfo = mtk_get_drvinfo, + .get_msglevel = mtk_get_msglevel, + .set_msglevel = mtk_set_msglevel, + .nway_reset = mtk_nway_reset, + .get_link = mtk_get_link, + .get_strings = mtk_get_strings, + .get_sset_count = mtk_get_sset_count, + .get_ethtool_stats = mtk_get_ethtool_stats, +}; + +static const struct net_device_ops mtk_netdev_ops = { + .ndo_init = mtk_init, + .ndo_uninit = mtk_uninit, + .ndo_open = mtk_open, + .ndo_stop = mtk_stop, + .ndo_start_xmit = mtk_start_xmit, + .ndo_set_mac_address = mtk_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_do_ioctl = mtk_do_ioctl, + .ndo_change_mtu = eth_change_mtu, + .ndo_tx_timeout = mtk_tx_timeout, + .ndo_get_stats64 = mtk_get_stats64, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = mtk_poll_controller, +#endif +}; + +static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) +{ + struct mtk_mac *mac; + const __be32 *_id = of_get_property(np, "reg", NULL); + int id, err; + + if (!_id) { + dev_err(eth->dev, "missing mac id\n"); + return -EINVAL; + } + + id = be32_to_cpup(_id); + if (id >= MTK_MAC_COUNT) { + dev_err(eth->dev, "%d is not a valid mac id\n", id); + return -EINVAL; + } + + if (eth->netdev[id]) { + dev_err(eth->dev, "duplicate mac id found: %d\n", id); + return -EINVAL; + } + + eth->netdev[id] = alloc_etherdev(sizeof(*mac)); + if (!eth->netdev[id]) { + dev_err(eth->dev, "alloc_etherdev failed\n"); + return -ENOMEM; + } + mac = netdev_priv(eth->netdev[id]); + eth->mac[id] = mac; + mac->id = id; + mac->hw = eth; + mac->of_node = np; + INIT_WORK(&mac->pending_work, mtk_pending_work); + + mac->hw_stats = devm_kzalloc(eth->dev, + sizeof(*mac->hw_stats), + GFP_KERNEL); + if (!mac->hw_stats) { + dev_err(eth->dev, "failed to allocate counter memory\n"); + err = -ENOMEM; + goto free_netdev; + } + spin_lock_init(&mac->hw_stats->stats_lock); + mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET; + + SET_NETDEV_DEV(eth->netdev[id], eth->dev); + eth->netdev[id]->netdev_ops = &mtk_netdev_ops; + eth->netdev[id]->base_addr = (unsigned long)eth->base; + eth->netdev[id]->vlan_features = MTK_HW_FEATURES & + ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); + eth->netdev[id]->features |= MTK_HW_FEATURES; + eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops; + + err = register_netdev(eth->netdev[id]); + if (err) { + dev_err(eth->dev, "error bringing up device\n"); + goto free_netdev; + } + eth->netdev[id]->irq = eth->irq; + netif_info(eth, probe, eth->netdev[id], + "mediatek frame engine at 0x%08lx, irq %d\n", + eth->netdev[id]->base_addr, eth->netdev[id]->irq); + + return 0; + +free_netdev: + free_netdev(eth->netdev[id]); + return err; +} + +static int mtk_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + struct device_node *mac_np; + const struct of_device_id *match; + struct mtk_soc_data *soc; + struct mtk_eth *eth; + int err; + + pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; + + device_reset(&pdev->dev); + + match = of_match_device(of_mtk_match, &pdev->dev); + soc = (struct mtk_soc_data *)match->data; + + eth = devm_kzalloc(&pdev->dev, sizeof(*eth), GFP_KERNEL); + if (!eth) + return -ENOMEM; + + eth->base = devm_ioremap_resource(&pdev->dev, res); + if (!eth->base) + return -EADDRNOTAVAIL; + + spin_lock_init(ð->page_lock); + + eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "mediatek,ethsys"); + if (IS_ERR(eth->ethsys)) { + dev_err(&pdev->dev, "no ethsys regmap found\n"); + return PTR_ERR(eth->ethsys); + } + + eth->pctl = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "mediatek,pctl"); + if (IS_ERR(eth->pctl)) { + dev_err(&pdev->dev, "no pctl regmap found\n"); + return PTR_ERR(eth->pctl); + } + + eth->rstc = devm_reset_control_get(&pdev->dev, "eth"); + if (IS_ERR(eth->rstc)) { + dev_err(&pdev->dev, "no eth reset found\n"); + return PTR_ERR(eth->rstc); + } + + eth->irq = platform_get_irq(pdev, 0); + if (eth->irq < 0) { + dev_err(&pdev->dev, "no IRQ resource found\n"); + return -ENXIO; + } + + eth->clk_ethif = devm_clk_get(&pdev->dev, "ethif"); + eth->clk_esw = devm_clk_get(&pdev->dev, "esw"); + eth->clk_gp1 = devm_clk_get(&pdev->dev, "gp1"); + eth->clk_gp2 = devm_clk_get(&pdev->dev, "gp2"); + if (IS_ERR(eth->clk_esw) || IS_ERR(eth->clk_gp1) || + IS_ERR(eth->clk_gp2) || IS_ERR(eth->clk_ethif)) + return -ENODEV; + + clk_prepare_enable(eth->clk_ethif); + clk_prepare_enable(eth->clk_esw); + clk_prepare_enable(eth->clk_gp1); + clk_prepare_enable(eth->clk_gp2); + + eth->dev = &pdev->dev; + eth->msg_enable = netif_msg_init(mtk_msg_level, MTK_DEFAULT_MSG_ENABLE); + + err = mtk_hw_init(eth); + if (err) + return err; + + for_each_child_of_node(pdev->dev.of_node, mac_np) { + if (!of_device_is_compatible(mac_np, + "mediatek,eth-mac")) + continue; + + if (!of_device_is_available(mac_np)) + continue; + + err = mtk_add_mac(eth, mac_np); + if (err) + goto err_free_dev; + } + + /* we run 2 devices on the same DMA ring so we need a dummy device + * for NAPI to work + */ + init_dummy_netdev(ð->dummy_dev); + netif_napi_add(ð->dummy_dev, ð->rx_napi, mtk_poll, + MTK_NAPI_WEIGHT); + + platform_set_drvdata(pdev, eth); + + return 0; + +err_free_dev: + mtk_cleanup(eth); + return err; +} + +static int mtk_remove(struct platform_device *pdev) +{ + struct mtk_eth *eth = platform_get_drvdata(pdev); + + clk_disable_unprepare(eth->clk_ethif); + clk_disable_unprepare(eth->clk_esw); + clk_disable_unprepare(eth->clk_gp1); + clk_disable_unprepare(eth->clk_gp2); + + netif_napi_del(ð->rx_napi); + mtk_cleanup(eth); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +const struct of_device_id of_mtk_match[] = { + { .compatible = "mediatek,mt7623-eth" }, + {}, +}; + +static struct platform_driver mtk_driver = { + .probe = mtk_probe, + .remove = mtk_remove, + .driver = { + .name = "mtk_soc_eth", + .owner = THIS_MODULE, + .of_match_table = of_mtk_match, + }, +}; + +module_platform_driver(mtk_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("John Crispin <blogic@openwrt.org>"); +MODULE_DESCRIPTION("Ethernet driver for MediaTek SoC"); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h new file mode 100644 index 000000000000..48a5292c8ed8 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -0,0 +1,421 @@ +/* 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 of the License + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> + * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> + * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> + */ + +#ifndef MTK_ETH_H +#define MTK_ETH_H + +#define MTK_QDMA_PAGE_SIZE 2048 +#define MTK_MAX_RX_LENGTH 1536 +#define MTK_TX_DMA_BUF_LEN 0x3fff +#define MTK_DMA_SIZE 256 +#define MTK_NAPI_WEIGHT 64 +#define MTK_MAC_COUNT 2 +#define MTK_RX_ETH_HLEN (VLAN_ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) +#define MTK_RX_HLEN (NET_SKB_PAD + MTK_RX_ETH_HLEN + NET_IP_ALIGN) +#define MTK_DMA_DUMMY_DESC 0xffffffff +#define MTK_DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | \ + NETIF_MSG_PROBE | \ + NETIF_MSG_LINK | \ + NETIF_MSG_TIMER | \ + NETIF_MSG_IFDOWN | \ + NETIF_MSG_IFUP | \ + NETIF_MSG_RX_ERR | \ + NETIF_MSG_TX_ERR) +#define MTK_HW_FEATURES (NETIF_F_IP_CSUM | \ + NETIF_F_RXCSUM | \ + NETIF_F_HW_VLAN_CTAG_TX | \ + NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_SG | NETIF_F_TSO | \ + NETIF_F_TSO6 | \ + NETIF_F_IPV6_CSUM) +#define NEXT_RX_DESP_IDX(X) (((X) + 1) & (MTK_DMA_SIZE - 1)) + +/* Frame Engine Global Reset Register */ +#define MTK_RST_GL 0x04 +#define RST_GL_PSE BIT(0) + +/* Frame Engine Interrupt Status Register */ +#define MTK_INT_STATUS2 0x08 +#define MTK_GDM1_AF BIT(28) +#define MTK_GDM2_AF BIT(29) + +/* Frame Engine Interrupt Grouping Register */ +#define MTK_FE_INT_GRP 0x20 + +/* CDMP Exgress Control Register */ +#define MTK_CDMP_EG_CTRL 0x404 + +/* GDM Exgress Control Register */ +#define MTK_GDMA_FWD_CFG(x) (0x500 + (x * 0x1000)) +#define MTK_GDMA_ICS_EN BIT(22) +#define MTK_GDMA_TCS_EN BIT(21) +#define MTK_GDMA_UCS_EN BIT(20) + +/* Unicast Filter MAC Address Register - Low */ +#define MTK_GDMA_MAC_ADRL(x) (0x508 + (x * 0x1000)) + +/* Unicast Filter MAC Address Register - High */ +#define MTK_GDMA_MAC_ADRH(x) (0x50C + (x * 0x1000)) + +/* QDMA TX Queue Configuration Registers */ +#define MTK_QTX_CFG(x) (0x1800 + (x * 0x10)) +#define QDMA_RES_THRES 4 + +/* QDMA TX Queue Scheduler Registers */ +#define MTK_QTX_SCH(x) (0x1804 + (x * 0x10)) + +/* QDMA RX Base Pointer Register */ +#define MTK_QRX_BASE_PTR0 0x1900 + +/* QDMA RX Maximum Count Register */ +#define MTK_QRX_MAX_CNT0 0x1904 + +/* QDMA RX CPU Pointer Register */ +#define MTK_QRX_CRX_IDX0 0x1908 + +/* QDMA RX DMA Pointer Register */ +#define MTK_QRX_DRX_IDX0 0x190C + +/* QDMA Global Configuration Register */ +#define MTK_QDMA_GLO_CFG 0x1A04 +#define MTK_RX_2B_OFFSET BIT(31) +#define MTK_RX_BT_32DWORDS (3 << 11) +#define MTK_TX_WB_DDONE BIT(6) +#define MTK_DMA_SIZE_16DWORDS (2 << 4) +#define MTK_RX_DMA_BUSY BIT(3) +#define MTK_TX_DMA_BUSY BIT(1) +#define MTK_RX_DMA_EN BIT(2) +#define MTK_TX_DMA_EN BIT(0) +#define MTK_DMA_BUSY_TIMEOUT HZ + +/* QDMA Reset Index Register */ +#define MTK_QDMA_RST_IDX 0x1A08 +#define MTK_PST_DRX_IDX0 BIT(16) + +/* QDMA Delay Interrupt Register */ +#define MTK_QDMA_DELAY_INT 0x1A0C + +/* QDMA Flow Control Register */ +#define MTK_QDMA_FC_THRES 0x1A10 +#define FC_THRES_DROP_MODE BIT(20) +#define FC_THRES_DROP_EN (7 << 16) +#define FC_THRES_MIN 0x4444 + +/* QDMA Interrupt Status Register */ +#define MTK_QMTK_INT_STATUS 0x1A18 +#define MTK_RX_DONE_INT1 BIT(17) +#define MTK_RX_DONE_INT0 BIT(16) +#define MTK_TX_DONE_INT3 BIT(3) +#define MTK_TX_DONE_INT2 BIT(2) +#define MTK_TX_DONE_INT1 BIT(1) +#define MTK_TX_DONE_INT0 BIT(0) +#define MTK_RX_DONE_INT (MTK_RX_DONE_INT0 | MTK_RX_DONE_INT1) +#define MTK_TX_DONE_INT (MTK_TX_DONE_INT0 | MTK_TX_DONE_INT1 | \ + MTK_TX_DONE_INT2 | MTK_TX_DONE_INT3) + +/* QDMA Interrupt Status Register */ +#define MTK_QDMA_INT_MASK 0x1A1C + +/* QDMA Interrupt Mask Register */ +#define MTK_QDMA_HRED2 0x1A44 + +/* QDMA TX Forward CPU Pointer Register */ +#define MTK_QTX_CTX_PTR 0x1B00 + +/* QDMA TX Forward DMA Pointer Register */ +#define MTK_QTX_DTX_PTR 0x1B04 + +/* QDMA TX Release CPU Pointer Register */ +#define MTK_QTX_CRX_PTR 0x1B10 + +/* QDMA TX Release DMA Pointer Register */ +#define MTK_QTX_DRX_PTR 0x1B14 + +/* QDMA FQ Head Pointer Register */ +#define MTK_QDMA_FQ_HEAD 0x1B20 + +/* QDMA FQ Head Pointer Register */ +#define MTK_QDMA_FQ_TAIL 0x1B24 + +/* QDMA FQ Free Page Counter Register */ +#define MTK_QDMA_FQ_CNT 0x1B28 + +/* QDMA FQ Free Page Buffer Length Register */ +#define MTK_QDMA_FQ_BLEN 0x1B2C + +/* GMA1 Received Good Byte Count Register */ +#define MTK_GDM1_TX_GBCNT 0x2400 +#define MTK_STAT_OFFSET 0x40 + +/* QDMA descriptor txd4 */ +#define TX_DMA_CHKSUM (0x7 << 29) +#define TX_DMA_TSO BIT(28) +#define TX_DMA_FPORT_SHIFT 25 +#define TX_DMA_FPORT_MASK 0x7 +#define TX_DMA_INS_VLAN BIT(16) + +/* QDMA descriptor txd3 */ +#define TX_DMA_OWNER_CPU BIT(31) +#define TX_DMA_LS0 BIT(30) +#define TX_DMA_PLEN0(_x) (((_x) & MTK_TX_DMA_BUF_LEN) << 16) +#define TX_DMA_SWC BIT(14) +#define TX_DMA_SDL(_x) (((_x) & 0x3fff) << 16) + +/* QDMA descriptor rxd2 */ +#define RX_DMA_DONE BIT(31) +#define RX_DMA_PLEN0(_x) (((_x) & 0x3fff) << 16) +#define RX_DMA_GET_PLEN0(_x) (((_x) >> 16) & 0x3fff) + +/* QDMA descriptor rxd3 */ +#define RX_DMA_VID(_x) ((_x) & 0xfff) + +/* QDMA descriptor rxd4 */ +#define RX_DMA_L4_VALID BIT(24) +#define RX_DMA_FPORT_SHIFT 19 +#define RX_DMA_FPORT_MASK 0x7 + +/* PHY Indirect Access Control registers */ +#define MTK_PHY_IAC 0x10004 +#define PHY_IAC_ACCESS BIT(31) +#define PHY_IAC_READ BIT(19) +#define PHY_IAC_WRITE BIT(18) +#define PHY_IAC_START BIT(16) +#define PHY_IAC_ADDR_SHIFT 20 +#define PHY_IAC_REG_SHIFT 25 +#define PHY_IAC_TIMEOUT HZ + +/* Mac control registers */ +#define MTK_MAC_MCR(x) (0x10100 + (x * 0x100)) +#define MAC_MCR_MAX_RX_1536 BIT(24) +#define MAC_MCR_IPG_CFG (BIT(18) | BIT(16)) +#define MAC_MCR_FORCE_MODE BIT(15) +#define MAC_MCR_TX_EN BIT(14) +#define MAC_MCR_RX_EN BIT(13) +#define MAC_MCR_BACKOFF_EN BIT(9) +#define MAC_MCR_BACKPR_EN BIT(8) +#define MAC_MCR_FORCE_RX_FC BIT(5) +#define MAC_MCR_FORCE_TX_FC BIT(4) +#define MAC_MCR_SPEED_1000 BIT(3) +#define MAC_MCR_SPEED_100 BIT(2) +#define MAC_MCR_FORCE_DPX BIT(1) +#define MAC_MCR_FORCE_LINK BIT(0) +#define MAC_MCR_FIXED_LINK (MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG | \ + MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN | \ + MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN | \ + MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_RX_FC | \ + MAC_MCR_FORCE_TX_FC | MAC_MCR_SPEED_1000 | \ + MAC_MCR_FORCE_DPX | MAC_MCR_FORCE_LINK) + +/* GPIO port control registers for GMAC 2*/ +#define GPIO_OD33_CTRL8 0x4c0 +#define GPIO_BIAS_CTRL 0xed0 +#define GPIO_DRV_SEL10 0xf00 + +/* ethernet subsystem config register */ +#define ETHSYS_SYSCFG0 0x14 +#define SYSCFG0_GE_MASK 0x3 +#define SYSCFG0_GE_MODE(x, y) (x << (12 + (y * 2))) + +struct mtk_rx_dma { + unsigned int rxd1; + unsigned int rxd2; + unsigned int rxd3; + unsigned int rxd4; +} __packed __aligned(4); + +struct mtk_tx_dma { + unsigned int txd1; + unsigned int txd2; + unsigned int txd3; + unsigned int txd4; +} __packed __aligned(4); + +struct mtk_eth; +struct mtk_mac; + +/* struct mtk_hw_stats - the structure that holds the traffic statistics. + * @stats_lock: make sure that stats operations are atomic + * @reg_offset: the status register offset of the SoC + * @syncp: the refcount + * + * All of the supported SoCs have hardware counters for traffic statistics. + * Whenever the status IRQ triggers we can read the latest stats from these + * counters and store them in this struct. + */ +struct mtk_hw_stats { + u64 tx_bytes; + u64 tx_packets; + u64 tx_skip; + u64 tx_collisions; + u64 rx_bytes; + u64 rx_packets; + u64 rx_overflow; + u64 rx_fcs_errors; + u64 rx_short_errors; + u64 rx_long_errors; + u64 rx_checksum_errors; + u64 rx_flow_control_packets; + + spinlock_t stats_lock; + u32 reg_offset; + struct u64_stats_sync syncp; +}; + +/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how + * memory was allocated so that it can be freed properly + */ +enum mtk_tx_flags { + MTK_TX_FLAGS_SINGLE0 = 0x01, + MTK_TX_FLAGS_PAGE0 = 0x02, +}; + +/* struct mtk_tx_buf - This struct holds the pointers to the memory pointed at + * by the TX descriptor s + * @skb: The SKB pointer of the packet being sent + * @dma_addr0: The base addr of the first segment + * @dma_len0: The length of the first segment + * @dma_addr1: The base addr of the second segment + * @dma_len1: The length of the second segment + */ +struct mtk_tx_buf { + struct sk_buff *skb; + u32 flags; + DEFINE_DMA_UNMAP_ADDR(dma_addr0); + DEFINE_DMA_UNMAP_LEN(dma_len0); + DEFINE_DMA_UNMAP_ADDR(dma_addr1); + DEFINE_DMA_UNMAP_LEN(dma_len1); +}; + +/* struct mtk_tx_ring - This struct holds info describing a TX ring + * @dma: The descriptor ring + * @buf: The memory pointed at by the ring + * @phys: The physical addr of tx_buf + * @next_free: Pointer to the next free descriptor + * @last_free: Pointer to the last free descriptor + * @thresh: The threshold of minimum amount of free descriptors + * @free_count: QDMA uses a linked list. Track how many free descriptors + * are present + */ +struct mtk_tx_ring { + struct mtk_tx_dma *dma; + struct mtk_tx_buf *buf; + dma_addr_t phys; + struct mtk_tx_dma *next_free; + struct mtk_tx_dma *last_free; + u16 thresh; + atomic_t free_count; +}; + +/* struct mtk_rx_ring - This struct holds info describing a RX ring + * @dma: The descriptor ring + * @data: The memory pointed at by the ring + * @phys: The physical addr of rx_buf + * @frag_size: How big can each fragment be + * @buf_size: The size of each packet buffer + * @calc_idx: The current head of ring + */ +struct mtk_rx_ring { + struct mtk_rx_dma *dma; + u8 **data; + dma_addr_t phys; + u16 frag_size; + u16 buf_size; + u16 calc_idx; +}; + +/* currently no SoC has more than 2 macs */ +#define MTK_MAX_DEVS 2 + +/* struct mtk_eth - This is the main datasructure for holding the state + * of the driver + * @dev: The device pointer + * @base: The mapped register i/o base + * @page_lock: Make sure that register operations are atomic + * @dummy_dev: we run 2 netdevs on 1 physical DMA ring and need a + * dummy for NAPI to work + * @netdev: The netdev instances + * @mac: Each netdev is linked to a physical MAC + * @irq: The IRQ that we are using + * @msg_enable: Ethtool msg level + * @ethsys: The register map pointing at the range used to setup + * MII modes + * @pctl: The register map pointing at the range used to setup + * GMAC port drive/slew values + * @dma_refcnt: track how many netdevs are using the DMA engine + * @tx_ring: Pointer to the memore holding info about the TX ring + * @rx_ring: Pointer to the memore holding info about the RX ring + * @rx_napi: The NAPI struct + * @scratch_ring: Newer SoCs need memory for a second HW managed TX ring + * @scratch_head: The scratch memory that scratch_ring points to. + * @clk_ethif: The ethif clock + * @clk_esw: The switch clock + * @clk_gp1: The gmac1 clock + * @clk_gp2: The gmac2 clock + * @mii_bus: If there is a bus we need to create an instance for it + */ + +struct mtk_eth { + struct device *dev; + void __iomem *base; + struct reset_control *rstc; + spinlock_t page_lock; + struct net_device dummy_dev; + struct net_device *netdev[MTK_MAX_DEVS]; + struct mtk_mac *mac[MTK_MAX_DEVS]; + int irq; + u32 msg_enable; + unsigned long sysclk; + struct regmap *ethsys; + struct regmap *pctl; + atomic_t dma_refcnt; + struct mtk_tx_ring tx_ring; + struct mtk_rx_ring rx_ring; + struct napi_struct rx_napi; + struct mtk_tx_dma *scratch_ring; + void *scratch_head; + struct clk *clk_ethif; + struct clk *clk_esw; + struct clk *clk_gp1; + struct clk *clk_gp2; + struct mii_bus *mii_bus; +}; + +/* struct mtk_mac - the structure that holds the info about the MACs of the + * SoC + * @id: The number of the MAC + * @of_node: Our devicetree node + * @hw: Backpointer to our main datastruture + * @hw_stats: Packet statistics counter + * @phy_dev: The attached PHY if available + * @pending_work: The workqueue used to reset the dma ring + */ +struct mtk_mac { + int id; + struct device_node *of_node; + struct mtk_eth *hw; + struct mtk_hw_stats *hw_stats; + struct phy_device *phy_dev; + struct work_struct pending_work; +}; + +/* the struct describing the SoC. these are declared in the soc_xyz.c files */ +extern const struct of_device_id of_mtk_match[]; + +/* read the hardware status register */ +void mtk_stats_update_mac(struct mtk_mac *mac); + +void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg); +u32 mtk_r32(struct mtk_eth *eth, unsigned reg); + +#endif /* MTK_ETH_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 16b26d17c54c..b4b258c8ca47 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2258,7 +2258,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) struct mlx4_en_dev *mdev = en_priv->mdev; u64 mac_u64 = mlx4_mac_to_u64(mac); - if (!is_valid_ether_addr(mac)) + if (is_multicast_ether_addr(mac)) return -EINVAL; return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index b8a51515e73c..503ec23e84cc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1272,6 +1272,7 @@ err_set_port: static int mlx4_mf_bond(struct mlx4_dev *dev) { int err = 0; + int nvfs; struct mlx4_slaves_pport slaves_port1; struct mlx4_slaves_pport slaves_port2; DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX); @@ -1288,11 +1289,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev) return -EINVAL; } + /* number of virtual functions is number of total functions minus one + * physical function for each port. + */ + nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + + bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2; + /* limit on maximum allowed VFs */ - if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + - bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) > - MAX_MF_BOND_ALLOWED_SLAVES) + if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) { + mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n", + nvfs, MAX_MF_BOND_ALLOWED_SLAVES); return -EINVAL; + } if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) { mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n"); diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 787b7bb54d52..211c65087997 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -193,10 +193,10 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -389,10 +389,10 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -479,10 +479,10 @@ int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -588,10 +588,10 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -764,10 +764,10 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 11b592dbf16a..4fc45ee0c5d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -6,6 +6,6 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \ en_main.o en_fs.o en_ethtool.o en_tx.o en_rx.o \ - en_txrx.o en_clock.o vxlan.o + en_txrx.o en_clock.o vxlan.o en_tc.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 9c0e80e64b43..0f76d321030f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -43,6 +43,7 @@ #include <linux/mlx5/port.h> #include <linux/mlx5/vport.h> #include <linux/mlx5/transobj.h> +#include <linux/rhashtable.h> #include "wq.h" #include "mlx5_core.h" @@ -237,6 +238,7 @@ struct mlx5e_pport_stats { static const char rq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "csum_none", "csum_sw", "lro_packets", @@ -246,16 +248,18 @@ static const char rq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_rq_stats { u64 packets; + u64 bytes; u64 csum_none; u64 csum_sw; u64 lro_packets; u64 lro_bytes; u64 wqe_err; -#define NUM_RQ_STATS 6 +#define NUM_RQ_STATS 7 }; static const char sq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "tso_packets", "tso_bytes", "tso_inner_packets", @@ -271,6 +275,7 @@ static const char sq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_sq_stats { /* commonly accessed in data path */ u64 packets; + u64 bytes; u64 tso_packets; u64 tso_bytes; u64 tso_inner_packets; @@ -282,7 +287,7 @@ struct mlx5e_sq_stats { u64 stopped; u64 wake; u64 dropped; -#define NUM_SQ_STATS 11 +#define NUM_SQ_STATS 12 }; struct mlx5e_stats { @@ -328,14 +333,9 @@ enum { MLX5E_RQ_STATE_POST_WQES_ENABLE, }; -enum cq_flags { - MLX5E_CQ_HAS_CQES = 1, -}; - struct mlx5e_cq { /* data path - accessed per cqe */ struct mlx5_cqwq wq; - unsigned long flags; /* data path - accessed per napi poll */ struct napi_struct *napi; @@ -476,6 +476,8 @@ enum mlx5e_traffic_types { MLX5E_NUM_TT, }; +#define IS_HASHING_TT(tt) (tt != MLX5E_TT_ANY) + enum mlx5e_rqt_ix { MLX5E_INDIRECTION_RQT, MLX5E_SINGLE_RQ_RQT, @@ -526,8 +528,16 @@ struct mlx5e_flow_table { struct mlx5_flow_group **g; }; +struct mlx5e_tc_flow_table { + struct mlx5_flow_table *t; + + struct rhashtable_params ht_params; + struct rhashtable ht; +}; + struct mlx5e_flow_tables { struct mlx5_flow_namespace *ns; + struct mlx5e_tc_flow_table tc; struct mlx5e_flow_table vlan; struct mlx5e_flow_table main; }; @@ -646,9 +656,12 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); int mlx5e_redirect_rqt(struct mlx5e_priv *priv, enum mlx5e_rqt_ix rqt_ix); +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv); int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels); static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, struct mlx5e_tx_wqe *wqe, int bf_sz) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index be6543570b2b..2018eebe1531 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -62,10 +62,11 @@ static void mlx5e_timestamp_overflow(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, overflow_work); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period); } @@ -136,10 +137,11 @@ static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns = timespec64_to_ns(ts); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_init(&tstamp->clock, &tstamp->cycles, ns); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -150,10 +152,11 @@ static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns; + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); ns = timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); *ts = ns_to_timespec64(ns); @@ -164,10 +167,11 @@ static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_adjtime(&tstamp->clock, delta); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -176,6 +180,7 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) { u64 adj; u32 diff; + unsigned long flags; int neg_adj = 0; struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); @@ -189,11 +194,11 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : tstamp->nominal_c_mult + diff; - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 0959656404b3..68834b715f6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -386,6 +386,8 @@ static int mlx5e_set_channels(struct net_device *dev, mlx5e_close_locked(dev); priv->params.num_channels = count; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); if (was_opened) err = mlx5e_open_locked(dev); @@ -716,18 +718,36 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return 0; } +static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen) +{ + struct mlx5_core_dev *mdev = priv->mdev; + void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx); + int i; + + MLX5_SET(modify_tir_in, in, bitmask.hash, 1); + mlx5e_build_tir_ctx_hash(tirc, priv); + + for (i = 0; i < MLX5E_NUM_TT; i++) + if (IS_HASHING_TT(i)) + mlx5_core_modify_tir(mdev, priv->tirn[i], in, inlen); +} + static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc) { struct mlx5e_priv *priv = netdev_priv(dev); - bool close_open; - int err = 0; + int inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + void *in; if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_XOR) && (hfunc != ETH_RSS_HASH_TOP)) return -EINVAL; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + mutex_lock(&priv->state_lock); if (indir) { @@ -736,11 +756,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, mlx5e_redirect_rqt(priv, MLX5E_INDIRECTION_RQT); } - close_open = (key || (hfunc != ETH_RSS_HASH_NO_CHANGE)) && - test_bit(MLX5E_STATE_OPENED, &priv->state); - if (close_open) - mlx5e_close_locked(dev); - if (key) memcpy(priv->params.toeplitz_hash_key, key, sizeof(priv->params.toeplitz_hash_key)); @@ -748,12 +763,13 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE) priv->params.rss_hfunc = hfunc; - if (close_open) - err = mlx5e_open_locked(priv->netdev); + mlx5e_modify_tirs_hash(priv, in, inlen); mutex_unlock(&priv->state_lock); - return err; + kvfree(in); + + return 0; } static int mlx5e_get_rxnfc(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 80d81abc4820..d00a24203410 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -1041,7 +1041,7 @@ static int mlx5e_create_main_flow_table(struct mlx5e_priv *priv) int err; ft->num_groups = 0; - ft->t = mlx5_create_flow_table(priv->fts.ns, 0, MLX5E_MAIN_TABLE_SIZE); + ft->t = mlx5_create_flow_table(priv->fts.ns, 1, MLX5E_MAIN_TABLE_SIZE); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); @@ -1150,7 +1150,7 @@ static int mlx5e_create_vlan_flow_table(struct mlx5e_priv *priv) int err; ft->num_groups = 0; - ft->t = mlx5_create_flow_table(priv->fts.ns, 0, MLX5E_VLAN_TABLE_SIZE); + ft->t = mlx5_create_flow_table(priv->fts.ns, 1, MLX5E_VLAN_TABLE_SIZE); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5063c0e0f8ac..ac5807803c84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -30,9 +30,12 @@ * SOFTWARE. */ +#include <net/tc_act/tc_gact.h> +#include <net/pkt_cls.h> #include <linux/mlx5/fs.h> #include <net/vxlan.h> #include "en.h" +#include "en_tc.h" #include "eswitch.h" #include "vxlan.h" @@ -143,6 +146,10 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) return; /* Collect firts the SW counters and then HW for consistency */ + s->rx_packets = 0; + s->rx_bytes = 0; + s->tx_packets = 0; + s->tx_bytes = 0; s->tso_packets = 0; s->tso_bytes = 0; s->tso_inner_packets = 0; @@ -160,6 +167,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (i = 0; i < priv->params.num_channels; i++) { rq_stats = &priv->channel[i]->rq.stats; + s->rx_packets += rq_stats->packets; + s->rx_bytes += rq_stats->bytes; s->lro_packets += rq_stats->lro_packets; s->lro_bytes += rq_stats->lro_bytes; s->rx_csum_none += rq_stats->csum_none; @@ -169,6 +178,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (j = 0; j < priv->params.num_tc; j++) { sq_stats = &priv->channel[i]->sq[j].stats; + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; s->tso_packets += sq_stats->tso_packets; s->tso_bytes += sq_stats->tso_bytes; s->tso_inner_packets += sq_stats->tso_inner_packets; @@ -233,23 +244,6 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) s->tx_broadcast_bytes = MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); - s->rx_packets = - s->rx_unicast_packets + - s->rx_multicast_packets + - s->rx_broadcast_packets; - s->rx_bytes = - s->rx_unicast_bytes + - s->rx_multicast_bytes + - s->rx_broadcast_bytes; - s->tx_packets = - s->tx_unicast_packets + - s->tx_multicast_packets + - s->tx_broadcast_packets; - s->tx_bytes = - s->tx_unicast_bytes + - s->tx_multicast_bytes + - s->tx_broadcast_bytes; - /* Update calculated offload counters */ s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner; s->rx_csum_good = s->rx_packets - s->rx_csum_none - @@ -1211,7 +1205,6 @@ static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc) ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE); ix = priv->params.indirection_rqt[ix]; - ix = ix % priv->params.num_channels; MLX5_SET(rqtc, rqtc, rq_num[i], test_bit(MLX5E_STATE_OPENED, &priv->state) ? priv->channel[ix]->rq.rqn : @@ -1329,7 +1322,22 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv) lro_timer_supported_periods[2])); } -static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv) +{ + MLX5_SET(tirc, tirc, rx_hash_fn, + mlx5e_rx_hash_fn(priv->params.rss_hfunc)); + if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { + void *rss_key = MLX5_ADDR_OF(tirc, tirc, + rx_hash_toeplitz_key); + size_t len = MLX5_FLD_SZ_BYTES(tirc, + rx_hash_toeplitz_key); + + MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); + memcpy(rss_key, priv->params.toeplitz_hash_key, len); + } +} + +static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -1337,6 +1345,7 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) void *tirc; int inlen; int err; + int tt; inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = mlx5_vzalloc(inlen); @@ -1348,7 +1357,11 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) mlx5e_build_tir_ctx_lro(tirc, priv); - err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + for (tt = 0; tt < MLX5E_NUM_TT; tt++) { + err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + if (err) + break; + } kvfree(in); @@ -1703,17 +1716,7 @@ static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt) default: MLX5_SET(tirc, tirc, indirect_table, priv->rqtn[MLX5E_INDIRECTION_RQT]); - MLX5_SET(tirc, tirc, rx_hash_fn, - mlx5e_rx_hash_fn(priv->params.rss_hfunc)); - if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { - void *rss_key = MLX5_ADDR_OF(tirc, tirc, - rx_hash_toeplitz_key); - size_t len = MLX5_FLD_SZ_BYTES(tirc, - rx_hash_toeplitz_key); - - MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); - memcpy(rss_key, priv->params.toeplitz_hash_key, len); - } + mlx5e_build_tir_ctx_hash(tirc, priv); break; } @@ -1883,7 +1886,25 @@ static int mlx5e_setup_tc(struct net_device *netdev, u8 tc) static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle, __be16 proto, struct tc_to_netdev *tc) { - if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) + struct mlx5e_priv *priv = netdev_priv(dev); + + if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS)) + goto mqprio; + + switch (tc->type) { + case TC_SETUP_CLSFLOWER: + switch (tc->cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return mlx5e_configure_flower(priv, proto, tc->cls_flower); + case TC_CLSFLOWER_DESTROY: + return mlx5e_delete_flower(priv, tc->cls_flower); + } + default: + return -EOPNOTSUPP; + } + +mqprio: + if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; return mlx5e_setup_tc(dev, tc->tc); @@ -1950,8 +1971,10 @@ static int mlx5e_set_features(struct net_device *netdev, mlx5e_close_locked(priv->netdev); priv->params.lro_en = !!(features & NETIF_F_LRO); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV4_TCP); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV6_TCP); + err = mlx5e_modify_tirs_lro(priv); + if (err) + mlx5_core_warn(priv->mdev, "lro modify failed, %d\n", + err); if (was_opened) err = mlx5e_open_locked(priv->netdev); @@ -1966,6 +1989,13 @@ static int mlx5e_set_features(struct net_device *netdev, mlx5e_disable_vlan_filter(priv); } + if ((changes & NETIF_F_HW_TC) && !(features & NETIF_F_HW_TC) && + mlx5e_tc_num_filters(priv)) { + netdev_err(netdev, + "Active offloaded tc filters, can't turn hw_tc_offload off\n"); + return -EINVAL; + } + return err; } @@ -2253,12 +2283,20 @@ static void mlx5e_ets_init(struct mlx5e_priv *priv) } #endif +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels) +{ + int i; + + for (i = 0; i < len; i++) + indirection_rqt[i] = i % num_channels; +} + static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, struct net_device *netdev, int num_channels) { struct mlx5e_priv *priv = netdev_priv(netdev); - int i; priv->params.log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; @@ -2281,8 +2319,8 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, netdev_rss_key_fill(priv->params.toeplitz_hash_key, sizeof(priv->params.toeplitz_hash_key)); - for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) - priv->params.indirection_rqt[i] = i % num_channels; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, num_channels); priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; @@ -2365,6 +2403,13 @@ static void mlx5e_build_netdev(struct net_device *netdev) if (!priv->params.lro_en) netdev->features &= ~NETIF_F_LRO; +#define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f) + if (FT_CAP(flow_modify_en) && + FT_CAP(modify_root) && + FT_CAP(identified_miss_table_mode) && + FT_CAP(flow_table_modify)) + priv->netdev->hw_features |= NETIF_F_HW_TC; + netdev->features |= NETIF_F_HIGHDMA; netdev->priv_flags |= IFF_UNICAST_FLT; @@ -2486,6 +2531,10 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) mlx5e_vxlan_init(priv); + err = mlx5e_tc_init(priv); + if (err) + goto err_destroy_flow_tables; + #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_ieee_setets_core(priv, &priv->params.ets); #endif @@ -2493,7 +2542,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); - goto err_destroy_flow_tables; + goto err_tc_cleanup; } if (mlx5e_vxlan_allowed(mdev)) @@ -2504,6 +2553,9 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) return priv; +err_tc_cleanup: + mlx5e_tc_cleanup(priv); + err_destroy_flow_tables: mlx5e_destroy_flow_tables(priv); @@ -2551,6 +2603,7 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) mlx5e_disable_async_events(priv); flush_scheduled_work(); unregister_netdev(netdev); + mlx5e_tc_cleanup(priv); mlx5e_vxlan_cleanup(priv); mlx5e_destroy_flow_tables(priv); mlx5e_destroy_tirs(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 519a07f253f9..58d4e2f962c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -35,6 +35,7 @@ #include <linux/tcp.h> #include <net/busy_poll.h> #include "en.h" +#include "en_tc.h" static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp) { @@ -224,6 +225,8 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, if (cqe_has_vlan(cqe)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->vlan_info)); + + skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK; } int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) @@ -231,10 +234,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); int work_done; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return 0; - for (work_done = 0; work_done < budget; work_done++) { struct mlx5e_rx_wqe *wqe; struct mlx5_cqe64 *cqe; @@ -268,6 +267,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) mlx5e_build_rx_skb(cqe, rq, skb); rq->stats.packets++; + rq->stats.bytes += be32_to_cpu(cqe->byte_cnt); napi_gro_receive(cq->napi, skb); wq_ll_pop: @@ -280,8 +280,5 @@ wq_ll_pop: /* ensure cq space is freed before enabling more cqes */ wmb(); - if (work_done == budget) - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c new file mode 100644 index 000000000000..b3de09f13425 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -0,0 +1,429 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <net/flow_dissector.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_skbedit.h> +#include <linux/mlx5/fs.h> +#include <linux/mlx5/device.h> +#include <linux/rhashtable.h> +#include "en.h" +#include "en_tc.h" + +struct mlx5e_tc_flow { + struct rhash_head node; + u64 cookie; + struct mlx5_flow_rule *rule; +}; + +#define MLX5E_TC_FLOW_TABLE_NUM_ENTRIES 1024 +#define MLX5E_TC_FLOW_TABLE_NUM_GROUPS 4 + +static struct mlx5_flow_rule *mlx5e_tc_add_flow(struct mlx5e_priv *priv, + u32 *match_c, u32 *match_v, + u32 action, u32 flow_tag) +{ + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + {.ft = priv->fts.vlan.t}, + }; + struct mlx5_flow_rule *rule; + bool table_created = false; + + if (IS_ERR_OR_NULL(priv->fts.tc.t)) { + priv->fts.tc.t = + mlx5_create_auto_grouped_flow_table(priv->fts.ns, 0, + MLX5E_TC_FLOW_TABLE_NUM_ENTRIES, + MLX5E_TC_FLOW_TABLE_NUM_GROUPS); + if (IS_ERR(priv->fts.tc.t)) { + netdev_err(priv->netdev, + "Failed to create tc offload table\n"); + return ERR_CAST(priv->fts.tc.t); + } + + table_created = true; + } + + rule = mlx5_add_flow_rule(priv->fts.tc.t, MLX5_MATCH_OUTER_HEADERS, + match_c, match_v, + action, flow_tag, + action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST ? &dest : NULL); + + if (IS_ERR(rule) && table_created) { + mlx5_destroy_flow_table(priv->fts.tc.t); + priv->fts.tc.t = NULL; + } + + return rule; +} + +static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, + struct mlx5_flow_rule *rule) +{ + mlx5_del_flow_rule(rule); + + if (!mlx5e_tc_num_filters(priv)) { + mlx5_destroy_flow_table(priv->fts.tc.t); + priv->fts.tc.t = NULL; + } +} + +static int parse_cls_flower(struct mlx5e_priv *priv, + u32 *match_c, u32 *match_v, + struct tc_cls_flower_offload *f) +{ + void *headers_c = MLX5_ADDR_OF(fte_match_param, match_c, outer_headers); + void *headers_v = MLX5_ADDR_OF(fte_match_param, match_v, outer_headers); + u16 addr_type = 0; + u8 ip_proto = 0; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS))) { + netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", + f->dissector->used_keys); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + addr_type = key->addr_type; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + ip_proto = key->ip_proto; + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, + ntohs(mask->n_proto)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, + ntohs(key->n_proto)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol, + mask->ip_proto); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, + key->ip_proto); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + struct flow_dissector_key_eth_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + dmac_47_16), + mask->dst); + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dmac_47_16), + key->dst); + + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + smac_47_16), + mask->src); + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + smac_47_16), + key->src); + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->mask); + + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + src_ipv4_src_ipv6.ipv4_layout.ipv4), + &mask->src, sizeof(mask->src)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + src_ipv4_src_ipv6.ipv4_layout.ipv4), + &key->src, sizeof(key->src)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &mask->dst, sizeof(mask->dst)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &key->dst, sizeof(key->dst)); + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_dissector_key_ipv6_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->key); + struct flow_dissector_key_ipv6_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->mask); + + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + &mask->src, sizeof(mask->src)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + &key->src, sizeof(key->src)); + + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &mask->dst, sizeof(mask->dst)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &key->dst, sizeof(key->dst)); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->mask); + switch (ip_proto) { + case IPPROTO_TCP: + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + tcp_sport, ntohs(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + tcp_sport, ntohs(key->src)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + tcp_dport, ntohs(mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + tcp_dport, ntohs(key->dst)); + break; + + case IPPROTO_UDP: + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + udp_sport, ntohs(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + udp_sport, ntohs(key->src)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + udp_dport, ntohs(mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + udp_dport, ntohs(key->dst)); + break; + default: + netdev_err(priv->netdev, + "Only UDP and TCP transport are supported\n"); + return -EINVAL; + } + } + + return 0; +} + +static int parse_tc_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, + u32 *action, u32 *flow_tag) +{ + const struct tc_action *a; + + if (tc_no_actions(exts)) + return -EINVAL; + + *flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; + *action = 0; + + tc_for_each_action(a, exts) { + /* Only support a single action per rule */ + if (*action) + return -EINVAL; + + if (is_tcf_gact_shot(a)) { + *action |= MLX5_FLOW_CONTEXT_ACTION_DROP; + continue; + } + + if (is_tcf_skbedit_mark(a)) { + u32 mark = tcf_skbedit_mark(a); + + if (mark & ~MLX5E_TC_FLOW_ID_MASK) { + netdev_warn(priv->netdev, "Bad flow mark - only 16 bit is supported: 0x%x\n", + mark); + return -EINVAL; + } + + *flow_tag = mark; + *action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + continue; + } + + return -EINVAL; + } + + return 0; +} + +int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, + struct tc_cls_flower_offload *f) +{ + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + u32 *match_c; + u32 *match_v; + int err = 0; + u32 flow_tag; + u32 action; + struct mlx5e_tc_flow *flow; + struct mlx5_flow_rule *old = NULL; + + flow = rhashtable_lookup_fast(&tc->ht, &f->cookie, + tc->ht_params); + if (flow) + old = flow->rule; + else + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + + match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL); + match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL); + if (!match_c || !match_v || !flow) { + err = -ENOMEM; + goto err_free; + } + + flow->cookie = f->cookie; + + err = parse_cls_flower(priv, match_c, match_v, f); + if (err < 0) + goto err_free; + + err = parse_tc_actions(priv, f->exts, &action, &flow_tag); + if (err < 0) + goto err_free; + + err = rhashtable_insert_fast(&tc->ht, &flow->node, + tc->ht_params); + if (err) + goto err_free; + + flow->rule = mlx5e_tc_add_flow(priv, match_c, match_v, action, + flow_tag); + if (IS_ERR(flow->rule)) { + err = PTR_ERR(flow->rule); + goto err_hash_del; + } + + if (old) + mlx5e_tc_del_flow(priv, old); + + goto out; + +err_hash_del: + rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params); + +err_free: + if (!old) + kfree(flow); +out: + kfree(match_c); + kfree(match_v); + return err; +} + +int mlx5e_delete_flower(struct mlx5e_priv *priv, + struct tc_cls_flower_offload *f) +{ + struct mlx5e_tc_flow *flow; + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + + flow = rhashtable_lookup_fast(&tc->ht, &f->cookie, + tc->ht_params); + if (!flow) + return -EINVAL; + + rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params); + + mlx5e_tc_del_flow(priv, flow->rule); + + kfree(flow); + + return 0; +} + +static const struct rhashtable_params mlx5e_tc_flow_ht_params = { + .head_offset = offsetof(struct mlx5e_tc_flow, node), + .key_offset = offsetof(struct mlx5e_tc_flow, cookie), + .key_len = sizeof(((struct mlx5e_tc_flow *)0)->cookie), + .automatic_shrinking = true, +}; + +int mlx5e_tc_init(struct mlx5e_priv *priv) +{ + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + + tc->ht_params = mlx5e_tc_flow_ht_params; + return rhashtable_init(&tc->ht, &tc->ht_params); +} + +static void _mlx5e_tc_del_flow(void *ptr, void *arg) +{ + struct mlx5e_tc_flow *flow = ptr; + struct mlx5e_priv *priv = arg; + + mlx5e_tc_del_flow(priv, flow->rule); + kfree(flow); +} + +void mlx5e_tc_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + + rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, priv); + + if (!IS_ERR_OR_NULL(priv->fts.tc.t)) { + mlx5_destroy_flow_table(priv->fts.tc.t); + priv->fts.tc.t = NULL; + } +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h new file mode 100644 index 000000000000..d677428dc10f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -0,0 +1,51 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_EN_TC_H__ +#define __MLX5_EN_TC_H__ + +#define MLX5E_TC_FLOW_ID_MASK 0x0000ffff + +int mlx5e_tc_init(struct mlx5e_priv *priv); +void mlx5e_tc_cleanup(struct mlx5e_priv *priv); + +int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, + struct tc_cls_flower_offload *f); +int mlx5e_delete_flower(struct mlx5e_priv *priv, + struct tc_cls_flower_offload *f); + +static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) +{ + return atomic_read(&priv->fts.tc.ht.nelems); +} + +#endif /* __MLX5_EN_TC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index c34f4f3e9537..94a14f85f70d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -177,6 +177,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) unsigned int skb_len = skb->len; u8 opcode = MLX5_OPCODE_SEND; dma_addr_t dma_addr = 0; + unsigned int num_bytes; bool bf = false; u16 headlen; u16 ds_cnt; @@ -216,16 +217,17 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->stats.tso_bytes += skb->len - ihs; } - wi->num_bytes = skb->len + - (skb_shinfo(skb)->gso_segs - 1) * ihs; + num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; } else { bf = sq->bf_budget && !skb->xmit_more && !skb_shinfo(skb)->nr_frags; ihs = mlx5e_get_inline_hdr_size(sq, skb, bf); - wi->num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); } + wi->num_bytes = num_bytes; + if (skb_vlan_tag_present(skb)) { mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs, &skb_data, &skb_len); @@ -317,6 +319,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->bf_budget = bf ? sq->bf_budget - 1 : 0; sq->stats.packets++; + sq->stats.bytes += num_bytes; return NETDEV_TX_OK; dma_unmap_wqe_err: @@ -345,10 +348,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) u16 sqcc; int i; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return false; - sq = container_of(cq, struct mlx5e_sq, cq); npkts = 0; @@ -432,10 +431,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) netif_tx_wake_queue(sq->txq); sq->stats.wake++; } - if (i == MLX5E_TX_CQ_POLL_BUDGET) { - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return true; - } - return false; + return (i == MLX5E_TX_CQ_POLL_BUDGET); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 4ac8d716dbdd..66d51a77609e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -88,7 +88,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq) { struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags); barrier(); napi_schedule(cq->napi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index a9894d2e8e26..f46f1db0fc00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -218,19 +218,22 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, match_value); memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param)); - in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); - list_for_each_entry(dst, &fte->node.children, node.list) { - unsigned int id; - - MLX5_SET(dest_format_struct, in_dests, destination_type, - dst->dest_attr.type); - if (dst->dest_attr.type == - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) - id = dst->dest_attr.ft->id; - else - id = dst->dest_attr.tir_num; - MLX5_SET(dest_format_struct, in_dests, destination_id, id); - in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); + if (fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); + list_for_each_entry(dst, &fte->node.children, node.list) { + unsigned int id; + + MLX5_SET(dest_format_struct, in_dests, destination_type, + dst->dest_attr.type); + if (dst->dest_attr.type == + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) { + id = dst->dest_attr.ft->id; + } else { + id = dst->dest_attr.tir_num; + } + MLX5_SET(dest_format_struct, in_dests, destination_id, id); + in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); + } } memset(out, 0, sizeof(out)); err = mlx5_cmd_exec_check_status(dev, in, inlen, out, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 6f68dba8d7ed..e848d708d2b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -73,8 +73,8 @@ #define BY_PASS_MIN_LEVEL (KENREL_MIN_LEVEL + MLX5_BY_PASS_NUM_PRIOS +\ LEFTOVERS_MAX_FT) -#define KERNEL_MAX_FT 2 -#define KERNEL_NUM_PRIOS 1 +#define KERNEL_MAX_FT 3 +#define KERNEL_NUM_PRIOS 2 #define KENREL_MIN_LEVEL 2 struct node_caps { @@ -360,8 +360,8 @@ static void del_rule(struct fs_node *node) memcpy(match_value, fte->val, sizeof(fte->val)); fs_get_obj(ft, fg->node.parent); list_del(&rule->node.list); - fte->dests_size--; - if (fte->dests_size) { + if ((fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && + --fte->dests_size) { err = mlx5_cmd_update_fte(dev, ft, fg->id, fte); if (err) @@ -763,7 +763,8 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest) return NULL; rule->node.type = FS_TYPE_FLOW_DEST; - memcpy(&rule->dest_attr, dest, sizeof(*dest)); + if (dest) + memcpy(&rule->dest_attr, dest, sizeof(*dest)); return rule; } @@ -785,8 +786,9 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte, /* Add dest to dests list- added as first element after the head */ tree_init_node(&rule->node, 1, del_rule); list_add_tail(&rule->node.list, &fte->node.children); - fte->dests_size++; - if (fte->dests_size == 1) + if (dest) + fte->dests_size++; + if (fte->dests_size == 1 || !dest) err = mlx5_cmd_create_fte(get_dev(&ft->node), ft, fg->id, fte); else @@ -802,7 +804,8 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte, free_rule: list_del(&rule->node.list); kfree(rule); - fte->dests_size--; + if (dest) + fte->dests_size--; return ERR_PTR(err); } @@ -996,6 +999,9 @@ mlx5_add_flow_rule(struct mlx5_flow_table *ft, struct mlx5_flow_group *g; struct mlx5_flow_rule *rule; + if ((action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && !dest) + return ERR_PTR(-EINVAL); + nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); fs_for_each_fg(g, ft) if (compare_match_criteria(g->mask.match_criteria_enable, diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c071077aafbd..7992c553c1f5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -215,7 +215,7 @@ mlxsw_pci_queue_elem_info_producer_get(struct mlxsw_pci_queue *q) { int index = q->producer_counter & (q->count - 1); - if ((q->producer_counter - q->consumer_counter) == q->count) + if ((u16) (q->producer_counter - q->consumer_counter) == q->count) return NULL; return mlxsw_pci_queue_elem_info_get(q, index); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 53487d3eb9f6..4afbc3e9e381 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2592,9 +2592,7 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, if (mlxsw_sp_port->bridged) { mlxsw_sp_port_active_vlans_del(mlxsw_sp_port); mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false); - - if (lag->ref_count == 1) - mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); + mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); } if (lag->ref_count == 1) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 1b691d7e4a2a..4b8abaf06321 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -123,6 +123,8 @@ struct mlxsw_sp { #define MLXSW_SP_DEFAULT_LEARNING_INTERVAL 100 unsigned int interval; /* ms */ } fdb_notify; +#define MLXSW_SP_MIN_AGEING_TIME 10 +#define MLXSW_SP_MAX_AGEING_TIME 1000000 #define MLXSW_SP_DEFAULT_AGEING_TIME 300 u32 ageing_time; struct mlxsw_sp_upper master_bridge; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 7b56098acc58..e1c74efff51a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -311,8 +311,13 @@ static int mlxsw_sp_port_attr_br_ageing_set(struct mlxsw_sp_port *mlxsw_sp_port, unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t); u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000; - if (switchdev_trans_ph_prepare(trans)) - return 0; + if (switchdev_trans_ph_prepare(trans)) { + if (ageing_time < MLXSW_SP_MIN_AGEING_TIME || + ageing_time > MLXSW_SP_MAX_AGEING_TIME) + return -ERANGE; + else + return 0; + } return mlxsw_sp_ageing_set(mlxsw_sp, ageing_time); } diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 00cfd95ca59d..3e67f451f2ab 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -474,9 +474,9 @@ static int moxart_mac_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ndev->base_addr = res->start; priv->base = devm_ioremap_resource(p_dev, res); - ret = IS_ERR(priv->base); - if (ret) { + if (IS_ERR(priv->base)) { dev_err(p_dev, "devm_ioremap_resource failed\n"); + ret = PTR_ERR(priv->base); goto init_fail; } diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index e5604eec81bf..fcb8e9ba51d9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -303,6 +303,9 @@ struct qed_hwfn { bool b_int_enabled; bool b_int_requested; + /* True if the driver requests for the link */ + bool b_drv_link_init; + struct qed_mcp_info *mcp_info; struct qed_hw_cid_data *p_tx_cids; diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 592e0e6d9b42..a368f5e71d95 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -2919,7 +2919,19 @@ struct eth_vport_rx_mode { }; struct eth_vport_tpa_param { - u64 reserved[2]; + u8 tpa_ipv4_en_flg; + u8 tpa_ipv6_en_flg; + u8 tpa_ipv4_tunn_en_flg; + u8 tpa_ipv6_tunn_en_flg; + u8 tpa_pkt_split_flg; + u8 tpa_hdr_data_split_flg; + u8 tpa_gro_consistent_flg; + u8 tpa_max_aggs_num; + u16 tpa_max_size; + u16 tpa_min_size_to_start; + u16 tpa_min_size_to_cont; + u8 max_buff_num; + u8 reserved; }; struct eth_vport_tx_mode { @@ -3609,6 +3621,9 @@ struct public_port { u32 fc_npiv_nvram_tbl_addr; u32 fc_npiv_nvram_tbl_size; u32 transceiver_data; +#define PMM_TRANSCEIVER_STATE_MASK 0x000000FF +#define PMM_TRANSCEIVER_STATE_SHIFT 0x00000000 +#define PMM_TRANSCEIVER_STATE_PRESENT 0x00000001 }; /**************************************/ @@ -3943,6 +3958,14 @@ enum MFW_DRV_MSG_TYPE { MFW_DRV_MSG_DCBX_REMOTE_MIB_UPDATED, MFW_DRV_MSG_DCBX_OPERATIONAL_MIB_UPDATED, MFW_DRV_MSG_ERROR_RECOVERY, + MFW_DRV_MSG_BW_UPDATE, + MFW_DRV_MSG_S_TAG_UPDATE, + MFW_DRV_MSG_GET_LAN_STATS, + MFW_DRV_MSG_GET_FCOE_STATS, + MFW_DRV_MSG_GET_ISCSI_STATS, + MFW_DRV_MSG_GET_RDMA_STATS, + MFW_DRV_MSG_FAILURE_DETECTED, + MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE, MFW_DRV_MSG_MAX }; diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 102ddc73b841..3f35c6ca9252 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -132,16 +132,29 @@ struct qed_sp_vport_update_params { struct qed_filter_accept_flags accept_flags; }; +enum qed_tpa_mode { + QED_TPA_MODE_NONE, + QED_TPA_MODE_UNUSED, + QED_TPA_MODE_GRO, + QED_TPA_MODE_MAX +}; + +struct qed_sp_vport_start_params { + enum qed_tpa_mode tpa_mode; + bool remove_inner_vlan; + bool drop_ttl0; + u8 max_buffers_per_cqe; + u32 concrete_fid; + u16 opaque_fid; + u8 vport_id; + u16 mtu; +}; + #define QED_MAX_SGES_NUM 16 #define CRC32_POLY 0x1edc6f41 static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, - u32 concrete_fid, - u16 opaque_fid, - u8 vport_id, - u16 mtu, - u8 drop_ttl0_flg, - u8 inner_vlan_removal_en_flg) + struct qed_sp_vport_start_params *p_params) { struct vport_start_ramrod_data *p_ramrod = NULL; struct qed_spq_entry *p_ent = NULL; @@ -150,13 +163,13 @@ static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, u16 rx_mode = 0; u8 abs_vport_id = 0; - rc = qed_fw_vport(p_hwfn, vport_id, &abs_vport_id); + rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id); if (rc != 0) return rc; memset(&init_data, 0, sizeof(init_data)); init_data.cid = qed_spq_get_cid(p_hwfn); - init_data.opaque_fid = opaque_fid; + init_data.opaque_fid = p_params->opaque_fid; init_data.comp_mode = QED_SPQ_MODE_EBLOCK; rc = qed_sp_init_request(p_hwfn, &p_ent, @@ -168,9 +181,9 @@ static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, p_ramrod = &p_ent->ramrod.vport_start; p_ramrod->vport_id = abs_vport_id; - p_ramrod->mtu = cpu_to_le16(mtu); - p_ramrod->inner_vlan_removal_en = inner_vlan_removal_en_flg; - p_ramrod->drop_ttl0_en = drop_ttl0_flg; + p_ramrod->mtu = cpu_to_le16(p_params->mtu); + p_ramrod->inner_vlan_removal_en = p_params->remove_inner_vlan; + p_ramrod->drop_ttl0_en = p_params->drop_ttl0; SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_UCAST_DROP_ALL, 1); SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_MCAST_DROP_ALL, 1); @@ -181,9 +194,26 @@ static int qed_sp_vport_start(struct qed_hwfn *p_hwfn, memset(&p_ramrod->tpa_param, 0, sizeof(struct eth_vport_tpa_param)); + p_ramrod->tpa_param.max_buff_num = p_params->max_buffers_per_cqe; + + switch (p_params->tpa_mode) { + case QED_TPA_MODE_GRO: + p_ramrod->tpa_param.tpa_max_aggs_num = ETH_TPA_MAX_AGGS_NUM; + p_ramrod->tpa_param.tpa_max_size = (u16)-1; + p_ramrod->tpa_param.tpa_min_size_to_cont = p_params->mtu / 2; + p_ramrod->tpa_param.tpa_min_size_to_start = p_params->mtu / 2; + p_ramrod->tpa_param.tpa_ipv4_en_flg = 1; + p_ramrod->tpa_param.tpa_ipv6_en_flg = 1; + p_ramrod->tpa_param.tpa_pkt_split_flg = 1; + p_ramrod->tpa_param.tpa_gro_consistent_flg = 1; + break; + default: + break; + } + /* Software Function ID in hwfn (PFs are 0 - 15, VFs are 16 - 135) */ p_ramrod->sw_fid = qed_concrete_to_sw_fid(p_hwfn->cdev, - concrete_fid); + p_params->concrete_fid); return qed_spq_post(p_hwfn, p_ent, NULL); } @@ -1592,24 +1622,25 @@ static void qed_register_eth_ops(struct qed_dev *cdev, } static int qed_start_vport(struct qed_dev *cdev, - u8 vport_id, - u16 mtu, - u8 drop_ttl0_flg, - u8 inner_vlan_removal_en_flg) + struct qed_start_vport_params *params) { int rc, i; for_each_hwfn(cdev, i) { + struct qed_sp_vport_start_params start = { 0 }; struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; - rc = qed_sp_vport_start(p_hwfn, - p_hwfn->hw_info.concrete_fid, - p_hwfn->hw_info.opaque_fid, - vport_id, - mtu, - drop_ttl0_flg, - inner_vlan_removal_en_flg); - + start.tpa_mode = params->gro_enable ? QED_TPA_MODE_GRO : + QED_TPA_MODE_NONE; + start.remove_inner_vlan = params->remove_inner_vlan; + start.drop_ttl0 = params->drop_ttl0; + start.opaque_fid = p_hwfn->hw_info.opaque_fid; + start.concrete_fid = p_hwfn->hw_info.concrete_fid; + start.vport_id = params->vport_id; + start.max_buffers_per_cqe = 16; + start.mtu = params->mtu; + + rc = qed_sp_vport_start(p_hwfn, &start); if (rc) { DP_ERR(cdev, "Failed to start VPORT\n"); return rc; @@ -1619,7 +1650,7 @@ static int qed_start_vport(struct qed_dev *cdev, DP_VERBOSE(cdev, (QED_MSG_SPQ | NETIF_MSG_IFUP), "Started V-PORT %d with MTU %d\n", - vport_id, mtu); + start.vport_id, start.mtu); } qed_reset_vport_stats(cdev); diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index f23ce734ab63..b89c9a8e1655 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -11,8 +11,8 @@ #include <linux/delay.h> #include <linux/errno.h> #include <linux/kernel.h> -#include <linux/mutex.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/string.h> #include "qed.h" #include "qed_hsi.h" @@ -168,8 +168,8 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, if (!p_info->mfw_mb_shadow || !p_info->mfw_mb_addr) goto err; - /* Initialize the MFW mutex */ - mutex_init(&p_info->mutex); + /* Initialize the MFW spinlock */ + spin_lock_init(&p_info->lock); return 0; @@ -179,6 +179,52 @@ err: return -ENOMEM; } +/* Locks the MFW mailbox of a PF to ensure a single access. + * The lock is achieved in most cases by holding a spinlock, causing other + * threads to wait till a previous access is done. + * In some cases (currently when a [UN]LOAD_REQ commands are sent), the single + * access is achieved by setting a blocking flag, which will fail other + * competing contexts to send their mailboxes. + */ +static int qed_mcp_mb_lock(struct qed_hwfn *p_hwfn, + u32 cmd) +{ + spin_lock_bh(&p_hwfn->mcp_info->lock); + + /* The spinlock shouldn't be acquired when the mailbox command is + * [UN]LOAD_REQ, since the engine is locked by the MFW, and a parallel + * pending [UN]LOAD_REQ command of another PF together with a spinlock + * (i.e. interrupts are disabled) - can lead to a deadlock. + * It is assumed that for a single PF, no other mailbox commands can be + * sent from another context while sending LOAD_REQ, and that any + * parallel commands to UNLOAD_REQ can be cancelled. + */ + if (cmd == DRV_MSG_CODE_LOAD_DONE || cmd == DRV_MSG_CODE_UNLOAD_DONE) + p_hwfn->mcp_info->block_mb_sending = false; + + if (p_hwfn->mcp_info->block_mb_sending) { + DP_NOTICE(p_hwfn, + "Trying to send a MFW mailbox command [0x%x] in parallel to [UN]LOAD_REQ. Aborting.\n", + cmd); + spin_unlock_bh(&p_hwfn->mcp_info->lock); + return -EBUSY; + } + + if (cmd == DRV_MSG_CODE_LOAD_REQ || cmd == DRV_MSG_CODE_UNLOAD_REQ) { + p_hwfn->mcp_info->block_mb_sending = true; + spin_unlock_bh(&p_hwfn->mcp_info->lock); + } + + return 0; +} + +static void qed_mcp_mb_unlock(struct qed_hwfn *p_hwfn, + u32 cmd) +{ + if (cmd != DRV_MSG_CODE_LOAD_REQ && cmd != DRV_MSG_CODE_UNLOAD_REQ) + spin_unlock_bh(&p_hwfn->mcp_info->lock); +} + int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { @@ -187,6 +233,13 @@ int qed_mcp_reset(struct qed_hwfn *p_hwfn, u32 org_mcp_reset_seq, cnt = 0; int rc = 0; + /* Ensure that only a single thread is accessing the mailbox at a + * certain time. + */ + rc = qed_mcp_mb_lock(p_hwfn, DRV_MSG_CODE_MCP_RESET); + if (rc != 0) + return rc; + /* Set drv command along with the updated sequence */ org_mcp_reset_seq = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0); DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, @@ -209,6 +262,8 @@ int qed_mcp_reset(struct qed_hwfn *p_hwfn, rc = -EAGAIN; } + qed_mcp_mb_unlock(p_hwfn, DRV_MSG_CODE_MCP_RESET); + return rc; } @@ -275,14 +330,12 @@ static int qed_do_mcp_cmd(struct qed_hwfn *p_hwfn, return rc; } -int qed_mcp_cmd(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - u32 cmd, - u32 param, - u32 *o_mcp_resp, - u32 *o_mcp_param) +static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_mcp_mb_params *p_mb_params) { - int rc = 0; + u32 union_data_addr; + int rc; /* MCP not initialized */ if (!qed_mcp_is_init(p_hwfn)) { @@ -290,28 +343,56 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, return -EBUSY; } - /* Lock Mutex to ensure only single thread is - * accessing the MCP at one time + union_data_addr = p_hwfn->mcp_info->drv_mb_addr + + offsetof(struct public_drv_mb, union_data); + + /* Ensure that only a single thread is accessing the mailbox at a + * certain time. */ - mutex_lock(&p_hwfn->mcp_info->mutex); - rc = qed_do_mcp_cmd(p_hwfn, p_ptt, cmd, param, - o_mcp_resp, o_mcp_param); - /* Release Mutex */ - mutex_unlock(&p_hwfn->mcp_info->mutex); + rc = qed_mcp_mb_lock(p_hwfn, p_mb_params->cmd); + if (rc) + return rc; + + if (p_mb_params->p_data_src != NULL) + qed_memcpy_to(p_hwfn, p_ptt, union_data_addr, + p_mb_params->p_data_src, + sizeof(*p_mb_params->p_data_src)); + + rc = qed_do_mcp_cmd(p_hwfn, p_ptt, p_mb_params->cmd, + p_mb_params->param, &p_mb_params->mcp_resp, + &p_mb_params->mcp_param); + + if (p_mb_params->p_data_dst != NULL) + qed_memcpy_from(p_hwfn, p_ptt, p_mb_params->p_data_dst, + union_data_addr, + sizeof(*p_mb_params->p_data_dst)); + + qed_mcp_mb_unlock(p_hwfn, p_mb_params->cmd); return rc; } -static void qed_mcp_set_drv_ver(struct qed_dev *cdev, - struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt) +int qed_mcp_cmd(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param) { - u32 i; + struct qed_mcp_mb_params mb_params; + int rc; + + memset(&mb_params, 0, sizeof(mb_params)); + mb_params.cmd = cmd; + mb_params.param = param; + rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); + if (rc) + return rc; + + *o_mcp_resp = mb_params.mcp_resp; + *o_mcp_param = mb_params.mcp_param; - /* Copy version string to MCP */ - for (i = 0; i < MCP_DRV_VER_STR_SIZE_DWORD; i++) - DRV_MB_WR(p_hwfn, p_ptt, union_data.ver_str[i], - *(u32 *)&cdev->ver_str[i * sizeof(u32)]); + return 0; } int qed_mcp_load_req(struct qed_hwfn *p_hwfn, @@ -319,26 +400,18 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn, u32 *p_load_code) { struct qed_dev *cdev = p_hwfn->cdev; - u32 param; + struct qed_mcp_mb_params mb_params; + union drv_union_data union_data; int rc; - if (!qed_mcp_is_init(p_hwfn)) { - DP_NOTICE(p_hwfn, "MFW is not initialized !\n"); - return -EBUSY; - } - - /* Save driver's version to shmem */ - qed_mcp_set_drv_ver(cdev, p_hwfn, p_ptt); - - DP_VERBOSE(p_hwfn, QED_MSG_SP, "fw_seq 0x%08x, drv_pulse 0x%x\n", - p_hwfn->mcp_info->drv_mb_seq, - p_hwfn->mcp_info->drv_pulse_seq); - + memset(&mb_params, 0, sizeof(mb_params)); /* Load Request */ - rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_LOAD_REQ, - (PDA_COMP | DRV_ID_MCP_HSI_VER_CURRENT | - cdev->drv_type), - p_load_code, ¶m); + mb_params.cmd = DRV_MSG_CODE_LOAD_REQ; + mb_params.param = PDA_COMP | DRV_ID_MCP_HSI_VER_CURRENT | + cdev->drv_type; + memcpy(&union_data.ver_str, cdev->ver_str, MCP_DRV_VER_STR_SIZE); + mb_params.p_data_src = &union_data; + rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); /* if mcp fails to respond we must abort */ if (rc) { @@ -346,6 +419,8 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn, return rc; } + *p_load_code = mb_params.mcp_resp; + /* If MFW refused (e.g. other port is in diagnostic mode) we * must abort. This can happen in the following cases: * - Other port is in diagnostic mode @@ -365,6 +440,33 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn, return 0; } +static void qed_mcp_handle_transceiver_change(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + u32 transceiver_state; + + transceiver_state = qed_rd(p_hwfn, p_ptt, + p_hwfn->mcp_info->port_addr + + offsetof(struct public_port, + transceiver_data)); + + DP_VERBOSE(p_hwfn, + (NETIF_MSG_HW | QED_MSG_SP), + "Received transceiver state update [0x%08x] from mfw [Addr 0x%x]\n", + transceiver_state, + (u32)(p_hwfn->mcp_info->port_addr + + offsetof(struct public_port, + transceiver_data))); + + transceiver_state = GET_FIELD(transceiver_state, + PMM_TRANSCEIVER_STATE); + + if (transceiver_state == PMM_TRANSCEIVER_STATE_PRESENT) + DP_NOTICE(p_hwfn, "Transceiver is present.\n"); + else + DP_NOTICE(p_hwfn, "Transceiver is unplugged.\n"); +} + static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_reset) @@ -390,7 +492,10 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, return; } - p_link->link_up = !!(status & LINK_STATUS_LINK_UP); + if (p_hwfn->b_drv_link_init) + p_link->link_up = !!(status & LINK_STATUS_LINK_UP); + else + p_link->link_up = false; p_link->full_duplex = true; switch ((status & LINK_STATUS_SPEED_AND_DUPLEX_MASK)) { @@ -492,53 +597,43 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, bool b_up) { struct qed_mcp_link_params *params = &p_hwfn->mcp_info->link_input; - u32 param = 0, reply = 0, cmd; - struct pmm_phy_cfg phy_cfg; + struct qed_mcp_mb_params mb_params; + union drv_union_data union_data; + struct pmm_phy_cfg *phy_cfg; int rc = 0; - u32 i; - - if (!qed_mcp_is_init(p_hwfn)) { - DP_NOTICE(p_hwfn, "MFW is not initialized !\n"); - return -EBUSY; - } + u32 cmd; /* Set the shmem configuration according to params */ - memset(&phy_cfg, 0, sizeof(phy_cfg)); + phy_cfg = &union_data.drv_phy_cfg; + memset(phy_cfg, 0, sizeof(*phy_cfg)); cmd = b_up ? DRV_MSG_CODE_INIT_PHY : DRV_MSG_CODE_LINK_RESET; if (!params->speed.autoneg) - phy_cfg.speed = params->speed.forced_speed; - phy_cfg.pause |= (params->pause.autoneg) ? PMM_PAUSE_AUTONEG : 0; - phy_cfg.pause |= (params->pause.forced_rx) ? PMM_PAUSE_RX : 0; - phy_cfg.pause |= (params->pause.forced_tx) ? PMM_PAUSE_TX : 0; - phy_cfg.adv_speed = params->speed.advertised_speeds; - phy_cfg.loopback_mode = params->loopback_mode; - - /* Write the requested configuration to shmem */ - for (i = 0; i < sizeof(phy_cfg); i += 4) - qed_wr(p_hwfn, p_ptt, - p_hwfn->mcp_info->drv_mb_addr + - offsetof(struct public_drv_mb, union_data) + i, - ((u32 *)&phy_cfg)[i >> 2]); + phy_cfg->speed = params->speed.forced_speed; + phy_cfg->pause |= (params->pause.autoneg) ? PMM_PAUSE_AUTONEG : 0; + phy_cfg->pause |= (params->pause.forced_rx) ? PMM_PAUSE_RX : 0; + phy_cfg->pause |= (params->pause.forced_tx) ? PMM_PAUSE_TX : 0; + phy_cfg->adv_speed = params->speed.advertised_speeds; + phy_cfg->loopback_mode = params->loopback_mode; + + p_hwfn->b_drv_link_init = b_up; if (b_up) { DP_VERBOSE(p_hwfn, NETIF_MSG_LINK, "Configuring Link: Speed 0x%08x, Pause 0x%08x, adv_speed 0x%08x, loopback 0x%08x, features 0x%08x\n", - phy_cfg.speed, - phy_cfg.pause, - phy_cfg.adv_speed, - phy_cfg.loopback_mode, - phy_cfg.feature_config_flags); + phy_cfg->speed, + phy_cfg->pause, + phy_cfg->adv_speed, + phy_cfg->loopback_mode, + phy_cfg->feature_config_flags); } else { DP_VERBOSE(p_hwfn, NETIF_MSG_LINK, "Resetting link\n"); } - DP_VERBOSE(p_hwfn, QED_MSG_SP, "fw_seq 0x%08x, drv_pulse 0x%x\n", - p_hwfn->mcp_info->drv_mb_seq, - p_hwfn->mcp_info->drv_pulse_seq); - - /* Load Request */ - rc = qed_mcp_cmd(p_hwfn, p_ptt, cmd, 0, &reply, ¶m); + memset(&mb_params, 0, sizeof(mb_params)); + mb_params.cmd = cmd; + mb_params.p_data_src = &union_data; + rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); /* if mcp fails to respond we must abort */ if (rc) { @@ -581,6 +676,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn, case MFW_DRV_MSG_LINK_CHANGE: qed_mcp_handle_link_change(p_hwfn, p_ptt, false); break; + case MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE: + qed_mcp_handle_transceiver_change(p_hwfn, p_ptt); + break; default: DP_NOTICE(p_hwfn, "Unimplemented MFW message %d\n", i); rc = -EINVAL; @@ -801,11 +899,11 @@ int qed_mcp_drain(struct qed_hwfn *p_hwfn, int rc; rc = qed_mcp_cmd(p_hwfn, p_ptt, - DRV_MSG_CODE_NIG_DRAIN, 100, + DRV_MSG_CODE_NIG_DRAIN, 1000, &resp, ¶m); /* Wait for the drain to complete before returning */ - msleep(120); + msleep(1020); return rc; } @@ -831,31 +929,28 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_mcp_drv_version *p_ver) { - int rc = 0; - u32 param = 0, reply = 0, i; - - if (!qed_mcp_is_init(p_hwfn)) { - DP_NOTICE(p_hwfn, "MFW is not initialized !\n"); - return -EBUSY; - } + struct drv_version_stc *p_drv_version; + struct qed_mcp_mb_params mb_params; + union drv_union_data union_data; + __be32 val; + u32 i; + int rc; - DRV_MB_WR(p_hwfn, p_ptt, union_data.drv_version.version, - p_ver->version); - /* Copy version string to shmem */ - for (i = 0; i < (MCP_DRV_VER_STR_SIZE - 4) / 4; i++) { - DRV_MB_WR(p_hwfn, p_ptt, - union_data.drv_version.name[i * sizeof(u32)], - *(u32 *)&p_ver->name[i * sizeof(u32)]); + p_drv_version = &union_data.drv_version; + p_drv_version->version = p_ver->version; + for (i = 0; i < MCP_DRV_VER_STR_SIZE - 1; i += 4) { + val = cpu_to_be32(p_ver->name[i]); + *(u32 *)&p_drv_version->name[i * sizeof(u32)] = val; } - rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_SET_VERSION, 0, &reply, - ¶m); - if (rc) { + memset(&mb_params, 0, sizeof(mb_params)); + mb_params.cmd = DRV_MSG_CODE_SET_VERSION; + mb_params.p_data_src = &union_data; + rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); + if (rc) DP_ERR(p_hwfn, "MCP response failure, aborting\n"); - return rc; - } - return 0; + return rc; } int qed_mcp_set_led(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 506197d5c3dd..50917a2131a5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -11,8 +11,8 @@ #include <linux/types.h> #include <linux/delay.h> -#include <linux/mutex.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include "qed_hsi.h" struct qed_mcp_link_speed_params { @@ -255,7 +255,8 @@ int qed_mcp_set_led(struct qed_hwfn *p_hwfn, #define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \ ((_p_hwfn)->cdev->num_ports_in_engines * 2)) struct qed_mcp_info { - struct mutex mutex; /* MCP access lock */ + spinlock_t lock; + bool block_mb_sending; u32 public_base; u32 drv_mb_addr; u32 mfw_mb_addr; @@ -272,6 +273,15 @@ struct qed_mcp_info { u16 mcp_hist; }; +struct qed_mcp_mb_params { + u32 cmd; + u32 param; + union drv_union_data *p_data_src; + union drv_union_data *p_data_dst; + u32 mcp_resp; + u32 mcp_param; +}; + /** * @brief Initialize the interface with the MCP * diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 02e17d331f22..d023251544d9 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -160,6 +160,7 @@ struct qede_dev { u16 q_num_rx_buffers; /* Must be a power of two */ u16 q_num_tx_buffers; /* Must be a power of two */ + bool gro_disable; struct list_head vlan_list; u16 configured_vlans; u16 non_configured_vlans; @@ -188,6 +189,24 @@ struct sw_rx_data { unsigned int page_offset; }; +enum qede_agg_state { + QEDE_AGG_STATE_NONE = 0, + QEDE_AGG_STATE_START = 1, + QEDE_AGG_STATE_ERROR = 2 +}; + +struct qede_agg_info { + struct sw_rx_data replace_buf; + dma_addr_t replace_buf_mapping; + struct sw_rx_data start_buf; + dma_addr_t start_buf_mapping; + struct eth_fast_path_rx_tpa_start_cqe start_cqe; + enum qede_agg_state agg_state; + struct sk_buff *skb; + int frag_id; + u16 vlan_tag; +}; + struct qede_rx_queue { __le16 *hw_cons_ptr; struct sw_rx_data *sw_rx_ring; @@ -197,6 +216,9 @@ struct qede_rx_queue { struct qed_chain rx_comp_ring; void __iomem *hw_rxq_prod_addr; + /* GRO */ + struct qede_agg_info tpa_info[ETH_TPA_MAX_AGGS_NUM]; + int rx_buf_size; unsigned int rx_buf_seg_size; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index ddd9e4aaa500..518af329502d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -866,6 +866,281 @@ static inline void qede_skb_receive(struct qede_dev *edev, napi_gro_receive(&fp->napi, skb); } +static void qede_set_gro_params(struct qede_dev *edev, + struct sk_buff *skb, + struct eth_fast_path_rx_tpa_start_cqe *cqe) +{ + u16 parsing_flags = le16_to_cpu(cqe->pars_flags.flags); + + if (((parsing_flags >> PARSING_AND_ERR_FLAGS_L3TYPE_SHIFT) & + PARSING_AND_ERR_FLAGS_L3TYPE_MASK) == 2) + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + else + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + + skb_shinfo(skb)->gso_size = __le16_to_cpu(cqe->len_on_first_bd) - + cqe->header_len; +} + +static int qede_fill_frag_skb(struct qede_dev *edev, + struct qede_rx_queue *rxq, + u8 tpa_agg_index, + u16 len_on_bd) +{ + struct sw_rx_data *current_bd = &rxq->sw_rx_ring[rxq->sw_rx_cons & + NUM_RX_BDS_MAX]; + struct qede_agg_info *tpa_info = &rxq->tpa_info[tpa_agg_index]; + struct sk_buff *skb = tpa_info->skb; + + if (unlikely(tpa_info->agg_state != QEDE_AGG_STATE_START)) + goto out; + + /* Add one frag and update the appropriate fields in the skb */ + skb_fill_page_desc(skb, tpa_info->frag_id++, + current_bd->data, current_bd->page_offset, + len_on_bd); + + if (unlikely(qede_realloc_rx_buffer(edev, rxq, current_bd))) { + tpa_info->agg_state = QEDE_AGG_STATE_ERROR; + goto out; + } + + qed_chain_consume(&rxq->rx_bd_ring); + rxq->sw_rx_cons++; + + skb->data_len += len_on_bd; + skb->truesize += rxq->rx_buf_seg_size; + skb->len += len_on_bd; + + return 0; + +out: + return -ENOMEM; +} + +static void qede_tpa_start(struct qede_dev *edev, + struct qede_rx_queue *rxq, + struct eth_fast_path_rx_tpa_start_cqe *cqe) +{ + struct qede_agg_info *tpa_info = &rxq->tpa_info[cqe->tpa_agg_index]; + struct eth_rx_bd *rx_bd_cons = qed_chain_consume(&rxq->rx_bd_ring); + struct eth_rx_bd *rx_bd_prod = qed_chain_produce(&rxq->rx_bd_ring); + struct sw_rx_data *replace_buf = &tpa_info->replace_buf; + dma_addr_t mapping = tpa_info->replace_buf_mapping; + struct sw_rx_data *sw_rx_data_cons; + struct sw_rx_data *sw_rx_data_prod; + enum pkt_hash_types rxhash_type; + u32 rxhash; + + sw_rx_data_cons = &rxq->sw_rx_ring[rxq->sw_rx_cons & NUM_RX_BDS_MAX]; + sw_rx_data_prod = &rxq->sw_rx_ring[rxq->sw_rx_prod & NUM_RX_BDS_MAX]; + + /* Use pre-allocated replacement buffer - we can't release the agg. + * start until its over and we don't want to risk allocation failing + * here, so re-allocate when aggregation will be over. + */ + dma_unmap_addr_set(sw_rx_data_prod, mapping, + dma_unmap_addr(replace_buf, mapping)); + + sw_rx_data_prod->data = replace_buf->data; + rx_bd_prod->addr.hi = cpu_to_le32(upper_32_bits(mapping)); + rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(mapping)); + sw_rx_data_prod->page_offset = replace_buf->page_offset; + + rxq->sw_rx_prod++; + + /* move partial skb from cons to pool (don't unmap yet) + * save mapping, incase we drop the packet later on. + */ + tpa_info->start_buf = *sw_rx_data_cons; + mapping = HILO_U64(le32_to_cpu(rx_bd_cons->addr.hi), + le32_to_cpu(rx_bd_cons->addr.lo)); + + tpa_info->start_buf_mapping = mapping; + rxq->sw_rx_cons++; + + /* set tpa state to start only if we are able to allocate skb + * for this aggregation, otherwise mark as error and aggregation will + * be dropped + */ + tpa_info->skb = netdev_alloc_skb(edev->ndev, + le16_to_cpu(cqe->len_on_first_bd)); + if (unlikely(!tpa_info->skb)) { + tpa_info->agg_state = QEDE_AGG_STATE_ERROR; + return; + } + + skb_put(tpa_info->skb, le16_to_cpu(cqe->len_on_first_bd)); + memcpy(&tpa_info->start_cqe, cqe, sizeof(tpa_info->start_cqe)); + + /* Start filling in the aggregation info */ + tpa_info->frag_id = 0; + tpa_info->agg_state = QEDE_AGG_STATE_START; + + rxhash = qede_get_rxhash(edev, cqe->bitfields, + cqe->rss_hash, &rxhash_type); + skb_set_hash(tpa_info->skb, rxhash, rxhash_type); + if ((le16_to_cpu(cqe->pars_flags.flags) >> + PARSING_AND_ERR_FLAGS_TAG8021QEXIST_SHIFT) & + PARSING_AND_ERR_FLAGS_TAG8021QEXIST_MASK) + tpa_info->vlan_tag = le16_to_cpu(cqe->vlan_tag); + else + tpa_info->vlan_tag = 0; + + /* This is needed in order to enable forwarding support */ + qede_set_gro_params(edev, tpa_info->skb, cqe); + + if (likely(cqe->ext_bd_len_list[0])) + qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, + le16_to_cpu(cqe->ext_bd_len_list[0])); + + if (unlikely(cqe->ext_bd_len_list[1])) { + DP_ERR(edev, + "Unlikely - got a TPA aggregation with more than one ext_bd_len_list entry in the TPA start\n"); + tpa_info->agg_state = QEDE_AGG_STATE_ERROR; + } +} + +#ifdef CONFIG_INET +static void qede_gro_ip_csum(struct sk_buff *skb) +{ + const struct iphdr *iph = ip_hdr(skb); + struct tcphdr *th; + + skb_set_network_header(skb, 0); + skb_set_transport_header(skb, sizeof(struct iphdr)); + th = tcp_hdr(skb); + + th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb), + iph->saddr, iph->daddr, 0); + + tcp_gro_complete(skb); +} + +static void qede_gro_ipv6_csum(struct sk_buff *skb) +{ + struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr *th; + + skb_set_network_header(skb, 0); + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + th = tcp_hdr(skb); + + th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), + &iph->saddr, &iph->daddr, 0); + tcp_gro_complete(skb); +} +#endif + +static void qede_gro_receive(struct qede_dev *edev, + struct qede_fastpath *fp, + struct sk_buff *skb, + u16 vlan_tag) +{ +#ifdef CONFIG_INET + if (skb_shinfo(skb)->gso_size) { + switch (skb->protocol) { + case htons(ETH_P_IP): + qede_gro_ip_csum(skb); + break; + case htons(ETH_P_IPV6): + qede_gro_ipv6_csum(skb); + break; + default: + DP_ERR(edev, + "Error: FW GRO supports only IPv4/IPv6, not 0x%04x\n", + ntohs(skb->protocol)); + } + } +#endif + skb_record_rx_queue(skb, fp->rss_id); + qede_skb_receive(edev, fp, skb, vlan_tag); +} + +static inline void qede_tpa_cont(struct qede_dev *edev, + struct qede_rx_queue *rxq, + struct eth_fast_path_rx_tpa_cont_cqe *cqe) +{ + int i; + + for (i = 0; cqe->len_list[i]; i++) + qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, + le16_to_cpu(cqe->len_list[i])); + + if (unlikely(i > 1)) + DP_ERR(edev, + "Strange - TPA cont with more than a single len_list entry\n"); +} + +static void qede_tpa_end(struct qede_dev *edev, + struct qede_fastpath *fp, + struct eth_fast_path_rx_tpa_end_cqe *cqe) +{ + struct qede_rx_queue *rxq = fp->rxq; + struct qede_agg_info *tpa_info; + struct sk_buff *skb; + int i; + + tpa_info = &rxq->tpa_info[cqe->tpa_agg_index]; + skb = tpa_info->skb; + + for (i = 0; cqe->len_list[i]; i++) + qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, + le16_to_cpu(cqe->len_list[i])); + if (unlikely(i > 1)) + DP_ERR(edev, + "Strange - TPA emd with more than a single len_list entry\n"); + + if (unlikely(tpa_info->agg_state != QEDE_AGG_STATE_START)) + goto err; + + /* Sanity */ + if (unlikely(cqe->num_of_bds != tpa_info->frag_id + 1)) + DP_ERR(edev, + "Strange - TPA had %02x BDs, but SKB has only %d frags\n", + cqe->num_of_bds, tpa_info->frag_id); + if (unlikely(skb->len != le16_to_cpu(cqe->total_packet_len))) + DP_ERR(edev, + "Strange - total packet len [cqe] is %4x but SKB has len %04x\n", + le16_to_cpu(cqe->total_packet_len), skb->len); + + memcpy(skb->data, + page_address(tpa_info->start_buf.data) + + tpa_info->start_cqe.placement_offset + + tpa_info->start_buf.page_offset, + le16_to_cpu(tpa_info->start_cqe.len_on_first_bd)); + + /* Recycle [mapped] start buffer for the next replacement */ + tpa_info->replace_buf = tpa_info->start_buf; + tpa_info->replace_buf_mapping = tpa_info->start_buf_mapping; + + /* Finalize the SKB */ + skb->protocol = eth_type_trans(skb, edev->ndev); + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* tcp_gro_complete() will copy NAPI_GRO_CB(skb)->count + * to skb_shinfo(skb)->gso_segs + */ + NAPI_GRO_CB(skb)->count = le16_to_cpu(cqe->num_of_coalesced_segs); + + qede_gro_receive(edev, fp, skb, tpa_info->vlan_tag); + + tpa_info->agg_state = QEDE_AGG_STATE_NONE; + + return; +err: + /* The BD starting the aggregation is still mapped; Re-use it for + * future aggregations [as replacement buffer] + */ + memcpy(&tpa_info->replace_buf, &tpa_info->start_buf, + sizeof(struct sw_rx_data)); + tpa_info->replace_buf_mapping = tpa_info->start_buf_mapping; + tpa_info->start_buf.data = NULL; + tpa_info->agg_state = QEDE_AGG_STATE_NONE; + dev_kfree_skb_any(tpa_info->skb); + tpa_info->skb = NULL; +} + static u8 qede_check_csum(u16 flag) { u16 csum_flag = 0; @@ -931,6 +1206,25 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget) goto next_cqe; } + if (cqe_type != ETH_RX_CQE_TYPE_REGULAR) { + switch (cqe_type) { + case ETH_RX_CQE_TYPE_TPA_START: + qede_tpa_start(edev, rxq, + &cqe->fast_path_tpa_start); + goto next_cqe; + case ETH_RX_CQE_TYPE_TPA_CONT: + qede_tpa_cont(edev, rxq, + &cqe->fast_path_tpa_cont); + goto next_cqe; + case ETH_RX_CQE_TYPE_TPA_END: + qede_tpa_end(edev, fp, + &cqe->fast_path_tpa_end); + goto next_rx_only; + default: + break; + } + } + /* Get the data from the SW ring */ sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX; sw_rx_data = &rxq->sw_rx_ring[sw_rx_index]; @@ -1057,9 +1351,9 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget) qede_skb_receive(edev, fp, skb, le16_to_cpu(fp_cqe->vlan_tag)); qed_chain_consume(&rxq->rx_bd_ring); - next_rx: rxq->sw_rx_cons++; +next_rx_only: rx_pkt++; next_cqe: /* don't consume bd rx buffer */ @@ -1952,9 +2246,31 @@ static void qede_free_rx_buffers(struct qede_dev *edev, } } +static void qede_free_sge_mem(struct qede_dev *edev, + struct qede_rx_queue *rxq) { + int i; + + if (edev->gro_disable) + return; + + for (i = 0; i < ETH_TPA_MAX_AGGS_NUM; i++) { + struct qede_agg_info *tpa_info = &rxq->tpa_info[i]; + struct sw_rx_data *replace_buf = &tpa_info->replace_buf; + + if (replace_buf) { + dma_unmap_page(&edev->pdev->dev, + dma_unmap_addr(replace_buf, mapping), + PAGE_SIZE, DMA_FROM_DEVICE); + __free_page(replace_buf->data); + } + } +} + static void qede_free_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq) { + qede_free_sge_mem(edev, rxq); + /* Free rx buffers */ qede_free_rx_buffers(edev, rxq); @@ -2010,6 +2326,53 @@ static int qede_alloc_rx_buffer(struct qede_dev *edev, return 0; } +static int qede_alloc_sge_mem(struct qede_dev *edev, + struct qede_rx_queue *rxq) +{ + dma_addr_t mapping; + int i; + + if (edev->gro_disable) + return 0; + + if (edev->ndev->mtu > PAGE_SIZE) { + edev->gro_disable = 1; + return 0; + } + + for (i = 0; i < ETH_TPA_MAX_AGGS_NUM; i++) { + struct qede_agg_info *tpa_info = &rxq->tpa_info[i]; + struct sw_rx_data *replace_buf = &tpa_info->replace_buf; + + replace_buf->data = alloc_pages(GFP_ATOMIC, 0); + if (unlikely(!replace_buf->data)) { + DP_NOTICE(edev, + "Failed to allocate TPA skb pool [replacement buffer]\n"); + goto err; + } + + mapping = dma_map_page(&edev->pdev->dev, replace_buf->data, 0, + rxq->rx_buf_size, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(&edev->pdev->dev, mapping))) { + DP_NOTICE(edev, + "Failed to map TPA replacement buffer\n"); + goto err; + } + + dma_unmap_addr_set(replace_buf, mapping, mapping); + tpa_info->replace_buf.page_offset = 0; + + tpa_info->replace_buf_mapping = mapping; + tpa_info->agg_state = QEDE_AGG_STATE_NONE; + } + + return 0; +err: + qede_free_sge_mem(edev, rxq); + edev->gro_disable = 1; + return -ENOMEM; +} + /* This function allocates all memory needed per Rx queue */ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq) @@ -2071,6 +2434,8 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, num_allocated); } + qede_alloc_sge_mem(edev, rxq); + return 0; err: @@ -2233,6 +2598,8 @@ static void qede_init_fp(struct qede_dev *edev) snprintf(fp->name, sizeof(fp->name), "%s-fp-%d", edev->ndev->name, rss_id); } + + edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO); } static int qede_set_real_num_queues(struct qede_dev *edev) @@ -2466,11 +2833,12 @@ static int qede_stop_queues(struct qede_dev *edev) static int qede_start_queues(struct qede_dev *edev) { int rc, tc, i; - int vport_id = 0, drop_ttl0_flg = 1, vlan_removal_en = 1; + int vlan_removal_en = 1; struct qed_dev *cdev = edev->cdev; struct qed_update_vport_rss_params *rss_params = &edev->rss_params; struct qed_update_vport_params vport_update_params; struct qed_queue_start_common_params q_params; + struct qed_start_vport_params start = {0}; if (!edev->num_rss) { DP_ERR(edev, @@ -2478,10 +2846,13 @@ static int qede_start_queues(struct qede_dev *edev) return -EINVAL; } - rc = edev->ops->vport_start(cdev, vport_id, - edev->ndev->mtu, - drop_ttl0_flg, - vlan_removal_en); + start.gro_enable = !edev->gro_disable; + start.mtu = edev->ndev->mtu; + start.vport_id = 0; + start.drop_ttl0 = true; + start.remove_inner_vlan = vlan_removal_en; + + rc = edev->ops->vport_start(cdev, &start); if (rc) { DP_ERR(edev, "Start V-PORT failed %d\n", rc); @@ -2490,7 +2861,7 @@ static int qede_start_queues(struct qede_dev *edev) DP_VERBOSE(edev, NETIF_MSG_IFUP, "Start vport ramrod passed, vport_id = %d, MTU = %d, vlan_removal_en = %d\n", - vport_id, edev->ndev->mtu + 0xe, vlan_removal_en); + start.vport_id, edev->ndev->mtu + 0xe, vlan_removal_en); for_each_rss(i) { struct qede_fastpath *fp = &edev->fp_array[i]; @@ -2555,7 +2926,7 @@ static int qede_start_queues(struct qede_dev *edev) /* Prepare and send the vport enable */ memset(&vport_update_params, 0, sizeof(vport_update_params)); - vport_update_params.vport_id = vport_id; + vport_update_params.vport_id = start.vport_id; vport_update_params.update_vport_active_flg = 1; vport_update_params.vport_active_flg = 1; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 46bbea8e023c..55007f1e6bbc 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -566,6 +566,7 @@ struct qlcnic_adapter_stats { u64 tx_dma_map_error; u64 spurious_intr; u64 mac_filter_limit_overrun; + u64 mbx_spurious_intr; }; /* @@ -1099,7 +1100,7 @@ struct qlcnic_mailbox { unsigned long status; spinlock_t queue_lock; /* Mailbox queue lock */ spinlock_t aen_lock; /* Mailbox response/AEN lock */ - atomic_t rsp_status; + u32 rsp_status; u32 num_cmds; }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 37a731be7d39..f9640d5ce6ba 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -491,7 +491,7 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter) static inline void qlcnic_83xx_notify_mbx_response(struct qlcnic_mailbox *mbx) { - atomic_set(&mbx->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED); + mbx->rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED; complete(&mbx->completion); } @@ -510,7 +510,7 @@ static void qlcnic_83xx_poll_process_aen(struct qlcnic_adapter *adapter) if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); } else { - if (atomic_read(&mbx->rsp_status) != rsp_status) + if (mbx->rsp_status != rsp_status) qlcnic_83xx_notify_mbx_response(mbx); } out: @@ -1023,7 +1023,7 @@ static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); } else { - if (atomic_read(&mbx->rsp_status) != rsp_status) + if (mbx->rsp_status != rsp_status) qlcnic_83xx_notify_mbx_response(mbx); } } @@ -2338,9 +2338,9 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter, static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data) { + u32 mask, resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED; struct qlcnic_adapter *adapter = data; struct qlcnic_mailbox *mbx; - u32 mask, resp, event; unsigned long flags; mbx = adapter->ahw->mailbox; @@ -2350,10 +2350,14 @@ static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data) goto out; event = readl(QLCNIC_MBX_FW(adapter->ahw, 0)); - if (event & QLCNIC_MBX_ASYNC_EVENT) + if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); - else - qlcnic_83xx_notify_mbx_response(mbx); + } else { + if (mbx->rsp_status != rsp_status) + qlcnic_83xx_notify_mbx_response(mbx); + else + adapter->stats.mbx_spurious_intr++; + } out: mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK); @@ -4050,10 +4054,10 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) struct qlcnic_adapter *adapter = mbx->adapter; const struct qlcnic_mbx_ops *mbx_ops = mbx->ops; struct device *dev = &adapter->pdev->dev; - atomic_t *rsp_status = &mbx->rsp_status; struct list_head *head = &mbx->cmd_q; struct qlcnic_hardware_context *ahw; struct qlcnic_cmd_args *cmd = NULL; + unsigned long flags; ahw = adapter->ahw; @@ -4063,7 +4067,9 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) return; } - atomic_set(rsp_status, QLC_83XX_MBX_RESPONSE_WAIT); + spin_lock_irqsave(&mbx->aen_lock, flags); + mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT; + spin_unlock_irqrestore(&mbx->aen_lock, flags); spin_lock(&mbx->queue_lock); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 494e8105adee..0a2318cad34d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -59,7 +59,8 @@ static const struct qlcnic_stats qlcnic_gstrings_stats[] = { QLC_OFF(stats.mac_filter_limit_overrun)}, {"spurious intr", QLC_SIZEOF(stats.spurious_intr), QLC_OFF(stats.spurious_intr)}, - + {"mbx spurious intr", QLC_SIZEOF(stats.mbx_spurious_intr), + QLC_OFF(stats.mbx_spurious_intr)}, }; static const char qlcnic_device_gstrings_stats[][ETH_GSTRING_LEN] = { diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 689a4a5c8dcf..1ef03939d25f 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -811,7 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev) dev->netdev_ops = &qcaspi_netdev_ops; qcaspi_set_ethtool_ops(dev); dev->watchdog_timeo = QCASPI_TX_TIMEOUT; - dev->flags = IFF_MULTICAST; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->tx_queue_len = 100; qca = netdev_priv(dev); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 537974cfd427..dd2cf3738b73 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4933,8 +4933,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_40: - RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: @@ -4943,8 +4941,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_47: case RTL_GIGA_MAC_VER_48: - RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: @@ -7730,10 +7726,13 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; + struct pci_dev *pdev = tp->pci_dev; struct rtl8169_counters *counters = tp->counters; unsigned int start; - if (netif_running(dev)) + pm_runtime_get_noresume(&pdev->dev); + + if (netif_running(dev) && pm_runtime_active(&pdev->dev)) rtl8169_rx_missed(dev, ioaddr); do { @@ -7761,7 +7760,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) * Fetch additonal counter values missing in stats collected by driver * from tally counters. */ - rtl8169_update_counters(dev); + if (pm_runtime_active(&pdev->dev)) + rtl8169_update_counters(dev); /* * Subtract values fetched during initalization. @@ -7774,6 +7774,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) - le16_to_cpu(tp->tc_offset.tx_aborted); + pm_runtime_put_noidle(&pdev->dev); + return stats; } @@ -7853,6 +7855,10 @@ static int rtl8169_runtime_suspend(struct device *device) rtl8169_net_suspend(dev); + /* Update counters before going runtime suspend */ + rtl8169_rx_missed(dev, tp->mmio_addr); + rtl8169_update_counters(dev); + return 0; } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 88656ceb6e29..8f2c4fb4c724 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1708,7 +1708,6 @@ static int ravb_set_gti(struct net_device *ndev) static int ravb_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - const struct of_device_id *match; struct ravb_private *priv; enum ravb_chip_id chip_id; struct net_device *ndev; @@ -1740,8 +1739,7 @@ static int ravb_probe(struct platform_device *pdev) ndev->base_addr = res->start; ndev->dma = -1; - match = of_match_device(of_match_ptr(ravb_match_table), &pdev->dev); - chip_id = (enum ravb_chip_id)match->data; + chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev); if (chip_id == RCAR_GEN3) irq = platform_get_irq_byname(pdev, "ch22"); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index a2767336b7c5..2e9a78164054 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1127,11 +1127,8 @@ static void sh_eth_ring_format(struct net_device *ndev) break; sh_eth_set_receive_align(skb); - /* RX descriptor */ - rxdesc = &mdp->rx_ring[i]; /* The size of the buffer is a multiple of 32 bytes. */ buf_len = ALIGN(mdp->rx_buf_sz, 32); - rxdesc->len = cpu_to_le32(buf_len << 16); dma_addr = dma_map_single(&ndev->dev, skb->data, buf_len, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, dma_addr)) { @@ -1139,6 +1136,10 @@ static void sh_eth_ring_format(struct net_device *ndev) break; } mdp->rx_skbuff[i] = skb; + + /* RX descriptor */ + rxdesc = &mdp->rx_ring[i]; + rxdesc->len = cpu_to_le32(buf_len << 16); rxdesc->addr = cpu_to_le32(dma_addr); rxdesc->status = cpu_to_le32(RD_RACT | RD_RFP); @@ -1154,7 +1155,8 @@ static void sh_eth_ring_format(struct net_device *ndev) mdp->dirty_rx = (u32) (i - mdp->num_rx_ring); /* Mark the last entry as wrapping the ring. */ - rxdesc->status |= cpu_to_le32(RD_RDLE); + if (rxdesc) + rxdesc->status |= cpu_to_le32(RD_RDLE); memset(mdp->tx_ring, 0, tx_ringsize); @@ -3044,15 +3046,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev) mdp->ether_link_active_low = pd->ether_link_active_low; /* set cpu data */ - if (id) { + if (id) mdp->cd = (struct sh_eth_cpu_data *)id->driver_data; - } else { - const struct of_device_id *match; + else + mdp->cd = (struct sh_eth_cpu_data *)of_device_get_match_data(&pdev->dev); - match = of_match_device(of_match_ptr(sh_eth_match_table), - &pdev->dev); - mdp->cd = (struct sh_eth_cpu_data *)match->data; - } mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type); if (!mdp->reg_offset) { dev_err(&pdev->dev, "Unknown register type (%d)\n", diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 07218c360d86..0e758bcb26b0 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -188,6 +188,7 @@ struct ofdpa { DECLARE_HASHTABLE(neigh_tbl, 16); spinlock_t neigh_tbl_lock; /* for neigh tbl accesses */ u32 neigh_tbl_next_index; + unsigned long ageing_time; }; struct ofdpa_port { @@ -2105,7 +2106,7 @@ static void ofdpa_fdb_cleanup(unsigned long data) struct ofdpa_port *ofdpa_port; struct ofdpa_fdb_tbl_entry *entry; struct hlist_node *tmp; - unsigned long next_timer = jiffies + BR_MIN_AGEING_TIME; + unsigned long next_timer = jiffies + ofdpa->ageing_time; unsigned long expires; unsigned long lock_flags; int flags = OFDPA_OP_FLAG_NOWAIT | OFDPA_OP_FLAG_REMOVE | @@ -2492,6 +2493,8 @@ static int ofdpa_init(struct rocker *rocker) (unsigned long) ofdpa); mod_timer(&ofdpa->fdb_cleanup_timer, jiffies); + ofdpa->ageing_time = BR_DEFAULT_AGEING_TIME; + return 0; } @@ -2648,9 +2651,12 @@ ofdpa_port_attr_bridge_ageing_time_set(struct rocker_port *rocker_port, struct switchdev_trans *trans) { struct ofdpa_port *ofdpa_port = rocker_port->wpriv; + struct ofdpa *ofdpa = ofdpa_port->ofdpa; if (!switchdev_trans_ph_prepare(trans)) { ofdpa_port->ageing_time = clock_t_to_jiffies(ageing_time); + if (ofdpa_port->ageing_time < ofdpa->ageing_time) + ofdpa->ageing_time = ofdpa_port->ageing_time; mod_timer(&ofdpa_port->ofdpa->fdb_cleanup_timer, jiffies); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 0faf16336035..efb54f356a67 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -199,21 +199,12 @@ int stmmac_mdio_register(struct net_device *ndev) struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; int addr, found; - struct device_node *mdio_node = NULL; - struct device_node *child_node = NULL; + struct device_node *mdio_node = priv->plat->mdio_node; if (!mdio_bus_data) return 0; if (IS_ENABLED(CONFIG_OF)) { - for_each_child_of_node(priv->device->of_node, child_node) { - if (of_device_is_compatible(child_node, - "snps,dwmac-mdio")) { - mdio_node = child_node; - break; - } - } - if (mdio_node) { netdev_dbg(ndev, "FOUND MDIO subnode\n"); } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 69ccf486d4fa..dcbd2a1601e8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -112,7 +112,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) if (!np) return NULL; - axi = kzalloc(sizeof(axi), GFP_KERNEL); + axi = kzalloc(sizeof(*axi), GFP_KERNEL); if (!axi) return ERR_PTR(-ENOMEM); @@ -146,6 +146,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + struct device_node *child_node = NULL; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -176,13 +177,19 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->phy_node = of_node_get(np); } + for_each_child_of_node(np, child_node) + if (of_device_is_compatible(child_node, "snps,dwmac-mdio")) { + plat->mdio_node = child_node; + break; + } + /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name) + if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node) plat->mdio_bus_data = NULL; else plat->mdio_bus_data = diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index fc8bbff2d7e3..af11ed1e0bcc 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -426,7 +426,7 @@ #define DWC_MMC_RXOCTETCOUNT_GB 0x0784 #define DWC_MMC_RXPACKETCOUNT_GB 0x0780 -static int debug = 3; +static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "DWC_eth_qos debug level (0=none,...,16=all)"); @@ -650,6 +650,11 @@ struct net_local { u32 mmc_tx_counters_mask; struct dwceqos_flowcontrol flowcontrol; + + /* Tracks the intermediate state of phy started but hardware + * init not finished yet. + */ + bool phy_defer; }; static void dwceqos_read_mmc_counters(struct net_local *lp, u32 rx_mask, @@ -901,6 +906,9 @@ static void dwceqos_adjust_link(struct net_device *ndev) struct phy_device *phydev = lp->phy_dev; int status_change = 0; + if (lp->phy_defer) + return; + if (phydev->link) { if ((lp->speed != phydev->speed) || (lp->duplex != phydev->duplex)) { @@ -1113,7 +1121,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) /* Allocate DMA descriptors */ size = DWCEQOS_RX_DCNT * sizeof(struct dwceqos_dma_desc); lp->rx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->rx_descs_addr, 0); + &lp->rx_descs_addr, GFP_KERNEL); if (!lp->rx_descs) goto err_out; lp->rx_descs_tail_addr = lp->rx_descs_addr + @@ -1121,7 +1129,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) size = DWCEQOS_TX_DCNT * sizeof(struct dwceqos_dma_desc); lp->tx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->tx_descs_addr, 0); + &lp->tx_descs_addr, GFP_KERNEL); if (!lp->tx_descs) goto err_out; lp->tx_descs_tail_addr = lp->tx_descs_addr + @@ -1635,6 +1643,12 @@ static void dwceqos_init_hw(struct net_local *lp) regval = dwceqos_read(lp, REG_DWCEQOS_MAC_CFG); dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, regval | DWCEQOS_MAC_CFG_TE | DWCEQOS_MAC_CFG_RE); + + lp->phy_defer = false; + mutex_lock(&lp->phy_dev->lock); + phy_read_status(lp->phy_dev); + dwceqos_adjust_link(lp->ndev); + mutex_unlock(&lp->phy_dev->lock); } static void dwceqos_tx_reclaim(unsigned long data) @@ -1880,9 +1894,13 @@ static int dwceqos_open(struct net_device *ndev) } netdev_reset_queue(ndev); + /* The dwceqos reset state machine requires all phy clocks to complete, + * hence the unusual init order with phy_start first. + */ + lp->phy_defer = true; + phy_start(lp->phy_dev); dwceqos_init_hw(lp); napi_enable(&lp->napi); - phy_start(lp->phy_dev); netif_start_queue(ndev); tasklet_enable(&lp->tx_bdreclaim_tasklet); @@ -1915,18 +1933,19 @@ static int dwceqos_stop(struct net_device *ndev) { struct net_local *lp = netdev_priv(ndev); - phy_stop(lp->phy_dev); - tasklet_disable(&lp->tx_bdreclaim_tasklet); - netif_stop_queue(ndev); napi_disable(&lp->napi); - dwceqos_drain_dma(lp); + /* Stop all tx before we drain the tx dma. */ + netif_tx_lock_bh(lp->ndev); + netif_stop_queue(ndev); + netif_tx_unlock_bh(lp->ndev); - netif_tx_lock(lp->ndev); + dwceqos_drain_dma(lp); dwceqos_reset_hw(lp); + phy_stop(lp->phy_dev); + dwceqos_descriptor_free(lp); - netif_tx_unlock(lp->ndev); return 0; } @@ -2178,12 +2197,10 @@ static int dwceqos_start_xmit(struct sk_buff *skb, struct net_device *ndev) ((trans.initial_descriptor + trans.nr_descriptors) % DWCEQOS_TX_DCNT)); - dwceqos_tx_finalize(skb, lp, &trans); - - netdev_sent_queue(ndev, skb->len); - spin_lock_bh(&lp->tx_lock); lp->tx_free -= trans.nr_descriptors; + dwceqos_tx_finalize(skb, lp, &trans); + netdev_sent_queue(ndev, skb->len); spin_unlock_bh(&lp->tx_lock); ndev->trans_start = jiffies; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index bc5da357e16d..192631a345df 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -68,6 +68,7 @@ struct geneve_dev { u8 tos; /* TOS override */ union geneve_addr remote; /* IP address for link partner */ struct list_head next; /* geneve's per namespace list */ + __be32 label; /* IPv6 flowlabel override */ __be16 dst_port; bool collect_md; struct gro_cells gro_cells; @@ -462,8 +463,6 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head, goto out; } - flush = 0; - for (p = *head; p; p = p->next) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -480,14 +479,13 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head, rcu_read_lock(); ptype = gro_find_receive_by_type(type); - if (!ptype) { - flush = 1; + if (!ptype) goto out_unlock; - } skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); pp = ptype->callbacks.gro_receive(head, skb); + flush = 0; out_unlock: rcu_read_unlock(); @@ -775,10 +773,10 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, struct flowi4 *fl4, struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); struct dst_cache *dst_cache; struct rtable *rt = NULL; - bool use_cache = true; __u8 tos; memset(fl4, 0, sizeof(*fl4)); @@ -804,7 +802,6 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, dst_cache = &geneve->dst_cache; } - use_cache = use_cache && !skb->mark; if (use_cache) { rt = dst_cache_get_ip4(dst_cache, &fl4->saddr); if (rt) @@ -832,11 +829,11 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, struct flowi6 *fl6, struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs6 = geneve->sock6; struct dst_entry *dst = NULL; struct dst_cache *dst_cache; - bool use_cache = true; __u8 prio; memset(fl6, 0, sizeof(*fl6)); @@ -847,6 +844,7 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, fl6->daddr = info->key.u.ipv6.dst; fl6->saddr = info->key.u.ipv6.src; fl6->flowi6_tos = RT_TOS(info->key.tos); + fl6->flowlabel = info->key.label; dst_cache = &info->dst_cache; } else { prio = geneve->tos; @@ -858,11 +856,11 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, } fl6->flowi6_tos = RT_TOS(prio); + fl6->flowlabel = geneve->label; fl6->daddr = geneve->remote.sin6.sin6_addr; dst_cache = &geneve->dst_cache; } - use_cache = use_cache && !skb->mark; if (use_cache) { dst = dst_cache_get_ip6(dst_cache, &fl6->saddr); if (dst) @@ -940,7 +938,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, u8 vni[3]; tunnel_id_to_vni(key->tun_id, vni); - if (key->tun_flags & TUNNEL_GENEVE_OPT) + if (info->options_len) opts = ip_tunnel_info_opts(info); if (key->tun_flags & TUNNEL_CSUM) @@ -1000,6 +998,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct flowi6 fl6; __u8 prio, ttl; __be16 sport; + __be32 label; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); u32 flags = geneve->flags; @@ -1027,7 +1026,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, u8 vni[3]; tunnel_id_to_vni(key->tun_id, vni); - if (key->tun_flags & TUNNEL_GENEVE_OPT) + if (info->options_len) opts = ip_tunnel_info_opts(info); if (key->tun_flags & TUNNEL_CSUM) @@ -1043,6 +1042,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, prio = ip_tunnel_ecn_encap(key->tos, iip, skb); ttl = key->ttl; + label = info->key.label; } else { err = geneve6_build_skb(dst, skb, 0, geneve->vni, 0, NULL, flags, xnet); @@ -1054,9 +1054,11 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (!ttl && ipv6_addr_is_multicast(&fl6.daddr)) ttl = 1; ttl = ttl ? : ip6_dst_hoplimit(dst); + label = geneve->label; } + udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, - &fl6.saddr, &fl6.daddr, prio, ttl, + &fl6.saddr, &fl6.daddr, prio, ttl, label, sport, geneve->dst_port, !!(flags & GENEVE_F_UDP_ZERO_CSUM6_TX)); return NETDEV_TX_OK; @@ -1240,6 +1242,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, + [IFLA_GENEVE_LABEL] = { .type = NLA_U32 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, @@ -1297,8 +1300,8 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, static int geneve_configure(struct net *net, struct net_device *dev, union geneve_addr *remote, - __u32 vni, __u8 ttl, __u8 tos, __be16 dst_port, - bool metadata, u32 flags) + __u32 vni, __u8 ttl, __u8 tos, __be32 label, + __be16 dst_port, bool metadata, u32 flags) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); @@ -1308,7 +1311,7 @@ static int geneve_configure(struct net *net, struct net_device *dev, if (!remote) return -EINVAL; if (metadata && - (remote->sa.sa_family != AF_UNSPEC || vni || tos || ttl)) + (remote->sa.sa_family != AF_UNSPEC || vni || tos || ttl || label)) return -EINVAL; geneve->net = net; @@ -1323,10 +1326,14 @@ static int geneve_configure(struct net *net, struct net_device *dev, (remote->sa.sa_family == AF_INET6 && ipv6_addr_is_multicast(&remote->sin6.sin6_addr))) return -EINVAL; + if (label && remote->sa.sa_family != AF_INET6) + return -EINVAL; + geneve->remote = *remote; geneve->ttl = ttl; geneve->tos = tos; + geneve->label = label; geneve->dst_port = dst_port; geneve->collect_md = metadata; geneve->flags = flags; @@ -1369,6 +1376,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev, __u8 ttl = 0, tos = 0; bool metadata = false; union geneve_addr remote = geneve_remote_unspec; + __be32 label = 0; __u32 vni = 0; u32 flags = 0; @@ -1405,6 +1413,10 @@ static int geneve_newlink(struct net *net, struct net_device *dev, if (data[IFLA_GENEVE_TOS]) tos = nla_get_u8(data[IFLA_GENEVE_TOS]); + if (data[IFLA_GENEVE_LABEL]) + label = nla_get_be32(data[IFLA_GENEVE_LABEL]) & + IPV6_FLOWLABEL_MASK; + if (data[IFLA_GENEVE_PORT]) dst_port = nla_get_be16(data[IFLA_GENEVE_PORT]); @@ -1423,8 +1435,8 @@ static int geneve_newlink(struct net *net, struct net_device *dev, nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) flags |= GENEVE_F_UDP_ZERO_CSUM6_RX; - return geneve_configure(net, dev, &remote, vni, ttl, tos, dst_port, - metadata, flags); + return geneve_configure(net, dev, &remote, vni, ttl, tos, label, + dst_port, metadata, flags); } static void geneve_dellink(struct net_device *dev, struct list_head *head) @@ -1441,6 +1453,7 @@ static size_t geneve_get_size(const struct net_device *dev) nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ + nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ @@ -1471,7 +1484,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) } if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) || - nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos)) + nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos) || + nla_put_be32(skb, IFLA_GENEVE_LABEL, geneve->label)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_GENEVE_PORT, geneve->dst_port)) @@ -1523,7 +1537,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, return dev; err = geneve_configure(net, dev, &geneve_remote_unspec, - 0, 0, 0, htons(dst_port), true, + 0, 0, 0, 0, htons(dst_port), true, GENEVE_F_UDP_ZERO_CSUM6_RX); if (err) goto err; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index a37bbda37ffa..47d07c576a34 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1175,22 +1175,18 @@ int rndis_filter_device_add(struct hv_device *dev, ret = rndis_filter_set_rss_param(rndis_device, net_device->num_chn); /* - * Wait for the host to send us the sub-channel offers. + * Set the number of sub-channels to be received. */ spin_lock_irqsave(&net_device->sc_lock, flags); sc_delta = num_rss_qs - (net_device->num_chn - 1); net_device->num_sc_offered -= sc_delta; spin_unlock_irqrestore(&net_device->sc_lock, flags); - while (net_device->num_sc_offered != 0) { - t = wait_for_completion_timeout(&net_device->channel_init_wait, 10*HZ); - if (t == 0) - WARN(1, "Netvsc: Waiting for sub-channel processing"); - } out: if (ret) { net_device->max_chn = 1; net_device->num_chn = 1; + net_device->num_sc_offered = 0; } return 0; /* return 0 because primary channel can be used alone */ @@ -1204,6 +1200,17 @@ void rndis_filter_device_remove(struct hv_device *dev) { struct netvsc_device *net_dev = hv_get_drvdata(dev); struct rndis_device *rndis_dev = net_dev->extension; + unsigned long t; + + /* If not all subchannel offers are complete, wait for them until + * completion to avoid race. + */ + while (net_dev->num_sc_offered > 0) { + t = wait_for_completion_timeout(&net_dev->channel_init_wait, + 10 * HZ); + if (t == 0) + WARN(1, "Netvsc: Waiting for sub-channel processing"); + } /* Halt and release the rndis device */ rndis_filter_halt_device(rndis_dev); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index d636d051fac8..95394edd1ed5 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -760,6 +760,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN; if (copylen > good_linear) copylen = good_linear; + else if (copylen < ETH_HLEN) + copylen = ETH_HLEN; linear = copylen; i = *from; iov_iter_advance(&i, copylen); @@ -769,10 +771,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (!zerocopy) { copylen = len; - if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear) + linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len); + if (linear > good_linear) linear = good_linear; - else - linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len); + else if (linear < ETH_HLEN) + linear = ETH_HLEN; } skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen, diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 48219c83fb00..4516c8a4fd82 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -297,6 +297,17 @@ static int kszphy_config_init(struct phy_device *phydev) if (priv->led_mode >= 0) kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode); + if (phy_interrupt_is_valid(phydev)) { + int ctl = phy_read(phydev, MII_BMCR); + + if (ctl < 0) + return ctl; + + ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE); + if (ret < 0) + return ret; + } + return 0; } @@ -636,6 +647,21 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } +static int kszphy_resume(struct phy_device *phydev) +{ + int value; + + mutex_lock(&phydev->lock); + + value = phy_read(phydev, MII_BMCR); + phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN); + + kszphy_config_intr(phydev); + mutex_unlock(&phydev->lock); + + return 0; +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -845,7 +871,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8061, .name = "Micrel KSZ8061", diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 04f4eb34fa80..931836e09a6b 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -443,9 +443,14 @@ static ssize_t ppp_read(struct file *file, char __user *buf, * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && - (ppp->flags & SC_LOOP_TRAFFIC) == 0) + (ppp->flags & SC_LOOP_TRAFFIC) == 0) { + ppp_recv_unlock(ppp); break; + } + ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) @@ -532,9 +537,12 @@ static unsigned int ppp_poll(struct file *file, poll_table *wait) else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= POLLIN | POLLRDNORM; + ppp_recv_unlock(ppp); } return mask; @@ -2810,6 +2818,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, out2: mutex_unlock(&pn->all_ppp_mutex); + rtnl_unlock(); free_netdev(dev); out1: *retp = ret; diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 224e7d82de6d..cf77f2dffa69 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -134,7 +134,6 @@ static void ax88172a_remove_mdio(struct usbnet *dev) netdev_info(dev->net, "deregistering mdio bus %s\n", priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index dc0212c3cc28..86ba30ba35e8 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -837,7 +837,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; - /* reset data interface */ + /* Reset data interface. Some devices will not reset properly + * unless they are configured first. Toggle the altsetting to + * force a reset + */ + usb_set_interface(dev->udev, iface_no, data_altsetting); temp = usb_set_interface(dev->udev, iface_no, 0); if (temp) { dev_dbg(&intf->dev, "set interface failed\n"); @@ -984,8 +988,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting); static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) { - int ret; - /* MBIM backwards compatible function? */ if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM) return -ENODEV; @@ -994,16 +996,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) * Additionally, generic NCM devices are assumed to accept arbitrarily * placed NDP. */ - ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); - - /* - * We should get an event when network connection is "connected" or - * "disconnected". Set network connection in "disconnected" state - * (carrier is OFF) during attach, so the IP network stack does not - * start IPv6 negotiation and more. - */ - usbnet_link_change(dev, 0, 0); - return ret; + return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); } static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max) @@ -1586,7 +1579,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) static const struct driver_info cdc_ncm_info = { .description = "CDC NCM", - .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET, + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_LINK_INTR, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1599,7 +1593,7 @@ static const struct driver_info cdc_ncm_info = { static const struct driver_info wwan_info = { .description = "Mobile Broadband Network Device", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN, + | FLAG_LINK_INTR | FLAG_WWAN, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1612,7 +1606,7 @@ static const struct driver_info wwan_info = { static const struct driver_info wwan_noarp_info = { .description = "Mobile Broadband Network Device (NO ARP)", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN | FLAG_NOARP, + | FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 570deef53f74..a3a4ccf7cf52 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -861,8 +861,10 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx/EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ @@ -885,6 +887,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ {QMI_FIXED_INTF(0x1e0e, 0x9001, 5)}, /* SIMCom 7230E */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 0b0ba7ef14e4..10798128c03f 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1769,6 +1769,13 @@ out3: if (info->unbind) info->unbind (dev, udev); out1: + /* subdrivers must undo all they did in bind() if they + * fail it, but we may fail later and a deferred kevent + * may trigger an error resubmitting itself and, worse, + * schedule a timer. So we kill it all just in case. + */ + cancel_work_sync(&dev->kevent); + del_timer_sync(&dev->delay); free_netdev(net); out: return status; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 0cbf520cea77..fc895d0e85d9 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -814,7 +814,7 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) /* - * parse and copy relevant protocol headers: + * parse relevant protocol headers: * For a tso pkt, relevant headers are L2/3/4 including options * For a pkt requesting csum offloading, they are L2/3 and may include L4 * if it's a TCP/UDP pkt @@ -827,15 +827,14 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) * Other effects: * 1. related *ctx fields are updated. * 2. ctx->copy_size is # of bytes copied - * 3. the portion copied is guaranteed to be in the linear part + * 3. the portion to be copied is guaranteed to be in the linear part * */ static int -vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, - struct vmxnet3_tx_ctx *ctx, - struct vmxnet3_adapter *adapter) +vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) { - struct Vmxnet3_TxDataDesc *tdd; u8 protocol = 0; if (ctx->mss) { /* TSO */ @@ -892,16 +891,34 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, return 0; } + return 1; +err: + return -1; +} + +/* + * copy relevant protocol headers to the transmit ring: + * For a tso pkt, relevant headers are L2/3/4 including options + * For a pkt requesting csum offloading, they are L2/3 and may include L4 + * if it's a TCP/UDP pkt + * + * + * Note that this requires that vmxnet3_parse_hdr be called first to set the + * appropriate bits in ctx first + */ +static void +vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_TxDataDesc *tdd; + tdd = tq->data_ring.base + tq->tx_ring.next2fill; memcpy(tdd->data, skb->data, ctx->copy_size); netdev_dbg(adapter->netdev, "copy %u bytes to dataRing[%u]\n", ctx->copy_size, tq->tx_ring.next2fill); - return 1; - -err: - return -1; } @@ -998,22 +1015,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } - spin_lock_irqsave(&tq->tx_lock, flags); - - if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { - tq->stats.tx_ring_full++; - netdev_dbg(adapter->netdev, - "tx queue stopped on %s, next2comp %u" - " next2fill %u\n", adapter->netdev->name, - tq->tx_ring.next2comp, tq->tx_ring.next2fill); - - vmxnet3_tq_stop(tq, adapter); - spin_unlock_irqrestore(&tq->tx_lock, flags); - return NETDEV_TX_BUSY; - } - - - ret = vmxnet3_parse_and_copy_hdr(skb, tq, &ctx, adapter); + ret = vmxnet3_parse_hdr(skb, tq, &ctx, adapter); if (ret >= 0) { BUG_ON(ret <= 0 && ctx.copy_size != 0); /* hdrs parsed, check against other limits */ @@ -1033,9 +1035,26 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } else { tq->stats.drop_hdr_inspect_err++; - goto unlock_drop_pkt; + goto drop_pkt; } + spin_lock_irqsave(&tq->tx_lock, flags); + + if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { + tq->stats.tx_ring_full++; + netdev_dbg(adapter->netdev, + "tx queue stopped on %s, next2comp %u" + " next2fill %u\n", adapter->netdev->name, + tq->tx_ring.next2comp, tq->tx_ring.next2fill); + + vmxnet3_tq_stop(tq, adapter); + spin_unlock_irqrestore(&tq->tx_lock, flags); + return NETDEV_TX_BUSY; + } + + + vmxnet3_copy_hdr(skb, tq, &ctx, adapter); + /* fill tx descs related to addr & len */ if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter)) goto unlock_drop_pkt; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 9ce088bb28ab..9a9fabb900c1 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -103,20 +103,23 @@ static struct dst_ops vrf_dst_ops = { #if IS_ENABLED(CONFIG_IPV6) static bool check_ipv6_frame(const struct sk_buff *skb) { - const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data; - size_t hlen = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h; + struct ipv6hdr _ipv6h; bool rc = true; - if (skb->len < hlen) + ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h); + if (!ipv6h) goto out; if (ipv6h->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; + struct icmp6hdr _icmph; - if (skb->len < hlen + sizeof(*icmph)) + icmph = skb_header_pointer(skb, sizeof(_ipv6h), + sizeof(_icmph), &_icmph); + if (!icmph) goto out; - icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h)); switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 8ca243d93b78..800106a7246c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -591,8 +591,6 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ - flush = 0; - for (p = *head; p; p = p->next) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -606,6 +604,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, } pp = eth_gro_receive(head, skb); + flush = 0; out: skb_gro_remcsum_cleanup(skb, &grc); @@ -948,8 +947,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + cb->args[1] = err; goto out; + } skip: ++idx; } @@ -1176,9 +1177,10 @@ static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, md->gbp = ntohs(gbp->policy_id); tun_dst = (struct metadata_dst *)skb_dst(skb); - if (tun_dst) + if (tun_dst) { tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; - + tun_dst->u.tun_info.options_len = sizeof(*md); + } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; @@ -1753,17 +1755,15 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct sk_buff *skb, int oif, u8 tos, __be32 daddr, __be32 *saddr, struct dst_cache *dst_cache, - struct ip_tunnel_info *info) + const struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct rtable *rt = NULL; - bool use_cache = false; struct flowi4 fl4; - /* when the ip_tunnel_info is availble, the tos used for lookup is - * packet independent, so we can use the cache - */ - if (!skb->mark && (!tos || info)) { - use_cache = true; + if (tos && !info) + use_cache = false; + if (use_cache) { rt = dst_cache_get_ip4(dst_cache, saddr); if (rt) return rt; @@ -1788,16 +1788,21 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, #if IS_ENABLED(CONFIG_IPV6) static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, - struct sk_buff *skb, int oif, + struct sk_buff *skb, int oif, u8 tos, + __be32 label, const struct in6_addr *daddr, struct in6_addr *saddr, - struct dst_cache *dst_cache) + struct dst_cache *dst_cache, + const struct ip_tunnel_info *info) { + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct dst_entry *ndst; struct flowi6 fl6; int err; - if (!skb->mark) { + if (tos && !info) + use_cache = false; + if (use_cache) { ndst = dst_cache_get_ip6(dst_cache, saddr); if (ndst) return ndst; @@ -1805,8 +1810,10 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; + fl6.flowi6_tos = RT_TOS(tos); fl6.daddr = *daddr; fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; + fl6.flowlabel = label; fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; @@ -1817,7 +1824,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, return ERR_PTR(err); *saddr = fl6.saddr; - if (!skb->mark) + if (use_cache) dst_cache_set_ip6(dst_cache, ndst, saddr); return ndst; } @@ -1882,7 +1889,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 src_port = 0, dst_port; - __be32 vni; + __be32 vni, label; __be16 df = 0; __u8 tos, ttl; int err; @@ -1933,12 +1940,14 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); + label = vxlan->cfg.label; src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); if (info) { ttl = info->key.ttl; tos = info->key.tos; + label = info->key.label; udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); if (info->options_len) @@ -2013,9 +2022,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, sk = vxlan->vn6_sock->sock->sk; ndst = vxlan6_get_route(vxlan, skb, - rdst ? rdst->remote_ifindex : 0, - &dst->sin6.sin6_addr, &saddr, - dst_cache); + rdst ? rdst->remote_ifindex : 0, tos, + label, &dst->sin6.sin6_addr, &saddr, + dst_cache, info); if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", &dst->sin6.sin6_addr); @@ -2050,6 +2059,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (!info) udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), @@ -2059,8 +2069,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } udp_tunnel6_xmit_skb(ndst, sk, skb, dev, - &saddr, &dst->sin6.sin6_addr, - 0, ttl, src_port, dst_port, !udp_sum); + &saddr, &dst->sin6.sin6_addr, tos, ttl, + label, src_port, dst_port, !udp_sum); #endif } @@ -2382,9 +2392,9 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) if (!vxlan->vn6_sock) return -EINVAL; - ndst = vxlan6_get_route(vxlan, skb, 0, - &info->key.u.ipv6.dst, - &info->key.u.ipv6.src, NULL); + ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos, + info->key.label, &info->key.u.ipv6.dst, + &info->key.u.ipv6.src, NULL, info); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); @@ -2498,6 +2508,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, + [IFLA_VXLAN_LABEL] = { .type = NLA_U32 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, @@ -2732,6 +2743,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, vxlan->flags |= VXLAN_F_IPV6; } + if (conf->label && !use_ipv6) { + pr_info("label only supported in use with IPv6\n"); + return -EINVAL; + } + if (conf->remote_ifindex) { lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); dst->remote_ifindex = conf->remote_ifindex; @@ -2880,6 +2896,10 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (data[IFLA_VXLAN_TTL]) conf.ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); + if (data[IFLA_VXLAN_LABEL]) + conf.label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & + IPV6_FLOWLABEL_MASK; + if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING])) conf.flags |= VXLAN_F_LEARN; @@ -2983,6 +3003,7 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ + nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ @@ -3046,6 +3067,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || + nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 7e2c43f701bc..5d28e9405f32 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -382,18 +382,18 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = { [ND_CMD_ARS_CAP] = { .in_num = 2, .in_sizes = { 8, 8, }, - .out_num = 2, - .out_sizes = { 4, 4, }, + .out_num = 4, + .out_sizes = { 4, 4, 4, 4, }, }, [ND_CMD_ARS_START] = { - .in_num = 4, - .in_sizes = { 8, 8, 2, 6, }, - .out_num = 1, - .out_sizes = { 4, }, + .in_num = 5, + .in_sizes = { 8, 8, 2, 1, 5, }, + .out_num = 2, + .out_sizes = { 4, 4, }, }, [ND_CMD_ARS_STATUS] = { - .out_num = 2, - .out_sizes = { 4, UINT_MAX, }, + .out_num = 3, + .out_sizes = { 4, 4, UINT_MAX, }, }, }; @@ -442,8 +442,8 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, return in_field[1]; else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) return out_field[1]; - else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1) - return ND_CMD_ARS_STATUS_MAX; + else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) + return out_field[1] - 8; return UINT_MAX; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7edf31671dab..8d0b54670184 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -41,7 +41,7 @@ struct pmem_device { phys_addr_t phys_addr; /* when non-zero this device is hosting a 'pfn' instance */ phys_addr_t data_offset; - unsigned long pfn_flags; + u64 pfn_flags; void __pmem *virt_addr; size_t size; struct badblocks bb; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3cd921e6121e..03c46412fff4 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -55,8 +55,9 @@ static void nvme_free_ns(struct kref *kref) ns->disk->private_data = NULL; spin_unlock(&dev_list_lock); - nvme_put_ctrl(ns->ctrl); put_disk(ns->disk); + ida_simple_remove(&ns->ctrl->ns_ida, ns->instance); + nvme_put_ctrl(ns->ctrl); kfree(ns); } @@ -183,7 +184,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, goto out_unmap; } - if (meta_buffer) { + if (meta_buffer && meta_len) { struct bio_integrity_payload *bip; meta = kmalloc(meta_len, GFP_KERNEL); @@ -373,6 +374,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) if (copy_from_user(&io, uio, sizeof(io))) return -EFAULT; + if (io.flags) + return -EINVAL; switch (io.opcode) { case nvme_cmd_write: @@ -424,6 +427,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return -EACCES; if (copy_from_user(&cmd, ucmd, sizeof(cmd))) return -EFAULT; + if (cmd.flags) + return -EINVAL; memset(&c, 0, sizeof(c)); c.common.opcode = cmd.opcode; @@ -556,6 +561,10 @@ static int nvme_revalidate_disk(struct gendisk *disk) u16 old_ms; unsigned short bs; + if (test_bit(NVME_NS_DEAD, &ns->flags)) { + set_capacity(disk, 0); + return -ENODEV; + } if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) { dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n", __func__, ns->ctrl->instance, ns->ns_id); @@ -831,6 +840,23 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) return ret; } +static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, + struct request_queue *q) +{ + if (ctrl->max_hw_sectors) { + u32 max_segments = + (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1; + + blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); + blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); + } + if (ctrl->stripe_size) + blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9); + if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) + blk_queue_flush(q, REQ_FLUSH | REQ_FUA); + blk_queue_virt_boundary(q, ctrl->page_size - 1); +} + /* * Initialize the cached copies of the Identify data and various controller * register in our nvme_ctrl structure. This should be called as soon as @@ -888,6 +914,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) } } + nvme_set_queue_limits(ctrl, ctrl->admin_q); + kfree(id); return 0; } @@ -1118,9 +1146,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (!ns) return; + ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL); + if (ns->instance < 0) + goto out_free_ns; + ns->queue = blk_mq_init_queue(ctrl->tagset); if (IS_ERR(ns->queue)) - goto out_free_ns; + goto out_release_instance; queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue); ns->queue->queuedata = ns; ns->ctrl = ctrl; @@ -1134,17 +1166,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->disk = disk; ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */ + blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); - if (ctrl->max_hw_sectors) { - blk_queue_max_hw_sectors(ns->queue, ctrl->max_hw_sectors); - blk_queue_max_segments(ns->queue, - (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1); - } - if (ctrl->stripe_size) - blk_queue_chunk_sectors(ns->queue, ctrl->stripe_size >> 9); - if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) - blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA); - blk_queue_virt_boundary(ns->queue, ctrl->page_size - 1); + nvme_set_queue_limits(ctrl, ns->queue); disk->major = nvme_major; disk->first_minor = 0; @@ -1153,7 +1177,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) disk->queue = ns->queue; disk->driverfs_dev = ctrl->device; disk->flags = GENHD_FL_EXT_DEVT; - sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, nsid); + sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance); if (nvme_revalidate_disk(ns->disk)) goto out_free_disk; @@ -1173,40 +1197,29 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) kfree(disk); out_free_queue: blk_cleanup_queue(ns->queue); + out_release_instance: + ida_simple_remove(&ctrl->ns_ida, ns->instance); out_free_ns: kfree(ns); } static void nvme_ns_remove(struct nvme_ns *ns) { - bool kill = nvme_io_incapable(ns->ctrl) && - !blk_queue_dying(ns->queue); - - lockdep_assert_held(&ns->ctrl->namespaces_mutex); - - if (kill) { - blk_set_queue_dying(ns->queue); + if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) + return; - /* - * The controller was shutdown first if we got here through - * device removal. The shutdown may requeue outstanding - * requests. These need to be aborted immediately so - * del_gendisk doesn't block indefinitely for their completion. - */ - blk_mq_abort_requeue_list(ns->queue); - } if (ns->disk->flags & GENHD_FL_UP) { if (blk_get_integrity(ns->disk)) blk_integrity_unregister(ns->disk); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_attr_group); del_gendisk(ns->disk); - } - if (kill || !blk_queue_dying(ns->queue)) { blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); } + mutex_lock(&ns->ctrl->namespaces_mutex); list_del_init(&ns->list); + mutex_unlock(&ns->ctrl->namespaces_mutex); nvme_put_ns(ns); } @@ -1300,10 +1313,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) { struct nvme_ns *ns, *next; - mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) nvme_ns_remove(ns); - mutex_unlock(&ctrl->namespaces_mutex); } static DEFINE_IDA(nvme_instance_ida); @@ -1350,6 +1361,7 @@ static void nvme_free_ctrl(struct kref *kref) put_device(ctrl->device); nvme_release_instance(ctrl); + ida_destroy(&ctrl->ns_ida); ctrl->ops->free_ctrl(ctrl); } @@ -1390,6 +1402,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, } get_device(ctrl->device); dev_set_drvdata(ctrl->device, ctrl); + ida_init(&ctrl->ns_ida); spin_lock(&dev_list_lock); list_add_tail(&ctrl->node, &nvme_ctrl_list); @@ -1402,6 +1415,38 @@ out: return ret; } +/** + * nvme_kill_queues(): Ends all namespace queues + * @ctrl: the dead controller that needs to end + * + * Call this function when the driver determines it is unable to get the + * controller in a state capable of servicing IO. + */ +void nvme_kill_queues(struct nvme_ctrl *ctrl) +{ + struct nvme_ns *ns; + + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { + if (!kref_get_unless_zero(&ns->kref)) + continue; + + /* + * Revalidating a dead namespace sets capacity to 0. This will + * end buffered writers dirtying pages that can't be synced. + */ + if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + revalidate_disk(ns->disk); + + blk_set_queue_dying(ns->queue); + blk_mq_abort_requeue_list(ns->queue); + blk_mq_start_stopped_hw_queues(ns->queue, true); + + nvme_put_ns(ns); + } + mutex_unlock(&ctrl->namespaces_mutex); +} + void nvme_stop_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9664d07d807d..fb15ba5f5d19 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -72,6 +72,7 @@ struct nvme_ctrl { struct mutex namespaces_mutex; struct device *device; /* char device */ struct list_head node; + struct ida ns_ida; char name[12]; char serial[20]; @@ -102,6 +103,7 @@ struct nvme_ns { struct request_queue *queue; struct gendisk *disk; struct kref kref; + int instance; u8 eui[8]; u8 uuid[16]; @@ -112,6 +114,11 @@ struct nvme_ns { bool ext; u8 pi_type; int type; + unsigned long flags; + +#define NVME_NS_REMOVING 0 +#define NVME_NS_DEAD 1 + u64 mode_select_num_blocks; u32 mode_select_block_len; }; @@ -240,6 +247,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl); void nvme_stop_queues(struct nvme_ctrl *ctrl); void nvme_start_queues(struct nvme_ctrl *ctrl); +void nvme_kill_queues(struct nvme_ctrl *ctrl); struct request *nvme_alloc_request(struct request_queue *q, struct nvme_command *cmd, unsigned int flags); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a128672472ec..680f5780750c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -86,7 +86,6 @@ struct nvme_queue; static int nvme_reset(struct nvme_dev *dev); static void nvme_process_cq(struct nvme_queue *nvmeq); -static void nvme_remove_dead_ctrl(struct nvme_dev *dev); static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); /* @@ -120,6 +119,7 @@ struct nvme_dev { unsigned long flags; #define NVME_CTRL_RESETTING 0 +#define NVME_CTRL_REMOVING 1 struct nvme_ctrl ctrl; struct completion ioq_wait; @@ -286,6 +286,17 @@ static int nvme_init_request(void *data, struct request *req, return 0; } +static void nvme_queue_scan(struct nvme_dev *dev) +{ + /* + * Do not queue new scan work when a controller is reset during + * removal. + */ + if (test_bit(NVME_CTRL_REMOVING, &dev->flags)) + return; + queue_work(nvme_workq, &dev->scan_work); +} + static void nvme_complete_async_event(struct nvme_dev *dev, struct nvme_completion *cqe) { @@ -300,7 +311,7 @@ static void nvme_complete_async_event(struct nvme_dev *dev, switch (result & 0xff07) { case NVME_AER_NOTICE_NS_CHANGED: dev_info(dev->dev, "rescanning\n"); - queue_work(nvme_workq, &dev->scan_work); + nvme_queue_scan(dev); default: dev_warn(dev->dev, "async event result %08x\n", result); } @@ -679,7 +690,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, spin_lock_irq(&nvmeq->q_lock); if (unlikely(nvmeq->cq_vector < 0)) { - ret = BLK_MQ_RQ_QUEUE_BUSY; + if (ns && !test_bit(NVME_NS_DEAD, &ns->flags)) + ret = BLK_MQ_RQ_QUEUE_BUSY; + else + ret = BLK_MQ_RQ_QUEUE_ERROR; spin_unlock_irq(&nvmeq->q_lock); goto out; } @@ -1250,6 +1264,12 @@ static struct blk_mq_ops nvme_mq_ops = { static void nvme_dev_remove_admin(struct nvme_dev *dev) { if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) { + /* + * If the controller was reset during removal, it's possible + * user requests may be waiting on a stopped queue. Start the + * queue to flush these to completion. + */ + blk_mq_start_stopped_hw_queues(dev->ctrl.admin_q, true); blk_cleanup_queue(dev->ctrl.admin_q); blk_mq_free_tag_set(&dev->admin_tagset); } @@ -1690,14 +1710,14 @@ static int nvme_dev_add(struct nvme_dev *dev) return 0; dev->ctrl.tagset = &dev->tagset; } - queue_work(nvme_workq, &dev->scan_work); + nvme_queue_scan(dev); return 0; } -static int nvme_dev_map(struct nvme_dev *dev) +static int nvme_pci_enable(struct nvme_dev *dev) { u64 cap; - int bars, result = -ENOMEM; + int result = -ENOMEM; struct pci_dev *pdev = to_pci_dev(dev->dev); if (pci_enable_device_mem(pdev)) @@ -1705,24 +1725,14 @@ static int nvme_dev_map(struct nvme_dev *dev) dev->entry[0].vector = pdev->irq; pci_set_master(pdev); - bars = pci_select_bars(pdev, IORESOURCE_MEM); - if (!bars) - goto disable_pci; - - if (pci_request_selected_regions(pdev, bars, "nvme")) - goto disable_pci; if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) && dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32))) goto disable; - dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); - if (!dev->bar) - goto disable; - if (readl(dev->bar + NVME_REG_CSTS) == -1) { result = -ENODEV; - goto unmap; + goto disable; } /* @@ -1732,7 +1742,7 @@ static int nvme_dev_map(struct nvme_dev *dev) if (!pdev->irq) { result = pci_enable_msix(pdev, dev->entry, 1); if (result < 0) - goto unmap; + goto disable; } cap = lo_hi_readq(dev->bar + NVME_REG_CAP); @@ -1759,18 +1769,20 @@ static int nvme_dev_map(struct nvme_dev *dev) pci_save_state(pdev); return 0; - unmap: - iounmap(dev->bar); - dev->bar = NULL; disable: - pci_release_regions(pdev); - disable_pci: pci_disable_device(pdev); return result; } static void nvme_dev_unmap(struct nvme_dev *dev) { + if (dev->bar) + iounmap(dev->bar); + pci_release_regions(to_pci_dev(dev->dev)); +} + +static void nvme_pci_disable(struct nvme_dev *dev) +{ struct pci_dev *pdev = to_pci_dev(dev->dev); if (pdev->msi_enabled) @@ -1778,12 +1790,6 @@ static void nvme_dev_unmap(struct nvme_dev *dev) else if (pdev->msix_enabled) pci_disable_msix(pdev); - if (dev->bar) { - iounmap(dev->bar); - dev->bar = NULL; - pci_release_regions(pdev); - } - if (pci_is_enabled(pdev)) { pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); @@ -1842,7 +1848,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_dev_list_remove(dev); mutex_lock(&dev->shutdown_lock); - if (dev->bar) { + if (pci_is_enabled(to_pci_dev(dev->dev))) { nvme_stop_queues(&dev->ctrl); csts = readl(dev->bar + NVME_REG_CSTS); } @@ -1855,7 +1861,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); } - nvme_dev_unmap(dev); + nvme_pci_disable(dev); for (i = dev->queue_count - 1; i >= 0; i--) nvme_clear_queue(dev->queues[i]); @@ -1899,10 +1905,20 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) kfree(dev); } +static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) +{ + dev_warn(dev->dev, "Removing after probe failure status: %d\n", status); + + kref_get(&dev->ctrl.kref); + nvme_dev_disable(dev, false); + if (!schedule_work(&dev->remove_work)) + nvme_put_ctrl(&dev->ctrl); +} + static void nvme_reset_work(struct work_struct *work) { struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work); - int result; + int result = -ENODEV; if (WARN_ON(test_bit(NVME_CTRL_RESETTING, &dev->flags))) goto out; @@ -1911,37 +1927,37 @@ static void nvme_reset_work(struct work_struct *work) * If we're called to reset a live controller first shut it down before * moving on. */ - if (dev->bar) + if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); set_bit(NVME_CTRL_RESETTING, &dev->flags); - result = nvme_dev_map(dev); + result = nvme_pci_enable(dev); if (result) goto out; result = nvme_configure_admin_queue(dev); if (result) - goto unmap; + goto out; nvme_init_queue(dev->queues[0], 0); result = nvme_alloc_admin_tags(dev); if (result) - goto disable; + goto out; result = nvme_init_identify(&dev->ctrl); if (result) - goto free_tags; + goto out; result = nvme_setup_io_queues(dev); if (result) - goto free_tags; + goto out; dev->ctrl.event_limit = NVME_NR_AEN_COMMANDS; result = nvme_dev_list_add(dev); if (result) - goto remove; + goto out; /* * Keep the controller around but remove all namespaces if we don't have @@ -1958,19 +1974,8 @@ static void nvme_reset_work(struct work_struct *work) clear_bit(NVME_CTRL_RESETTING, &dev->flags); return; - remove: - nvme_dev_list_remove(dev); - free_tags: - nvme_dev_remove_admin(dev); - blk_put_queue(dev->ctrl.admin_q); - dev->ctrl.admin_q = NULL; - dev->queues[0]->tags = NULL; - disable: - nvme_disable_admin_queue(dev, false); - unmap: - nvme_dev_unmap(dev); out: - nvme_remove_dead_ctrl(dev); + nvme_remove_dead_ctrl(dev, result); } static void nvme_remove_dead_ctrl_work(struct work_struct *work) @@ -1978,19 +1983,12 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work) struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work); struct pci_dev *pdev = to_pci_dev(dev->dev); + nvme_kill_queues(&dev->ctrl); if (pci_get_drvdata(pdev)) pci_stop_and_remove_bus_device_locked(pdev); nvme_put_ctrl(&dev->ctrl); } -static void nvme_remove_dead_ctrl(struct nvme_dev *dev) -{ - dev_warn(dev->dev, "Removing after probe failure\n"); - kref_get(&dev->ctrl.kref); - if (!schedule_work(&dev->remove_work)) - nvme_put_ctrl(&dev->ctrl); -} - static int nvme_reset(struct nvme_dev *dev) { if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q)) @@ -2042,6 +2040,27 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = { .free_ctrl = nvme_pci_free_ctrl, }; +static int nvme_dev_map(struct nvme_dev *dev) +{ + int bars; + struct pci_dev *pdev = to_pci_dev(dev->dev); + + bars = pci_select_bars(pdev, IORESOURCE_MEM); + if (!bars) + return -ENODEV; + if (pci_request_selected_regions(pdev, bars, "nvme")) + return -ENODEV; + + dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); + if (!dev->bar) + goto release; + + return 0; + release: + pci_release_regions(pdev); + return -ENODEV; +} + static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int node, result = -ENOMEM; @@ -2066,6 +2085,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev->dev = get_device(&pdev->dev); pci_set_drvdata(pdev, dev); + result = nvme_dev_map(dev); + if (result) + goto free; + INIT_LIST_HEAD(&dev->node); INIT_WORK(&dev->scan_work, nvme_dev_scan); INIT_WORK(&dev->reset_work, nvme_reset_work); @@ -2089,6 +2112,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) nvme_release_prp_pools(dev); put_pci: put_device(dev->dev); + nvme_dev_unmap(dev); free: kfree(dev->queues); kfree(dev->entry); @@ -2112,10 +2136,16 @@ static void nvme_shutdown(struct pci_dev *pdev) nvme_dev_disable(dev, true); } +/* + * The driver's remove may be called on a device in a partially initialized + * state. This function must not have any dependencies on the device state in + * order to proceed. + */ static void nvme_remove(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); + set_bit(NVME_CTRL_REMOVING, &dev->flags); pci_set_drvdata(pdev, NULL); flush_work(&dev->scan_work); nvme_remove_namespaces(&dev->ctrl); @@ -2126,6 +2156,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_free_queues(dev, 0); nvme_release_cmb(dev); nvme_release_prp_pools(dev); + nvme_dev_unmap(dev); nvme_put_ctrl(&dev->ctrl); } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 669739b302b2..5e7838290998 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -303,6 +303,7 @@ EXPORT_SYMBOL(of_phy_find_device); * @dev: pointer to net_device claiming the phy * @phy_np: Pointer to device tree node for the PHY * @hndlr: Link state callback for the network device + * @flags: flags to pass to the PHY * @iface: PHY data interface type * * If successful, returns a pointer to the phy_device with the embedded diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig index 75a605426538..d1cdd9c992ac 100644 --- a/drivers/pci/host/Kconfig +++ b/drivers/pci/host/Kconfig @@ -14,6 +14,7 @@ config PCI_DRA7XX config PCI_MVEBU bool "Marvell EBU PCIe controller" depends on ARCH_MVEBU || ARCH_DOVE + depends on ARM depends on OF config PCIE_DW diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c index ed34c9520a02..6153853ca9c3 100644 --- a/drivers/pci/host/pci-keystone-dw.c +++ b/drivers/pci/host/pci-keystone-dw.c @@ -58,11 +58,6 @@ #define to_keystone_pcie(x) container_of(x, struct keystone_pcie, pp) -static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys) -{ - return sys->private_data; -} - static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset, u32 *bit_pos) { @@ -108,7 +103,7 @@ static void ks_dw_pcie_msi_irq_ack(struct irq_data *d) struct pcie_port *pp; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); update_reg_offset_bit_pos(offset, ®_offset, &bit_pos); @@ -146,7 +141,7 @@ static void ks_dw_pcie_msi_irq_mask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); @@ -167,7 +162,7 @@ static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c index 3923bed93c7e..f39961bcf7aa 100644 --- a/drivers/pci/host/pci-layerscape.c +++ b/drivers/pci/host/pci-layerscape.c @@ -77,6 +77,16 @@ static void ls_pcie_fix_class(struct ls_pcie *pcie) iowrite16(PCI_CLASS_BRIDGE_PCI, pcie->dbi + PCI_CLASS_DEVICE); } +/* Drop MSG TLP except for Vendor MSG */ +static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie) +{ + u32 val; + + val = ioread32(pcie->dbi + PCIE_STRFMR1); + val &= 0xDFFFFFFF; + iowrite32(val, pcie->dbi + PCIE_STRFMR1); +} + static int ls1021_pcie_link_up(struct pcie_port *pp) { u32 state; @@ -97,7 +107,7 @@ static int ls1021_pcie_link_up(struct pcie_port *pp) static void ls1021_pcie_host_init(struct pcie_port *pp) { struct ls_pcie *pcie = to_ls_pcie(pp); - u32 val, index[2]; + u32 index[2]; pcie->scfg = syscon_regmap_lookup_by_phandle(pp->dev->of_node, "fsl,pcie-scfg"); @@ -116,13 +126,7 @@ static void ls1021_pcie_host_init(struct pcie_port *pp) dw_pcie_setup_rc(pp); - /* - * LS1021A Workaround for internal TKT228622 - * to fix the INTx hang issue - */ - val = ioread32(pcie->dbi + PCIE_STRFMR1); - val &= 0xffff; - iowrite32(val, pcie->dbi + PCIE_STRFMR1); + ls_pcie_drop_msg_tlp(pcie); } static int ls_pcie_link_up(struct pcie_port *pp) @@ -147,6 +151,7 @@ static void ls_pcie_host_init(struct pcie_port *pp) iowrite32(1, pcie->dbi + PCIE_DBI_RO_WR_EN); ls_pcie_fix_class(pcie); ls_pcie_clear_multifunction(pcie); + ls_pcie_drop_msg_tlp(pcie); iowrite32(0, pcie->dbi + PCIE_DBI_RO_WR_EN); } diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index c777b97207d5..5f70fee59a94 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -53,7 +53,7 @@ struct pcifront_device { }; struct pcifront_sd { - int domain; + struct pci_sysdata sd; struct pcifront_device *pdev; }; @@ -67,7 +67,9 @@ static inline void pcifront_init_sd(struct pcifront_sd *sd, unsigned int domain, unsigned int bus, struct pcifront_device *pdev) { - sd->domain = domain; + /* Because we do not expose that information via XenBus. */ + sd->sd.node = first_online_node; + sd->sd.domain = domain; sd->pdev = pdev; } @@ -468,8 +470,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev, dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n", domain, bus); - bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL); - sd = kmalloc(sizeof(*sd), GFP_KERNEL); + bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL); + sd = kzalloc(sizeof(*sd), GFP_KERNEL); if (!bus_entry || !sd) { err = -ENOMEM; goto err_out; diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c index 9429e66be096..8eafc6f0df88 100644 --- a/drivers/power/bq27xxx_battery_i2c.c +++ b/drivers/power/bq27xxx_battery_i2c.c @@ -21,6 +21,9 @@ #include <linux/power/bq27xxx_battery.h> +static DEFINE_IDR(battery_id); +static DEFINE_MUTEX(battery_mutex); + static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data) { struct bq27xxx_device_info *di = data; @@ -70,19 +73,33 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client, { struct bq27xxx_device_info *di; int ret; + char *name; + int num; + + /* Get new ID for the new battery device */ + mutex_lock(&battery_mutex); + num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); + mutex_unlock(&battery_mutex); + if (num < 0) + return num; + + name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s-%d", id->name, num); + if (!name) + goto err_mem; di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL); if (!di) - return -ENOMEM; + goto err_mem; + di->id = num; di->dev = &client->dev; di->chip = id->driver_data; - di->name = id->name; + di->name = name; di->bus.read = bq27xxx_battery_i2c_read; ret = bq27xxx_battery_setup(di); if (ret) - return ret; + goto err_failed; /* Schedule a polling after about 1 min */ schedule_delayed_work(&di->work, 60 * HZ); @@ -103,6 +120,16 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client, } return 0; + +err_mem: + ret = -ENOMEM; + +err_failed: + mutex_lock(&battery_mutex); + idr_remove(&battery_id, num); + mutex_unlock(&battery_mutex); + + return ret; } static int bq27xxx_battery_i2c_remove(struct i2c_client *client) @@ -111,6 +138,10 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client) bq27xxx_battery_teardown(di); + mutex_lock(&battery_mutex); + idr_remove(&battery_id, di->id); + mutex_unlock(&battery_mutex); + return 0; } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 3b3e0998fa6e..d6a691e27d33 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -4002,6 +4002,7 @@ static ssize_t ipr_store_update_fw(struct device *dev, struct ipr_sglist *sglist; char fname[100]; char *src; + char *endline; int result, dnld_size; if (!capable(CAP_SYS_ADMIN)) @@ -4009,6 +4010,10 @@ static ssize_t ipr_store_update_fw(struct device *dev, snprintf(fname, sizeof(fname), "%s", buf); + endline = strchr(fname, '\n'); + if (endline) + *endline = '\0'; + if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) { dev_err(&ioa_cfg->pdev->dev, "Firmware file %s not found\n", fname); return -EIO; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index fa6b2c4eb7a2..8c6e31874171 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1344,6 +1344,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret) switch (ret) { case BLKPREP_KILL: + case BLKPREP_INVALID: req->errors = DID_NO_CONNECT << 16; /* release the command and kill it */ if (req->special) { diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c index 91a003011acf..a9bac3bf20de 100644 --- a/drivers/sh/pm_runtime.c +++ b/drivers/sh/pm_runtime.c @@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = { static int __init sh_pm_runtime_init(void) { - if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { + if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { if (!of_find_compatible_node(NULL, NULL, "renesas,cpg-mstp-clocks")) return 0; diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig index 0c675861623f..d8e4219c2324 100644 --- a/drivers/ssb/Kconfig +++ b/drivers/ssb/Kconfig @@ -83,6 +83,7 @@ config SSB_SDIOHOST config SSB_HOST_SOC bool "Support for SSB bus on SoC" depends on SSB && BCM47XX_NVRAM + select SSB_SPROM help Host interface for a SSB directly mapped into memory. This is for some Broadcom SoCs from the BCM47xx and BCM53xx lines. diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c index 3ec7e65a3ffa..db49af90217e 100644 --- a/drivers/staging/media/davinci_vpfe/vpfe_video.c +++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c @@ -147,7 +147,7 @@ static int vpfe_prepare_pipeline(struct vpfe_video_device *video) mutex_lock(&mdev->graph_mutex); ret = media_entity_graph_walk_init(&graph, entity->graph_obj.mdev); if (ret) { - mutex_unlock(&video->lock); + mutex_unlock(&mdev->graph_mutex); return -ENOMEM; } media_entity_graph_walk_start(&graph, entity); diff --git a/drivers/usb/chipidea/ci_hdrc_pci.c b/drivers/usb/chipidea/ci_hdrc_pci.c index b59195edf636..b635ab67490d 100644 --- a/drivers/usb/chipidea/ci_hdrc_pci.c +++ b/drivers/usb/chipidea/ci_hdrc_pci.c @@ -85,8 +85,8 @@ static int ci_hdrc_pci_probe(struct pci_dev *pdev, /* register a nop PHY */ ci->phy = usb_phy_generic_register(); - if (!ci->phy) - return -ENOMEM; + if (IS_ERR(ci->phy)) + return PTR_ERR(ci->phy); memset(res, 0, sizeof(res)); res[0].start = pci_resource_start(pdev, 0); diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c index a4f7db2e18dd..df47110bad2d 100644 --- a/drivers/usb/chipidea/debug.c +++ b/drivers/usb/chipidea/debug.c @@ -100,6 +100,9 @@ static ssize_t ci_port_test_write(struct file *file, const char __user *ubuf, if (sscanf(buf, "%u", &mode) != 1) return -EINVAL; + if (mode > 255) + return -EBADRQC; + pm_runtime_get_sync(ci->dev); spin_lock_irqsave(&ci->lock, flags); ret = hw_port_test_set(ci, mode); diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c index 45f86da1d6d3..03b6743461d1 100644 --- a/drivers/usb/chipidea/otg.c +++ b/drivers/usb/chipidea/otg.c @@ -158,7 +158,7 @@ static void ci_otg_work(struct work_struct *work) int ci_hdrc_otg_init(struct ci_hdrc *ci) { INIT_WORK(&ci->work, ci_otg_work); - ci->wq = create_singlethread_workqueue("ci_otg"); + ci->wq = create_freezable_workqueue("ci_otg"); if (!ci->wq) { dev_err(ci->dev, "can't create workqueue\n"); return -ENODEV; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 350dcd9af5d8..51b436918f78 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5401,6 +5401,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) } bos = udev->bos; + udev->bos = NULL; for (i = 0; i < SET_CONFIG_TRIES; ++i) { @@ -5493,11 +5494,8 @@ done: usb_set_usb2_hardware_lpm(udev, 1); usb_unlocked_enable_lpm(udev); usb_enable_ltm(udev); - /* release the new BOS descriptor allocated by hub_port_init() */ - if (udev->bos != bos) { - usb_release_bos_descriptor(udev); - udev->bos = bos; - } + usb_release_bos_descriptor(udev); + udev->bos = bos; return 0; re_enumerate: diff --git a/drivers/usb/dwc2/Kconfig b/drivers/usb/dwc2/Kconfig index fd95ba6ec317..f0decc0d69b5 100644 --- a/drivers/usb/dwc2/Kconfig +++ b/drivers/usb/dwc2/Kconfig @@ -1,5 +1,6 @@ config USB_DWC2 tristate "DesignWare USB2 DRD Core Support" + depends on HAS_DMA depends on USB || USB_GADGET help Say Y here if your system has a Dual Role Hi-Speed USB diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c index e991d55914db..46c4ba75dc2a 100644 --- a/drivers/usb/dwc2/core.c +++ b/drivers/usb/dwc2/core.c @@ -619,6 +619,12 @@ void dwc2_force_dr_mode(struct dwc2_hsotg *hsotg) __func__, hsotg->dr_mode); break; } + + /* + * NOTE: This is required for some rockchip soc based + * platforms. + */ + msleep(50); } /* diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 36606fc33c0d..a41274aa52ad 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -1174,14 +1174,11 @@ static int dwc2_process_non_isoc_desc(struct dwc2_hsotg *hsotg, failed = dwc2_update_non_isoc_urb_state_ddma(hsotg, chan, qtd, dma_desc, halt_status, n_bytes, xfer_done); - if (*xfer_done && urb->status != -EINPROGRESS) - failed = 1; - - if (failed) { + if (failed || (*xfer_done && urb->status != -EINPROGRESS)) { dwc2_host_complete(hsotg, qtd, urb->status); dwc2_hcd_qtd_unlink_and_free(hsotg, qtd, qh); - dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x status=%08x\n", - failed, *xfer_done, urb->status); + dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x\n", + failed, *xfer_done); return failed; } @@ -1236,21 +1233,23 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, list_for_each_safe(qtd_item, qtd_tmp, &qh->qtd_list) { int i; + int qtd_desc_count; qtd = list_entry(qtd_item, struct dwc2_qtd, qtd_list_entry); xfer_done = 0; + qtd_desc_count = qtd->n_desc; - for (i = 0; i < qtd->n_desc; i++) { + for (i = 0; i < qtd_desc_count; i++) { if (dwc2_process_non_isoc_desc(hsotg, chan, chnum, qtd, desc_num, halt_status, - &xfer_done)) { - qtd = NULL; - break; - } + &xfer_done)) + goto stop_scan; + desc_num++; } } +stop_scan: if (qh->ep_type != USB_ENDPOINT_XFER_CONTROL) { /* * Resetting the data toggle for bulk and interrupt endpoints @@ -1258,7 +1257,7 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, */ if (halt_status == DWC2_HC_XFER_STALL) qh->data_toggle = DWC2_HC_PID_DATA0; - else if (qtd) + else dwc2_hcd_save_data_toggle(hsotg, chan, chnum, qtd); } diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index f8253803a050..cadba8b13c48 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -525,11 +525,19 @@ void dwc2_hcd_save_data_toggle(struct dwc2_hsotg *hsotg, u32 pid = (hctsiz & TSIZ_SC_MC_PID_MASK) >> TSIZ_SC_MC_PID_SHIFT; if (chan->ep_type != USB_ENDPOINT_XFER_CONTROL) { + if (WARN(!chan || !chan->qh, + "chan->qh must be specified for non-control eps\n")) + return; + if (pid == TSIZ_SC_MC_PID_DATA0) chan->qh->data_toggle = DWC2_HC_PID_DATA0; else chan->qh->data_toggle = DWC2_HC_PID_DATA1; } else { + if (WARN(!qtd, + "qtd must be specified for control eps\n")) + return; + if (pid == TSIZ_SC_MC_PID_DATA0) qtd->data_toggle = DWC2_HC_PID_DATA0; else diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 29130682e547..e4f8b90d9627 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -856,7 +856,6 @@ struct dwc3 { unsigned pullups_connected:1; unsigned resize_fifos:1; unsigned setup_packet_pending:1; - unsigned start_config_issued:1; unsigned three_stage_setup:1; unsigned usb3_lpm_capable:1; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 3a9354abcb68..8d6b75c2f53b 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -555,7 +555,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) int ret; u32 reg; - dwc->start_config_issued = false; cfg = le16_to_cpu(ctrl->wValue); switch (state) { @@ -737,10 +736,6 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY"); ret = dwc3_ep0_set_isoch_delay(dwc, ctrl); break; - case USB_REQ_SET_INTERFACE: - dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_INTERFACE"); - dwc->start_config_issued = false; - /* Fall through */ default: dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver"); ret = dwc3_ep0_delegate_req(dwc, ctrl); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 7d1dd82a95ac..2363bad45af8 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -385,24 +385,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep) dep->trb_pool_dma = 0; } +static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep); + +/** + * dwc3_gadget_start_config - Configure EP resources + * @dwc: pointer to our controller context structure + * @dep: endpoint that is being enabled + * + * The assignment of transfer resources cannot perfectly follow the + * data book due to the fact that the controller driver does not have + * all knowledge of the configuration in advance. It is given this + * information piecemeal by the composite gadget framework after every + * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook + * programming model in this scenario can cause errors. For two + * reasons: + * + * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION + * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of + * multiple interfaces. + * + * 2) The databook does not mention doing more DEPXFERCFG for new + * endpoint on alt setting (8.1.6). + * + * The following simplified method is used instead: + * + * All hardware endpoints can be assigned a transfer resource and this + * setting will stay persistent until either a core reset or + * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and + * do DEPXFERCFG for every hardware endpoint as well. We are + * guaranteed that there are as many transfer resources as endpoints. + * + * This function is called for each endpoint when it is being enabled + * but is triggered only when called for EP0-out, which always happens + * first, and which should only happen in one of the above conditions. + */ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep) { struct dwc3_gadget_ep_cmd_params params; u32 cmd; + int i; + int ret; + + if (dep->number) + return 0; memset(¶ms, 0x00, sizeof(params)); + cmd = DWC3_DEPCMD_DEPSTARTCFG; - if (dep->number != 1) { - cmd = DWC3_DEPCMD_DEPSTARTCFG; - /* XferRscIdx == 0 for ep0 and 2 for the remaining */ - if (dep->number > 1) { - if (dwc->start_config_issued) - return 0; - dwc->start_config_issued = true; - cmd |= DWC3_DEPCMD_PARAM(2); - } + ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + if (ret) + return ret; - return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) { + struct dwc3_ep *dep = dwc->eps[i]; + + if (!dep) + continue; + + ret = dwc3_gadget_set_xfer_resource(dwc, dep); + if (ret) + return ret; } return 0; @@ -516,10 +558,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, struct dwc3_trb *trb_st_hw; struct dwc3_trb *trb_link; - ret = dwc3_gadget_set_xfer_resource(dwc, dep); - if (ret) - return ret; - dep->endpoint.desc = desc; dep->comp_desc = comp_desc; dep->type = usb_endpoint_type(desc); @@ -1636,8 +1674,6 @@ static int dwc3_gadget_start(struct usb_gadget *g, } dwc3_writel(dwc->regs, DWC3_DCFG, reg); - dwc->start_config_issued = false; - /* Start with SuperSpeed Default */ dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512); @@ -2237,7 +2273,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_DCTL, reg); dwc3_disconnect_gadget(dwc); - dwc->start_config_issued = false; dwc->gadget.speed = USB_SPEED_UNKNOWN; dwc->setup_packet_pending = false; @@ -2288,7 +2323,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) dwc3_stop_active_transfers(dwc); dwc3_clear_stall_all_ep(dwc); - dwc->start_config_issued = false; /* Reset device address to zero */ reg = dwc3_readl(dwc->regs, DWC3_DCFG); diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 7e179f81d05c..87fb0fd6aaab 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -130,7 +130,8 @@ struct dev_data { setup_can_stall : 1, setup_out_ready : 1, setup_out_error : 1, - setup_abort : 1; + setup_abort : 1, + gadget_registered : 1; unsigned setup_wLength; /* the rest is basically write-once */ @@ -1179,7 +1180,8 @@ dev_release (struct inode *inode, struct file *fd) /* closing ep0 === shutdown all */ - usb_gadget_unregister_driver (&gadgetfs_driver); + if (dev->gadget_registered) + usb_gadget_unregister_driver (&gadgetfs_driver); /* at this point "good" hardware has disconnected the * device from USB; the host won't see it any more. @@ -1847,6 +1849,7 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) * kick in after the ep0 descriptor is closed. */ value = len; + dev->gadget_registered = true; } return value; diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 53c0692f1b09..93d28cb00b76 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2340,7 +2340,7 @@ static struct qe_udc *qe_udc_config(struct platform_device *ofdev) { struct qe_udc *udc; struct device_node *np = ofdev->dev.of_node; - unsigned int tmp_addr = 0; + unsigned long tmp_addr = 0; struct usb_device_para __iomem *usbpram; unsigned int i; u64 size; diff --git a/drivers/usb/gadget/udc/net2280.h b/drivers/usb/gadget/udc/net2280.h index 4dff60d34f73..0d32052bf16f 100644 --- a/drivers/usb/gadget/udc/net2280.h +++ b/drivers/usb/gadget/udc/net2280.h @@ -369,9 +369,20 @@ static inline void set_max_speed(struct net2280_ep *ep, u32 max) static const u32 ep_enhanced[9] = { 0x10, 0x60, 0x30, 0x80, 0x50, 0x20, 0x70, 0x40, 0x90 }; - if (ep->dev->enhanced_mode) + if (ep->dev->enhanced_mode) { reg = ep_enhanced[ep->num]; - else{ + switch (ep->dev->gadget.speed) { + case USB_SPEED_SUPER: + reg += 2; + break; + case USB_SPEED_FULL: + reg += 1; + break; + case USB_SPEED_HIGH: + default: + break; + } + } else { reg = (ep->num + 1) * 0x10; if (ep->dev->gadget.speed != USB_SPEED_HIGH) reg += 1; diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index fd73a3ea07c2..b86a6f03592e 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -413,9 +413,10 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, if (!driver->udc_name || strcmp(driver->udc_name, dev_name(&udc->dev)) == 0) { ret = udc_bind_to_driver(udc, driver); + if (ret != -EPROBE_DEFER) + list_del(&driver->pending); if (ret) goto err4; - list_del(&driver->pending); break; } } diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 795a45b1b25b..58487a473521 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -662,7 +662,7 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma, csr &= ~(MUSB_TXCSR_AUTOSET | MUSB_TXCSR_DMAMODE); csr |= MUSB_TXCSR_DMAENAB; /* against programmer's guide */ } - channel->desired_mode = mode; + channel->desired_mode = *mode; musb_writew(epio, MUSB_TXCSR, csr); return 0; @@ -2003,10 +2003,8 @@ void musb_host_rx(struct musb *musb, u8 epnum) qh->offset, urb->transfer_buffer_length); - done = musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, - urb, xfer_len, - iso_err); - if (done) + if (musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, urb, + xfer_len, iso_err)) goto finish; else dev_err(musb->controller, "error: rx_dma failed\n"); diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 970a30e155cb..72b387d592c2 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -757,14 +757,8 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host) otg->host = host; dev_dbg(otg->usb_phy->dev, "host driver registered w/ tranceiver\n"); - /* - * Kick the state machine work, if peripheral is not supported - * or peripheral is already registered with us. - */ - if (motg->pdata->mode == USB_DR_MODE_HOST || otg->gadget) { - pm_runtime_get_sync(otg->usb_phy->dev); - schedule_work(&motg->sm_work); - } + pm_runtime_get_sync(otg->usb_phy->dev); + schedule_work(&motg->sm_work); return 0; } @@ -827,14 +821,8 @@ static int msm_otg_set_peripheral(struct usb_otg *otg, dev_dbg(otg->usb_phy->dev, "peripheral driver registered w/ tranceiver\n"); - /* - * Kick the state machine work, if host is not supported - * or host is already registered with us. - */ - if (motg->pdata->mode == USB_DR_MODE_PERIPHERAL || otg->host) { - pm_runtime_get_sync(otg->usb_phy->dev); - schedule_work(&motg->sm_work); - } + pm_runtime_get_sync(otg->usb_phy->dev); + schedule_work(&motg->sm_work); return 0; } diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig index f612dda9c977..56ecb8b5115d 100644 --- a/drivers/usb/serial/Kconfig +++ b/drivers/usb/serial/Kconfig @@ -475,22 +475,6 @@ config USB_SERIAL_MOS7840 To compile this driver as a module, choose M here: the module will be called mos7840. If unsure, choose N. -config USB_SERIAL_MXUPORT11 - tristate "USB Moxa UPORT 11x0 Serial Driver" - ---help--- - Say Y here if you want to use a MOXA UPort 11x0 Serial hub. - - This driver supports: - - - UPort 1110 : 1 port RS-232 USB to Serial Hub. - - UPort 1130 : 1 port RS-422/485 USB to Serial Hub. - - UPort 1130I : 1 port RS-422/485 USB to Serial Hub with Isolation. - - UPort 1150 : 1 port RS-232/422/485 USB to Serial Hub. - - UPort 1150I : 1 port RS-232/422/485 USB to Serial Hub with Isolation. - - To compile this driver as a module, choose M here: the - module will be called mxu11x0. - config USB_SERIAL_MXUPORT tristate "USB Moxa UPORT Serial Driver" ---help--- diff --git a/drivers/usb/serial/Makefile b/drivers/usb/serial/Makefile index f3fa5e53702d..349d9df0895f 100644 --- a/drivers/usb/serial/Makefile +++ b/drivers/usb/serial/Makefile @@ -38,7 +38,6 @@ obj-$(CONFIG_USB_SERIAL_METRO) += metro-usb.o obj-$(CONFIG_USB_SERIAL_MOS7720) += mos7720.o obj-$(CONFIG_USB_SERIAL_MOS7840) += mos7840.o obj-$(CONFIG_USB_SERIAL_MXUPORT) += mxuport.o -obj-$(CONFIG_USB_SERIAL_MXUPORT11) += mxu11x0.o obj-$(CONFIG_USB_SERIAL_NAVMAN) += navman.o obj-$(CONFIG_USB_SERIAL_OMNINET) += omninet.o obj-$(CONFIG_USB_SERIAL_OPTICON) += opticon.o diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 987813b8a7f9..73a366de5102 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -163,6 +163,9 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ + { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ + { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ diff --git a/drivers/usb/serial/mxu11x0.c b/drivers/usb/serial/mxu11x0.c deleted file mode 100644 index 619607323bfd..000000000000 --- a/drivers/usb/serial/mxu11x0.c +++ /dev/null @@ -1,1006 +0,0 @@ -/* - * USB Moxa UPORT 11x0 Serial Driver - * - * Copyright (C) 2007 MOXA Technologies Co., Ltd. - * Copyright (C) 2015 Mathieu Othacehe <m.othacehe@gmail.com> - * - * 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; either version 2 of the License, or - * (at your option) any later version. - * - * - * Supports the following Moxa USB to serial converters: - * UPort 1110, 1 port RS-232 USB to Serial Hub. - * UPort 1130, 1 port RS-422/485 USB to Serial Hub. - * UPort 1130I, 1 port RS-422/485 USB to Serial Hub with isolation - * protection. - * UPort 1150, 1 port RS-232/422/485 USB to Serial Hub. - * UPort 1150I, 1 port RS-232/422/485 USB to Serial Hub with isolation - * protection. - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/firmware.h> -#include <linux/jiffies.h> -#include <linux/serial.h> -#include <linux/serial_reg.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/mutex.h> -#include <linux/tty.h> -#include <linux/tty_driver.h> -#include <linux/tty_flip.h> -#include <linux/uaccess.h> -#include <linux/usb.h> -#include <linux/usb/serial.h> - -/* Vendor and product ids */ -#define MXU1_VENDOR_ID 0x110a -#define MXU1_1110_PRODUCT_ID 0x1110 -#define MXU1_1130_PRODUCT_ID 0x1130 -#define MXU1_1150_PRODUCT_ID 0x1150 -#define MXU1_1151_PRODUCT_ID 0x1151 -#define MXU1_1131_PRODUCT_ID 0x1131 - -/* Commands */ -#define MXU1_GET_VERSION 0x01 -#define MXU1_GET_PORT_STATUS 0x02 -#define MXU1_GET_PORT_DEV_INFO 0x03 -#define MXU1_GET_CONFIG 0x04 -#define MXU1_SET_CONFIG 0x05 -#define MXU1_OPEN_PORT 0x06 -#define MXU1_CLOSE_PORT 0x07 -#define MXU1_START_PORT 0x08 -#define MXU1_STOP_PORT 0x09 -#define MXU1_TEST_PORT 0x0A -#define MXU1_PURGE_PORT 0x0B -#define MXU1_RESET_EXT_DEVICE 0x0C -#define MXU1_GET_OUTQUEUE 0x0D -#define MXU1_WRITE_DATA 0x80 -#define MXU1_READ_DATA 0x81 -#define MXU1_REQ_TYPE_CLASS 0x82 - -/* Module identifiers */ -#define MXU1_I2C_PORT 0x01 -#define MXU1_IEEE1284_PORT 0x02 -#define MXU1_UART1_PORT 0x03 -#define MXU1_UART2_PORT 0x04 -#define MXU1_RAM_PORT 0x05 - -/* Modem status */ -#define MXU1_MSR_DELTA_CTS 0x01 -#define MXU1_MSR_DELTA_DSR 0x02 -#define MXU1_MSR_DELTA_RI 0x04 -#define MXU1_MSR_DELTA_CD 0x08 -#define MXU1_MSR_CTS 0x10 -#define MXU1_MSR_DSR 0x20 -#define MXU1_MSR_RI 0x40 -#define MXU1_MSR_CD 0x80 -#define MXU1_MSR_DELTA_MASK 0x0F -#define MXU1_MSR_MASK 0xF0 - -/* Line status */ -#define MXU1_LSR_OVERRUN_ERROR 0x01 -#define MXU1_LSR_PARITY_ERROR 0x02 -#define MXU1_LSR_FRAMING_ERROR 0x04 -#define MXU1_LSR_BREAK 0x08 -#define MXU1_LSR_ERROR 0x0F -#define MXU1_LSR_RX_FULL 0x10 -#define MXU1_LSR_TX_EMPTY 0x20 - -/* Modem control */ -#define MXU1_MCR_LOOP 0x04 -#define MXU1_MCR_DTR 0x10 -#define MXU1_MCR_RTS 0x20 - -/* Mask settings */ -#define MXU1_UART_ENABLE_RTS_IN 0x0001 -#define MXU1_UART_DISABLE_RTS 0x0002 -#define MXU1_UART_ENABLE_PARITY_CHECKING 0x0008 -#define MXU1_UART_ENABLE_DSR_OUT 0x0010 -#define MXU1_UART_ENABLE_CTS_OUT 0x0020 -#define MXU1_UART_ENABLE_X_OUT 0x0040 -#define MXU1_UART_ENABLE_XA_OUT 0x0080 -#define MXU1_UART_ENABLE_X_IN 0x0100 -#define MXU1_UART_ENABLE_DTR_IN 0x0800 -#define MXU1_UART_DISABLE_DTR 0x1000 -#define MXU1_UART_ENABLE_MS_INTS 0x2000 -#define MXU1_UART_ENABLE_AUTO_START_DMA 0x4000 -#define MXU1_UART_SEND_BREAK_SIGNAL 0x8000 - -/* Parity */ -#define MXU1_UART_NO_PARITY 0x00 -#define MXU1_UART_ODD_PARITY 0x01 -#define MXU1_UART_EVEN_PARITY 0x02 -#define MXU1_UART_MARK_PARITY 0x03 -#define MXU1_UART_SPACE_PARITY 0x04 - -/* Stop bits */ -#define MXU1_UART_1_STOP_BITS 0x00 -#define MXU1_UART_1_5_STOP_BITS 0x01 -#define MXU1_UART_2_STOP_BITS 0x02 - -/* Bits per character */ -#define MXU1_UART_5_DATA_BITS 0x00 -#define MXU1_UART_6_DATA_BITS 0x01 -#define MXU1_UART_7_DATA_BITS 0x02 -#define MXU1_UART_8_DATA_BITS 0x03 - -/* Operation modes */ -#define MXU1_UART_232 0x00 -#define MXU1_UART_485_RECEIVER_DISABLED 0x01 -#define MXU1_UART_485_RECEIVER_ENABLED 0x02 - -/* Pipe transfer mode and timeout */ -#define MXU1_PIPE_MODE_CONTINUOUS 0x01 -#define MXU1_PIPE_MODE_MASK 0x03 -#define MXU1_PIPE_TIMEOUT_MASK 0x7C -#define MXU1_PIPE_TIMEOUT_ENABLE 0x80 - -/* Config struct */ -struct mxu1_uart_config { - __be16 wBaudRate; - __be16 wFlags; - u8 bDataBits; - u8 bParity; - u8 bStopBits; - char cXon; - char cXoff; - u8 bUartMode; -} __packed; - -/* Purge modes */ -#define MXU1_PURGE_OUTPUT 0x00 -#define MXU1_PURGE_INPUT 0x80 - -/* Read/Write data */ -#define MXU1_RW_DATA_ADDR_SFR 0x10 -#define MXU1_RW_DATA_ADDR_IDATA 0x20 -#define MXU1_RW_DATA_ADDR_XDATA 0x30 -#define MXU1_RW_DATA_ADDR_CODE 0x40 -#define MXU1_RW_DATA_ADDR_GPIO 0x50 -#define MXU1_RW_DATA_ADDR_I2C 0x60 -#define MXU1_RW_DATA_ADDR_FLASH 0x70 -#define MXU1_RW_DATA_ADDR_DSP 0x80 - -#define MXU1_RW_DATA_UNSPECIFIED 0x00 -#define MXU1_RW_DATA_BYTE 0x01 -#define MXU1_RW_DATA_WORD 0x02 -#define MXU1_RW_DATA_DOUBLE_WORD 0x04 - -struct mxu1_write_data_bytes { - u8 bAddrType; - u8 bDataType; - u8 bDataCounter; - __be16 wBaseAddrHi; - __be16 wBaseAddrLo; - u8 bData[0]; -} __packed; - -/* Interrupt codes */ -#define MXU1_CODE_HARDWARE_ERROR 0xFF -#define MXU1_CODE_DATA_ERROR 0x03 -#define MXU1_CODE_MODEM_STATUS 0x04 - -static inline int mxu1_get_func_from_code(unsigned char code) -{ - return code & 0x0f; -} - -/* Download firmware max packet size */ -#define MXU1_DOWNLOAD_MAX_PACKET_SIZE 64 - -/* Firmware image header */ -struct mxu1_firmware_header { - __le16 wLength; - u8 bCheckSum; -} __packed; - -#define MXU1_UART_BASE_ADDR 0xFFA0 -#define MXU1_UART_OFFSET_MCR 0x0004 - -#define MXU1_BAUD_BASE 923077 - -#define MXU1_TRANSFER_TIMEOUT 2 -#define MXU1_DOWNLOAD_TIMEOUT 1000 -#define MXU1_DEFAULT_CLOSING_WAIT 4000 /* in .01 secs */ - -struct mxu1_port { - u8 msr; - u8 mcr; - u8 uart_mode; - spinlock_t spinlock; /* Protects msr */ - struct mutex mutex; /* Protects mcr */ - bool send_break; -}; - -struct mxu1_device { - u16 mxd_model; -}; - -static const struct usb_device_id mxu1_idtable[] = { - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1110_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1130_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) }, - { } -}; - -MODULE_DEVICE_TABLE(usb, mxu1_idtable); - -/* Write the given buffer out to the control pipe. */ -static int mxu1_send_ctrl_data_urb(struct usb_serial *serial, - u8 request, - u16 value, u16 index, - void *data, size_t size) -{ - int status; - - status = usb_control_msg(serial->dev, - usb_sndctrlpipe(serial->dev, 0), - request, - (USB_DIR_OUT | USB_TYPE_VENDOR | - USB_RECIP_DEVICE), value, index, - data, size, - USB_CTRL_SET_TIMEOUT); - if (status < 0) { - dev_err(&serial->interface->dev, - "%s - usb_control_msg failed: %d\n", - __func__, status); - return status; - } - - if (status != size) { - dev_err(&serial->interface->dev, - "%s - short write (%d / %zd)\n", - __func__, status, size); - return -EIO; - } - - return 0; -} - -/* Send a vendor request without any data */ -static int mxu1_send_ctrl_urb(struct usb_serial *serial, - u8 request, u16 value, u16 index) -{ - return mxu1_send_ctrl_data_urb(serial, request, value, index, - NULL, 0); -} - -static int mxu1_download_firmware(struct usb_serial *serial, - const struct firmware *fw_p) -{ - int status = 0; - int buffer_size; - int pos; - int len; - int done; - u8 cs = 0; - u8 *buffer; - struct usb_device *dev = serial->dev; - struct mxu1_firmware_header *header; - unsigned int pipe; - - pipe = usb_sndbulkpipe(dev, serial->port[0]->bulk_out_endpointAddress); - - buffer_size = fw_p->size + sizeof(*header); - buffer = kmalloc(buffer_size, GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - memcpy(buffer, fw_p->data, fw_p->size); - memset(buffer + fw_p->size, 0xff, buffer_size - fw_p->size); - - for (pos = sizeof(*header); pos < buffer_size; pos++) - cs = (u8)(cs + buffer[pos]); - - header = (struct mxu1_firmware_header *)buffer; - header->wLength = cpu_to_le16(buffer_size - sizeof(*header)); - header->bCheckSum = cs; - - dev_dbg(&dev->dev, "%s - downloading firmware\n", __func__); - - for (pos = 0; pos < buffer_size; pos += done) { - len = min(buffer_size - pos, MXU1_DOWNLOAD_MAX_PACKET_SIZE); - - status = usb_bulk_msg(dev, pipe, buffer + pos, len, &done, - MXU1_DOWNLOAD_TIMEOUT); - if (status) - break; - } - - kfree(buffer); - - if (status) { - dev_err(&dev->dev, "failed to download firmware: %d\n", status); - return status; - } - - msleep_interruptible(100); - usb_reset_device(dev); - - dev_dbg(&dev->dev, "%s - download successful\n", __func__); - - return 0; -} - -static int mxu1_port_probe(struct usb_serial_port *port) -{ - struct mxu1_port *mxport; - struct mxu1_device *mxdev; - - if (!port->interrupt_in_urb) { - dev_err(&port->dev, "no interrupt urb\n"); - return -ENODEV; - } - - mxport = kzalloc(sizeof(struct mxu1_port), GFP_KERNEL); - if (!mxport) - return -ENOMEM; - - spin_lock_init(&mxport->spinlock); - mutex_init(&mxport->mutex); - - mxdev = usb_get_serial_data(port->serial); - - switch (mxdev->mxd_model) { - case MXU1_1110_PRODUCT_ID: - case MXU1_1150_PRODUCT_ID: - case MXU1_1151_PRODUCT_ID: - mxport->uart_mode = MXU1_UART_232; - break; - case MXU1_1130_PRODUCT_ID: - case MXU1_1131_PRODUCT_ID: - mxport->uart_mode = MXU1_UART_485_RECEIVER_DISABLED; - break; - } - - usb_set_serial_port_data(port, mxport); - - port->port.closing_wait = - msecs_to_jiffies(MXU1_DEFAULT_CLOSING_WAIT * 10); - port->port.drain_delay = 1; - - return 0; -} - -static int mxu1_port_remove(struct usb_serial_port *port) -{ - struct mxu1_port *mxport; - - mxport = usb_get_serial_port_data(port); - kfree(mxport); - - return 0; -} - -static int mxu1_startup(struct usb_serial *serial) -{ - struct mxu1_device *mxdev; - struct usb_device *dev = serial->dev; - struct usb_host_interface *cur_altsetting; - char fw_name[32]; - const struct firmware *fw_p = NULL; - int err; - - dev_dbg(&serial->interface->dev, "%s - product 0x%04X, num configurations %d, configuration value %d\n", - __func__, le16_to_cpu(dev->descriptor.idProduct), - dev->descriptor.bNumConfigurations, - dev->actconfig->desc.bConfigurationValue); - - /* create device structure */ - mxdev = kzalloc(sizeof(struct mxu1_device), GFP_KERNEL); - if (!mxdev) - return -ENOMEM; - - usb_set_serial_data(serial, mxdev); - - mxdev->mxd_model = le16_to_cpu(dev->descriptor.idProduct); - - cur_altsetting = serial->interface->cur_altsetting; - - /* if we have only 1 configuration, download firmware */ - if (cur_altsetting->desc.bNumEndpoints == 1) { - - snprintf(fw_name, - sizeof(fw_name), - "moxa/moxa-%04x.fw", - mxdev->mxd_model); - - err = request_firmware(&fw_p, fw_name, &serial->interface->dev); - if (err) { - dev_err(&serial->interface->dev, "failed to request firmware: %d\n", - err); - goto err_free_mxdev; - } - - err = mxu1_download_firmware(serial, fw_p); - if (err) - goto err_release_firmware; - - /* device is being reset */ - err = -ENODEV; - goto err_release_firmware; - } - - return 0; - -err_release_firmware: - release_firmware(fw_p); -err_free_mxdev: - kfree(mxdev); - - return err; -} - -static void mxu1_release(struct usb_serial *serial) -{ - struct mxu1_device *mxdev; - - mxdev = usb_get_serial_data(serial); - kfree(mxdev); -} - -static int mxu1_write_byte(struct usb_serial_port *port, u32 addr, - u8 mask, u8 byte) -{ - int status; - size_t size; - struct mxu1_write_data_bytes *data; - - dev_dbg(&port->dev, "%s - addr 0x%08X, mask 0x%02X, byte 0x%02X\n", - __func__, addr, mask, byte); - - size = sizeof(struct mxu1_write_data_bytes) + 2; - data = kzalloc(size, GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->bAddrType = MXU1_RW_DATA_ADDR_XDATA; - data->bDataType = MXU1_RW_DATA_BYTE; - data->bDataCounter = 1; - data->wBaseAddrHi = cpu_to_be16(addr >> 16); - data->wBaseAddrLo = cpu_to_be16(addr); - data->bData[0] = mask; - data->bData[1] = byte; - - status = mxu1_send_ctrl_data_urb(port->serial, MXU1_WRITE_DATA, 0, - MXU1_RAM_PORT, data, size); - if (status < 0) - dev_err(&port->dev, "%s - failed: %d\n", __func__, status); - - kfree(data); - - return status; -} - -static int mxu1_set_mcr(struct usb_serial_port *port, unsigned int mcr) -{ - int status; - - status = mxu1_write_byte(port, - MXU1_UART_BASE_ADDR + MXU1_UART_OFFSET_MCR, - MXU1_MCR_RTS | MXU1_MCR_DTR | MXU1_MCR_LOOP, - mcr); - return status; -} - -static void mxu1_set_termios(struct tty_struct *tty, - struct usb_serial_port *port, - struct ktermios *old_termios) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct mxu1_uart_config *config; - tcflag_t cflag, iflag; - speed_t baud; - int status; - unsigned int mcr; - - cflag = tty->termios.c_cflag; - iflag = tty->termios.c_iflag; - - if (old_termios && - !tty_termios_hw_change(&tty->termios, old_termios) && - tty->termios.c_iflag == old_termios->c_iflag) { - dev_dbg(&port->dev, "%s - nothing to change\n", __func__); - return; - } - - dev_dbg(&port->dev, - "%s - cflag 0x%08x, iflag 0x%08x\n", __func__, cflag, iflag); - - if (old_termios) { - dev_dbg(&port->dev, "%s - old cflag 0x%08x, old iflag 0x%08x\n", - __func__, - old_termios->c_cflag, - old_termios->c_iflag); - } - - config = kzalloc(sizeof(*config), GFP_KERNEL); - if (!config) - return; - - /* these flags must be set */ - config->wFlags |= MXU1_UART_ENABLE_MS_INTS; - config->wFlags |= MXU1_UART_ENABLE_AUTO_START_DMA; - if (mxport->send_break) - config->wFlags |= MXU1_UART_SEND_BREAK_SIGNAL; - config->bUartMode = mxport->uart_mode; - - switch (C_CSIZE(tty)) { - case CS5: - config->bDataBits = MXU1_UART_5_DATA_BITS; - break; - case CS6: - config->bDataBits = MXU1_UART_6_DATA_BITS; - break; - case CS7: - config->bDataBits = MXU1_UART_7_DATA_BITS; - break; - default: - case CS8: - config->bDataBits = MXU1_UART_8_DATA_BITS; - break; - } - - if (C_PARENB(tty)) { - config->wFlags |= MXU1_UART_ENABLE_PARITY_CHECKING; - if (C_CMSPAR(tty)) { - if (C_PARODD(tty)) - config->bParity = MXU1_UART_MARK_PARITY; - else - config->bParity = MXU1_UART_SPACE_PARITY; - } else { - if (C_PARODD(tty)) - config->bParity = MXU1_UART_ODD_PARITY; - else - config->bParity = MXU1_UART_EVEN_PARITY; - } - } else { - config->bParity = MXU1_UART_NO_PARITY; - } - - if (C_CSTOPB(tty)) - config->bStopBits = MXU1_UART_2_STOP_BITS; - else - config->bStopBits = MXU1_UART_1_STOP_BITS; - - if (C_CRTSCTS(tty)) { - /* RTS flow control must be off to drop RTS for baud rate B0 */ - if (C_BAUD(tty) != B0) - config->wFlags |= MXU1_UART_ENABLE_RTS_IN; - config->wFlags |= MXU1_UART_ENABLE_CTS_OUT; - } - - if (I_IXOFF(tty) || I_IXON(tty)) { - config->cXon = START_CHAR(tty); - config->cXoff = STOP_CHAR(tty); - - if (I_IXOFF(tty)) - config->wFlags |= MXU1_UART_ENABLE_X_IN; - - if (I_IXON(tty)) - config->wFlags |= MXU1_UART_ENABLE_X_OUT; - } - - baud = tty_get_baud_rate(tty); - if (!baud) - baud = 9600; - config->wBaudRate = MXU1_BAUD_BASE / baud; - - dev_dbg(&port->dev, "%s - BaudRate=%d, wBaudRate=%d, wFlags=0x%04X, bDataBits=%d, bParity=%d, bStopBits=%d, cXon=%d, cXoff=%d, bUartMode=%d\n", - __func__, baud, config->wBaudRate, config->wFlags, - config->bDataBits, config->bParity, config->bStopBits, - config->cXon, config->cXoff, config->bUartMode); - - cpu_to_be16s(&config->wBaudRate); - cpu_to_be16s(&config->wFlags); - - status = mxu1_send_ctrl_data_urb(port->serial, MXU1_SET_CONFIG, 0, - MXU1_UART1_PORT, config, - sizeof(*config)); - if (status) - dev_err(&port->dev, "cannot set config: %d\n", status); - - mutex_lock(&mxport->mutex); - mcr = mxport->mcr; - - if (C_BAUD(tty) == B0) - mcr &= ~(MXU1_MCR_DTR | MXU1_MCR_RTS); - else if (old_termios && (old_termios->c_cflag & CBAUD) == B0) - mcr |= MXU1_MCR_DTR | MXU1_MCR_RTS; - - status = mxu1_set_mcr(port, mcr); - if (status) - dev_err(&port->dev, "cannot set modem control: %d\n", status); - else - mxport->mcr = mcr; - - mutex_unlock(&mxport->mutex); - - kfree(config); -} - -static int mxu1_get_serial_info(struct usb_serial_port *port, - struct serial_struct __user *ret_arg) -{ - struct serial_struct ret_serial; - unsigned cwait; - - if (!ret_arg) - return -EFAULT; - - cwait = port->port.closing_wait; - if (cwait != ASYNC_CLOSING_WAIT_NONE) - cwait = jiffies_to_msecs(cwait) / 10; - - memset(&ret_serial, 0, sizeof(ret_serial)); - - ret_serial.type = PORT_16550A; - ret_serial.line = port->minor; - ret_serial.port = 0; - ret_serial.xmit_fifo_size = port->bulk_out_size; - ret_serial.baud_base = MXU1_BAUD_BASE; - ret_serial.close_delay = 5*HZ; - ret_serial.closing_wait = cwait; - - if (copy_to_user(ret_arg, &ret_serial, sizeof(*ret_arg))) - return -EFAULT; - - return 0; -} - - -static int mxu1_set_serial_info(struct usb_serial_port *port, - struct serial_struct __user *new_arg) -{ - struct serial_struct new_serial; - unsigned cwait; - - if (copy_from_user(&new_serial, new_arg, sizeof(new_serial))) - return -EFAULT; - - cwait = new_serial.closing_wait; - if (cwait != ASYNC_CLOSING_WAIT_NONE) - cwait = msecs_to_jiffies(10 * new_serial.closing_wait); - - port->port.closing_wait = cwait; - - return 0; -} - -static int mxu1_ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg) -{ - struct usb_serial_port *port = tty->driver_data; - - switch (cmd) { - case TIOCGSERIAL: - return mxu1_get_serial_info(port, - (struct serial_struct __user *)arg); - case TIOCSSERIAL: - return mxu1_set_serial_info(port, - (struct serial_struct __user *)arg); - } - - return -ENOIOCTLCMD; -} - -static int mxu1_tiocmget(struct tty_struct *tty) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - unsigned int result; - unsigned int msr; - unsigned int mcr; - unsigned long flags; - - mutex_lock(&mxport->mutex); - spin_lock_irqsave(&mxport->spinlock, flags); - - msr = mxport->msr; - mcr = mxport->mcr; - - spin_unlock_irqrestore(&mxport->spinlock, flags); - mutex_unlock(&mxport->mutex); - - result = ((mcr & MXU1_MCR_DTR) ? TIOCM_DTR : 0) | - ((mcr & MXU1_MCR_RTS) ? TIOCM_RTS : 0) | - ((mcr & MXU1_MCR_LOOP) ? TIOCM_LOOP : 0) | - ((msr & MXU1_MSR_CTS) ? TIOCM_CTS : 0) | - ((msr & MXU1_MSR_CD) ? TIOCM_CAR : 0) | - ((msr & MXU1_MSR_RI) ? TIOCM_RI : 0) | - ((msr & MXU1_MSR_DSR) ? TIOCM_DSR : 0); - - dev_dbg(&port->dev, "%s - 0x%04X\n", __func__, result); - - return result; -} - -static int mxu1_tiocmset(struct tty_struct *tty, - unsigned int set, unsigned int clear) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - int err; - unsigned int mcr; - - mutex_lock(&mxport->mutex); - mcr = mxport->mcr; - - if (set & TIOCM_RTS) - mcr |= MXU1_MCR_RTS; - if (set & TIOCM_DTR) - mcr |= MXU1_MCR_DTR; - if (set & TIOCM_LOOP) - mcr |= MXU1_MCR_LOOP; - - if (clear & TIOCM_RTS) - mcr &= ~MXU1_MCR_RTS; - if (clear & TIOCM_DTR) - mcr &= ~MXU1_MCR_DTR; - if (clear & TIOCM_LOOP) - mcr &= ~MXU1_MCR_LOOP; - - err = mxu1_set_mcr(port, mcr); - if (!err) - mxport->mcr = mcr; - - mutex_unlock(&mxport->mutex); - - return err; -} - -static void mxu1_break(struct tty_struct *tty, int break_state) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - - if (break_state == -1) - mxport->send_break = true; - else - mxport->send_break = false; - - mxu1_set_termios(tty, port, NULL); -} - -static int mxu1_open(struct tty_struct *tty, struct usb_serial_port *port) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct usb_serial *serial = port->serial; - int status; - u16 open_settings; - - open_settings = (MXU1_PIPE_MODE_CONTINUOUS | - MXU1_PIPE_TIMEOUT_ENABLE | - (MXU1_TRANSFER_TIMEOUT << 2)); - - mxport->msr = 0; - - status = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); - if (status) { - dev_err(&port->dev, "failed to submit interrupt urb: %d\n", - status); - return status; - } - - if (tty) - mxu1_set_termios(tty, port, NULL); - - status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT, - open_settings, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send open command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send start command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT, - MXU1_PURGE_INPUT, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot clear input buffers: %d\n", - status); - - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT, - MXU1_PURGE_OUTPUT, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot clear output buffers: %d\n", - status); - - goto unlink_int_urb; - } - - /* - * reset the data toggle on the bulk endpoints to work around bug in - * host controllers where things get out of sync some times - */ - usb_clear_halt(serial->dev, port->write_urb->pipe); - usb_clear_halt(serial->dev, port->read_urb->pipe); - - if (tty) - mxu1_set_termios(tty, port, NULL); - - status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT, - open_settings, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send open command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send start command: %d\n", status); - goto unlink_int_urb; - } - - status = usb_serial_generic_open(tty, port); - if (status) - goto unlink_int_urb; - - return 0; - -unlink_int_urb: - usb_kill_urb(port->interrupt_in_urb); - - return status; -} - -static void mxu1_close(struct usb_serial_port *port) -{ - int status; - - usb_serial_generic_close(port); - usb_kill_urb(port->interrupt_in_urb); - - status = mxu1_send_ctrl_urb(port->serial, MXU1_CLOSE_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "failed to send close port command: %d\n", - status); - } -} - -static void mxu1_handle_new_msr(struct usb_serial_port *port, u8 msr) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct async_icount *icount; - unsigned long flags; - - dev_dbg(&port->dev, "%s - msr 0x%02X\n", __func__, msr); - - spin_lock_irqsave(&mxport->spinlock, flags); - mxport->msr = msr & MXU1_MSR_MASK; - spin_unlock_irqrestore(&mxport->spinlock, flags); - - if (msr & MXU1_MSR_DELTA_MASK) { - icount = &port->icount; - if (msr & MXU1_MSR_DELTA_CTS) - icount->cts++; - if (msr & MXU1_MSR_DELTA_DSR) - icount->dsr++; - if (msr & MXU1_MSR_DELTA_CD) - icount->dcd++; - if (msr & MXU1_MSR_DELTA_RI) - icount->rng++; - - wake_up_interruptible(&port->port.delta_msr_wait); - } -} - -static void mxu1_interrupt_callback(struct urb *urb) -{ - struct usb_serial_port *port = urb->context; - unsigned char *data = urb->transfer_buffer; - int length = urb->actual_length; - int function; - int status; - u8 msr; - - switch (urb->status) { - case 0: - break; - case -ECONNRESET: - case -ENOENT: - case -ESHUTDOWN: - dev_dbg(&port->dev, "%s - urb shutting down: %d\n", - __func__, urb->status); - return; - default: - dev_dbg(&port->dev, "%s - nonzero urb status: %d\n", - __func__, urb->status); - goto exit; - } - - if (length != 2) { - dev_dbg(&port->dev, "%s - bad packet size: %d\n", - __func__, length); - goto exit; - } - - if (data[0] == MXU1_CODE_HARDWARE_ERROR) { - dev_err(&port->dev, "hardware error: %d\n", data[1]); - goto exit; - } - - function = mxu1_get_func_from_code(data[0]); - - dev_dbg(&port->dev, "%s - function %d, data 0x%02X\n", - __func__, function, data[1]); - - switch (function) { - case MXU1_CODE_DATA_ERROR: - dev_dbg(&port->dev, "%s - DATA ERROR, data 0x%02X\n", - __func__, data[1]); - break; - - case MXU1_CODE_MODEM_STATUS: - msr = data[1]; - mxu1_handle_new_msr(port, msr); - break; - - default: - dev_err(&port->dev, "unknown interrupt code: 0x%02X\n", - data[1]); - break; - } - -exit: - status = usb_submit_urb(urb, GFP_ATOMIC); - if (status) { - dev_err(&port->dev, "resubmit interrupt urb failed: %d\n", - status); - } -} - -static struct usb_serial_driver mxu11x0_device = { - .driver = { - .owner = THIS_MODULE, - .name = "mxu11x0", - }, - .description = "MOXA UPort 11x0", - .id_table = mxu1_idtable, - .num_ports = 1, - .port_probe = mxu1_port_probe, - .port_remove = mxu1_port_remove, - .attach = mxu1_startup, - .release = mxu1_release, - .open = mxu1_open, - .close = mxu1_close, - .ioctl = mxu1_ioctl, - .set_termios = mxu1_set_termios, - .tiocmget = mxu1_tiocmget, - .tiocmset = mxu1_tiocmset, - .tiocmiwait = usb_serial_generic_tiocmiwait, - .get_icount = usb_serial_generic_get_icount, - .break_ctl = mxu1_break, - .read_int_callback = mxu1_interrupt_callback, -}; - -static struct usb_serial_driver *const serial_drivers[] = { - &mxu11x0_device, NULL -}; - -module_usb_serial_driver(serial_drivers, mxu1_idtable); - -MODULE_AUTHOR("Mathieu Othacehe <m.othacehe@gmail.com>"); -MODULE_DESCRIPTION("MOXA UPort 11x0 USB to Serial Hub Driver"); -MODULE_LICENSE("GPL"); -MODULE_FIRMWARE("moxa/moxa-1110.fw"); -MODULE_FIRMWARE("moxa/moxa-1130.fw"); -MODULE_FIRMWARE("moxa/moxa-1131.fw"); -MODULE_FIRMWARE("moxa/moxa-1150.fw"); -MODULE_FIRMWARE("moxa/moxa-1151.fw"); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index db86e512e0fc..348e19834b83 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -270,6 +270,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_UE910_V2 0x1012 #define TELIT_PRODUCT_LE922_USBCFG0 0x1042 #define TELIT_PRODUCT_LE922_USBCFG3 0x1043 +#define TELIT_PRODUCT_LE922_USBCFG5 0x1045 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 @@ -315,6 +316,7 @@ static void option_instat_callback(struct urb *urb); #define TOSHIBA_PRODUCT_G450 0x0d45 #define ALINK_VENDOR_ID 0x1e0e +#define SIMCOM_PRODUCT_SIM7100E 0x9001 /* Yes, ALINK_VENDOR_ID */ #define ALINK_PRODUCT_PH300 0x9100 #define ALINK_PRODUCT_3GU 0x9200 @@ -607,6 +609,10 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info simcom_sim7100e_blacklist = { + .reserved = BIT(5) | BIT(6), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -1122,9 +1128,13 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */ + { USB_DEVICE_AND_INTERFACE_INFO(QUALCOMM_VENDOR_ID, 0x6001, 0xff, 0xff, 0xff), /* 4G LTE usb-modem U901 */ + .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), @@ -1176,6 +1186,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3), .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), @@ -1645,6 +1657,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(ALINK_VENDOR_ID, 0x9000) }, { USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) }, { USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) }, + { USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E), + .driver_info = (kernel_ulong_t)&simcom_sim7100e_blacklist }, { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200), .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist }, diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 9919d2a9faf2..1bc6089b9008 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -157,14 +157,17 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9056)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9060)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9061)}, /* Sierra Wireless Modem */ - {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx/EM74xx */ - {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx/EM74xx */ + {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9078)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81b1)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 2760a7ba3f30..8c80a48e3233 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -446,7 +446,8 @@ static long vfio_pci_ioctl(void *device_data, info.num_regions = VFIO_PCI_NUM_REGIONS; info.num_irqs = VFIO_PCI_NUM_IRQS; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct pci_dev *pdev = vdev->pdev; @@ -520,7 +521,8 @@ static long vfio_pci_ioctl(void *device_data, return -EINVAL; } - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -555,7 +557,8 @@ static long vfio_pci_ioctl(void *device_data, else info.flags |= VFIO_IRQ_INFO_NORESIZE; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 418cdd9ba3f4..e65b142d3422 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -219,7 +219,8 @@ static long vfio_platform_ioctl(void *device_data, info.num_regions = vdev->num_regions; info.num_irqs = vdev->num_irqs; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct vfio_region_info info; @@ -240,7 +241,8 @@ static long vfio_platform_ioctl(void *device_data, info.size = vdev->regions[info.index].size; info.flags = vdev->regions[info.index].flags; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -259,7 +261,8 @@ static long vfio_platform_ioctl(void *device_data, info.flags = vdev->irqs[info.index].flags; info.count = vdev->irqs[info.index].count; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6f1ea3dddbad..75b24e93cedb 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -999,7 +999,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.iova_pgsizes = vfio_pgsize_bitmap(iommu); - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_IOMMU_MAP_DMA) { struct vfio_iommu_type1_dma_map map; @@ -1032,7 +1033,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, if (ret) return ret; - return copy_to_user((void __user *)arg, &unmap, minsz); + return copy_to_user((void __user *)arg, &unmap, minsz) ? + -EFAULT : 0; } return -ENOTTY; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index ad2146a9ab2d..236553e81027 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1156,6 +1156,8 @@ int vhost_init_used(struct vhost_virtqueue *vq) { __virtio16 last_used_idx; int r; + bool is_le = vq->is_le; + if (!vq->private_data) { vq->is_le = virtio_legacy_is_little_endian(); return 0; @@ -1165,15 +1167,20 @@ int vhost_init_used(struct vhost_virtqueue *vq) r = vhost_update_used_flags(vq); if (r) - return r; + goto err; vq->signalled_used_valid = false; - if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) - return -EFAULT; + if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) { + r = -EFAULT; + goto err; + } r = __get_user(last_used_idx, &vq->used->idx); if (r) - return r; + goto err; vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx); return 0; +err: + vq->is_le = is_le; + return r; } EXPORT_SYMBOL_GPL(vhost_init_used); diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 92f394927f24..6e92917ba77a 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -709,6 +709,7 @@ static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, } if (!err) { + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; if (vc) @@ -956,6 +957,7 @@ static const char *fbcon_startup(void) ops->currcon = -1; ops->graphics = 1; ops->cur_rotate = -1; + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; p->con_rotate = initial_rotation; set_blitting_type(vc, info); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index c0c11fad4611..7760fc1a2218 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -679,7 +679,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) pci_read_config_dword(pci_dev, notify + offsetof(struct virtio_pci_notify_cap, - cap.length), + cap.offset), ¬ify_offset); /* We don't know how many VQs we'll map, ahead of the time. diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 0f6d8515ba4f..80825a7e8e48 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1569,6 +1569,17 @@ config WATCHDOG_RIO machines. The watchdog timeout period is normally one minute but can be changed with a boot-time parameter. +config WATCHDOG_SUN4V + tristate "Sun4v Watchdog support" + select WATCHDOG_CORE + depends on SPARC64 + help + Say Y here to support the hypervisor watchdog capability embedded + in the SPARC sun4v architecture. + + To compile this driver as a module, choose M here. The module will + be called sun4v_wdt. + # XTENSA Architecture # Xen Architecture diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index f566753256ab..f6a6a387c6c7 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -179,6 +179,7 @@ obj-$(CONFIG_SH_WDT) += shwdt.o obj-$(CONFIG_WATCHDOG_RIO) += riowd.o obj-$(CONFIG_WATCHDOG_CP1XXX) += cpwd.o +obj-$(CONFIG_WATCHDOG_SUN4V) += sun4v_wdt.o # XTENSA Architecture diff --git a/drivers/watchdog/sun4v_wdt.c b/drivers/watchdog/sun4v_wdt.c new file mode 100644 index 000000000000..1467fe50a76f --- /dev/null +++ b/drivers/watchdog/sun4v_wdt.c @@ -0,0 +1,191 @@ +/* + * sun4v watchdog timer + * (c) Copyright 2016 Oracle Corporation + * + * Implement a simple watchdog driver using the built-in sun4v hypervisor + * watchdog support. If time expires, the hypervisor stops or bounces + * the guest domain. + * + * 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; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/watchdog.h> +#include <asm/hypervisor.h> +#include <asm/mdesc.h> + +#define WDT_TIMEOUT 60 +#define WDT_MAX_TIMEOUT 31536000 +#define WDT_MIN_TIMEOUT 1 +#define WDT_DEFAULT_RESOLUTION_MS 1000 /* 1 second */ + +static unsigned int timeout; +module_param(timeout, uint, 0); +MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default=" + __MODULE_STRING(WDT_TIMEOUT) ")"); + +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, S_IRUGO); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +static int sun4v_wdt_stop(struct watchdog_device *wdd) +{ + sun4v_mach_set_watchdog(0, NULL); + + return 0; +} + +static int sun4v_wdt_ping(struct watchdog_device *wdd) +{ + int hverr; + + /* + * HV watchdog timer will round up the timeout + * passed in to the nearest multiple of the + * watchdog resolution in milliseconds. + */ + hverr = sun4v_mach_set_watchdog(wdd->timeout * 1000, NULL); + if (hverr == HV_EINVAL) + return -EINVAL; + + return 0; +} + +static int sun4v_wdt_set_timeout(struct watchdog_device *wdd, + unsigned int timeout) +{ + wdd->timeout = timeout; + + return 0; +} + +static const struct watchdog_info sun4v_wdt_ident = { + .options = WDIOF_SETTIMEOUT | + WDIOF_MAGICCLOSE | + WDIOF_KEEPALIVEPING, + .identity = "sun4v hypervisor watchdog", + .firmware_version = 0, +}; + +static struct watchdog_ops sun4v_wdt_ops = { + .owner = THIS_MODULE, + .start = sun4v_wdt_ping, + .stop = sun4v_wdt_stop, + .ping = sun4v_wdt_ping, + .set_timeout = sun4v_wdt_set_timeout, +}; + +static struct watchdog_device wdd = { + .info = &sun4v_wdt_ident, + .ops = &sun4v_wdt_ops, + .min_timeout = WDT_MIN_TIMEOUT, + .max_timeout = WDT_MAX_TIMEOUT, + .timeout = WDT_TIMEOUT, +}; + +static int __init sun4v_wdt_init(void) +{ + struct mdesc_handle *handle; + u64 node; + const u64 *value; + int err = 0; + unsigned long major = 1, minor = 1; + + /* + * There are 2 properties that can be set from the control + * domain for the watchdog. + * watchdog-resolution + * watchdog-max-timeout + * + * We can expect a handle to be returned otherwise something + * serious is wrong. Correct to return -ENODEV here. + */ + + handle = mdesc_grab(); + if (!handle) + return -ENODEV; + + node = mdesc_node_by_name(handle, MDESC_NODE_NULL, "platform"); + err = -ENODEV; + if (node == MDESC_NODE_NULL) + goto out_release; + + /* + * This is a safe way to validate if we are on the right + * platform. + */ + if (sun4v_hvapi_register(HV_GRP_CORE, major, &minor)) + goto out_hv_unreg; + + /* Allow value of watchdog-resolution up to 1s (default) */ + value = mdesc_get_property(handle, node, "watchdog-resolution", NULL); + err = -EINVAL; + if (value) { + if (*value == 0 || + *value > WDT_DEFAULT_RESOLUTION_MS) + goto out_hv_unreg; + } + + value = mdesc_get_property(handle, node, "watchdog-max-timeout", NULL); + if (value) { + /* + * If the property value (in ms) is smaller than + * min_timeout, return -EINVAL. + */ + if (*value < wdd.min_timeout * 1000) + goto out_hv_unreg; + + /* + * If the property value is smaller than + * default max_timeout then set watchdog max_timeout to + * the value of the property in seconds. + */ + if (*value < wdd.max_timeout * 1000) + wdd.max_timeout = *value / 1000; + } + + watchdog_init_timeout(&wdd, timeout, NULL); + + watchdog_set_nowayout(&wdd, nowayout); + + err = watchdog_register_device(&wdd); + if (err) + goto out_hv_unreg; + + pr_info("initialized (timeout=%ds, nowayout=%d)\n", + wdd.timeout, nowayout); + + mdesc_release(handle); + + return 0; + +out_hv_unreg: + sun4v_hvapi_unregister(HV_GRP_CORE); + +out_release: + mdesc_release(handle); + return err; +} + +static void __exit sun4v_wdt_exit(void) +{ + sun4v_hvapi_unregister(HV_GRP_CORE); + watchdog_unregister_device(&wdd); +} + +module_init(sun4v_wdt_init); +module_exit(sun4v_wdt_exit); + +MODULE_AUTHOR("Wim Coekaerts <wim.coekaerts@oracle.com>"); +MODULE_DESCRIPTION("sun4v watchdog driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 73dafdc494aa..fb0221434f81 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -227,8 +227,9 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, /* * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able * to access the BARs where the MSI-X entries reside. + * But VF devices are unique in which the PF needs to be checked. */ - pci_read_config_word(dev, PCI_COMMAND, &cmd); + pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd); if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY)) return -ENXIO; @@ -332,6 +333,9 @@ void xen_pcibk_do_op(struct work_struct *data) struct xen_pcibk_dev_data *dev_data = NULL; struct xen_pci_op *op = &pdev->op; int test_intx = 0; +#ifdef CONFIG_PCI_MSI + unsigned int nr = 0; +#endif *op = pdev->sh_info->op; barrier(); @@ -360,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data) op->err = xen_pcibk_disable_msi(pdev, dev, op); break; case XEN_PCI_OP_enable_msix: + nr = op->value; op->err = xen_pcibk_enable_msix(pdev, dev, op); break; case XEN_PCI_OP_disable_msix: @@ -382,7 +387,7 @@ void xen_pcibk_do_op(struct work_struct *data) if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) { unsigned int i; - for (i = 0; i < op->value; i++) + for (i = 0; i < nr; i++) pdev->sh_info->op.msix_entries[i].vector = op->msix_entries[i].vector; } diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index ad4eb1024d1f..c46ee189466f 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -849,15 +849,31 @@ static int scsiback_map(struct vscsibk_info *info) } /* + Check for a translation entry being present +*/ +static struct v2p_entry *scsiback_chk_translation_entry( + struct vscsibk_info *info, struct ids_tuple *v) +{ + struct list_head *head = &(info->v2p_entry_lists); + struct v2p_entry *entry; + + list_for_each_entry(entry, head, l) + if ((entry->v.chn == v->chn) && + (entry->v.tgt == v->tgt) && + (entry->v.lun == v->lun)) + return entry; + + return NULL; +} + +/* Add a new translation entry */ static int scsiback_add_translation_entry(struct vscsibk_info *info, char *phy, struct ids_tuple *v) { int err = 0; - struct v2p_entry *entry; struct v2p_entry *new; - struct list_head *head = &(info->v2p_entry_lists); unsigned long flags; char *lunp; unsigned long long unpacked_lun; @@ -917,15 +933,10 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, spin_lock_irqsave(&info->v2p_lock, flags); /* Check double assignment to identical virtual ID */ - list_for_each_entry(entry, head, l) { - if ((entry->v.chn == v->chn) && - (entry->v.tgt == v->tgt) && - (entry->v.lun == v->lun)) { - pr_warn("Virtual ID is already used. Assignment was not performed.\n"); - err = -EEXIST; - goto out; - } - + if (scsiback_chk_translation_entry(info, v)) { + pr_warn("Virtual ID is already used. Assignment was not performed.\n"); + err = -EEXIST; + goto out; } /* Create a new translation entry and add to the list */ @@ -933,18 +944,18 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, new->v = *v; new->tpg = tpg; new->lun = unpacked_lun; - list_add_tail(&new->l, head); + list_add_tail(&new->l, &info->v2p_entry_lists); out: spin_unlock_irqrestore(&info->v2p_lock, flags); out_free: - mutex_lock(&tpg->tv_tpg_mutex); - tpg->tv_tpg_fe_count--; - mutex_unlock(&tpg->tv_tpg_mutex); - - if (err) + if (err) { + mutex_lock(&tpg->tv_tpg_mutex); + tpg->tv_tpg_fe_count--; + mutex_unlock(&tpg->tv_tpg_mutex); kfree(new); + } return err; } @@ -956,39 +967,40 @@ static void __scsiback_del_translation_entry(struct v2p_entry *entry) } /* - Delete the translation entry specfied + Delete the translation entry specified */ static int scsiback_del_translation_entry(struct vscsibk_info *info, struct ids_tuple *v) { struct v2p_entry *entry; - struct list_head *head = &(info->v2p_entry_lists); unsigned long flags; + int ret = 0; spin_lock_irqsave(&info->v2p_lock, flags); /* Find out the translation entry specified */ - list_for_each_entry(entry, head, l) { - if ((entry->v.chn == v->chn) && - (entry->v.tgt == v->tgt) && - (entry->v.lun == v->lun)) { - goto found; - } - } - - spin_unlock_irqrestore(&info->v2p_lock, flags); - return 1; - -found: - /* Delete the translation entry specfied */ - __scsiback_del_translation_entry(entry); + entry = scsiback_chk_translation_entry(info, v); + if (entry) + __scsiback_del_translation_entry(entry); + else + ret = -ENOENT; spin_unlock_irqrestore(&info->v2p_lock, flags); - return 0; + return ret; } static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, char *phy, struct ids_tuple *vir, int try) { + struct v2p_entry *entry; + unsigned long flags; + + if (try) { + spin_lock_irqsave(&info->v2p_lock, flags); + entry = scsiback_chk_translation_entry(info, vir); + spin_unlock_irqrestore(&info->v2p_lock, flags); + if (entry) + return; + } if (!scsiback_add_translation_entry(info, phy, vir)) { if (xenbus_printf(XBT_NIL, info->dev->nodename, state, "%d", XenbusStateInitialised)) { diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 9433e46518c8..912b64edb42b 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -188,6 +188,8 @@ static int queue_reply(struct list_head *queue, const void *data, size_t len) if (len == 0) return 0; + if (len > XENSTORE_PAYLOAD_MAX) + return -EINVAL; rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL); if (rb == NULL) diff --git a/fs/affs/file.c b/fs/affs/file.c index 0548c53f41d5..22fc7c802d69 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -511,8 +511,6 @@ affs_do_readpage_ofs(struct page *page, unsigned to) pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino, page->index, to); BUG_ON(to > PAGE_CACHE_SIZE); - kmap(page); - data = page_address(page); bsize = AFFS_SB(sb)->s_data_blksize; tmp = page->index << PAGE_CACHE_SHIFT; bidx = tmp / bsize; @@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to) return PTR_ERR(bh); tmp = min(bsize - boff, to - pos); BUG_ON(pos + tmp > to || tmp > bsize); + data = kmap_atomic(page); memcpy(data + pos, AFFS_DATA(bh) + boff, tmp); + kunmap_atomic(data); affs_brelse(bh); bidx++; pos += tmp; boff = 0; } flush_dcache_page(page); - kunmap(page); return 0; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 051ea4809c14..7d914c67a9d0 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -653,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top) if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = (unsigned long) get_random_int(); + random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 39b3a174a425..826b164a4b5b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1201,7 +1201,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; - bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0; + if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access) + bdev->bd_inode->i_flags = S_DAX; + else + bdev->bd_inode->i_flags = 0; + if (!partno) { ret = -ENXIO; bdev->bd_part = disk_get_part(disk, partno); @@ -1693,13 +1697,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait) return try_to_free_buffers(page); } +static int blkdev_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + if (dax_mapping(mapping)) { + struct block_device *bdev = I_BDEV(mapping->host); + + return dax_writeback_mapping_range(mapping, bdev, wbc); + } + return generic_writepages(mapping, wbc); +} + static const struct address_space_operations def_blk_aops = { .readpage = blkdev_readpage, .readpages = blkdev_readpages, .writepage = blkdev_writepage, .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, - .writepages = generic_writepages, + .writepages = blkdev_writepages, .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, .is_dirty_writeback = buffer_check_dirty_writeback, diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7cf8509deda7..2c849b08a91b 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + if (err == -EEXIST) + err = 0; if (err) { - BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c22213789090..19adeb0ef82a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1756,6 +1756,10 @@ int ceph_pool_perm_check(struct ceph_inode_info *ci, int need) u32 pool; int ret, flags; + /* does not support pool namespace yet */ + if (ci->i_pool_ns_len) + return -EIO; + if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode), NOPOOLPERM)) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index cdbf8cf3d52c..6fe0ad26a7df 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2753,7 +2753,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, void *inline_data, int inline_len, struct ceph_buffer *xattr_buf, struct ceph_mds_session *session, - struct ceph_cap *cap, int issued) + struct ceph_cap *cap, int issued, + u32 pool_ns_len) __releases(ci->i_ceph_lock) __releases(mdsc->snap_rwsem) { @@ -2873,6 +2874,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) { /* file layout may have changed */ ci->i_layout = grant->layout; + ci->i_pool_ns_len = pool_ns_len; + /* size/truncate_seq? */ queue_trunc = ceph_fill_file_size(inode, issued, le32_to_cpu(grant->truncate_seq), @@ -3411,6 +3414,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, u32 inline_len = 0; void *snaptrace; size_t snaptrace_len; + u32 pool_ns_len = 0; void *p, *end; dout("handle_caps from mds%d\n", mds); @@ -3463,6 +3467,21 @@ void ceph_handle_caps(struct ceph_mds_session *session, p += inline_len; } + if (le16_to_cpu(msg->hdr.version) >= 8) { + u64 flush_tid; + u32 caller_uid, caller_gid; + u32 osd_epoch_barrier; + /* version >= 5 */ + ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad); + /* version >= 6 */ + ceph_decode_64_safe(&p, end, flush_tid, bad); + /* version >= 7 */ + ceph_decode_32_safe(&p, end, caller_uid, bad); + ceph_decode_32_safe(&p, end, caller_gid, bad); + /* version >= 8 */ + ceph_decode_32_safe(&p, end, pool_ns_len, bad); + } + /* lookup ino */ inode = ceph_find_inode(sb, vino); ci = ceph_inode(inode); @@ -3518,7 +3537,8 @@ void ceph_handle_caps(struct ceph_mds_session *session, &cap, &issued); handle_cap_grant(mdsc, inode, h, inline_version, inline_data, inline_len, - msg->middle, session, cap, issued); + msg->middle, session, cap, issued, + pool_ns_len); if (realm) ceph_put_snap_realm(mdsc, realm); goto done_unlocked; @@ -3542,7 +3562,8 @@ void ceph_handle_caps(struct ceph_mds_session *session, issued |= __ceph_caps_dirty(ci); handle_cap_grant(mdsc, inode, h, inline_version, inline_data, inline_len, - msg->middle, session, cap, issued); + msg->middle, session, cap, issued, + pool_ns_len); goto done_unlocked; case CEPH_CAP_OP_FLUSH_ACK: diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index fb4ba2e4e2a5..5849b88bbed3 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -396,6 +396,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) ci->i_symlink = NULL; memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout)); + ci->i_pool_ns_len = 0; ci->i_fragtree = RB_ROOT; mutex_init(&ci->i_fragtree_mutex); @@ -756,6 +757,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool) ci->i_ceph_flags &= ~CEPH_I_POOL_PERM; ci->i_layout = info->layout; + ci->i_pool_ns_len = iinfo->pool_ns_len; queue_trunc = ceph_fill_file_size(inode, issued, le32_to_cpu(info->truncate_seq), diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index e7b130a637f9..911d64d865f1 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -100,6 +100,14 @@ static int parse_reply_info_in(void **p, void *end, } else info->inline_version = CEPH_INLINE_NONE; + if (features & CEPH_FEATURE_FS_FILE_LAYOUT_V2) { + ceph_decode_32_safe(p, end, info->pool_ns_len, bad); + ceph_decode_need(p, end, info->pool_ns_len, bad); + *p += info->pool_ns_len; + } else { + info->pool_ns_len = 0; + } + return 0; bad: return err; @@ -2298,6 +2306,14 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); + /* deny access to directories with pool_ns layouts */ + if (req->r_inode && S_ISDIR(req->r_inode->i_mode) && + ceph_inode(req->r_inode)->i_pool_ns_len) + return -EIO; + if (req->r_locked_dir && + ceph_inode(req->r_locked_dir)->i_pool_ns_len) + return -EIO; + /* issue */ mutex_lock(&mdsc->mutex); __register_request(mdsc, req, dir); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index ccf11ef0ca87..37712ccffcc6 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -44,6 +44,7 @@ struct ceph_mds_reply_info_in { u64 inline_version; u32 inline_len; char *inline_data; + u32 pool_ns_len; }; /* diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 75b7d125ce66..9c458eb52245 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -287,6 +287,7 @@ struct ceph_inode_info { struct ceph_dir_layout i_dir_layout; struct ceph_file_layout i_layout; + size_t i_pool_ns_len; char *i_symlink; /* for dirs */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c48ca13673e3..2eea40353e60 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1013,7 +1013,6 @@ const struct file_operations cifs_file_strict_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .clone_file_range = cifs_clone_file_range, - .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 68c4547528c4..83aac8ba50b0 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -31,19 +31,15 @@ * so that it will fit. We use hash_64 to convert the value to 31 bits, and * then add 1, to ensure that we don't end up with a 0 as the value. */ -#if BITS_PER_LONG == 64 static inline ino_t cifs_uniqueid_to_ino_t(u64 fileid) { + if ((sizeof(ino_t)) < (sizeof(u64))) + return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; + return (ino_t)fileid; + } -#else -static inline ino_t -cifs_uniqueid_to_ino_t(u64 fileid) -{ - return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; -} -#endif extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 90b4f9f7de66..76fcb50295a3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1396,11 +1396,10 @@ openRetry: * current bigbuf. */ static int -cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = get_rfc1002_length(server->smallbuf); int remaining = rfclen + 4 - server->total_read; - struct cifs_readdata *rdata = mid->callback_data; while (remaining > 0) { int length; @@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) remaining -= length; } - dequeue_mid(mid, rdata->result); return 0; } +static int +cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + int length; + struct cifs_readdata *rdata = mid->callback_data; + + length = discard_remaining_data(server); + dequeue_mid(mid, rdata->result); + return length; +} + int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { @@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_status_pending && + server->ops->is_status_pending(buf, server, 0)) { + discard_remaining_data(server); + return -1; + } + /* Was the SMB read successful? */ rdata->result = server->ops->map_error(buf, false); if (rdata->result != 0) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 10f8d5cf5681..42e1f440eb1e 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1106,21 +1106,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, { char *data_offset; struct create_context *cc; - unsigned int next = 0; + unsigned int next; + unsigned int remaining; char *name; data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); + remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; - do { - cc = (struct create_context *)((char *)cc + next); + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) != 4 || - strncmp(name, "RqLs", 4)) { - next = le32_to_cpu(cc->Next); - continue; - } - return server->ops->parse_lease_buf(cc, epoch); - } while (next != 0); + if (le16_to_cpu(cc->NameLength) == 4 && + strncmp(name, "RqLs", 4) == 0) + return server->ops->parse_lease_buf(cc, epoch); + + next = le32_to_cpu(cc->Next); + if (!next) + break; + remaining -= next; + cc = (struct create_context *)((char *)cc + next); + } return 0; } @@ -79,15 +79,14 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n) } /* - * dax_clear_blocks() is called from within transaction context from XFS, + * dax_clear_sectors() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS * semantics for all operations. */ -int dax_clear_blocks(struct inode *inode, sector_t block, long _size) +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size) { - struct block_device *bdev = inode->i_sb->s_bdev; struct blk_dax_ctl dax = { - .sector = block << (inode->i_blkbits - 9), + .sector = _sector, .size = _size, }; @@ -109,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size) wmb_pmem(); return 0; } -EXPORT_SYMBOL_GPL(dax_clear_blocks); +EXPORT_SYMBOL_GPL(dax_clear_sectors); /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */ static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first, @@ -485,11 +484,10 @@ static int dax_writeback_one(struct block_device *bdev, * end]. This is required by data integrity operations to ensure file data is * on persistent storage prior to completion of the operation. */ -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end) +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc) { struct inode *inode = mapping->host; - struct block_device *bdev = inode->i_sb->s_bdev; pgoff_t start_index, end_index, pmd_index; pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; @@ -500,8 +498,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT)) return -EIO; - start_index = start >> PAGE_CACHE_SHIFT; - end_index = end >> PAGE_CACHE_SHIFT; + if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL) + return 0; + + start_index = wbc->range_start >> PAGE_CACHE_SHIFT; + end_index = wbc->range_end >> PAGE_CACHE_SHIFT; pmd_index = DAX_PMD_INDEX(start_index); rcu_read_lock(); diff --git a/fs/dcache.c b/fs/dcache.c index 92d5140de851..2398f9f94337 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } -/* - * Make sure other CPUs see the inode attached before the type is set. - */ static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry, unsigned flags; dentry->d_inode = inode; - smp_wmb(); flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; WRITE_ONCE(dentry->d_flags, flags); } -/* - * Ideally, we want to make sure that other CPUs see the flags cleared before - * the inode is detached, but this is really a violation of RCU principles - * since the ordering suggests we should always set inode before flags. - * - * We should instead replace or discard the entire dentry - but that sucks - * performancewise on mass deletion/rename. - */ static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); - smp_wmb(); dentry->d_inode = NULL; } @@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; + + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1758,8 +1747,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); if (inode) hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); fsnotify_d_instantiate(dentry, inode); } diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 2c88d683cd91..c1400b109805 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -80,23 +80,6 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return ret; } -static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct inode *inode = file_inode(vma->vm_file); - struct ext2_inode_info *ei = EXT2_I(inode); - int ret; - - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); - down_read(&ei->dax_sem); - - ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL); - - up_read(&ei->dax_sem); - sb_end_pagefault(inode->i_sb); - return ret; -} - static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { @@ -124,7 +107,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, .pmd_fault = ext2_dax_pmd_fault, - .page_mkwrite = ext2_dax_mkwrite, + .page_mkwrite = ext2_dax_fault, .pfn_mkwrite = ext2_dax_pfn_mkwrite, }; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 338eefda70c6..6bd58e6ff038 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode, * so that it's not found by another thread before it's * initialised */ - err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key), - 1 << inode->i_blkbits); + err = dax_clear_sectors(inode->i_sb->s_bdev, + le32_to_cpu(chain[depth-1].key) << + (inode->i_blkbits - 9), + 1 << inode->i_blkbits); if (err) { mutex_unlock(&ei->truncate_mutex); goto cleanup; @@ -874,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) static int ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) { +#ifdef CONFIG_FS_DAX + if (dax_mapping(mapping)) { + return dax_writeback_mapping_range(mapping, + mapping->host->i_sb->s_bdev, + wbc); + } +#endif + return mpage_writepages(mapping, wbc, ext2_get_block); } @@ -1296,7 +1306,7 @@ void ext2_set_inode_flags(struct inode *inode) inode->i_flags |= S_NOATIME; if (flags & EXT2_DIRSYNC_FL) inode->i_flags |= S_DIRSYNC; - if (test_opt(inode->i_sb, DAX)) + if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode)) inode->i_flags |= S_DAX; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 474f1a4d2ca8..4cd318f31cbe 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -262,23 +262,8 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return result; } -static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - int err; - struct inode *inode = file_inode(vma->vm_file); - - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); - down_read(&EXT4_I(inode)->i_mmap_sem); - err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL); - up_read(&EXT4_I(inode)->i_mmap_sem); - sb_end_pagefault(inode->i_sb); - - return err; -} - /* - * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite() + * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault() * handler we check for races agaist truncate. Note that since we cycle through * i_mmap_sem, we are sure that also any hole punching that began before we * were called is finished by now and so if it included part of the file we @@ -311,7 +296,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .pmd_fault = ext4_dax_pmd_fault, - .page_mkwrite = ext4_dax_mkwrite, + .page_mkwrite = ext4_dax_fault, .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; #else diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9cc57c3b4661..aee960b1af34 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2478,6 +2478,10 @@ static int ext4_writepages(struct address_space *mapping, trace_ext4_writepages(inode, wbc); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, + wbc); + /* * No pages to write? This is mainly a kludge to avoid starting * a transaction for special inodes like journal inode on last iput() @@ -4155,7 +4159,7 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) new_fl |= S_DIRSYNC; - if (test_opt(inode->i_sb, DAX)) + if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode)) new_fl |= S_DAX; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a99b010e2194..eae5917c534e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -583,6 +583,11 @@ group_extend_out: "Online defrag not supported with bigalloc"); err = -EOPNOTSUPP; goto mext_out; + } else if (IS_DAX(inode)) { + ext4_msg(sb, KERN_ERR, + "Online defrag not supported with DAX"); + err = -EOPNOTSUPP; + goto mext_out; } err = mnt_want_write_file(filp); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1f76d8950a57..5c46ed9f3e14 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi, #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ +static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); +static struct workqueue_struct *isw_wq; + void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -317,7 +320,6 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; - struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -424,8 +426,9 @@ skip_switch: wb_put(new_wb); iput(inode); - deactivate_super(sb); kfree(isw); + + atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) @@ -435,7 +438,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); - schedule_work(&isw->work); + queue_work(isw_wq, &isw->work); } /** @@ -471,20 +474,20 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); - - if (inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) - goto out_unlock; - - if (!atomic_inc_not_zero(&inode->i_sb->s_active)) - goto out_unlock; - + if (!(inode->i_sb->s_flags & MS_ACTIVE) || + inode->i_state & (I_WB_SWITCH | I_FREEING) || + inode_to_wb(inode) == isw->new_wb) { + spin_unlock(&inode->i_lock); + goto out_free; + } inode->i_state |= I_WB_SWITCH; spin_unlock(&inode->i_lock); ihold(inode); isw->inode = inode; + atomic_inc(&isw_nr_in_flight); + /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the mapping's @@ -494,8 +497,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; -out_unlock: - spin_unlock(&inode->i_lock); out_free: if (isw->new_wb) wb_put(isw->new_wb); @@ -847,6 +848,33 @@ restart: wb_put(last_wb); } +/** + * cgroup_writeback_umount - flush inode wb switches for umount + * + * This function is called when a super_block is about to be destroyed and + * flushes in-flight inode wb switches. An inode wb switch goes through + * RCU and then workqueue, so the two need to be flushed in order to ensure + * that all previously scheduled switches are finished. As wb switches are + * rare occurrences and synchronize_rcu() can take a while, perform + * flushing iff wb switches are in flight. + */ +void cgroup_writeback_umount(void) +{ + if (atomic_read(&isw_nr_in_flight)) { + synchronize_rcu(); + flush_workqueue(isw_wq); + } +} + +static int __init cgroup_writeback_init(void) +{ + isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); + if (!isw_wq) + return -ENOMEM; + return 0; +} +fs_initcall(cgroup_writeback_init); + #else /* CONFIG_CGROUP_WRITEBACK */ static struct bdi_writeback * diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 506765afa1a3..bb8d67e2740a 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -376,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); dnode_secno dno; int r; - int rep = 0; int err; hpfs_lock(dir->i_sb); hpfs_adjust_length(name, &len); -again: + err = -ENOENT; de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh); if (!de) @@ -401,33 +400,9 @@ again: hpfs_error(dir->i_sb, "there was error when removing dirent"); err = -EFSERROR; break; - case 2: /* no space for deleting, try to truncate file */ - + case 2: /* no space for deleting */ err = -ENOSPC; - if (rep++) - break; - - dentry_unhash(dentry); - if (!d_unhashed(dentry)) { - hpfs_unlock(dir->i_sb); - return -ENOSPC; - } - if (generic_permission(inode, MAY_WRITE) || - !S_ISREG(inode->i_mode) || - get_write_access(inode)) { - d_rehash(dentry); - } else { - struct iattr newattrs; - /*pr_info("truncating file before delete.\n");*/ - newattrs.ia_size = 0; - newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - err = notify_change(dentry, &newattrs, NULL); - put_write_access(inode); - if (!err) - goto again; - } - hpfs_unlock(dir->i_sb); - return -ENOSPC; + break; default: drop_nlink(inode); err = 0; diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking index 3ea36554107f..8918ac905a3b 100644 --- a/fs/jffs2/README.Locking +++ b/fs/jffs2/README.Locking @@ -2,10 +2,6 @@ JFFS2 LOCKING DOCUMENTATION --------------------------- -At least theoretically, JFFS2 does not require the Big Kernel Lock -(BKL), which was always helpfully obtained for it by Linux 2.4 VFS -code. It has its own locking, as described below. - This document attempts to describe the existing locking rules for JFFS2. It is not expected to remain perfectly up to date, but ought to be fairly close. @@ -69,6 +65,7 @@ Ordering constraints: any f->sem held. 2. Never attempt to lock two file mutexes in one thread. No ordering rules have been made for doing so. + 3. Never lock a page cache page with f->sem held. erase_completion_lock spinlock diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index 0ae91ad6df2d..b288c8ae1236 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -50,7 +50,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c) static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, - struct jffs2_inode_cache *ic) + struct jffs2_inode_cache *ic, + int *dir_hardlinks) { struct jffs2_full_dirent *fd; @@ -69,19 +70,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n", fd->name, fd->ino, ic->ino); jffs2_mark_node_obsolete(c, fd->raw); + /* Clear the ic/raw union so it doesn't cause problems later. */ + fd->ic = NULL; continue; } + /* From this point, fd->raw is no longer used so we can set fd->ic */ + fd->ic = child_ic; + child_ic->pino_nlink++; + /* If we appear (at this stage) to have hard-linked directories, + * set a flag to trigger a scan later */ if (fd->type == DT_DIR) { - if (child_ic->pino_nlink) { - JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n", - fd->name, fd->ino, ic->ino); - /* TODO: What do we do about it? */ - } else { - child_ic->pino_nlink = ic->ino; - } - } else - child_ic->pino_nlink++; + child_ic->flags |= INO_FLAGS_IS_DIR; + if (child_ic->pino_nlink > 1) + *dir_hardlinks = 1; + } dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino); /* Can't free scan_dents so far. We might need them in pass 2 */ @@ -95,8 +98,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, */ static int jffs2_build_filesystem(struct jffs2_sb_info *c) { - int ret; - int i; + int ret, i, dir_hardlinks = 0; struct jffs2_inode_cache *ic; struct jffs2_full_dirent *fd; struct jffs2_full_dirent *dead_fds = NULL; @@ -120,7 +122,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) /* Now scan the directory tree, increasing nlink according to every dirent found. */ for_each_inode(i, c, ic) { if (ic->scan_dents) { - jffs2_build_inode_pass1(c, ic); + jffs2_build_inode_pass1(c, ic, &dir_hardlinks); cond_resched(); } } @@ -156,6 +158,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) } dbg_fsbuild("pass 2a complete\n"); + + if (dir_hardlinks) { + /* If we detected directory hardlinks earlier, *hopefully* + * they are gone now because some of the links were from + * dead directories which still had some old dirents lying + * around and not yet garbage-collected, but which have + * been discarded above. So clear the pino_nlink field + * in each directory, so that the final scan below can + * print appropriate warnings. */ + for_each_inode(i, c, ic) { + if (ic->flags & INO_FLAGS_IS_DIR) + ic->pino_nlink = 0; + } + } dbg_fsbuild("freeing temporary data structures\n"); /* Finally, we can scan again and free the dirent structs */ @@ -163,6 +179,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) while(ic->scan_dents) { fd = ic->scan_dents; ic->scan_dents = fd->next; + /* We do use the pino_nlink field to count nlink of + * directories during fs build, so set it to the + * parent ino# now. Now that there's hopefully only + * one. */ + if (fd->type == DT_DIR) { + if (!fd->ic) { + /* We'll have complained about it and marked the coresponding + raw node obsolete already. Just skip it. */ + continue; + } + + /* We *have* to have set this in jffs2_build_inode_pass1() */ + BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR)); + + /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks + * is set. Otherwise, we know this should never trigger anyway, so + * we don't do the check. And ic->pino_nlink still contains the nlink + * value (which is 1). */ + if (dir_hardlinks && fd->ic->pino_nlink) { + JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n", + fd->name, fd->ino, ic->ino, fd->ic->pino_nlink); + /* Should we unlink it from its previous parent? */ + } + + /* For directories, ic->pino_nlink holds that parent inode # */ + fd->ic->pino_nlink = ic->ino; + } jffs2_free_full_dirent(fd); } ic->scan_dents = NULL; @@ -241,11 +284,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c, /* Reduce nlink of the child. If it's now zero, stick it on the dead_fds list to be cleaned up later. Else just free the fd */ - - if (fd->type == DT_DIR) - child_ic->pino_nlink = 0; - else - child_ic->pino_nlink--; + child_ic->pino_nlink--; if (!child_ic->pino_nlink) { dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n", diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index c5ac5944bc1b..cad86bac3453 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -137,39 +137,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; - uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; - jffs2_dbg(1, "%s()\n", __func__); - - if (pageofs > inode->i_size) { - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - return ret; - } - - mutex_lock(&f->sem); pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) { - if (alloc_len) - jffs2_complete_reservation(c); - mutex_unlock(&f->sem); + if (!pg) return -ENOMEM; - } *pagep = pg; - if (alloc_len) { + jffs2_dbg(1, "%s()\n", __func__); + + if (pageofs > inode->i_size) { /* Make new hole frag from old EOF to new page */ + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; + uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + goto out_page; + + mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -196,6 +190,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -210,10 +205,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; + mutex_unlock(&f->sem); } /* @@ -222,18 +219,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { + mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); + mutex_unlock(&f->sem); if (ret) goto out_page; } - mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); - mutex_unlock(&f->sem); return ret; } diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 5a2dec2b064c..95d5880a63ee 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era BUG_ON(start > orig_start); } - /* First, use readpage() to read the appropriate page into the page cache */ - /* Q: What happens if we actually try to GC the _same_ page for which commit_write() - * triggered garbage collection in the first place? - * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the - * page OK. We'll actually write it out again in commit_write, which is a little - * suboptimal, but at least we're correct. - */ + /* The rules state that we must obtain the page lock *before* f->sem, so + * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's + * actually going to *change* so we're safe; we only allow reading. + * + * It is important to note that jffs2_write_begin() will ensure that its + * page is marked Uptodate before allocating space. That means that if we + * end up here trying to GC the *same* page that jffs2_write_begin() is + * trying to write out, read_cache_page() will not deadlock. */ + mutex_unlock(&f->sem); pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg); + mutex_lock(&f->sem); if (IS_ERR(pg_ptr)) { pr_warn("read_cache_page() returned error: %ld\n", diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index fa35ff79ab35..0637271f3770 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -194,6 +194,7 @@ struct jffs2_inode_cache { #define INO_STATE_CLEARING 6 /* In clear_inode() */ #define INO_FLAGS_XATTR_CHECKED 0x01 /* has no duplicate xattr_ref */ +#define INO_FLAGS_IS_DIR 0x02 /* is a directory */ #define RAWNODE_CLASS_INODE_CACHE 0 #define RAWNODE_CLASS_XATTR_DATUM 1 @@ -249,7 +250,10 @@ struct jffs2_readinode_info struct jffs2_full_dirent { - struct jffs2_raw_node_ref *raw; + union { + struct jffs2_raw_node_ref *raw; + struct jffs2_inode_cache *ic; /* Just during part of build */ + }; struct jffs2_full_dirent *next; uint32_t version; uint32_t ino; /* == zero for unlink */ diff --git a/fs/namei.c b/fs/namei.c index f624d132e01e..9c590e0f66e9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1712,6 +1712,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link, return 0; if (!follow) return 0; + /* make sure that d_is_symlink above matches inode */ + if (nd->flags & LOOKUP_RCU) { + if (read_seqcount_retry(&link->dentry->d_seq, seq)) + return -ECHILD; + } return pick_link(nd, link, inode, seq); } @@ -1743,11 +1748,11 @@ static int walk_component(struct nameidata *nd, int flags) if (err < 0) return err; - inode = d_backing_inode(path.dentry); seq = 0; /* we are already out of RCU mode */ err = -ENOENT; if (d_is_negative(path.dentry)) goto out_path_put; + inode = d_backing_inode(path.dentry); } if (flags & WALK_PUT) @@ -3192,12 +3197,12 @@ retry_lookup: return error; BUG_ON(nd->flags & LOOKUP_RCU); - inode = d_backing_inode(path.dentry); seq = 0; /* out of RCU mode, so the value doesn't matter */ if (unlikely(d_is_negative(path.dentry))) { path_to_nameidata(&path, nd); return -ENOENT; } + inode = d_backing_inode(path.dentry); finish_lookup: if (nd->depth) put_link(nd); @@ -3206,11 +3211,6 @@ finish_lookup: if (unlikely(error)) return error; - if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) { - path_to_nameidata(&path, nd); - return -ELOOP; - } - if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) { path_to_nameidata(&path, nd); } else { @@ -3229,6 +3229,10 @@ finish_open: return error; } audit_inode(nd->name, nd->path.dentry, 0); + if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) { + error = -ELOOP; + goto out; + } error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; @@ -3273,6 +3277,10 @@ opened: goto exit_fput; } out: + if (unlikely(error > 0)) { + WARN_ON(1); + error = -EINVAL; + } if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c index c59a59c37f3d..35ab51c04814 100644 --- a/fs/nfs/blocklayout/extent_tree.c +++ b/fs/nfs/blocklayout/extent_tree.c @@ -476,6 +476,7 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg, for (i = 0; i < nr_pages; i++) put_page(arg->layoutupdate_pages[i]); + vfree(arg->start_p); kfree(arg->layoutupdate_pages); } else { put_page(arg->layoutupdate_page); @@ -559,10 +560,15 @@ retry: if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) { void *p = start_p, *end = p + arg->layoutupdate_len; + struct page *page = NULL; int i = 0; - for ( ; p < end; p += PAGE_SIZE) - arg->layoutupdate_pages[i++] = vmalloc_to_page(p); + arg->start_p = start_p; + for ( ; p < end; p += PAGE_SIZE) { + page = vmalloc_to_page(p); + arg->layoutupdate_pages[i++] = page; + get_page(page); + } } dprintk("%s found %zu ranges\n", __func__, count); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index bd25dc7077f7..dff83460e5a6 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -16,29 +16,8 @@ #define NFSDBG_FACILITY NFSDBG_PROC -static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, - fmode_t fmode) -{ - struct nfs_open_context *open; - struct nfs_lock_context *lock; - int ret; - - open = get_nfs_open_context(nfs_file_open_context(file)); - lock = nfs_get_lock_context(open); - if (IS_ERR(lock)) { - put_nfs_open_context(open); - return PTR_ERR(lock); - } - - ret = nfs4_set_rw_stateid(dst, open, lock, fmode); - - nfs_put_lock_context(lock); - put_nfs_open_context(open); - return ret; -} - static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, - loff_t offset, loff_t len) + struct nfs_lock_context *lock, loff_t offset, loff_t len) { struct inode *inode = file_inode(filep); struct nfs_server *server = NFS_SERVER(inode); @@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context, + lock, FMODE_WRITE); if (status) return status; @@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; int err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_fallocate(msg, filep, offset, len); - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + err = _nfs42_proc_fallocate(msg, filep, lock, offset, len); + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -135,7 +126,8 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return err; } -static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +static loff_t _nfs42_proc_llseek(struct file *filep, + struct nfs_lock_context *lock, loff_t offset, int whence) { struct inode *inode = file_inode(filep); struct nfs42_seek_args args = { @@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) if (!nfs_server_capable(inode, NFS_CAP_SEEK)) return -ENOTSUPP; - status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ); + status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context, + lock, FMODE_READ); if (status) return status; @@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; loff_t err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_llseek(filep, offset, whence); + err = _nfs42_proc_llseek(filep, lock, offset, whence); if (err >= 0) break; - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -298,8 +302,9 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, } static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, - struct file *dst_f, loff_t src_offset, - loff_t dst_offset, loff_t count) + struct file *dst_f, struct nfs_lock_context *src_lock, + struct nfs_lock_context *dst_lock, loff_t src_offset, + loff_t dst_offset, loff_t count) { struct inode *src_inode = file_inode(src_f); struct inode *dst_inode = file_inode(dst_f); @@ -320,11 +325,13 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ); + status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context, + src_lock, FMODE_READ); if (status) return status; - status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context, + dst_lock, FMODE_WRITE); if (status) return status; @@ -349,22 +356,48 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f, }; struct inode *inode = file_inode(src_f); struct nfs_server *server = NFS_SERVER(file_inode(src_f)); - struct nfs4_exception exception = { }; - int err; + struct nfs_lock_context *src_lock; + struct nfs_lock_context *dst_lock; + struct nfs4_exception src_exception = { }; + struct nfs4_exception dst_exception = { }; + int err, err2; if (!nfs_server_capable(inode, NFS_CAP_CLONE)) return -EOPNOTSUPP; + src_lock = nfs_get_lock_context(nfs_file_open_context(src_f)); + if (IS_ERR(src_lock)) + return PTR_ERR(src_lock); + + src_exception.inode = file_inode(src_f); + src_exception.state = src_lock->open_context->state; + + dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f)); + if (IS_ERR(dst_lock)) { + err = PTR_ERR(dst_lock); + goto out_put_src_lock; + } + + dst_exception.inode = file_inode(dst_f); + dst_exception.state = dst_lock->open_context->state; + do { - err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset, - dst_offset, count); + err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock, + src_offset, dst_offset, count); if (err == -ENOTSUPP || err == -EOPNOTSUPP) { NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE; - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + break; } - err = nfs4_handle_exception(server, err, &exception); - } while (exception.retry); - return err; + err2 = nfs4_handle_exception(server, err, &src_exception); + err = nfs4_handle_exception(server, err, &dst_exception); + if (!err) + err = err2; + } while (src_exception.retry || dst_exception.retry); + nfs_put_lock_context(dst_lock); +out_put_src_lock: + nfs_put_lock_context(src_lock); + return err; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4bfc33ad0563..14881594dd07 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2466,9 +2466,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = d_add_unique(dentry, igrab(state->inode)); if (dentry == NULL) { dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + } else { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry; } nfs_set_verifier(dentry, nfs_save_change_attribute(d_inode(opendata->dir))); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 482b6e94bb37..2fa483e6dbe2 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) } } +/* + * Mark a pnfs_layout_hdr and all associated layout segments as invalid + * + * In order to continue using the pnfs_layout_hdr, a full recovery + * is required. + * Note that caller must hold inode->i_lock. + */ +static int +pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, + struct list_head *lseg_list) +{ + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); +} + static int pnfs_iomode_to_fail_bit(u32 iomode) { @@ -554,9 +575,8 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) spin_lock(&nfsi->vfs_inode.i_lock); lo = nfsi->layout; if (lo) { - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL); pnfs_get_layout_hdr(lo); + pnfs_mark_layout_stateid_invalid(lo, &tmp_list); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); spin_unlock(&nfsi->vfs_inode.i_lock); @@ -617,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, { struct pnfs_layout_hdr *lo; struct inode *inode; - struct pnfs_layout_range range = { - .iomode = IOMODE_ANY, - .offset = 0, - .length = NFS4_MAX_UINT64, - }; LIST_HEAD(lseg_list); int ret = 0; @@ -636,11 +651,11 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, spin_lock(&inode->i_lock); list_del_init(&lo->plh_bulk_destroy); - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - if (is_bulk_recall) - set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); - if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range)) + if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) { + if (is_bulk_recall) + set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); ret = -EAGAIN; + } spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&lseg_list); /* Free all lsegs that are attached to commit buckets */ @@ -1738,8 +1753,19 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) if (lo->plh_return_iomode != 0) iomode = IOMODE_ANY; lo->plh_return_iomode = iomode; + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } +/** + * pnfs_mark_matching_lsegs_return - Free or return matching layout segments + * @lo: pointer to layout header + * @tmp_list: list header to be used with pnfs_free_lseg_list() + * @return_range: describe layout segment ranges to be returned + * + * This function is mainly intended for use by layoutrecall. It attempts + * to free the layout segment immediately, or else to mark it for return + * as soon as its reference count drops to zero. + */ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, @@ -1762,12 +1788,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); + if (mark_lseg_invalid(lseg, tmp_list)) + continue; + remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); pnfs_set_plh_return_iomode(lo, return_range->iomode); - if (!mark_lseg_invalid(lseg, tmp_list)) - remaining++; - set_bit(NFS_LAYOUT_RETURN_REQUESTED, - &lo->plh_flags); } return remaining; } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 794fd1587f34..cda0361e95a4 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -956,6 +956,7 @@ clean_orphan: tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, update_isize, end); if (tmp_ret < 0) { + ocfs2_inode_unlock(inode, 1); ret = tmp_ret; mlog_errno(ret); brelse(di_bh); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index ed95272d57a6..52f6de5d40a9 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -618,7 +618,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir) * sole user of this dentry. Too tricky... Just unhash for * now. */ - d_drop(dentry); + if (!err) + d_drop(dentry); inode_unlock(dir); return err; @@ -903,6 +904,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, if (!overwrite && new_is_dir && !old_opaque && new_opaque) ovl_remove_opaque(newdentry); + /* + * Old dentry now lives in different location. Dentries in + * lowerstack are stale. We cannot drop them here because + * access to them is lockless. This could be only pure upper + * or opaque directory - numlower is zero. Or upper non-dir + * entry - its pureness is tracked by flag opaque. + */ if (old_opaque != new_opaque) { ovl_dentry_set_opaque(old, new_opaque); if (!overwrite) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 49e204560655..a4ff5d0d7db9 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -65,6 +65,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) inode_lock(upperdentry->d_inode); err = notify_change(upperdentry, attr, NULL); + if (!err) + ovl_copyattr(upperdentry->d_inode, dentry->d_inode); inode_unlock(upperdentry->d_inode); } ovl_drop_write(dentry); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 8d826bd56b26..619ad4b016d2 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -76,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) if (oe->__upperdentry) { type = __OVL_PATH_UPPER; - if (oe->numlower) { - if (S_ISDIR(dentry->d_inode->i_mode)) - type |= __OVL_PATH_MERGE; - } else if (!oe->opaque) { + /* + * Non-dir dentry can hold lower dentry from previous + * location. Its purity depends only on opaque flag. + */ + if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode)) + type |= __OVL_PATH_MERGE; + else if (!oe->opaque) type |= __OVL_PATH_PURE; - } } else { if (oe->numlower > 1) type |= __OVL_PATH_MERGE; @@ -341,6 +343,7 @@ static const struct dentry_operations ovl_dentry_operations = { static const struct dentry_operations ovl_reval_dentry_operations = { .d_release = ovl_dentry_release, + .d_select_inode = ovl_d_select_inode, .d_revalidate = ovl_dentry_revalidate, .d_weak_revalidate = ovl_dentry_weak_revalidate, }; diff --git a/fs/pnode.c b/fs/pnode.c index 6367e1e435c6..c524fdddc7fb 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; +static inline bool peers(struct mount *m1, struct mount *m2) +{ + return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; +} + static int propagate_one(struct mount *m) { struct mount *child; @@ -212,7 +217,7 @@ static int propagate_one(struct mount *m) /* skip if mountpoint isn't covered by it */ if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) return 0; - if (m->mnt_group_id == last_dest->mnt_group_id) { + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { struct mount *n, *p; @@ -223,7 +228,7 @@ static int propagate_one(struct mount *m) last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } - if (n->mnt_group_id != last_dest->mnt_group_id) { + if (!peers(n, last_dest)) { last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } diff --git a/fs/read_write.c b/fs/read_write.c index 324ec271cc4e..dadf24e5c95b 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -17,6 +17,7 @@ #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> +#include <linux/fs.h> #include "internal.h" #include <asm/uaccess.h> @@ -183,7 +184,7 @@ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, - ~0ULL, 0); + OFFSET_MAX, 0); default: return -EINVAL; } @@ -1532,10 +1533,12 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND) || - !file_in->f_op->clone_file_range) + (file_out->f_flags & O_APPEND)) return -EBADF; + if (!file_in->f_op->clone_file_range) + return -EOPNOTSUPP; + ret = clone_verify_area(file_in, pos_in, len, false); if (ret) return ret; diff --git a/fs/super.c b/fs/super.c index 1182af8fd5ff..74914b1bae70 100644 --- a/fs/super.c +++ b/fs/super.c @@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb) sb->s_flags &= ~MS_ACTIVE; fsnotify_unmount_inodes(sb); + cgroup_writeback_umount(); evict_inodes(sb); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 50311703135b..66cdb44616d5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -287,6 +287,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address, goto out; /* + * We don't do userfault handling for the final child pid update. + */ + if (current->flags & PF_EXITING) + goto out; + + /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY diff --git a/fs/xattr.c b/fs/xattr.c index 07d0e47f6a7f..4861322e28e8 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -940,7 +940,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; - int err; + int err = 0; #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl) { @@ -965,11 +965,11 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) - return err; + break; } spin_unlock(&xattrs->lock); - return size - remaining_size; + return err ? err : size - remaining_size; } /* diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 379c089fb051..a9ebabfe7587 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -55,7 +55,7 @@ xfs_count_page_state( } while ((bh = bh->b_this_page) != head); } -STATIC struct block_device * +struct block_device * xfs_find_bdev_for_inode( struct inode *inode) { @@ -1208,6 +1208,10 @@ xfs_vm_writepages( struct writeback_control *wbc) { xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, + xfs_find_bdev_for_inode(mapping->host), wbc); + return generic_writepages(mapping, wbc); } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index f6ffc9ae5ceb..a4343c63fb38 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -62,5 +62,6 @@ int xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset, struct buffer_head *map_bh, int create); extern void xfs_count_page_state(struct page *, int *, int *); +extern struct block_device *xfs_find_bdev_for_inode(struct inode *); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 45ec9e40150c..6c876012b2e5 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -75,7 +75,8 @@ xfs_zero_extent( ssize_t size = XFS_FSB_TO_B(mp, count_fsb); if (IS_DAX(VFS_I(ip))) - return dax_clear_blocks(VFS_I(ip), block, size); + return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)), + sector, size); /* * let the block layer decide on the fastest method of diff --git a/include/linux/ata.h b/include/linux/ata.h index d2992bfa1706..c1a2f345cbe6 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -487,8 +487,8 @@ enum ata_tf_protocols { }; enum ata_ioctls { - ATA_IOC_GET_IO32 = 0x309, - ATA_IOC_SET_IO32 = 0x324, + ATA_IOC_GET_IO32 = 0x309, /* HDIO_GET_32BIT */ + ATA_IOC_SET_IO32 = 0x324, /* HDIO_SET_32BIT */ }; /* core structures */ diff --git a/include/linux/bio.h b/include/linux/bio.h index 5349e6816cbb..cb6888824108 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -310,6 +310,43 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) bio->bi_flags &= ~(1U << bit); } +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = bio_iovec(bio); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + if (!bio_flagged(bio, BIO_CLONED)) { + *bv = bio->bi_io_vec[bio->bi_vcnt - 1]; + return; + } + + if (unlikely(!bio_multiple_segments(bio))) { + *bv = bio_iovec(bio); + return; + } + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4571ef1a12a9..413c84fbc4ed 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -895,7 +895,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) { struct request_queue *q = rq->q; - if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC)) + if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD)) @@ -1372,6 +1372,13 @@ static inline void put_dev_sector(Sector p) page_cache_release(p.v); } +static inline bool __bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + return offset || + ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); +} + /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. @@ -1381,18 +1388,22 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, { if (!queue_virt_boundary(q)) return false; - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return __bvec_gap_to_prev(q, bprv, offset); } static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev)) - return false; + if (bio_has_data(prev) && queue_virt_boundary(q)) { + struct bio_vec pb, nb; + + bio_get_last_bvec(prev, &pb); + bio_get_first_bvec(next, &nb); - return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + } + + return false; } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 51e498e5470e..21ee41b92e8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,6 +10,7 @@ #include <uapi/linux/bpf.h> #include <linux/workqueue.h> #include <linux/file.h> +#include <linux/percpu.h> struct bpf_map; @@ -36,6 +37,7 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; + u32 map_flags; u32 pages; struct user_struct *user; const struct bpf_map_ops *ops; @@ -163,6 +165,8 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f const struct bpf_func_proto *bpf_get_trace_printk_proto(void); #ifdef CONFIG_BPF_SYSCALL +DECLARE_PER_CPU(int, bpf_prog_active); + void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); @@ -175,6 +179,7 @@ struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); +int bpf_map_precharge_memlock(u32 pages); extern int sysctl_unprivileged_bpf_disabled; @@ -190,6 +195,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); +int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index c1ef6f14e7be..15151f3c4120 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -75,6 +75,7 @@ #define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ // duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 #define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ +#define CEPH_FEATURE_FS_FILE_LAYOUT_V2 (1ULL<<58) /* file_layout_t */ /* * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature diff --git a/include/linux/dax.h b/include/linux/dax.h index 818e45078929..636dd59ab505 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,7 +7,7 @@ ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, get_block_t, dio_iodone_t, int flags); -int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, @@ -52,6 +52,8 @@ static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end); + +struct writeback_control; +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc); #endif diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 7781ce110503..c4b5f4b3f8f8 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -409,9 +409,7 @@ static inline bool d_mountpoint(const struct dentry *dentry) */ static inline unsigned __d_entry_type(const struct dentry *dentry) { - unsigned type = READ_ONCE(dentry->d_flags); - smp_rmb(); - return type & DCACHE_ENTRY_TYPE; + return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index a338a688ee4a..dcb89e3515db 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,10 +46,6 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) -/* values as per ieee8021QBridgeFdbAgingTime */ -#define BR_MIN_AGEING_TIME (10 * HZ) -#define BR_MAX_AGEING_TIME (1000000 * HZ) - #define BR_DEFAULT_AGEING_TIME (300 * HZ) extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); diff --git a/include/linux/libata.h b/include/linux/libata.h index bec2abbd7ab2..2c4ebef79d0c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -720,7 +720,7 @@ struct ata_device { union { u16 id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */ u32 gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */ - }; + } ____cacheline_aligned; /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index bed40dff0e86..141ffdd59960 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -26,9 +26,8 @@ enum { /* need to set a limit somewhere, but yes, this is likely overkill */ ND_IOCTL_MAX_BUFLEN = SZ_4M, - ND_CMD_MAX_ELEM = 4, + ND_CMD_MAX_ELEM = 5, ND_CMD_MAX_ENVELOPE = 16, - ND_CMD_ARS_STATUS_MAX = SZ_4K, ND_MAX_MAPPINGS = 32, /* region flag indicating to direct-map persistent memory by default */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 03ffe9530365..9d91ce39eb0f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4259,7 +4259,9 @@ struct mlx5_ifc_modify_tir_bitmask_bits { u8 reserved_at_20[0x1b]; u8 self_lb_en[0x1]; - u8 reserved_at_3c[0x3]; + u8 reserved_at_3c[0x1]; + u8 hash[0x1]; + u8 reserved_at_3e[0x1]; u8 lro[0x1]; }; diff --git a/include/linux/net.h b/include/linux/net.h index 0b4ac7da583a..49175e4ced11 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -215,6 +215,7 @@ int __sock_create(struct net *net, int family, int type, int proto, int sock_create(int family, int type, int proto, struct socket **res); int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); +struct socket *sock_alloc(void); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index efe7cec111fa..41df0b450757 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -268,6 +268,7 @@ struct header_ops { void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); + bool (*validate)(const char *ll_header, unsigned int len); }; /* These flag bits are private to the generic network queueing @@ -785,6 +786,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, enum { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, + TC_SETUP_CLSFLOWER, }; struct tc_cls_u32_offload; @@ -794,6 +796,7 @@ struct tc_to_netdev { union { u8 tc; struct tc_cls_u32_offload *cls_u32; + struct tc_cls_flower_offload *cls_flower; }; }; @@ -1459,8 +1462,7 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length, which means that this is the - * minimum size of a packet. + * @hard_header_len: Maximum hardware header length. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -2687,6 +2689,24 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } +/* ll_header must have at least hard_header_len allocated */ +static inline bool dev_validate_header(const struct net_device *dev, + char *ll_header, int len) +{ + if (likely(len >= dev->hard_header_len)) + return true; + + if (capable(CAP_SYS_RAWIO)) { + memset(ll_header + len, 0, dev->hard_header_len - len); + return true; + } + + if (dev->header_ops && dev->header_ops->validate) + return dev->header_ops->validate(ll_header, len); + + return false; +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0ad556726181..9230f9aee896 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -141,22 +141,6 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; - -static inline bool nf_hook_list_active(struct list_head *hook_list, - u_int8_t pf, unsigned int hook) -{ - if (__builtin_constant_p(pf) && - __builtin_constant_p(hook)) - return static_key_false(&nf_hooks_needed[pf][hook]); - - return !list_empty(hook_list); -} -#else -static inline bool nf_hook_list_active(struct list_head *hook_list, - u_int8_t pf, unsigned int hook) -{ - return !list_empty(hook_list); -} #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); @@ -177,9 +161,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { - struct list_head *hook_list = &net->nf.hooks[pf][hook]; + struct list_head *hook_list; + +#ifdef HAVE_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return 1; +#endif + + hook_list = &net->nf.hooks[pf][hook]; - if (nf_hook_list_active(hook_list, pf, hook)) { + if (!list_empty(hook_list)) { struct nf_hook_state state; nf_hook_state_init(&state, hook_list, hook, thresh, diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index c5577410c25d..80a305b85323 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -200,6 +200,9 @@ struct xt_table { u_int8_t af; /* address/protocol family */ int priority; /* hook order */ + /* called when table is needed in the given netns */ + int (*table_init)(struct net *net); + /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; @@ -408,8 +411,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) return cnt; } -struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *); -void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *); +struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 6f074db2f23d..029b95e8924e 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -48,10 +48,11 @@ struct arpt_error { } extern void *arpt_alloc_initial_table(const struct xt_table *); -extern struct xt_table *arpt_register_table(struct net *net, - const struct xt_table *table, - const struct arpt_replace *repl); -extern void arpt_unregister_table(struct xt_table *table); +int arpt_register_table(struct net *net, const struct xt_table *table, + const struct arpt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void arpt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index aa598f942c01..7bfc5893ec31 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -24,10 +24,11 @@ extern void ipt_init(void) __init; -extern struct xt_table *ipt_register_table(struct net *net, - const struct xt_table *table, - const struct ipt_replace *repl); -extern void ipt_unregister_table(struct net *net, struct xt_table *table); +int ipt_register_table(struct net *net, const struct xt_table *table, + const struct ipt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void ipt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); /* Standard entry. */ struct ipt_standard { diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 0f76e5c674f9..b21c392d6012 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -25,10 +25,11 @@ extern void ip6t_init(void) __init; extern void *ip6t_alloc_initial_table(const struct xt_table *); -extern struct xt_table *ip6t_register_table(struct net *net, - const struct xt_table *table, - const struct ip6t_replace *repl); -extern void ip6t_unregister_table(struct net *net, struct xt_table *table); +int ip6t_register_table(struct net *net, const struct xt_table *table, + const struct ip6t_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res); +void ip6t_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 48e0320cd643..67300f8e5f2f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -550,9 +550,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, static inline loff_t nfs_size_to_loff_t(__u64 size) { - if (size > (__u64) OFFSET_MAX - 1) - return OFFSET_MAX - 1; - return (loff_t) size; + return min_t(u64, size, OFFSET_MAX); } static inline ino_t diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 791098a08a87..d320906cf13e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -275,6 +275,7 @@ struct nfs4_layoutcommit_args { size_t layoutupdate_len; struct page *layoutupdate_page; struct page **layoutupdate_pages; + __be32 *start_p; }; struct nfs4_layoutcommit_res { diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..27716254dcc5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -988,23 +988,6 @@ static inline int pci_is_managed(struct pci_dev *pdev) return pdev->is_managed; } -static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq) -{ - pdev->irq = irq; - pdev->irq_managed = 1; -} - -static inline void pci_reset_managed_irq(struct pci_dev *pdev) -{ - pdev->irq = 0; - pdev->irq_managed = 0; -} - -static inline bool pci_has_managed_irq(struct pci_dev *pdev) -{ - return pdev->irq_managed && pdev->irq > 0; -} - void pci_disable_device(struct pci_dev *dev); extern unsigned int pcibios_max_latency; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7da3c25999df..0967a2467457 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -397,6 +397,7 @@ struct pmu { * enum perf_event_active_state - the states of a event */ enum perf_event_active_state { + PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, @@ -905,7 +906,7 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) } } -extern struct static_key_deferred perf_sched_events; +extern struct static_key_false perf_sched_events; static __always_inline bool perf_sw_migrate_enabled(void) @@ -924,7 +925,7 @@ static inline void perf_event_task_migrate(struct task_struct *task) static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { - if (static_key_false(&perf_sched_events.key)) + if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (perf_sw_migrate_enabled() && task->sched_migrated) { @@ -941,7 +942,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, { perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); - if (static_key_false(&perf_sched_events.key)) + if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 998d8f1c3c91..b50c0492629d 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -49,6 +49,7 @@ struct bq27xxx_reg_cache { struct bq27xxx_device_info { struct device *dev; + int id; enum bq27xxx_chip chip; const char *name; struct bq27xxx_access_methods bus; diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index e53b0ca49e41..e1d69834a11f 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -39,6 +39,14 @@ struct qed_update_vport_params { struct qed_update_vport_rss_params rss_params; }; +struct qed_start_vport_params { + bool remove_inner_vlan; + bool gro_enable; + bool drop_ttl0; + u8 vport_id; + u16 mtu; +}; + struct qed_stop_rxq_params { u8 rss_id; u8 rx_queue_id; @@ -118,9 +126,7 @@ struct qed_eth_ops { void *cookie); int (*vport_start)(struct qed_dev *cdev, - u8 vport_id, u16 mtu, - u8 drop_ttl0_flg, - u8 inner_vlan_removal_en_flg); + struct qed_start_vport_params *params); int (*vport_stop)(struct qed_dev *cdev, u8 vport_id); diff --git a/include/linux/random.h b/include/linux/random.h index a75840c1aa71..9c29122037f9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops; #endif unsigned int get_random_int(void); +unsigned long get_random_long(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); u32 prandom_u32(void); diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 14ec1652daf4..17d4f849c65e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -319,6 +319,27 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, }) /** + * list_next_or_null_rcu - get the first element from a list + * @head: the head for the list. + * @ptr: the list head to take the next element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the ptr is at the end of the list, NULL is returned. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). + */ +#define list_next_or_null_rcu(head, ptr, type, member) \ +({ \ + struct list_head *__head = (head); \ + struct list_head *__ptr = (ptr); \ + struct list_head *__next = READ_ONCE(__ptr->next); \ + likely(__next != __head) ? list_entry_rcu(__next, type, \ + member) : NULL; \ +}) + +/** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 797cefb888fb..15d0df943466 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1981,6 +1981,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +/** + * skb_tailroom_reserve - adjust reserved_tailroom + * @skb: buffer to alter + * @mtu: maximum amount of headlen permitted + * @needed_tailroom: minimum amount of reserved_tailroom + * + * Set reserved_tailroom so that headlen can be as large as possible but + * not larger than mtu and tailroom cannot be smaller than + * needed_tailroom. + * The required headroom should already have been reserved before using + * this function. + */ +static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, + unsigned int needed_tailroom) +{ + SKB_LINEAR_ASSERT(skb); + if (mtu < skb_tailroom(skb) - needed_tailroom) + /* use at most mtu */ + skb->reserved_tailroom = skb_tailroom(skb) - mtu; + else + /* use up to all available space */ + skb->reserved_tailroom = needed_tailroom; +} + #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 diff --git a/include/linux/socket.h b/include/linux/socket.h index 5bf59c8493b7..73bf6c6a833b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -200,7 +200,9 @@ struct ucred { #define AF_ALG 38 /* Algorithm sockets */ #define AF_NFC 39 /* NFC sockets */ #define AF_VSOCK 40 /* vSockets */ -#define AF_MAX 41 /* For now.. */ +#define AF_KCM 41 /* Kernel Connection Multiplexor*/ + +#define AF_MAX 42 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -246,6 +248,7 @@ struct ucred { #define PF_ALG AF_ALG #define PF_NFC AF_NFC #define PF_VSOCK AF_VSOCK +#define PF_KCM AF_KCM #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -274,6 +277,7 @@ struct ucred { #define MSG_MORE 0x8000 /* Sender will send more */ #define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ +#define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ @@ -322,6 +326,7 @@ struct ucred { #define SOL_CAIF 278 #define SOL_ALG 279 #define SOL_NFC 280 +#define SOL_KCM 281 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 6e53fa8942a4..4bcf5a61aada 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -114,6 +114,7 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 429fdfc3baf5..925730bc9fc1 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -568,6 +568,8 @@ enum { FILTER_DYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, + FILTER_COMM, + FILTER_CPU, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b333c945e571..d0b5ca5d4e08 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -198,6 +198,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_io(struct writeback_control *wbc, struct page *page, size_t bytes); +void cgroup_writeback_umount(void); /** * inode_attach_wb - associate an inode with its wb @@ -301,6 +302,10 @@ static inline void wbc_account_io(struct writeback_control *wbc, { } +static inline void cgroup_writeback_umount(void) +{ +} + #endif /* CONFIG_CGROUP_WRITEBACK */ /* diff --git a/include/net/act_api.h b/include/net/act_api.h index 342be6c5ab5c..2a19fe111c78 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -78,11 +78,6 @@ static inline void tcf_lastuse_update(struct tcf_t *tm) tm->lastuse = now; } -#ifdef CONFIG_NET_CLS_ACT - -#define ACT_P_CREATED 1 -#define ACT_P_DELETED 1 - struct tc_action { void *priv; const struct tc_action_ops *ops; @@ -92,6 +87,11 @@ struct tc_action { struct tcf_hashinfo *hinfo; }; +#ifdef CONFIG_NET_CLS_ACT + +#define ACT_P_CREATED 1 +#define ACT_P_DELETED 1 + struct tc_action_ops { struct list_head head; char kind[IFNAMSIZ]; @@ -171,5 +171,16 @@ int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); + +#define tc_no_actions(_exts) \ + (list_empty(&(_exts)->actions)) + +#define tc_for_each_action(_a, _exts) \ + list_for_each_entry(a, &(_exts)->actions, list) +#else /* CONFIG_NET_CLS_ACT */ + +#define tc_no_actions(_exts) true +#define tc_for_each_action(_a, _exts) while (0) + #endif /* CONFIG_NET_CLS_ACT */ #endif diff --git a/include/net/checksum.h b/include/net/checksum.h index 10a16b5bd1c7..5c30891e84e5 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -88,8 +88,11 @@ static inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) { u32 sum = (__force u32)csum2; - if (offset&1) - sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF); + + /* rotate sum to align it with a 16b boundary */ + if (offset & 1) + sum = ror32(sum, 8); + return csum_add(csum, (__force __wsum)sum); } @@ -102,10 +105,7 @@ csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) static inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { - u32 sum = (__force u32)csum2; - if (offset&1) - sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF); - return csum_sub(csum, (__force __wsum)sum); + return csum_block_add(csum, ~csum2, offset); } static inline __wsum csum_unfold(__sum16 n) @@ -120,6 +120,11 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) #define CSUM_MANGLED_0 ((__force __sum16)0xffff) +static inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) +{ + *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); +} + static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 84b833af6882..5db9f5910428 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -126,7 +126,7 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, ip_tunnel_key_init(&tun_dst->u.tun_info.key, iph->saddr, iph->daddr, iph->tos, iph->ttl, - 0, 0, tunnel_id, flags); + 0, 0, 0, tunnel_id, flags); return tun_dst; } @@ -152,8 +152,11 @@ static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, info->key.u.ipv6.src = ip6h->saddr; info->key.u.ipv6.dst = ip6h->daddr; + info->key.tos = ipv6_get_dsfield(ip6h); info->key.ttl = ip6h->hop_limit; + info->key.label = ip6_flowlabel(ip6h); + return tun_dst; } diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8c8548cf5888..d3d60dccd19f 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -184,4 +184,17 @@ static inline bool flow_keys_have_l4(struct flow_keys *keys) u32 flow_hash_from_keys(struct flow_keys *keys); +static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) +{ + return flow_dissector->used_keys & (1 << key_id); +} + +static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id, + void *target_container) +{ + return ((char *)target_container) + flow_dissector->offset[key_id]; +} + #endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 5f28b606633e..5dc2e454f866 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -48,6 +48,7 @@ struct ip_tunnel_key { __be16 tun_flags; u8 tos; /* TOS for IPv4, TC for IPv6 */ u8 ttl; /* TTL for IPv4, HL for IPv6 */ + __be32 label; /* Flow Label for IPv6 */ __be16 tp_src; __be16 tp_dst; }; @@ -140,6 +141,7 @@ struct ip_tunnel { #define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) #define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800) #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) +#define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_OPTIONS_PRESENT (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT) @@ -180,7 +182,7 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, - u8 tos, u8 ttl, + u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, __be64 tun_id, __be16 tun_flags) { @@ -191,6 +193,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, 0, IP_TUNNEL_KEY_IPV4_PAD_LEN); key->tos = tos; key->ttl = ttl; + key->label = label; key->tun_flags = tun_flags; /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of @@ -206,6 +209,20 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE); } +static inline bool +ip_tunnel_dst_cache_usable(const struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + if (skb->mark) + return false; + if (!info) + return true; + if (info->key.tun_flags & TUNNEL_NOCACHE) + return false; + + return true; +} + static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info *tun_info) { @@ -354,6 +371,17 @@ static inline void ip_tunnel_unneed_metadata(void) { } +static inline void ip_tunnel_info_opts_get(void *to, + const struct ip_tunnel_info *info) +{ +} + +static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, + const void *from, int len) +{ + info->options_len = 0; +} + #endif /* CONFIG_INET */ #endif /* __NET_IP_TUNNELS_H */ diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index 8f81bbbc38fc..e0f4109e64c6 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); +#ifdef CONFIG_WEXT_CORE +/* flush all previous wext events - if work is done from netdev notifiers */ +void wireless_nlevent_flush(void); +#else +static inline void wireless_nlevent_flush(void) {} +#endif /* We may need a function to send a stream of events to user space. * More on that later... */ diff --git a/include/net/kcm.h b/include/net/kcm.h new file mode 100644 index 000000000000..2840b5825dcc --- /dev/null +++ b/include/net/kcm.h @@ -0,0 +1,226 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#ifndef __NET_KCM_H_ +#define __NET_KCM_H_ + +#include <linux/skbuff.h> +#include <net/sock.h> +#include <uapi/linux/kcm.h> + +extern unsigned int kcm_net_id; + +#define KCM_STATS_ADD(stat, count) ((stat) += (count)) +#define KCM_STATS_INCR(stat) ((stat)++) + +struct kcm_psock_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; + unsigned int rx_aborts; + unsigned int rx_mem_fail; + unsigned int rx_need_more_hdr; + unsigned int rx_msg_too_big; + unsigned int rx_msg_timeouts; + unsigned int rx_bad_hdr_len; + unsigned long long reserved; + unsigned long long unreserved; + unsigned int tx_aborts; +}; + +struct kcm_mux_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; + unsigned int rx_ready_drops; + unsigned int tx_retries; + unsigned int psock_attach; + unsigned int psock_unattach_rsvd; + unsigned int psock_unattach; +}; + +struct kcm_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; +}; + +struct kcm_tx_msg { + unsigned int sent; + unsigned int fragidx; + unsigned int frag_offset; + unsigned int msg_flags; + struct sk_buff *frag_skb; + struct sk_buff *last_skb; +}; + +struct kcm_rx_msg { + int full_len; + int accum_len; + int offset; + int early_eaten; +}; + +/* Socket structure for KCM client sockets */ +struct kcm_sock { + struct sock sk; + struct kcm_mux *mux; + struct list_head kcm_sock_list; + int index; + u32 done : 1; + struct work_struct done_work; + + struct kcm_stats stats; + + /* Transmit */ + struct kcm_psock *tx_psock; + struct work_struct tx_work; + struct list_head wait_psock_list; + struct sk_buff *seq_skb; + + /* Don't use bit fields here, these are set under different locks */ + bool tx_wait; + bool tx_wait_more; + + /* Receive */ + struct kcm_psock *rx_psock; + struct list_head wait_rx_list; /* KCMs waiting for receiving */ + bool rx_wait; + u32 rx_disabled : 1; +}; + +struct bpf_prog; + +/* Structure for an attached lower socket */ +struct kcm_psock { + struct sock *sk; + struct kcm_mux *mux; + int index; + + u32 tx_stopped : 1; + u32 rx_stopped : 1; + u32 done : 1; + u32 unattaching : 1; + + void (*save_state_change)(struct sock *sk); + void (*save_data_ready)(struct sock *sk); + void (*save_write_space)(struct sock *sk); + + struct list_head psock_list; + + struct kcm_psock_stats stats; + + /* Receive */ + struct sk_buff *rx_skb_head; + struct sk_buff **rx_skb_nextp; + struct sk_buff *ready_rx_msg; + struct list_head psock_ready_list; + struct work_struct rx_work; + struct delayed_work rx_delayed_work; + struct bpf_prog *bpf_prog; + struct kcm_sock *rx_kcm; + unsigned long long saved_rx_bytes; + unsigned long long saved_rx_msgs; + struct timer_list rx_msg_timer; + unsigned int rx_need_bytes; + + /* Transmit */ + struct kcm_sock *tx_kcm; + struct list_head psock_avail_list; + unsigned long long saved_tx_bytes; + unsigned long long saved_tx_msgs; +}; + +/* Per net MUX list */ +struct kcm_net { + struct mutex mutex; + struct kcm_psock_stats aggregate_psock_stats; + struct kcm_mux_stats aggregate_mux_stats; + struct list_head mux_list; + int count; +}; + +/* Structure for a MUX */ +struct kcm_mux { + struct list_head kcm_mux_list; + struct rcu_head rcu; + struct kcm_net *knet; + + struct list_head kcm_socks; /* All KCM sockets on MUX */ + int kcm_socks_cnt; /* Total KCM socket count for MUX */ + struct list_head psocks; /* List of all psocks on MUX */ + int psocks_cnt; /* Total attached sockets */ + + struct kcm_mux_stats stats; + struct kcm_psock_stats aggregate_psock_stats; + + /* Receive */ + spinlock_t rx_lock ____cacheline_aligned_in_smp; + struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */ + struct list_head psocks_ready; /* List of psocks with a msg ready */ + struct sk_buff_head rx_hold_queue; + + /* Transmit */ + spinlock_t lock ____cacheline_aligned_in_smp; /* TX and mux locking */ + struct list_head psocks_avail; /* List of available psocks */ + struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */ +}; + +#ifdef CONFIG_PROC_FS +int kcm_proc_init(void); +void kcm_proc_exit(void); +#else +static inline int kcm_proc_init(void) { return 0; } +static inline void kcm_proc_exit(void) { } +#endif + +static inline void aggregate_psock_stats(struct kcm_psock_stats *stats, + struct kcm_psock_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_PSOCK_STATS(rx_msgs); + SAVE_PSOCK_STATS(rx_bytes); + SAVE_PSOCK_STATS(rx_aborts); + SAVE_PSOCK_STATS(rx_mem_fail); + SAVE_PSOCK_STATS(rx_need_more_hdr); + SAVE_PSOCK_STATS(rx_msg_too_big); + SAVE_PSOCK_STATS(rx_msg_timeouts); + SAVE_PSOCK_STATS(rx_bad_hdr_len); + SAVE_PSOCK_STATS(tx_msgs); + SAVE_PSOCK_STATS(tx_bytes); + SAVE_PSOCK_STATS(reserved); + SAVE_PSOCK_STATS(unreserved); + SAVE_PSOCK_STATS(tx_aborts); +#undef SAVE_PSOCK_STATS +} + +static inline void aggregate_mux_stats(struct kcm_mux_stats *stats, + struct kcm_mux_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_MUX_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_MUX_STATS(rx_msgs); + SAVE_MUX_STATS(rx_bytes); + SAVE_MUX_STATS(tx_msgs); + SAVE_MUX_STATS(tx_bytes); + SAVE_MUX_STATS(rx_ready_drops); + SAVE_MUX_STATS(psock_attach); + SAVE_MUX_STATS(psock_unattach_rsvd); + SAVE_MUX_STATS(psock_unattach); +#undef SAVE_MUX_STATS +} + +#endif /* __NET_KCM_H_ */ diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h index e2a518b60e19..a3f3c11b2526 100644 --- a/include/net/netfilter/nft_masq.h +++ b/include/net/netfilter/nft_masq.h @@ -2,7 +2,9 @@ #define _NFT_MASQ_H_ struct nft_masq { - u32 flags; + u32 flags; + enum nft_registers sreg_proto_min:8; + enum nft_registers sreg_proto_max:8; }; extern const struct nla_policy nft_masq_policy[]; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index c0368db6df54..10d0848f5b8a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -58,7 +58,10 @@ struct netns_ipv6 { struct timer_list ip6_fib_timer; struct hlist_head *fib_table_hash; struct fib6_table *fib6_main_tbl; + struct list_head fib6_walkers; struct dst_ops ip6_dst_ops; + rwlock_t fib6_walker_lock; + spinlock_t fib6_gc_lock; unsigned int ip6_rt_gc_expire; unsigned long ip6_rt_last_gc; #ifdef CONFIG_IPV6_MULTIPLE_TABLES diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bea14eee373e..caa5e18636df 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -409,4 +409,18 @@ static inline bool tc_should_offload(struct net_device *dev, u32 flags) return true; } +enum tc_fl_command { + TC_CLSFLOWER_REPLACE, + TC_CLSFLOWER_DESTROY, +}; + +struct tc_cls_flower_offload { + enum tc_fl_command command; + unsigned long cookie; + struct flow_dissector *dissector; + struct fl_flow_key *mask; + struct fl_flow_key *key; + struct tcf_exts *exts; +}; + #endif diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 04a31830711b..93c520b83d10 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -16,9 +16,9 @@ struct tcf_gact { #define to_gact(a) \ container_of(a->priv, struct tcf_gact, common) -#ifdef CONFIG_NET_CLS_ACT static inline bool is_tcf_gact_shot(const struct tc_action *a) { +#ifdef CONFIG_NET_CLS_ACT struct tcf_gact *gact; if (a->ops && a->ops->type != TCA_ACT_GACT) @@ -28,7 +28,7 @@ static inline bool is_tcf_gact_shot(const struct tc_action *a) if (gact->tcf_action == TC_ACT_SHOT) return true; +#endif return false; } -#endif #endif /* __NET_TC_GACT_H */ diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 0df9a0db4a8e..b496d5ad7d42 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -20,6 +20,7 @@ #define __NET_TC_SKBEDIT_H #include <net/act_api.h> +#include <linux/tc_act/tc_skbedit.h> struct tcf_skbedit { struct tcf_common common; @@ -32,4 +33,19 @@ struct tcf_skbedit { #define to_skbedit(a) \ container_of(a->priv, struct tcf_skbedit, common) +/* Return true iff action is mark */ +static inline bool is_tcf_skbedit_mark(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) + return to_skbedit(a)->flags == SKBEDIT_F_MARK; +#endif + return false; +} + +static inline u32 tcf_skbedit_mark(const struct tc_action *a) +{ + return to_skbedit(a)->mark; +} + #endif /* __NET_TC_SKBEDIT_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index e90db8546806..0302636af98c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1816,4 +1816,28 @@ static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) skb->truesize = 2; } +static inline int tcp_inq(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + int answ; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + answ = 0; + } else if (sock_flag(sk, SOCK_URGINLINE) || + !tp->urg_data || + before(tp->urg_seq, tp->copied_seq) || + !before(tp->urg_seq, tp->rcv_nxt)) { + + answ = tp->rcv_nxt - tp->copied_seq; + + /* Subtract 1, if FIN was received */ + if (answ && sock_flag(sk, SOCK_DONE)) + answ--; + } else { + answ = tp->urg_seq - tp->copied_seq; + } + + return answ; +} + #endif /* _TCP_H */ diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 97f5adb121a6..b83114077cee 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -88,8 +88,8 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, - __u8 prio, __u8 ttl, __be16 src_port, - __be16 dst_port, bool nocheck); + __u8 prio, __u8 ttl, __be32 label, + __be16 src_port, __be16 dst_port, bool nocheck); #endif void udp_tunnel_sock_release(struct socket *sock); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 6eda4ed4d78b..a763c96ecde4 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -162,6 +162,7 @@ struct vxlan_config { u16 port_max; u8 tos; u8 ttl; + __be32 label; u32 flags; unsigned long age_interval; unsigned int addrmax; diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index e2b712c90d3f..c21c38ce7450 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -343,7 +343,7 @@ void snd_hdac_bus_enter_link_reset(struct hdac_bus *bus); void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus); void snd_hdac_bus_update_rirb(struct hdac_bus *bus); -void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, +int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, void (*ack)(struct hdac_bus *, struct hdac_stream *)); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6496f98d3d68..924f537183fd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -101,12 +101,15 @@ enum bpf_prog_type { #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +#define BPF_F_NO_PREALLOC (1U << 0) + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ __u32 key_size; /* size of key in bytes */ __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* prealloc or not */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -298,6 +301,17 @@ enum bpf_func_id { * Return: csum result */ BPF_FUNC_csum_diff, + + /** + * bpf_skb_[gs]et_tunnel_opt(skb, opt, size) + * retrieve or populate tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: 0 on success for set, option size for get + */ + BPF_FUNC_skb_get_tunnel_opt, + BPF_FUNC_skb_set_tunnel_opt, __BPF_FUNC_MAX_ID, }; @@ -305,6 +319,7 @@ enum bpf_func_id { /* BPF_FUNC_skb_store_bytes flags. */ #define BPF_F_RECOMPUTE_CSUM (1ULL << 0) +#define BPF_F_INVALIDATE_HASH (1ULL << 1) /* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. * First 4 bits are for passing the header field size. @@ -327,6 +342,10 @@ enum bpf_func_id { #define BPF_F_FAST_STACK_CMP (1ULL << 9) #define BPF_F_REUSE_STACKID (1ULL << 10) +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) +#define BPF_F_DONT_FRAGMENT (1ULL << 2) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -356,6 +375,7 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; + __u32 tunnel_label; }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d452cea59020..249eef9a21bd 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -456,6 +456,7 @@ enum { IFLA_VXLAN_GBP, IFLA_VXLAN_REMCSUM_NOPARTIAL, IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -478,6 +479,7 @@ enum { IFLA_GENEVE_UDP_CSUM, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + IFLA_GENEVE_LABEL, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) diff --git a/include/uapi/linux/kcm.h b/include/uapi/linux/kcm.h new file mode 100644 index 000000000000..a5a530940b99 --- /dev/null +++ b/include/uapi/linux/kcm.h @@ -0,0 +1,40 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * User API to clone KCM sockets and attach transport socket to a KCM + * multiplexor. + */ + +#ifndef KCM_KERNEL_H +#define KCM_KERNEL_H + +struct kcm_attach { + int fd; + int bpf_fd; +}; + +struct kcm_unattach { + int fd; +}; + +struct kcm_clone { + int fd; +}; + +#define SIOCKCMATTACH (SIOCPROTOPRIVATE + 0) +#define SIOCKCMUNATTACH (SIOCPROTOPRIVATE + 1) +#define SIOCKCMCLONE (SIOCPROTOPRIVATE + 2) + +#define KCMPROTO_CONNECTED 0 + +/* Socket options */ +#define KCM_RECV_DISABLE 1 + +#endif + diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 1e3c8cb43bd7..625b38f65764 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -66,27 +66,33 @@ struct media_device_info { /* * DVB entities */ -#define MEDIA_ENT_F_DTV_DEMOD (MEDIA_ENT_F_BASE + 1) -#define MEDIA_ENT_F_TS_DEMUX (MEDIA_ENT_F_BASE + 2) -#define MEDIA_ENT_F_DTV_CA (MEDIA_ENT_F_BASE + 3) -#define MEDIA_ENT_F_DTV_NET_DECAP (MEDIA_ENT_F_BASE + 4) +#define MEDIA_ENT_F_DTV_DEMOD (MEDIA_ENT_F_BASE + 0x00001) +#define MEDIA_ENT_F_TS_DEMUX (MEDIA_ENT_F_BASE + 0x00002) +#define MEDIA_ENT_F_DTV_CA (MEDIA_ENT_F_BASE + 0x00003) +#define MEDIA_ENT_F_DTV_NET_DECAP (MEDIA_ENT_F_BASE + 0x00004) /* - * Connectors + * I/O entities */ -/* It is a responsibility of the entity drivers to add connectors and links */ -#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 21) -#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 22) -#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 23) -/* For internal test signal generators and other debug connectors */ -#define MEDIA_ENT_F_CONN_TEST (MEDIA_ENT_F_BASE + 24) +#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 0x01001) +#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 0x01002) +#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 0x01003) /* - * I/O entities + * Connectors */ -#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 31) -#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 32) -#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 33) +/* It is a responsibility of the entity drivers to add connectors and links */ +#ifdef __KERNEL__ + /* + * For now, it should not be used in userspace, as some + * definitions may change + */ + +#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 0x30001) +#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 0x30002) +#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 0x30003) + +#endif /* * Don't touch on those. The ranges MEDIA_ENT_F_OLD_BASE and @@ -291,14 +297,14 @@ struct media_v2_entity { __u32 id; char name[64]; /* FIXME: move to a property? (RFC says so) */ __u32 function; /* Main function of the entity */ - __u16 reserved[12]; -}; + __u32 reserved[6]; +} __attribute__ ((packed)); /* Should match the specific fields at media_intf_devnode */ struct media_v2_intf_devnode { __u32 major; __u32 minor; -}; +} __attribute__ ((packed)); struct media_v2_interface { __u32 id; @@ -310,22 +316,22 @@ struct media_v2_interface { struct media_v2_intf_devnode devnode; __u32 raw[16]; }; -}; +} __attribute__ ((packed)); struct media_v2_pad { __u32 id; __u32 entity_id; __u32 flags; - __u16 reserved[9]; -}; + __u32 reserved[5]; +} __attribute__ ((packed)); struct media_v2_link { __u32 id; __u32 source_id; __u32 sink_id; __u32 flags; - __u32 reserved[5]; -}; + __u32 reserved[6]; +} __attribute__ ((packed)); struct media_v2_topology { __u64 topology_version; @@ -345,7 +351,7 @@ struct media_v2_topology { __u32 num_links; __u32 reserved4; __u64 ptr_links; -}; +} __attribute__ ((packed)); static inline void __user *media_get_uptr(__u64 arg) { diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 5b4a4be06e2b..cc68b92124d4 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -66,14 +66,18 @@ struct nd_cmd_ars_cap { __u64 length; __u32 status; __u32 max_ars_out; + __u32 clear_err_unit; + __u32 reserved; } __packed; struct nd_cmd_ars_start { __u64 address; __u64 length; __u16 type; - __u8 reserved[6]; + __u8 flags; + __u8 reserved[5]; __u32 status; + __u32 scrub_time; } __packed; struct nd_cmd_ars_status { @@ -81,11 +85,14 @@ struct nd_cmd_ars_status { __u32 out_length; __u64 address; __u64 length; + __u64 restart_address; + __u64 restart_length; __u16 type; + __u16 flags; __u32 num_records; struct nd_ars_record { __u32 handle; - __u32 flags; + __u32 reserved; __u64 err_address; __u64 length; } __packed records[0]; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index be41ffc128b8..eeffde196f80 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -681,6 +681,7 @@ enum nft_exthdr_attributes { * @NFT_META_IIFGROUP: packet input interface group * @NFT_META_OIFGROUP: packet output interface group * @NFT_META_CGROUP: socket control group (skb->sk->sk_classid) + * @NFT_META_PRANDOM: a 32bit pseudo-random number */ enum nft_meta_keys { NFT_META_LEN, @@ -707,6 +708,7 @@ enum nft_meta_keys { NFT_META_IIFGROUP, NFT_META_OIFGROUP, NFT_META_CGROUP, + NFT_META_PRANDOM, }; /** @@ -949,10 +951,14 @@ enum nft_nat_attributes { * enum nft_masq_attributes - nf_tables masquerade expression attributes * * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32) + * @NFTA_MASQ_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers) + * @NFTA_MASQ_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers) */ enum nft_masq_attributes { NFTA_MASQ_UNSPEC, NFTA_MASQ_FLAGS, + NFTA_MASQ_REG_PROTO_MIN, + NFTA_MASQ_REG_PROTO_MAX, __NFTA_MASQ_MAX }; #define NFTA_MASQ_MAX (__NFTA_MASQ_MAX - 1) diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 9874f5680926..c43c5f78b9c4 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -417,6 +417,8 @@ enum { TCA_FLOWER_KEY_TCP_DST, /* be16 */ TCA_FLOWER_KEY_UDP_SRC, /* be16 */ TCA_FLOWER_KEY_UDP_DST, /* be16 */ + + TCA_FLOWER_FLAGS, __TCA_FLOWER_MAX, }; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 8a932d079c24..eed911d091da 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,7 +1,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index bd3bdf2486a7..76d5a794e426 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -53,7 +53,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0) + attr->value_size == 0 || attr->map_flags) return ERR_PTR(-EINVAL); if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1)) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index a68e95133fcd..fff3650d52fc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1,4 +1,5 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -13,6 +14,7 @@ #include <linux/jhash.h> #include <linux/filter.h> #include <linux/vmalloc.h> +#include "percpu_freelist.h" struct bucket { struct hlist_head head; @@ -22,6 +24,8 @@ struct bucket { struct bpf_htab { struct bpf_map map; struct bucket *buckets; + void *elems; + struct pcpu_freelist freelist; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ @@ -29,15 +33,86 @@ struct bpf_htab { /* each htab element is struct htab_elem + key + value */ struct htab_elem { - struct hlist_node hash_node; - struct rcu_head rcu; union { - u32 hash; - u32 key_size; + struct hlist_node hash_node; + struct bpf_htab *htab; + struct pcpu_freelist_node fnode; }; + struct rcu_head rcu; + u32 hash; char key[0] __aligned(8); }; +static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, + void __percpu *pptr) +{ + *(void __percpu **)(l->key + key_size) = pptr; +} + +static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) +{ + return *(void __percpu **)(l->key + key_size); +} + +static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) +{ + return (struct htab_elem *) (htab->elems + i * htab->elem_size); +} + +static void htab_free_elems(struct bpf_htab *htab) +{ + int i; + + if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + goto free_elems; + + for (i = 0; i < htab->map.max_entries; i++) { + void __percpu *pptr; + + pptr = htab_elem_get_ptr(get_htab_elem(htab, i), + htab->map.key_size); + free_percpu(pptr); + } +free_elems: + vfree(htab->elems); +} + +static int prealloc_elems_and_freelist(struct bpf_htab *htab) +{ + int err = -ENOMEM, i; + + htab->elems = vzalloc(htab->elem_size * htab->map.max_entries); + if (!htab->elems) + return -ENOMEM; + + if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH) + goto skip_percpu_elems; + + for (i = 0; i < htab->map.max_entries; i++) { + u32 size = round_up(htab->map.value_size, 8); + void __percpu *pptr; + + pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN); + if (!pptr) + goto free_elems; + htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, + pptr); + } + +skip_percpu_elems: + err = pcpu_freelist_init(&htab->freelist); + if (err) + goto free_elems; + + pcpu_freelist_populate(&htab->freelist, htab->elems, htab->elem_size, + htab->map.max_entries); + return 0; + +free_elems: + htab_free_elems(htab); + return err; +} + /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { @@ -46,6 +121,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) int err, i; u64 cost; + if (attr->map_flags & ~BPF_F_NO_PREALLOC) + /* reserved bits should not be used */ + return ERR_PTR(-EINVAL); + htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); @@ -55,6 +134,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.key_size = attr->key_size; htab->map.value_size = attr->value_size; htab->map.max_entries = attr->max_entries; + htab->map.map_flags = attr->map_flags; /* check sanity of attributes. * value_size == 0 may be allowed in the future to use map as a set @@ -92,7 +172,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (percpu) htab->elem_size += sizeof(void *); else - htab->elem_size += htab->map.value_size; + htab->elem_size += round_up(htab->map.value_size, 8); /* prevent zero size kmalloc and check for u32 overflow */ if (htab->n_buckets == 0 || @@ -112,6 +192,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(htab->map.pages); + if (err) + goto free_htab; + err = -ENOMEM; htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), GFP_USER | __GFP_NOWARN); @@ -127,10 +212,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } - atomic_set(&htab->count, 0); + if (!(attr->map_flags & BPF_F_NO_PREALLOC)) { + err = prealloc_elems_and_freelist(htab); + if (err) + goto free_buckets; + } return &htab->map; +free_buckets: + kvfree(htab->buckets); free_htab: kfree(htab); return ERR_PTR(err); @@ -249,42 +340,42 @@ find_first_elem: } } - /* itereated over all buckets and all elements */ + /* iterated over all buckets and all elements */ return -ENOENT; } - -static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, - void __percpu *pptr) -{ - *(void __percpu **)(l->key + key_size) = pptr; -} - -static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) -{ - return *(void __percpu **)(l->key + key_size); -} - -static void htab_percpu_elem_free(struct htab_elem *l) +static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { - free_percpu(htab_elem_get_ptr(l, l->key_size)); + if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) + free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); kfree(l); + } -static void htab_percpu_elem_free_rcu(struct rcu_head *head) +static void htab_elem_free_rcu(struct rcu_head *head) { struct htab_elem *l = container_of(head, struct htab_elem, rcu); + struct bpf_htab *htab = l->htab; - htab_percpu_elem_free(l); + /* must increment bpf_prog_active to avoid kprobe+bpf triggering while + * we're calling kfree, otherwise deadlock is possible if kprobes + * are placed somewhere inside of slub + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + htab_elem_free(htab, l); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); } -static void free_htab_elem(struct htab_elem *l, bool percpu, u32 key_size) +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { - if (percpu) { - l->key_size = key_size; - call_rcu(&l->rcu, htab_percpu_elem_free_rcu); + if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { + pcpu_freelist_push(&htab->freelist, &l->fnode); } else { - kfree_rcu(l, rcu); + atomic_dec(&htab->count); + l->htab = htab; + call_rcu(&l->rcu, htab_elem_free_rcu); } } @@ -293,23 +384,39 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, bool percpu, bool onallcpus) { u32 size = htab->map.value_size; + bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); struct htab_elem *l_new; void __percpu *pptr; - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return NULL; + if (prealloc) { + l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); + if (!l_new) + return ERR_PTR(-E2BIG); + } else { + if (atomic_inc_return(&htab->count) > htab->map.max_entries) { + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); + } memcpy(l_new->key, key, key_size); if (percpu) { /* round up value_size to 8 bytes */ size = round_up(size, 8); - /* alloc_percpu zero-fills */ - pptr = __alloc_percpu_gfp(size, 8, GFP_ATOMIC | __GFP_NOWARN); - if (!pptr) { - kfree(l_new); - return NULL; + if (prealloc) { + pptr = htab_elem_get_ptr(l_new, key_size); + } else { + /* alloc_percpu zero-fills */ + pptr = __alloc_percpu_gfp(size, 8, + GFP_ATOMIC | __GFP_NOWARN); + if (!pptr) { + kfree(l_new); + return ERR_PTR(-ENOMEM); + } } if (!onallcpus) { @@ -324,7 +431,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, off += size; } } - htab_elem_set_ptr(l_new, key_size, pptr); + if (!prealloc) + htab_elem_set_ptr(l_new, key_size, pptr); } else { memcpy(l_new->key + round_up(key_size, 8), value, size); } @@ -336,12 +444,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, u64 map_flags) { - if (!l_old && unlikely(atomic_read(&htab->count) >= htab->map.max_entries)) - /* if elem with this 'key' doesn't exist and we've reached - * max_entries limit, fail insertion of new elem - */ - return -E2BIG; - if (l_old && map_flags == BPF_NOEXIST) /* elem already exists */ return -EEXIST; @@ -375,13 +477,6 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, hash = htab_map_hash(key, key_size); - /* allocate new element outside of the lock, since - * we're most likley going to insert it - */ - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); - if (!l_new) - return -ENOMEM; - b = __select_bucket(htab, hash); head = &b->head; @@ -394,21 +489,24 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); + if (IS_ERR(l_new)) { + /* all pre-allocated elements are in use or memory exhausted */ + ret = PTR_ERR(l_new); + goto err; + } + /* add new element to the head of the list, so that * concurrent search will find it before old elem */ hlist_add_head_rcu(&l_new->hash_node, head); if (l_old) { hlist_del_rcu(&l_old->hash_node); - kfree_rcu(l_old, rcu); - } else { - atomic_inc(&htab->count); + free_htab_elem(htab, l_old); } - raw_spin_unlock_irqrestore(&b->lock, flags); - return 0; + ret = 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); - kfree(l_new); return ret; } @@ -466,12 +564,11 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } else { l_new = alloc_htab_elem(htab, key, value, key_size, hash, true, onallcpus); - if (!l_new) { - ret = -ENOMEM; + if (IS_ERR(l_new)) { + ret = PTR_ERR(l_new); goto err; } hlist_add_head_rcu(&l_new->hash_node, head); - atomic_inc(&htab->count); } ret = 0; err: @@ -489,7 +586,6 @@ static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_HASH; struct hlist_head *head; struct bucket *b; struct htab_elem *l; @@ -511,8 +607,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) if (l) { hlist_del_rcu(&l->hash_node); - atomic_dec(&htab->count); - free_htab_elem(l, percpu, key_size); + free_htab_elem(htab, l); ret = 0; } @@ -531,17 +626,10 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_for_each_entry_safe(l, n, head, hash_node) { hlist_del_rcu(&l->hash_node); - atomic_dec(&htab->count); - if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) { - l->key_size = htab->map.key_size; - htab_percpu_elem_free(l); - } else { - kfree(l); - } + htab_elem_free(htab, l); } } } - /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void htab_map_free(struct bpf_map *map) { @@ -554,10 +642,16 @@ static void htab_map_free(struct bpf_map *map) */ synchronize_rcu(); - /* some of kfree_rcu() callbacks for elements of this map may not have - * executed. It's ok. Proceed to free residual elements and map itself + /* some of free_htab_elem() callbacks for elements of this map may + * not have executed. Wait for them. */ - delete_all_elements(htab); + rcu_barrier(); + if (htab->map.map_flags & BPF_F_NO_PREALLOC) { + delete_all_elements(htab); + } else { + htab_free_elems(htab); + pcpu_freelist_destroy(&htab->freelist); + } kvfree(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 4504ca66118d..50da680c479f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5) if (!task) return -EINVAL; - memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm))); + strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm))); return 0; } diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c new file mode 100644 index 000000000000..5c51d1985b51 --- /dev/null +++ b/kernel/bpf/percpu_freelist.c @@ -0,0 +1,100 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include "percpu_freelist.h" + +int pcpu_freelist_init(struct pcpu_freelist *s) +{ + int cpu; + + s->freelist = alloc_percpu(struct pcpu_freelist_head); + if (!s->freelist) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct pcpu_freelist_head *head = per_cpu_ptr(s->freelist, cpu); + + raw_spin_lock_init(&head->lock); + head->first = NULL; + } + return 0; +} + +void pcpu_freelist_destroy(struct pcpu_freelist *s) +{ + free_percpu(s->freelist); +} + +static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) +{ + raw_spin_lock(&head->lock); + node->next = head->first; + head->first = node; + raw_spin_unlock(&head->lock); +} + +void pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); + + __pcpu_freelist_push(head, node); +} + +void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, + u32 nr_elems) +{ + struct pcpu_freelist_head *head; + unsigned long flags; + int i, cpu, pcpu_entries; + + pcpu_entries = nr_elems / num_possible_cpus() + 1; + i = 0; + + /* disable irq to workaround lockdep false positive + * in bpf usage pcpu_freelist_populate() will never race + * with pcpu_freelist_push() + */ + local_irq_save(flags); + for_each_possible_cpu(cpu) { +again: + head = per_cpu_ptr(s->freelist, cpu); + __pcpu_freelist_push(head, buf); + i++; + buf += elem_size; + if (i == nr_elems) + break; + if (i % pcpu_entries) + goto again; + } + local_irq_restore(flags); +} + +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +{ + struct pcpu_freelist_head *head; + struct pcpu_freelist_node *node; + int orig_cpu, cpu; + + orig_cpu = cpu = raw_smp_processor_id(); + while (1) { + head = per_cpu_ptr(s->freelist, cpu); + raw_spin_lock(&head->lock); + node = head->first; + if (node) { + head->first = node->next; + raw_spin_unlock(&head->lock); + return node; + } + raw_spin_unlock(&head->lock); + cpu = cpumask_next(cpu, cpu_possible_mask); + if (cpu >= nr_cpu_ids) + cpu = 0; + if (cpu == orig_cpu) + return NULL; + } +} diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h new file mode 100644 index 000000000000..3049aae8ea1e --- /dev/null +++ b/kernel/bpf/percpu_freelist.h @@ -0,0 +1,31 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef __PERCPU_FREELIST_H__ +#define __PERCPU_FREELIST_H__ +#include <linux/spinlock.h> +#include <linux/percpu.h> + +struct pcpu_freelist_head { + struct pcpu_freelist_node *first; + raw_spinlock_t lock; +}; + +struct pcpu_freelist { + struct pcpu_freelist_head __percpu *freelist; +}; + +struct pcpu_freelist_node { + struct pcpu_freelist_node *next; +}; + +void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); +void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, + u32 nr_elems); +int pcpu_freelist_init(struct pcpu_freelist *); +void pcpu_freelist_destroy(struct pcpu_freelist *s); +#endif diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 8a60ee14a977..499d9e933f8e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -10,9 +10,10 @@ #include <linux/vmalloc.h> #include <linux/stacktrace.h> #include <linux/perf_event.h> +#include "percpu_freelist.h" struct stack_map_bucket { - struct rcu_head rcu; + struct pcpu_freelist_node fnode; u32 hash; u32 nr; u64 ip[]; @@ -20,10 +21,34 @@ struct stack_map_bucket { struct bpf_stack_map { struct bpf_map map; + void *elems; + struct pcpu_freelist freelist; u32 n_buckets; - struct stack_map_bucket __rcu *buckets[]; + struct stack_map_bucket *buckets[]; }; +static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) +{ + u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + int err; + + smap->elems = vzalloc(elem_size * smap->map.max_entries); + if (!smap->elems) + return -ENOMEM; + + err = pcpu_freelist_init(&smap->freelist); + if (err) + goto free_elems; + + pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size, + smap->map.max_entries); + return 0; + +free_elems: + vfree(smap->elems); + return err; +} + /* Called from syscall */ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { @@ -35,6 +60,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); + if (attr->map_flags) + return ERR_PTR(-EINVAL); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || value_size < 8 || value_size % 8 || @@ -67,12 +95,22 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) smap->n_buckets = n_buckets; smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + err = bpf_map_precharge_memlock(smap->map.pages); + if (err) + goto free_smap; + err = get_callchain_buffers(); if (err) goto free_smap; + err = prealloc_elems_and_freelist(smap); + if (err) + goto put_buffers; + return &smap->map; +put_buffers: + put_callchain_buffers(); free_smap: kvfree(smap); return ERR_PTR(err); @@ -118,7 +156,7 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) ips = trace->ip + skip + init_nr; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); - bucket = rcu_dereference(smap->buckets[id]); + bucket = READ_ONCE(smap->buckets[id]); if (bucket && bucket->hash == hash) { if (flags & BPF_F_FAST_STACK_CMP) @@ -132,19 +170,18 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) if (bucket && !(flags & BPF_F_REUSE_STACKID)) return -EEXIST; - new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size, - GFP_ATOMIC | __GFP_NOWARN); + new_bucket = (struct stack_map_bucket *) + pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; memcpy(new_bucket->ip, ips, trace_len); - memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len); new_bucket->hash = hash; new_bucket->nr = trace_nr; old_bucket = xchg(&smap->buckets[id], new_bucket); if (old_bucket) - kfree_rcu(old_bucket, rcu); + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return id; } @@ -157,17 +194,34 @@ const struct bpf_func_proto bpf_get_stackid_proto = { .arg3_type = ARG_ANYTHING, }; -/* Called from syscall or from eBPF program */ +/* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) { + return NULL; +} + +/* Called from syscall */ +int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) +{ struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - struct stack_map_bucket *bucket; - u32 id = *(u32 *)key; + struct stack_map_bucket *bucket, *old_bucket; + u32 id = *(u32 *)key, trace_len; if (unlikely(id >= smap->n_buckets)) - return NULL; - bucket = rcu_dereference(smap->buckets[id]); - return bucket ? bucket->ip : NULL; + return -ENOENT; + + bucket = xchg(&smap->buckets[id], NULL); + if (!bucket) + return -ENOENT; + + trace_len = bucket->nr * sizeof(u64); + memcpy(value, bucket->ip, trace_len); + memset(value + trace_len, 0, map->value_size - trace_len); + + old_bucket = xchg(&smap->buckets[id], bucket); + if (old_bucket) + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); + return 0; } static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -193,7 +247,7 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key) old_bucket = xchg(&smap->buckets[id], NULL); if (old_bucket) { - kfree_rcu(old_bucket, rcu); + pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return 0; } else { return -ENOENT; @@ -204,13 +258,12 @@ static int stack_map_delete_elem(struct bpf_map *map, void *key) static void stack_map_free(struct bpf_map *map) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - int i; + /* wait for bpf programs to complete before freeing stack map */ synchronize_rcu(); - for (i = 0; i < smap->n_buckets; i++) - if (smap->buckets[i]) - kfree_rcu(smap->buckets[i], rcu); + vfree(smap->elems); + pcpu_freelist_destroy(&smap->freelist); kvfree(smap); put_callchain_buffers(); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c95a753c2007..2a2efe1bc76c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -18,6 +18,8 @@ #include <linux/filter.h> #include <linux/version.h> +DEFINE_PER_CPU(int, bpf_prog_active); + int sysctl_unprivileged_bpf_disabled __read_mostly; static LIST_HEAD(bpf_map_types); @@ -46,6 +48,19 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +int bpf_map_precharge_memlock(u32 pages) +{ + struct user_struct *user = get_current_user(); + unsigned long memlock_limit, cur; + + memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + cur = atomic_long_read(&user->locked_vm); + free_uid(user); + if (cur + pages > memlock_limit) + return -EPERM; + return 0; +} + static int bpf_map_charge_memlock(struct bpf_map *map) { struct user_struct *user = get_current_user(); @@ -151,7 +166,7 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL -#define BPF_MAP_CREATE_LAST_FIELD max_entries +#define BPF_MAP_CREATE_LAST_FIELD map_flags /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -229,6 +244,11 @@ static void __user *u64_to_ptr(__u64 val) return (void __user *) (unsigned long) val; } +int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) +{ + return -ENOTSUPP; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value @@ -275,6 +295,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { + err = bpf_stackmap_copy(map, key, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); @@ -347,6 +369,11 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from + * inside bpf map update or delete otherwise deadlocks are possible + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { @@ -356,6 +383,8 @@ static int map_update_elem(union bpf_attr *attr) err = map->ops->map_update_elem(map, key, value, attr->flags); rcu_read_unlock(); } + __this_cpu_dec(bpf_prog_active); + preempt_enable(); free_value: kfree(value); @@ -394,9 +423,13 @@ static int map_delete_elem(union bpf_attr *attr) if (copy_from_user(key, ukey, map->key_size) != 0) goto free_key; + preempt_disable(); + __this_cpu_inc(bpf_prog_active); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); free_key: kfree(key); diff --git a/kernel/events/core.c b/kernel/events/core.c index 0d58522103cd..614614821f00 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -64,8 +64,17 @@ static void remote_function(void *data) struct task_struct *p = tfc->p; if (p) { - tfc->ret = -EAGAIN; - if (task_cpu(p) != smp_processor_id() || !task_curr(p)) + /* -EAGAIN */ + if (task_cpu(p) != smp_processor_id()) + return; + + /* + * Now that we're on right CPU with IRQs disabled, we can test + * if we hit the right task without races. + */ + + tfc->ret = -ESRCH; /* No such (running) process */ + if (p != current) return; } @@ -92,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) .p = p, .func = func, .info = info, - .ret = -ESRCH, /* No such (running) process */ + .ret = -EAGAIN, }; + int ret; - if (task_curr(p)) - smp_call_function_single(task_cpu(p), remote_function, &data, 1); + do { + ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); + if (!ret) + ret = data.ret; + } while (ret == -EAGAIN); - return data.ret; + return ret; } /** @@ -169,19 +182,6 @@ static bool is_kernel_event(struct perf_event *event) * rely on ctx->is_active and therefore cannot use event_function_call(). * See perf_install_in_context(). * - * This is because we need a ctx->lock serialized variable (ctx->is_active) - * to reliably determine if a particular task/context is scheduled in. The - * task_curr() use in task_function_call() is racy in that a remote context - * switch is not a single atomic operation. - * - * As is, the situation is 'safe' because we set rq->curr before we do the - * actual context switch. This means that task_curr() will fail early, but - * we'll continue spinning on ctx->is_active until we've passed - * perf_event_task_sched_out(). - * - * Without this ctx->lock serialized variable we could have race where we find - * the task (and hence the context) would not be active while in fact they are. - * * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set. */ @@ -212,7 +212,7 @@ static int event_function(void *info) */ if (ctx->task) { if (ctx->task != current) { - ret = -EAGAIN; + ret = -ESRCH; goto unlock; } @@ -276,10 +276,10 @@ static void event_function_call(struct perf_event *event, event_f func, void *da return; } -again: if (task == TASK_TOMBSTONE) return; +again: if (!task_function_call(task, event_function, &efs)) return; @@ -289,13 +289,15 @@ again: * a concurrent perf_event_context_sched_out(). */ task = ctx->task; - if (task != TASK_TOMBSTONE) { - if (ctx->is_active) { - raw_spin_unlock_irq(&ctx->lock); - goto again; - } - func(event, NULL, ctx, data); + if (task == TASK_TOMBSTONE) { + raw_spin_unlock_irq(&ctx->lock); + return; } + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + func(event, NULL, ctx, data); raw_spin_unlock_irq(&ctx->lock); } @@ -314,6 +316,7 @@ again: enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, + EVENT_TIME = 0x4, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; @@ -321,7 +324,13 @@ enum event_type_t { * perf_sched_events : >0 events exist * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ -struct static_key_deferred perf_sched_events __read_mostly; + +static void perf_sched_delayed(struct work_struct *work); +DEFINE_STATIC_KEY_FALSE(perf_sched_events); +static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed); +static DEFINE_MUTEX(perf_sched_mutex); +static atomic_t perf_sched_count; + static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static DEFINE_PER_CPU(int, perf_sched_cb_usages); @@ -1288,16 +1297,18 @@ static u64 perf_event_time(struct perf_event *event) /* * Update the total_time_enabled and total_time_running fields for a event. - * The caller of this function needs to hold the ctx->lock. */ static void update_event_times(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; u64 run_end; + lockdep_assert_held(&ctx->lock); + if (event->state < PERF_EVENT_STATE_INACTIVE || event->group_leader->state < PERF_EVENT_STATE_INACTIVE) return; + /* * in cgroup mode, time_enabled represents * the time the event was enabled AND active @@ -1645,7 +1656,7 @@ out: static bool is_orphaned_event(struct perf_event *event) { - return event->state == PERF_EVENT_STATE_EXIT; + return event->state == PERF_EVENT_STATE_DEAD; } static inline int pmu_filter_match(struct perf_event *event) @@ -1690,14 +1701,14 @@ event_sched_out(struct perf_event *event, perf_pmu_disable(event->pmu); + event->tstamp_stopped = tstamp; + event->pmu->del(event, 0); + event->oncpu = -1; event->state = PERF_EVENT_STATE_INACTIVE; if (event->pending_disable) { event->pending_disable = 0; event->state = PERF_EVENT_STATE_OFF; } - event->tstamp_stopped = tstamp; - event->pmu->del(event, 0); - event->oncpu = -1; if (!is_software_event(event)) cpuctx->active_oncpu--; @@ -1732,7 +1743,6 @@ group_sched_out(struct perf_event *group_event, } #define DETACH_GROUP 0x01UL -#define DETACH_STATE 0x02UL /* * Cross CPU call to remove a performance event @@ -1752,8 +1762,6 @@ __perf_remove_from_context(struct perf_event *event, if (flags & DETACH_GROUP) perf_group_detach(event); list_del_event(event, ctx); - if (flags & DETACH_STATE) - event->state = PERF_EVENT_STATE_EXIT; if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; @@ -2063,14 +2071,27 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } -static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx); +static void ctx_sched_out(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type); static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type, struct task_struct *task); +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (!cpuctx->task_ctx) + return; + + if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) + return; + + ctx_sched_out(ctx, cpuctx, EVENT_ALL); +} + static void perf_event_sched_in(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, struct task_struct *task) @@ -2097,49 +2118,68 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, /* * Cross CPU call to install and enable a performance event * - * Must be called with ctx->mutex held + * Very similar to remote_function() + event_function() but cannot assume that + * things like ctx->is_active and cpuctx->task_ctx are set. */ static int __perf_install_in_context(void *info) { - struct perf_event_context *ctx = info; + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; + bool activate = true; + int ret = 0; raw_spin_lock(&cpuctx->ctx.lock); if (ctx->task) { raw_spin_lock(&ctx->lock); - /* - * If we hit the 'wrong' task, we've since scheduled and - * everything should be sorted, nothing to do! - */ task_ctx = ctx; - if (ctx->task != current) + + /* If we're on the wrong CPU, try again */ + if (task_cpu(ctx->task) != smp_processor_id()) { + ret = -ESRCH; goto unlock; + } /* - * If task_ctx is set, it had better be to us. + * If we're on the right CPU, see if the task we target is + * current, if not we don't have to activate the ctx, a future + * context switch will do that for us. */ - WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx); + if (ctx->task != current) + activate = false; + else + WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx); + } else if (task_ctx) { raw_spin_lock(&task_ctx->lock); } - ctx_resched(cpuctx, task_ctx); + if (activate) { + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + add_event_to_ctx(event, ctx); + ctx_resched(cpuctx, task_ctx); + } else { + add_event_to_ctx(event, ctx); + } + unlock: perf_ctx_unlock(cpuctx, task_ctx); - return 0; + return ret; } /* - * Attach a performance event to a context + * Attach a performance event to a context. + * + * Very similar to event_function_call, see comment there. */ static void perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { - struct task_struct *task = NULL; + struct task_struct *task = READ_ONCE(ctx->task); lockdep_assert_held(&ctx->mutex); @@ -2147,40 +2187,46 @@ perf_install_in_context(struct perf_event_context *ctx, if (event->cpu != -1) event->cpu = cpu; + if (!task) { + cpu_function_call(cpu, __perf_install_in_context, event); + return; + } + + /* + * Should not happen, we validate the ctx is still alive before calling. + */ + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) + return; + /* * Installing events is tricky because we cannot rely on ctx->is_active * to be set in case this is the nr_events 0 -> 1 transition. - * - * So what we do is we add the event to the list here, which will allow - * a future context switch to DTRT and then send a racy IPI. If the IPI - * fails to hit the right task, this means a context switch must have - * happened and that will have taken care of business. */ - raw_spin_lock_irq(&ctx->lock); - task = ctx->task; +again: /* - * Worse, we cannot even rely on the ctx actually existing anymore. If - * between find_get_context() and perf_install_in_context() the task - * went through perf_event_exit_task() its dead and we should not be - * adding new events. + * Cannot use task_function_call() because we need to run on the task's + * CPU regardless of whether its current or not. */ - if (task == TASK_TOMBSTONE) { + if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event)) + return; + + raw_spin_lock_irq(&ctx->lock); + task = ctx->task; + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { + /* + * Cannot happen because we already checked above (which also + * cannot happen), and we hold ctx->mutex, which serializes us + * against perf_event_exit_task_context(). + */ raw_spin_unlock_irq(&ctx->lock); return; } - update_context_time(ctx); + raw_spin_unlock_irq(&ctx->lock); /* - * Update cgrp time only if current cgrp matches event->cgrp. - * Must be done before calling add_event_to_ctx(). + * Since !ctx->is_active doesn't mean anything, we must IPI + * unconditionally. */ - update_cgrp_time_from_event(event); - add_event_to_ctx(event, ctx); - raw_spin_unlock_irq(&ctx->lock); - - if (task) - task_function_call(task, __perf_install_in_context, ctx); - else - cpu_function_call(cpu, __perf_install_in_context, ctx); + goto again; } /* @@ -2219,17 +2265,18 @@ static void __perf_event_enable(struct perf_event *event, event->state <= PERF_EVENT_STATE_ERROR) return; - update_context_time(ctx); + if (ctx->is_active) + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + __perf_event_mark_enabled(event); if (!ctx->is_active) return; if (!event_filter_match(event)) { - if (is_cgroup_event(event)) { - perf_cgroup_set_timestamp(current, ctx); // XXX ? + if (is_cgroup_event(event)) perf_cgroup_defer_enabled(event); - } + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); return; } @@ -2237,8 +2284,10 @@ static void __perf_event_enable(struct perf_event *event, * If the event is in a group and isn't the group leader, * then don't put it on unless the group is on. */ - if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) + if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); return; + } task_ctx = cpuctx->task_ctx; if (ctx->task) @@ -2344,24 +2393,33 @@ static void ctx_sched_out(struct perf_event_context *ctx, } ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); if (!ctx->is_active) cpuctx->task_ctx = NULL; } - update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); - if (!ctx->nr_active) + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* update (and stop) ctx time */ + update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx); + } + + if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; perf_pmu_disable(ctx->pmu); - if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) { + if (is_active & EVENT_PINNED) { list_for_each_entry(event, &ctx->pinned_groups, group_entry) group_sched_out(event, cpuctx, ctx); } - if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) { + if (is_active & EVENT_FLEXIBLE) { list_for_each_entry(event, &ctx->flexible_groups, group_entry) group_sched_out(event, cpuctx, ctx); } @@ -2641,18 +2699,6 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_sched_out(task, next); } -static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - if (!cpuctx->task_ctx) - return; - - if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) - return; - - ctx_sched_out(ctx, cpuctx, EVENT_ALL); -} - /* * Called with IRQs disabled */ @@ -2735,7 +2781,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (likely(!ctx->nr_events)) return; - ctx->is_active |= event_type; + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) cpuctx->task_ctx = ctx; @@ -2743,18 +2789,24 @@ ctx_sched_in(struct perf_event_context *ctx, WARN_ON_ONCE(cpuctx->task_ctx != ctx); } - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* start ctx time */ + now = perf_clock(); + ctx->timestamp = now; + perf_cgroup_set_timestamp(task, ctx); + } + /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ - if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) + if (is_active & EVENT_PINNED) ctx_pinned_sched_in(ctx, cpuctx); /* Then walk through the lower prio flexible groups */ - if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) + if (is_active & EVENT_FLEXIBLE) ctx_flexible_sched_in(ctx, cpuctx); } @@ -3120,6 +3172,7 @@ static void perf_event_enable_on_exec(int ctxn) cpuctx = __get_cpu_context(ctx); perf_ctx_lock(cpuctx, ctx); + ctx_sched_out(ctx, cpuctx, EVENT_TIME); list_for_each_entry(event, &ctx->event_list, event_entry) enabled |= event_enable_on_exec(event, ctx); @@ -3537,12 +3590,22 @@ static void unaccount_event(struct perf_event *event) if (has_branch_stack(event)) dec = true; - if (dec) - static_key_slow_dec_deferred(&perf_sched_events); + if (dec) { + if (!atomic_add_unless(&perf_sched_count, -1, 1)) + schedule_delayed_work(&perf_sched_work, HZ); + } unaccount_event_cpu(event, event->cpu); } +static void perf_sched_delayed(struct work_struct *work) +{ + mutex_lock(&perf_sched_mutex); + if (atomic_dec_and_test(&perf_sched_count)) + static_branch_disable(&perf_sched_events); + mutex_unlock(&perf_sched_mutex); +} + /* * The following implement mutual exclusion of events on "exclusive" pmus * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled @@ -3752,30 +3815,42 @@ static void put_event(struct perf_event *event) */ int perf_event_release_kernel(struct perf_event *event) { - struct perf_event_context *ctx; + struct perf_event_context *ctx = event->ctx; struct perf_event *child, *tmp; + /* + * If we got here through err_file: fput(event_file); we will not have + * attached to a context yet. + */ + if (!ctx) { + WARN_ON_ONCE(event->attach_state & + (PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP)); + goto no_ctx; + } + if (!is_kernel_event(event)) perf_remove_from_owner(event); ctx = perf_event_ctx_lock(event); WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE); - perf_event_ctx_unlock(event, ctx); + perf_remove_from_context(event, DETACH_GROUP); + raw_spin_lock_irq(&ctx->lock); /* - * At this point we must have event->state == PERF_EVENT_STATE_EXIT, - * either from the above perf_remove_from_context() or through - * perf_event_exit_event(). + * Mark this even as STATE_DEAD, there is no external reference to it + * anymore. * - * Therefore, anybody acquiring event->child_mutex after the below - * loop _must_ also see this, most importantly inherit_event() which - * will avoid placing more children on the list. + * Anybody acquiring event->child_mutex after the below loop _must_ + * also see this, most importantly inherit_event() which will avoid + * placing more children on the list. * * Thus this guarantees that we will in fact observe and kill _ALL_ * child events. */ - WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT); + event->state = PERF_EVENT_STATE_DEAD; + raw_spin_unlock_irq(&ctx->lock); + + perf_event_ctx_unlock(event, ctx); again: mutex_lock(&event->child_mutex); @@ -3830,8 +3905,8 @@ again: } mutex_unlock(&event->child_mutex); - /* Must be the last reference */ - put_event(event); +no_ctx: + put_event(event); /* Must be the 'last' reference */ return 0; } EXPORT_SYMBOL_GPL(perf_event_release_kernel); @@ -3988,7 +4063,7 @@ static bool is_event_hup(struct perf_event *event) { bool no_children; - if (event->state != PERF_EVENT_STATE_EXIT) + if (event->state > PERF_EVENT_STATE_EXIT) return false; mutex_lock(&event->child_mutex); @@ -7769,8 +7844,28 @@ static void account_event(struct perf_event *event) if (is_cgroup_event(event)) inc = true; - if (inc) - static_key_slow_inc(&perf_sched_events.key); + if (inc) { + if (atomic_inc_not_zero(&perf_sched_count)) + goto enabled; + + mutex_lock(&perf_sched_mutex); + if (!atomic_read(&perf_sched_count)) { + static_branch_enable(&perf_sched_events); + /* + * Guarantee that all CPUs observe they key change and + * call the perf scheduling hooks before proceeding to + * install events that need them. + */ + synchronize_sched(); + } + /* + * Now that we have waited for the sync_sched(), allow further + * increments to by-pass the mutex. + */ + atomic_inc(&perf_sched_count); + mutex_unlock(&perf_sched_mutex); + } +enabled: account_event_cpu(event, event->cpu); } @@ -8389,10 +8484,19 @@ SYSCALL_DEFINE5(perf_event_open, if (move_group) { gctx = group_leader->ctx; mutex_lock_double(&gctx->mutex, &ctx->mutex); + if (gctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } } else { mutex_lock(&ctx->mutex); } + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } + if (!perf_event_validate_size(event)) { err = -E2BIG; goto err_locked; @@ -8509,7 +8613,12 @@ err_context: perf_unpin_context(ctx); put_ctx(ctx); err_alloc: - free_event(event); + /* + * If event_file is set, the fput() above will have called ->release() + * and that will take care of freeing the event. + */ + if (!event_file) + free_event(event); err_cpus: put_online_cpus(); err_task: @@ -8563,12 +8672,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_unlock; + } + if (!exclusive_event_installable(event, ctx)) { - mutex_unlock(&ctx->mutex); - perf_unpin_context(ctx); - put_ctx(ctx); err = -EBUSY; - goto err_free; + goto err_unlock; } perf_install_in_context(ctx, event, cpu); @@ -8577,6 +8688,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, return event; +err_unlock: + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); err_free: free_event(event); err: @@ -8695,7 +8810,7 @@ perf_event_exit_event(struct perf_event *child_event, if (parent_event) perf_group_detach(child_event); list_del_event(child_event, child_ctx); - child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */ + child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */ raw_spin_unlock_irq(&child_ctx->lock); /* @@ -9313,9 +9428,6 @@ void __init perf_event_init(void) ret = init_hw_breakpoint(); WARN(ret, "hw_breakpoint initialization failed with: %d", ret); - /* do not patch jump label more than once per second */ - jump_label_rate_limit(&perf_sched_events, HZ); - /* * Build time assertion that we keep the data_head at the intended * location. IOW, validation we got the __reserved[] size right. diff --git a/kernel/memremap.c b/kernel/memremap.c index 7a1b5c3ef14e..b981a7b023f0 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -136,8 +136,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset, if (addr) { *ptr = addr; devres_add(dev, ptr); - } else + } else { devres_free(ptr); + return ERR_PTR(-ENXIO); + } return addr; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index cd64c979d0e1..57b939c81bce 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -420,7 +420,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * entity. */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { - printk_deferred_once("sched: DL replenish lagged to much\n"); + printk_deferred_once("sched: DL replenish lagged too much\n"); dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4b8caa392b86..3e4ffb3ace5f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -13,8 +13,6 @@ #include <linux/ctype.h> #include "trace.h" -static DEFINE_PER_CPU(int, bpf_prog_active); - /** * trace_call_bpf - invoke BPF program * @prog: BPF program diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f333e57c4614..05ddc0820771 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name) struct ftrace_event_field *field; struct list_head *head; - field = __find_event_field(&ftrace_generic_fields, name); + head = trace_get_fields(call); + field = __find_event_field(head, name); if (field) return field; - field = __find_event_field(&ftrace_common_fields, name); + field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; - head = trace_get_fields(call); - return __find_event_field(head, name); + return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, @@ -171,8 +171,10 @@ static int trace_define_generic_fields(void) { int ret; - __generic_field(int, cpu, FILTER_OTHER); - __generic_field(char *, comm, FILTER_PTR_STRING); + __generic_field(int, CPU, FILTER_CPU); + __generic_field(int, cpu, FILTER_CPU); + __generic_field(char *, COMM, FILTER_COMM); + __generic_field(char *, comm, FILTER_COMM); return ret; } @@ -869,7 +871,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->class && call->class->reg) + if (call->class && call->class->reg && + !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) return file; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f93a219b18da..6816302542b2 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps, return -EINVAL; } - if (is_string_field(field)) { + if (field->filter_type == FILTER_COMM) { + filter_build_regex(pred); + fn = filter_pred_comm; + pred->regex.field_len = TASK_COMM_LEN; + } else if (is_string_field(field)) { filter_build_regex(pred); - if (!strcmp(field->name, "comm")) { - fn = filter_pred_comm; - pred->regex.field_len = TASK_COMM_LEN; - } else if (field->filter_type == FILTER_STATIC_STRING) { + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) @@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps, } pred->val = val; - if (!strcmp(field->name, "cpu")) + if (field->filter_type == FILTER_CPU) fn = filter_pred_cpu; else fn = select_comparison_fn(pred->op, field->size, diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 202df6cffcca..2a1abbaca10e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -156,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack) for (; p < top && i < stack_trace_max.nr_entries; p++) { if (stack_dump_trace[i] == ULONG_MAX) break; - if (*p == stack_dump_trace[i]) { + /* + * The READ_ONCE_NOCHECK is used to let KASAN know that + * this is not a stack-out-of-bounds error. + */ + if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) { stack_dump_trace[x] = stack_dump_trace[i++]; this_size = stack_trace_index[x++] = (top - p) * sizeof(unsigned long); diff --git a/lib/random32.c b/lib/random32.c index 12111910ccd0..510d1ce7d4d2 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -255,6 +255,7 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state) prandom_warmup(state); } } +EXPORT_SYMBOL(prandom_seed_full_state); /* * Generate better values after random number generator diff --git a/mm/filemap.c b/mm/filemap.c index 23edccecadb0..3461d97ecb30 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -446,7 +446,8 @@ int filemap_write_and_wait(struct address_space *mapping) { int err = 0; - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = filemap_fdatawrite(mapping); /* * Even if the above returned error, the pages may be @@ -482,13 +483,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, { int err = 0; - if (dax_mapping(mapping) && mapping->nrexceptional) { - err = dax_writeback_mapping_range(mapping, lstart, lend); - if (err) - return err; - } - - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1c317b85ea7d..e10a4fee88d2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2836,6 +2836,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable_t pgtable; pmd_t _pmd; bool young, write, dirty; + unsigned long addr; int i; VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); @@ -2865,7 +2866,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry, *pte; /* * Note that NUMA hinting access restrictions are not @@ -2886,9 +2887,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } if (dirty) SetPageDirty(page + i); - pte = pte_offset_map(&_pmd, haddr); + pte = pte_offset_map(&_pmd, addr); BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); + set_pte_at(mm, addr, pte, entry); atomic_inc(&page[i]._mapcount); pte_unmap(pte); } @@ -2938,7 +2939,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pmd_populate(mm, pmd, pgtable); if (freeze) { - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + for (i = 0; i < HPAGE_PMD_NR; i++) { page_remove_rmap(page + i, false); put_page(page + i); } diff --git a/mm/memory.c b/mm/memory.c index 635451abc8f7..8132787ae4d5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(pmd_none(*pmd)) && unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd + * didn't become pmd_trans_huge under us and then back to pmd_none, as + * a result of MADV_DONTNEED running immediately after a huge pmd fault + * in a different thread of this mm, in turn leading to a misleading + * pmd_trans_huge() retval. All we have to ensure is that it is a + * regular pmd that we can walk with pte_offset_map() and we can do that + * through an atomic read in C, which is what pmd_trans_unstable() + * provides. + */ + if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd))) return 0; /* * A regular pmd is established and it can't morph into a huge pmd diff --git a/mm/migrate.c b/mm/migrate.c index b1034f9c77e7..3ad0fea5c438 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1582,7 +1582,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, (GFP_HIGHUSER_MOVABLE | __GFP_THISNODE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & - ~(__GFP_IO | __GFP_FS), 0); + ~__GFP_RECLAIM, 0); return newpage; } diff --git a/net/Kconfig b/net/Kconfig index 2760825e53fa..10640d5f8bee 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -360,6 +360,7 @@ source "net/can/Kconfig" source "net/irda/Kconfig" source "net/bluetooth/Kconfig" source "net/rxrpc/Kconfig" +source "net/kcm/Kconfig" config FIB_RULES bool diff --git a/net/Makefile b/net/Makefile index a5d04098dfce..81d14119eab5 100644 --- a/net/Makefile +++ b/net/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_IRDA) += irda/ obj-$(CONFIG_BT) += bluetooth/ obj-$(CONFIG_SUNRPC) += sunrpc/ obj-$(CONFIG_AF_RXRPC) += rxrpc/ +obj-$(CONFIG_AF_KCM) += kcm/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_L2TP) += l2tp/ obj-$(CONFIG_DECNET) += decnet/ diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index b563a3f5f2a8..2fa3be965101 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -228,8 +228,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) } #endif +static bool ax25_validate_header(const char *header, unsigned int len) +{ + ax25_digi digi; + + if (!len) + return false; + + if (header[0]) + return true; + + return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL, + NULL); +} + const struct header_ops ax25_header_ops = { .create = ax25_hard_header, + .validate = ax25_validate_header, }; EXPORT_SYMBOL(ax25_header_ops); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 82e3e9705017..dcea4f4c62b3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -723,6 +723,8 @@ int br_fdb_dump(struct sk_buff *skb, struct net_bridge_fdb_entry *f; hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { + int err; + if (idx < cb->args[0]) goto skip; @@ -741,12 +743,15 @@ int br_fdb_dump(struct sk_buff *skb, if (!filter_dev && f->dst) goto skip; - if (fdb_fill_info(skb, br, f, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, - NLM_F_MULTI) < 0) + err = fdb_fill_info(skb, br, f, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI); + if (err < 0) { + cb->args[1] = err; break; + } skip: ++idx; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 7ddbe7ec81d6..44114a94c576 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -37,6 +37,7 @@ #include <net/addrconf.h> #include <net/route.h> #include <net/netfilter/br_netfilter.h> +#include <net/netns/generic.h> #include <asm/uaccess.h> #include "br_private.h" @@ -44,6 +45,12 @@ #include <linux/sysctl.h> #endif +static int brnf_net_id __read_mostly; + +struct brnf_net { + bool enabled; +}; + #ifdef CONFIG_SYSCTL static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables __read_mostly = 1; @@ -938,6 +945,53 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { }, }; +static int brnf_device_event(struct notifier_block *unused, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct brnf_net *brnet; + struct net *net; + int ret; + + if (event != NETDEV_REGISTER || !(dev->priv_flags & IFF_EBRIDGE)) + return NOTIFY_DONE; + + ASSERT_RTNL(); + + net = dev_net(dev); + brnet = net_generic(net, brnf_net_id); + if (brnet->enabled) + return NOTIFY_OK; + + ret = nf_register_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops)); + if (ret) + return NOTIFY_BAD; + + brnet->enabled = true; + return NOTIFY_OK; +} + +static void __net_exit brnf_exit_net(struct net *net) +{ + struct brnf_net *brnet = net_generic(net, brnf_net_id); + + if (!brnet->enabled) + return; + + nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops)); + brnet->enabled = false; +} + +static struct pernet_operations brnf_net_ops __read_mostly = { + .exit = brnf_exit_net, + .id = &brnf_net_id, + .size = sizeof(struct brnf_net), +}; + +static struct notifier_block brnf_notifier __read_mostly = { + .notifier_call = brnf_device_event, +}; + #ifdef CONFIG_SYSCTL static int brnf_sysctl_call_tables(struct ctl_table *ctl, int write, @@ -1003,16 +1057,23 @@ static int __init br_netfilter_init(void) { int ret; - ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + ret = register_pernet_subsys(&brnf_net_ops); if (ret < 0) return ret; + ret = register_netdevice_notifier(&brnf_notifier); + if (ret < 0) { + unregister_pernet_subsys(&brnf_net_ops); + return ret; + } + #ifdef CONFIG_SYSCTL brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table); if (brnf_sysctl_header == NULL) { printk(KERN_WARNING "br_netfilter: can't register to sysctl.\n"); - nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + unregister_netdevice_notifier(&brnf_notifier); + unregister_pernet_subsys(&brnf_net_ops); return -ENOMEM; } #endif @@ -1024,7 +1085,8 @@ static int __init br_netfilter_init(void) static void __exit br_netfilter_fini(void) { RCU_INIT_POINTER(nf_br_ops, NULL); - nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + unregister_netdevice_notifier(&brnf_notifier); + unregister_pernet_subsys(&brnf_net_ops); #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(brnf_sysctl_header); #endif diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index c22816a0b1b1..e23449094188 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -562,6 +562,14 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) } +/* Set time interval that dynamic forwarding entries live + * For pure software bridge, allow values outside the 802.1 + * standard specification for special cases: + * 0 - entry never ages (all permanant) + * 1 - entry disappears (no persistance) + * + * Offloaded switch entries maybe more restrictive + */ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) { struct switchdev_attr attr = { @@ -573,9 +581,6 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) unsigned long t = clock_t_to_jiffies(ageing_time); int err; - if (t < BR_MIN_AGEING_TIME || t > BR_MAX_AGEING_TIME) - return -ERANGE; - err = switchdev_port_attr_set(br->dev, &attr); if (err) return err; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9cfedf565f5b..9382619a405b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1197,6 +1197,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, return new_piece; } +static size_t sizeof_footer(struct ceph_connection *con) +{ + return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ? + sizeof(struct ceph_msg_footer) : + sizeof(struct ceph_msg_footer_old); +} + static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { BUG_ON(!msg); @@ -2335,9 +2342,9 @@ static int read_partial_message(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; - return 0; + return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); @@ -2360,10 +2367,10 @@ static int read_partial_message(struct ceph_connection *con) /* skip this message */ dout("alloc_msg said skip message\n"); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; - return 0; + return 1; } BUG_ON(!con->in_msg); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 3534e12683d3..5bc053778fed 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2853,8 +2853,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (!req) { - pr_warn("%s osd%d tid %llu unknown, skipping\n", - __func__, osd->o_osd, tid); + dout("%s osd%d tid %llu unknown, skipping\n", __func__, + osd->o_osd, tid); m = NULL; *skip = 1; goto out; diff --git a/net/core/filter.c b/net/core/filter.c index 5e2a3b5e5196..6fc3893a6170 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1353,7 +1353,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) unsigned int len = (unsigned int) r4; void *ptr; - if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM))) + if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; /* bpf verifier guarantees that: @@ -1384,11 +1384,13 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) if (flags & BPF_F_RECOMPUTE_CSUM) skb_postpush_rcsum(skb, ptr, len); + if (flags & BPF_F_INVALIDATE_HASH) + skb_clear_hash(skb); return 0; } -const struct bpf_func_proto bpf_skb_store_bytes_proto = { +static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1419,7 +1421,7 @@ static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return 0; } -const struct bpf_func_proto bpf_skb_load_bytes_proto = { +static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1447,6 +1449,12 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EFAULT; switch (flags & BPF_F_HDR_FIELD_MASK) { + case 0: + if (unlikely(from != 0)) + return -EINVAL; + + csum_replace_by_diff(ptr, to); + break; case 2: csum_replace2(ptr, from, to); break; @@ -1464,7 +1472,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return 0; } -const struct bpf_func_proto bpf_l3_csum_replace_proto = { +static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1523,7 +1531,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return 0; } -const struct bpf_func_proto bpf_l4_csum_replace_proto = { +static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1562,7 +1570,7 @@ static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed) return csum_partial(sp->diff, diff_size, seed); } -const struct bpf_func_proto bpf_csum_diff_proto = { +static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1600,7 +1608,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) return dev_queue_xmit(skb2); } -const struct bpf_func_proto bpf_clone_redirect_proto = { +static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1652,7 +1660,7 @@ int skb_do_redirect(struct sk_buff *skb) return dev_queue_xmit(skb); } -const struct bpf_func_proto bpf_redirect_proto = { +static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1762,12 +1770,15 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EPROTO; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { + case offsetof(struct bpf_tunnel_key, tunnel_label): + goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; +set_compat: to = (struct bpf_tunnel_key *)compat; break; default: @@ -1779,11 +1790,13 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; - if (flags & BPF_F_TUNINFO_IPV6) + if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); - else + to->tunnel_label = be32_to_cpu(info->key.label); + } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); + } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy((void *)(long) r2, to, size); @@ -1791,7 +1804,7 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return 0; } -const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { +static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1801,6 +1814,32 @@ const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; +static u64 bpf_skb_get_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + u8 *to = (u8 *) (long) r2; + const struct ip_tunnel_info *info = skb_tunnel_info(skb); + + if (unlikely(!info || + !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) + return -ENOENT; + if (unlikely(size < info->options_len)) + return -ENOMEM; + + ip_tunnel_info_opts_get(to, info); + + return info->options_len; +} + +static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { + .func = bpf_skb_get_tunnel_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + static struct metadata_dst __percpu *md_dst; static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) @@ -1811,10 +1850,12 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; - if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6))) + if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_DONT_FRAGMENT))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { + case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. @@ -1827,6 +1868,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EINVAL; } } + if (unlikely(!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label)) + return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); @@ -1835,7 +1878,10 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info = &md->u.tun_info; info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY; + info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + if (flags & BPF_F_DONT_FRAGMENT) + info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; + info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; @@ -1844,14 +1890,18 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); + info->key.label = cpu_to_be32(from->tunnel_label) & + IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); + if (flags & BPF_F_ZERO_CSUM_TX) + info->key.tun_flags &= ~TUNNEL_CSUM; } return 0; } -const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { +static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1861,17 +1911,58 @@ const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -static const struct bpf_func_proto *bpf_get_skb_set_tunnel_key_proto(void) +#define BPF_TUNLEN_MAX 255 + +static u64 bpf_skb_set_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + u8 *from = (u8 *) (long) r2; + struct ip_tunnel_info *info = skb_tunnel_info(skb); + const struct metadata_dst *md = this_cpu_ptr(md_dst); + + if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) + return -EINVAL; + if (unlikely(size > BPF_TUNLEN_MAX)) + return -ENOMEM; + + ip_tunnel_info_opts_set(info, from, size); + + return 0; +} + +static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { + .func = bpf_skb_set_tunnel_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto * +bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { - /* race is not possible, since it's called from - * verifier that is holding verifier mutex + BUILD_BUG_ON(FIELD_SIZEOF(struct ip_tunnel_info, + options_len) != 1); + + /* Race is not possible, since it's called from verifier + * that is holding verifier mutex. */ - md_dst = metadata_dst_alloc_percpu(0, GFP_KERNEL); + md_dst = metadata_dst_alloc_percpu(BPF_TUNLEN_MAX, + GFP_KERNEL); if (!md_dst) return NULL; } - return &bpf_skb_set_tunnel_key_proto; + + switch (which) { + case BPF_FUNC_skb_set_tunnel_key: + return &bpf_skb_set_tunnel_key_proto; + case BPF_FUNC_skb_set_tunnel_opt: + return &bpf_skb_set_tunnel_opt_proto; + default: + return NULL; + } } static const struct bpf_func_proto * @@ -1925,7 +2016,11 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: - return bpf_get_skb_set_tunnel_key_proto(); + return bpf_get_skb_set_tunnel_proto(func_id); + case BPF_FUNC_skb_get_tunnel_opt: + return &bpf_skb_get_tunnel_opt_proto; + case BPF_FUNC_skb_set_tunnel_opt: + return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_get_route_realm: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7c7b8739b8b8..a669dea146c6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -19,25 +19,12 @@ #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> -static bool dissector_uses_key(const struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id) -{ - return flow_dissector->used_keys & (1 << key_id); -} - static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1 << key_id); } -static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id, - void *target_container) -{ - return ((char *) target_container) + flow_dissector->offset[key_id]; -} - void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 6128aac01b11..d2d9e5ebf58e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2970,6 +2970,7 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb, nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); out: netif_addr_unlock_bh(dev); + cb->args[1] = err; return idx; } EXPORT_SYMBOL(ndo_dflt_fdb_dump); @@ -3003,6 +3004,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) ops = br_dev->netdev_ops; } + cb->args[1] = 0; for_each_netdev(net, dev) { if (brport_idx && (dev->ifindex != brport_idx)) continue; @@ -3030,12 +3032,16 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, idx); } + if (cb->args[1] == -EMSGSIZE) + break; if (dev->netdev_ops->ndo_fdb_dump) idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, idx); else idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + if (cb->args[1] == -EMSGSIZE) + break; cops = NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7af7ec635d90..51d768e7bc90 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1918,6 +1918,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, struct splice_pipe_desc *spd, struct sock *sk) { int seg; + struct sk_buff *iter; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a @@ -1944,6 +1945,19 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, return true; } + skb_walk_frags(skb, iter) { + if (*offset >= iter->len) { + *offset -= iter->len; + continue; + } + /* __skb_splice_bits() only fails if the output has no room + * left, so no point in going over the frag_list for the error + * case. + */ + if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) + return true; + } + return false; } @@ -1970,9 +1984,7 @@ ssize_t skb_socket_splice(struct sock *sk, /* * Map data from the skb to a pipe. Should handle both the linear part, - * the fragments, and the frag list. It does NOT handle frag lists within - * the frag list, if such a thing exists. We'd probably need to recurse to - * handle that cleanly. + * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, @@ -1991,29 +2003,10 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; - struct sk_buff *frag_iter; int ret = 0; - /* - * __skb_splice_bits() only fails if the output has no room left, - * so no point in going over the frag_list for the error case. - */ - if (__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk)) - goto done; - else if (!tlen) - goto done; + __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); - /* - * now see if we have a frag_list to map - */ - skb_walk_frags(skb, frag_iter) { - if (!tlen) - break; - if (__skb_splice_bits(frag_iter, pipe, &offset, &tlen, &spd, sk)) - break; - } - -done: if (spd.nr_pages) ret = splice_cb(sk, pipe, &spd); @@ -3023,6 +3016,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + +/** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled @@ -4167,9 +4178,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, if (!pskb_may_pull(skb_chk, offset)) goto err; - __skb_pull(skb_chk, offset); + skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); - __skb_push(skb_chk, offset); + skb_push_rcsum(skb_chk, offset); if (ret) goto err; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index fa4daba8db55..d8fb47fcad05 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -935,6 +935,14 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) { int i; + dst->master_netdev->dsa_ptr = NULL; + + /* If we used a tagging format that doesn't have an ethertype + * field, make sure that all packets from this point get sent + * without the tag and go through the regular receive path. + */ + wmb(); + for (i = 0; i < dst->pd->nr_chips; i++) { struct dsa_switch *ds = dst->ds[i]; @@ -988,14 +996,6 @@ static int dsa_suspend(struct device *d) struct dsa_switch_tree *dst = platform_get_drvdata(pdev); int i, ret = 0; - dst->master_netdev->dsa_ptr = NULL; - - /* If we used a tagging format that doesn't have an ethertype - * field, make sure that all packets from this point get sent - * without the tag and go through the regular receive path. - */ - wmb(); - for (i = 0; i < dst->pd->nr_chips; i++) { struct dsa_switch *ds = dst->ds[i]; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index c102eb5ac55c..c34c7544d1db 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -665,7 +665,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) */ if (!in_dev) - goto out; + goto out_free_skb; arp = arp_hdr(skb); @@ -673,7 +673,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) default: if (arp->ar_pro != htons(ETH_P_IP) || htons(dev_type) != arp->ar_hrd) - goto out; + goto out_free_skb; break; case ARPHRD_ETHER: case ARPHRD_FDDI: @@ -690,17 +690,17 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) if ((arp->ar_hrd != htons(ARPHRD_ETHER) && arp->ar_hrd != htons(ARPHRD_IEEE802)) || arp->ar_pro != htons(ETH_P_IP)) - goto out; + goto out_free_skb; break; case ARPHRD_AX25: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_AX25)) - goto out; + goto out_free_skb; break; case ARPHRD_NETROM: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_NETROM)) - goto out; + goto out_free_skb; break; } @@ -708,7 +708,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) if (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST)) - goto out; + goto out_free_skb; /* * Extract fields @@ -733,7 +733,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) */ if (ipv4_is_multicast(tip) || (!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip))) - goto out; + goto out_free_skb; /* * For some 802.11 wireless deployments (and possibly other networks), @@ -741,7 +741,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) * and thus should not be accepted. */ if (sip == tip && IN_DEV_ORCONF(in_dev, DROP_GRATUITOUS_ARP)) - goto out; + goto out_free_skb; /* * Special case: We must set Frame Relay source Q.922 address @@ -778,7 +778,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) !arp_ignore(in_dev, sip, tip)) arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); - goto out; + goto out_consume_skb; } if (arp->ar_op == htons(ARPOP_REQUEST) && @@ -803,7 +803,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) neigh_release(n); } } - goto out; + goto out_consume_skb; } else if (IN_DEV_FORWARD(in_dev)) { if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || @@ -826,7 +826,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) in_dev->arp_parms, skb); goto out_free_dst; } - goto out; + goto out_consume_skb; } } } @@ -876,11 +876,16 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) neigh_release(n); } -out: +out_consume_skb: consume_skb(skb); + out_free_dst: dst_release(reply_dst); - return 0; + return NET_RX_SUCCESS; + +out_free_skb: + kfree_skb(skb); + return NET_RX_DROP; } static void parp_redo(struct sk_buff *skb) @@ -924,11 +929,11 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, consumeskb: consume_skb(skb); - return 0; + return NET_RX_SUCCESS; freeskb: kfree_skb(skb); out_of_mem: - return 0; + return NET_RX_DROP; } /* diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 88dab0c1670c..780484243e14 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -319,8 +319,6 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, skb_gro_pull(skb, hdrlen); - flush = 0; - for (p = *head; p; p = p->next) { const struct guehdr *guehdr2; @@ -352,6 +350,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, goto out_unlock; pp = ops->callbacks.gro_receive(head, skb); + flush = 0; out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 47f4c544c916..540866dbd27d 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -175,8 +175,6 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, null_compute_pseudo); } - flush = 0; - for (p = *head; p; p = p->next) { const struct gre_base_hdr *greh2; @@ -213,6 +211,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, skb_gro_postpull_rcsum(skb, greh, grehlen); pp = ptype->callbacks.gro_receive(head, skb); + flush = 0; out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 2aea9f1a2a31..9b4ca87f70ba 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -350,9 +350,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 202437d6087b..31936d387cfd 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -527,11 +527,12 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; + struct rtable *rt = NULL; struct flowi4 fl; - struct rtable *rt; int min_headroom; int tunnel_hlen; __be16 df, flags; + bool use_cache; int err; tun_info = skb_tunnel_info(skb); @@ -540,13 +541,14 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - rt = !skb->mark ? dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr) : - NULL; + use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); + if (use_cache) + rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr); if (!rt) { rt = gre_get_rt(skb, dev, &fl, key); if (IS_ERR(rt)) goto err_free_skb; - if (!skb->mark) + if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl.saddr); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f734c42acdaf..124bf0a66328 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1233,13 +1233,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (!skb) return -EINVAL; - cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { + if (skb->ip_summed != CHECKSUM_PARTIAL) + return -EOPNOTSUPP; + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } + cork->length += size; while (size > 0) { if (skb_is_gso(skb)) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index dff8a05739a2..6aad0192443d 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -607,6 +607,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -706,7 +708,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b488cac9c5ca..bf081927e06b 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1780,9 +1780,29 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -struct xt_table *arpt_register_table(struct net *net, - const struct xt_table *table, - const struct arpt_replace *repl) +static void __arpt_unregister_table(struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct arpt_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); +} + +int arpt_register_table(struct net *net, + const struct xt_table *table, + const struct arpt_replace *repl, + const struct nf_hook_ops *ops, + struct xt_table **res) { int ret; struct xt_table_info *newinfo; @@ -1791,10 +1811,8 @@ struct xt_table *arpt_register_table(struct net *net, struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); - if (!newinfo) { - ret = -ENOMEM; - goto out; - } + if (!newinfo) + return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); @@ -1809,30 +1827,28 @@ struct xt_table *arpt_register_table(struct net *net, ret = PTR_ERR(new_table); goto out_free; } - return new_table; + + /* set res now, will see skbs right after nf_register_net_hooks */ + WRITE_ONCE(*res, new_table); + + ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ret != 0) { + __arpt_unregister_table(new_table); + *res = NULL; + } + + return ret; out_free: xt_free_table_info(newinfo); -out: - return ERR_PTR(ret); + return ret; } -void arpt_unregister_table(struct xt_table *table) +void arpt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { - struct xt_table_info *private; - void *loc_cpu_entry; - struct module *table_owner = table->me; - struct arpt_entry *iter; - - private = xt_unregister_table(table); - - /* Decrease module usage counts and free resources */ - loc_cpu_entry = private->entries; - xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter); - if (private->number > private->initial_entries) - module_put(table_owner); - xt_free_table_info(private); + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + __arpt_unregister_table(table); } /* The built-in targets: standard (NULL) and error. */ diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 1897ee160920..dd8c80dc32a2 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -17,12 +17,15 @@ MODULE_DESCRIPTION("arptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \ (1 << NF_ARP_FORWARD)) +static int __net_init arptable_filter_table_init(struct net *net); + static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_ARP, .priority = NF_IP_PRI_FILTER, + .table_init = arptable_filter_table_init, }; /* The work comes in here from netfilter.c */ @@ -35,26 +38,32 @@ arptable_filter_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *arpfilter_ops __read_mostly; -static int __net_init arptable_filter_net_init(struct net *net) +static int __net_init arptable_filter_table_init(struct net *net) { struct arpt_replace *repl; - + int err; + + if (net->ipv4.arptable_filter) + return 0; + repl = arpt_alloc_initial_table(&packet_filter); if (repl == NULL) return -ENOMEM; - net->ipv4.arptable_filter = - arpt_register_table(net, &packet_filter, repl); + err = arpt_register_table(net, &packet_filter, repl, arpfilter_ops, + &net->ipv4.arptable_filter); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.arptable_filter); + return err; } static void __net_exit arptable_filter_net_exit(struct net *net) { - arpt_unregister_table(net->ipv4.arptable_filter); + if (!net->ipv4.arptable_filter) + return; + arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops); + net->ipv4.arptable_filter = NULL; } static struct pernet_operations arptable_filter_net_ops = { - .init = arptable_filter_net_init, .exit = arptable_filter_net_exit, }; @@ -62,26 +71,23 @@ static int __init arptable_filter_init(void) { int ret; + arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook); + if (IS_ERR(arpfilter_ops)) + return PTR_ERR(arpfilter_ops); + ret = register_pernet_subsys(&arptable_filter_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(arpfilter_ops); return ret; - - arpfilter_ops = xt_hook_link(&packet_filter, arptable_filter_hook); - if (IS_ERR(arpfilter_ops)) { - ret = PTR_ERR(arpfilter_ops); - goto cleanup_table; } - return ret; -cleanup_table: - unregister_pernet_subsys(&arptable_filter_net_ops); return ret; } static void __exit arptable_filter_fini(void) { - xt_hook_unlink(&packet_filter, arpfilter_ops); unregister_pernet_subsys(&arptable_filter_net_ops); + kfree(arpfilter_ops); } module_init(arptable_filter_init); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index b99affad6ba1..e53f8d6f326d 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -2062,9 +2062,27 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -struct xt_table *ipt_register_table(struct net *net, - const struct xt_table *table, - const struct ipt_replace *repl) +static void __ipt_unregister_table(struct net *net, struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct ipt_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter, net); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); +} + +int ipt_register_table(struct net *net, const struct xt_table *table, + const struct ipt_replace *repl, + const struct nf_hook_ops *ops, struct xt_table **res) { int ret; struct xt_table_info *newinfo; @@ -2073,10 +2091,8 @@ struct xt_table *ipt_register_table(struct net *net, struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); - if (!newinfo) { - ret = -ENOMEM; - goto out; - } + if (!newinfo) + return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); @@ -2091,30 +2107,27 @@ struct xt_table *ipt_register_table(struct net *net, goto out_free; } - return new_table; + /* set res now, will see skbs right after nf_register_net_hooks */ + WRITE_ONCE(*res, new_table); + + ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ret != 0) { + __ipt_unregister_table(net, new_table); + *res = NULL; + } + + return ret; out_free: xt_free_table_info(newinfo); -out: - return ERR_PTR(ret); + return ret; } -void ipt_unregister_table(struct net *net, struct xt_table *table) +void ipt_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { - struct xt_table_info *private; - void *loc_cpu_entry; - struct module *table_owner = table->me; - struct ipt_entry *iter; - - private = xt_unregister_table(table); - - /* Decrease module usage counts and free resources */ - loc_cpu_entry = private->entries; - xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter, net); - if (private->number > private->initial_entries) - module_put(table_owner); - xt_free_table_info(private); + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + __ipt_unregister_table(net, table); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 397ef2dd133e..7667f223d7f8 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -23,6 +23,7 @@ MODULE_DESCRIPTION("iptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) +static int __net_init iptable_filter_table_init(struct net *net); static const struct xt_table packet_filter = { .name = "filter", @@ -30,6 +31,7 @@ static const struct xt_table packet_filter = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_FILTER, + .table_init = iptable_filter_table_init, }; static unsigned int @@ -48,12 +50,16 @@ iptable_filter_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ -static bool forward = true; +static bool forward __read_mostly = true; module_param(forward, bool, 0000); -static int __net_init iptable_filter_net_init(struct net *net) +static int __net_init iptable_filter_table_init(struct net *net) { struct ipt_replace *repl; + int err; + + if (net->ipv4.iptable_filter) + return 0; repl = ipt_alloc_initial_table(&packet_filter); if (repl == NULL) @@ -62,15 +68,26 @@ static int __net_init iptable_filter_net_init(struct net *net) ((struct ipt_standard *)repl->entries)[1].target.verdict = forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; - net->ipv4.iptable_filter = - ipt_register_table(net, &packet_filter, repl); + err = ipt_register_table(net, &packet_filter, repl, filter_ops, + &net->ipv4.iptable_filter); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_filter); + return err; +} + +static int __net_init iptable_filter_net_init(struct net *net) +{ + if (net == &init_net || !forward) + return iptable_filter_table_init(net); + + return 0; } static void __net_exit iptable_filter_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_filter); + if (!net->ipv4.iptable_filter) + return; + ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops); + net->ipv4.iptable_filter = NULL; } static struct pernet_operations iptable_filter_net_ops = { @@ -82,24 +99,21 @@ static int __init iptable_filter_init(void) { int ret; + filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook); + if (IS_ERR(filter_ops)) + return PTR_ERR(filter_ops); + ret = register_pernet_subsys(&iptable_filter_net_ops); if (ret < 0) - return ret; - - /* Register hooks */ - filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook); - if (IS_ERR(filter_ops)) { - ret = PTR_ERR(filter_ops); - unregister_pernet_subsys(&iptable_filter_net_ops); - } + kfree(filter_ops); return ret; } static void __exit iptable_filter_fini(void) { - xt_hook_unlink(&packet_filter, filter_ops); unregister_pernet_subsys(&iptable_filter_net_ops); + kfree(filter_ops); } module_init(iptable_filter_init); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index ba5d392a13c4..57fc97cdac70 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) +static int __net_init iptable_mangle_table_init(struct net *net); + static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_MANGLE, + .table_init = iptable_mangle_table_init, }; static unsigned int @@ -92,27 +95,32 @@ iptable_mangle_hook(void *priv, } static struct nf_hook_ops *mangle_ops __read_mostly; - -static int __net_init iptable_mangle_net_init(struct net *net) +static int __net_init iptable_mangle_table_init(struct net *net) { struct ipt_replace *repl; + int ret; + + if (net->ipv4.iptable_mangle) + return 0; repl = ipt_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; - net->ipv4.iptable_mangle = - ipt_register_table(net, &packet_mangler, repl); + ret = ipt_register_table(net, &packet_mangler, repl, mangle_ops, + &net->ipv4.iptable_mangle); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_mangle); + return ret; } static void __net_exit iptable_mangle_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_mangle); + if (!net->ipv4.iptable_mangle) + return; + ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops); + net->ipv4.iptable_mangle = NULL; } static struct pernet_operations iptable_mangle_net_ops = { - .init = iptable_mangle_net_init, .exit = iptable_mangle_net_exit, }; @@ -120,15 +128,22 @@ static int __init iptable_mangle_init(void) { int ret; + mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); + if (IS_ERR(mangle_ops)) { + ret = PTR_ERR(mangle_ops); + return ret; + } + ret = register_pernet_subsys(&iptable_mangle_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(mangle_ops); return ret; + } - /* Register hooks */ - mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook); - if (IS_ERR(mangle_ops)) { - ret = PTR_ERR(mangle_ops); + ret = iptable_mangle_table_init(&init_net); + if (ret) { unregister_pernet_subsys(&iptable_mangle_net_ops); + kfree(mangle_ops); } return ret; @@ -136,8 +151,8 @@ static int __init iptable_mangle_init(void) static void __exit iptable_mangle_fini(void) { - xt_hook_unlink(&packet_mangler, mangle_ops); unregister_pernet_subsys(&iptable_mangle_net_ops); + kfree(mangle_ops); } module_init(iptable_mangle_init); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index ae2cd2752046..138a24bc76ad 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -18,6 +18,8 @@ #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_l3proto.h> +static int __net_init iptable_nat_table_init(struct net *net); + static const struct xt_table nf_nat_ipv4_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | @@ -26,6 +28,7 @@ static const struct xt_table nf_nat_ipv4_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV4, + .table_init = iptable_nat_table_init, }; static unsigned int iptable_nat_do_chain(void *priv, @@ -95,50 +98,50 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { }, }; -static int __net_init iptable_nat_net_init(struct net *net) +static int __net_init iptable_nat_table_init(struct net *net) { struct ipt_replace *repl; + int ret; + + if (net->ipv4.nat_table) + return 0; repl = ipt_alloc_initial_table(&nf_nat_ipv4_table); if (repl == NULL) return -ENOMEM; - net->ipv4.nat_table = ipt_register_table(net, &nf_nat_ipv4_table, repl); + ret = ipt_register_table(net, &nf_nat_ipv4_table, repl, + nf_nat_ipv4_ops, &net->ipv4.nat_table); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.nat_table); + return ret; } static void __net_exit iptable_nat_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.nat_table); + if (!net->ipv4.nat_table) + return; + ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops); + net->ipv4.nat_table = NULL; } static struct pernet_operations iptable_nat_net_ops = { - .init = iptable_nat_net_init, .exit = iptable_nat_net_exit, }; static int __init iptable_nat_init(void) { - int err; + int ret = register_pernet_subsys(&iptable_nat_net_ops); - err = register_pernet_subsys(&iptable_nat_net_ops); - if (err < 0) - goto err1; + if (ret) + return ret; - err = nf_register_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); - if (err < 0) - goto err2; - return 0; - -err2: - unregister_pernet_subsys(&iptable_nat_net_ops); -err1: - return err; + ret = iptable_nat_table_init(&init_net); + if (ret) + unregister_pernet_subsys(&iptable_nat_net_ops); + return ret; } static void __exit iptable_nat_exit(void) { - nf_unregister_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); unregister_pernet_subsys(&iptable_nat_net_ops); } diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 1ba02811acb0..2642ecd2645c 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -10,12 +10,15 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) +static int __net_init iptable_raw_table_init(struct net *net); + static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW, + .table_init = iptable_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -34,26 +37,32 @@ iptable_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init iptable_raw_net_init(struct net *net) +static int __net_init iptable_raw_table_init(struct net *net) { struct ipt_replace *repl; + int ret; + + if (net->ipv4.iptable_raw) + return 0; repl = ipt_alloc_initial_table(&packet_raw); if (repl == NULL) return -ENOMEM; - net->ipv4.iptable_raw = - ipt_register_table(net, &packet_raw, repl); + ret = ipt_register_table(net, &packet_raw, repl, rawtable_ops, + &net->ipv4.iptable_raw); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_raw); + return ret; } static void __net_exit iptable_raw_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_raw); + if (!net->ipv4.iptable_raw) + return; + ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops); + net->ipv4.iptable_raw = NULL; } static struct pernet_operations iptable_raw_net_ops = { - .init = iptable_raw_net_init, .exit = iptable_raw_net_exit, }; @@ -61,15 +70,20 @@ static int __init iptable_raw_init(void) { int ret; + rawtable_ops = xt_hook_ops_alloc(&packet_raw, iptable_raw_hook); + if (IS_ERR(rawtable_ops)) + return PTR_ERR(rawtable_ops); + ret = register_pernet_subsys(&iptable_raw_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(rawtable_ops); return ret; + } - /* Register hooks */ - rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook); - if (IS_ERR(rawtable_ops)) { - ret = PTR_ERR(rawtable_ops); + ret = iptable_raw_table_init(&init_net); + if (ret) { unregister_pernet_subsys(&iptable_raw_net_ops); + kfree(rawtable_ops); } return ret; @@ -77,8 +91,8 @@ static int __init iptable_raw_init(void) static void __exit iptable_raw_fini(void) { - xt_hook_unlink(&packet_raw, rawtable_ops); unregister_pernet_subsys(&iptable_raw_net_ops); + kfree(rawtable_ops); } module_init(iptable_raw_init); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index c2e23d5e9cd4..ff226596e4b5 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) +static int __net_init iptable_security_table_init(struct net *net); + static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_SECURITY, + .table_init = iptable_security_table_init, }; static unsigned int @@ -51,26 +54,33 @@ iptable_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init iptable_security_net_init(struct net *net) +static int __net_init iptable_security_table_init(struct net *net) { struct ipt_replace *repl; + int ret; + + if (net->ipv4.iptable_security) + return 0; repl = ipt_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; - net->ipv4.iptable_security = - ipt_register_table(net, &security_table, repl); + ret = ipt_register_table(net, &security_table, repl, sectbl_ops, + &net->ipv4.iptable_security); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv4.iptable_security); + return ret; } static void __net_exit iptable_security_net_exit(struct net *net) { - ipt_unregister_table(net, net->ipv4.iptable_security); + if (!net->ipv4.iptable_security) + return; + + ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops); + net->ipv4.iptable_security = NULL; } static struct pernet_operations iptable_security_net_ops = { - .init = iptable_security_net_init, .exit = iptable_security_net_exit, }; @@ -78,27 +88,29 @@ static int __init iptable_security_init(void) { int ret; + sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook); + if (IS_ERR(sectbl_ops)) + return PTR_ERR(sectbl_ops); + ret = register_pernet_subsys(&iptable_security_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(sectbl_ops); return ret; - - sectbl_ops = xt_hook_link(&security_table, iptable_security_hook); - if (IS_ERR(sectbl_ops)) { - ret = PTR_ERR(sectbl_ops); - goto cleanup_table; } - return ret; + ret = iptable_security_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&iptable_security_net_ops); + kfree(sectbl_ops); + } -cleanup_table: - unregister_pernet_subsys(&iptable_security_net_ops); return ret; } static void __exit iptable_security_fini(void) { - xt_hook_unlink(&security_table, sectbl_ops); unregister_pernet_subsys(&iptable_security_net_ops); + kfree(sectbl_ops); } module_init(iptable_security_init); diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index a04dee536b8e..d88da36b383c 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -31,10 +31,8 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, err = ip_defrag(net, skb, user); local_bh_enable(); - if (!err) { - ip_send_check(ip_hdr(skb)); + if (!err) skb->ignore_df = 1; - } return err; } diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index b72ffc58e255..51ced81b616c 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -25,7 +25,12 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; - + if (priv->sreg_proto_min) { + range.min_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_min]; + range.max_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_max]; + } regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->hook, &range, pkt->out); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f9faadb42485..a265f00b9df9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -556,20 +556,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) return -EINVAL; slow = lock_sock_fast(sk); - if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) - answ = 0; - else if (sock_flag(sk, SOCK_URGINLINE) || - !tp->urg_data || - before(tp->urg_seq, tp->copied_seq) || - !before(tp->urg_seq, tp->rcv_nxt)) { - - answ = tp->rcv_nxt - tp->copied_seq; - - /* Subtract 1, if FIN was received */ - if (answ && sock_flag(sk, SOCK_DONE)) - answ--; - } else - answ = tp->urg_seq - tp->copied_seq; + answ = tcp_inq(sk); unlock_sock_fast(sk, slow); break; case SIOCATMARK: diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c26241f3057b..7b7eec439906 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -551,7 +551,7 @@ reset: */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index fadd8b978951..ae90e4b34bd3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -452,7 +452,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 0; + newtp->segs_in = 1; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -812,6 +812,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 0ec08814f37d..96599d1a1318 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -89,6 +89,8 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 5c5d23e59da5..9508a20fbf61 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, *fragoff = _frag_off; return hp->nexthdr; } - return -ENOENT; + if (!found) + return -ENOENT; + if (fragoff) + *fragoff = _frag_off; + break; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0c7e276c230e..ea071fad67a0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -55,8 +55,6 @@ struct fib6_cleaner { void *arg; }; -static DEFINE_RWLOCK(fib6_walker_lock); - #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S #else @@ -66,7 +64,7 @@ static DEFINE_RWLOCK(fib6_walker_lock); static void fib6_prune_clones(struct net *net, struct fib6_node *fn); static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); -static int fib6_walk(struct fib6_walker *w); +static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); /* @@ -78,21 +76,21 @@ static int fib6_walk_continue(struct fib6_walker *w); static void fib6_gc_timer_cb(unsigned long arg); -static LIST_HEAD(fib6_walkers); -#define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh) +#define FOR_WALKERS(net, w) \ + list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) -static void fib6_walker_link(struct fib6_walker *w) +static void fib6_walker_link(struct net *net, struct fib6_walker *w) { - write_lock_bh(&fib6_walker_lock); - list_add(&w->lh, &fib6_walkers); - write_unlock_bh(&fib6_walker_lock); + write_lock_bh(&net->ipv6.fib6_walker_lock); + list_add(&w->lh, &net->ipv6.fib6_walkers); + write_unlock_bh(&net->ipv6.fib6_walker_lock); } -static void fib6_walker_unlink(struct fib6_walker *w) +static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { - write_lock_bh(&fib6_walker_lock); + write_lock_bh(&net->ipv6.fib6_walker_lock); list_del(&w->lh); - write_unlock_bh(&fib6_walker_lock); + write_unlock_bh(&net->ipv6.fib6_walker_lock); } static int fib6_new_sernum(struct net *net) @@ -325,12 +323,13 @@ static int fib6_dump_node(struct fib6_walker *w) static void fib6_dump_end(struct netlink_callback *cb) { + struct net *net = sock_net(cb->skb->sk); struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { cb->args[4] = 0; - fib6_walker_unlink(w); + fib6_walker_unlink(net, w); } cb->args[2] = 0; kfree(w); @@ -348,6 +347,7 @@ static int fib6_dump_done(struct netlink_callback *cb) static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct fib6_walker *w; int res; @@ -359,7 +359,7 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, w->skip = 0; read_lock_bh(&table->tb6_lock); - res = fib6_walk(w); + res = fib6_walk(net, w); read_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; @@ -379,7 +379,7 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, res = fib6_walk_continue(w); read_unlock_bh(&table->tb6_lock); if (res <= 0) { - fib6_walker_unlink(w); + fib6_walker_unlink(net, w); cb->args[4] = 0; } } @@ -1340,8 +1340,8 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } #endif - read_lock(&fib6_walker_lock); - FOR_WALKERS(w) { + read_lock(&net->ipv6.fib6_walker_lock); + FOR_WALKERS(net, w) { if (!child) { if (w->root == fn) { w->root = w->node = NULL; @@ -1368,7 +1368,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } } } - read_unlock(&fib6_walker_lock); + read_unlock(&net->ipv6.fib6_walker_lock); node_free(fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) @@ -1411,8 +1411,8 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, } /* Adjust walkers */ - read_lock(&fib6_walker_lock); - FOR_WALKERS(w) { + read_lock(&net->ipv6.fib6_walker_lock); + FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); w->leaf = rt->dst.rt6_next; @@ -1420,7 +1420,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, w->state = FWS_U; } } - read_unlock(&fib6_walker_lock); + read_unlock(&net->ipv6.fib6_walker_lock); rt->dst.rt6_next = NULL; @@ -1588,17 +1588,17 @@ skip: } } -static int fib6_walk(struct fib6_walker *w) +static int fib6_walk(struct net *net, struct fib6_walker *w) { int res; w->state = FWS_INIT; w->node = w->root; - fib6_walker_link(w); + fib6_walker_link(net, w); res = fib6_walk_continue(w); if (res <= 0) - fib6_walker_unlink(w); + fib6_walker_unlink(net, w); return res; } @@ -1668,7 +1668,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, c.arg = arg; c.net = net; - fib6_walk(&c.w); + fib6_walk(net, &c.w); } static void __fib6_clean_all(struct net *net, @@ -1725,14 +1725,15 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static struct fib6_gc_args +struct fib6_gc_args { int timeout; int more; -} gc_args; +}; static int fib6_age(struct rt6_info *rt, void *arg) { + struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; /* @@ -1748,10 +1749,10 @@ static int fib6_age(struct rt6_info *rt, void *arg) RT6_TRACE("expiring %p\n", rt); return -1; } - gc_args.more++; + gc_args->more++; } else if (rt->rt6i_flags & RTF_CACHE) { if (atomic_read(&rt->dst.__refcnt) == 0 && - time_after_eq(now, rt->dst.lastuse + gc_args.timeout)) { + time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { RT6_TRACE("aging clone %p\n", rt); return -1; } else if (rt->rt6i_flags & RTF_GATEWAY) { @@ -1769,21 +1770,20 @@ static int fib6_age(struct rt6_info *rt, void *arg) return -1; } } - gc_args.more++; + gc_args->more++; } return 0; } -static DEFINE_SPINLOCK(fib6_gc_lock); - void fib6_run_gc(unsigned long expires, struct net *net, bool force) { + struct fib6_gc_args gc_args; unsigned long now; if (force) { - spin_lock_bh(&fib6_gc_lock); - } else if (!spin_trylock_bh(&fib6_gc_lock)) { + spin_lock_bh(&net->ipv6.fib6_gc_lock); + } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } @@ -1792,7 +1792,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) gc_args.more = icmp6_dst_gc(); - fib6_clean_all(net, fib6_age, NULL); + fib6_clean_all(net, fib6_age, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; @@ -1802,7 +1802,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); - spin_unlock_bh(&fib6_gc_lock); + spin_unlock_bh(&net->ipv6.fib6_gc_lock); } static void fib6_gc_timer_cb(unsigned long arg) @@ -1814,6 +1814,9 @@ static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; + spin_lock_init(&net->ipv6.fib6_gc_lock); + rwlock_init(&net->ipv6.fib6_walker_lock); + INIT_LIST_HEAD(&net->ipv6.fib6_walkers); setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); @@ -1974,7 +1977,8 @@ static int ipv6_route_yield(struct fib6_walker *w) return 0; } -static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter) +static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, + struct net *net) { memset(&iter->w, 0, sizeof(iter->w)); iter->w.func = ipv6_route_yield; @@ -1984,7 +1988,7 @@ static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter) iter->w.args = iter; iter->sernum = iter->w.root->fn_sernum; INIT_LIST_HEAD(&iter->w.lh); - fib6_walker_link(&iter->w); + fib6_walker_link(net, &iter->w); } static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, @@ -2045,16 +2049,16 @@ iter_table: ++*pos; return iter->w.leaf; } else if (r < 0) { - fib6_walker_unlink(&iter->w); + fib6_walker_unlink(net, &iter->w); return NULL; } - fib6_walker_unlink(&iter->w); + fib6_walker_unlink(net, &iter->w); iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); if (!iter->tbl) return NULL; - ipv6_route_seq_setup_walk(iter); + ipv6_route_seq_setup_walk(iter, net); goto iter_table; } @@ -2069,7 +2073,7 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) iter->skip = *pos; if (iter->tbl) { - ipv6_route_seq_setup_walk(iter); + ipv6_route_seq_setup_walk(iter, net); return ipv6_route_seq_next(seq, NULL, pos); } else { return NULL; @@ -2085,10 +2089,11 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) static void ipv6_route_seq_stop(struct seq_file *seq, void *v) __releases(RCU_BH) { + struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (ipv6_route_iter_active(iter)) - fib6_walker_unlink(&iter->w); + fib6_walker_unlink(net, &iter->w); rcu_read_unlock_bh(); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f7c9560b75fa..4e636e60a360 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -777,6 +777,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) __u32 mtu; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3f3aabd2f07b..eb2ac4bb09ce 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1089,6 +1089,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index 14dacf1df529..a7520528ecd2 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -73,8 +73,8 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, - __u8 prio, __u8 ttl, __be16 src_port, - __be16 dst_port, bool nocheck) + __u8 prio, __u8 ttl, __be32 label, + __be16 src_port, __be16 dst_port, bool nocheck) { struct udphdr *uh; struct ipv6hdr *ip6h; @@ -98,7 +98,7 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); - ip6_flow_hdr(ip6h, prio, htonl(0)); + ip6_flow_hdr(ip6h, prio, label); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ee56d0a8699..d64ee7e83664 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) return NULL; skb->priority = TC_PRIO_CONTROL; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 99425cf2819b..84f9baf7aee8 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -2071,9 +2071,28 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -struct xt_table *ip6t_register_table(struct net *net, - const struct xt_table *table, - const struct ip6t_replace *repl) +static void __ip6t_unregister_table(struct net *net, struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct ip6t_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter, net); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); +} + +int ip6t_register_table(struct net *net, const struct xt_table *table, + const struct ip6t_replace *repl, + const struct nf_hook_ops *ops, + struct xt_table **res) { int ret; struct xt_table_info *newinfo; @@ -2082,10 +2101,8 @@ struct xt_table *ip6t_register_table(struct net *net, struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); - if (!newinfo) { - ret = -ENOMEM; - goto out; - } + if (!newinfo) + return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); @@ -2099,30 +2116,28 @@ struct xt_table *ip6t_register_table(struct net *net, ret = PTR_ERR(new_table); goto out_free; } - return new_table; + + /* set res now, will see skbs right after nf_register_net_hooks */ + WRITE_ONCE(*res, new_table); + + ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ret != 0) { + __ip6t_unregister_table(net, new_table); + *res = NULL; + } + + return ret; out_free: xt_free_table_info(newinfo); -out: - return ERR_PTR(ret); + return ret; } -void ip6t_unregister_table(struct net *net, struct xt_table *table) +void ip6t_unregister_table(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { - struct xt_table_info *private; - void *loc_cpu_entry; - struct module *table_owner = table->me; - struct ip6t_entry *iter; - - private = xt_unregister_table(table); - - /* Decrease module usage counts and free resources */ - loc_cpu_entry = private->entries; - xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter, net); - if (private->number > private->initial_entries) - module_put(table_owner); - xt_free_table_info(private); + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + __ip6t_unregister_table(net, table); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 8b277b983ca5..1343077dde93 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -22,12 +22,15 @@ MODULE_DESCRIPTION("ip6tables filter table"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) +static int __net_init ip6table_filter_table_init(struct net *net); + static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_FILTER, + .table_init = ip6table_filter_table_init, }; /* The work comes in here from netfilter.c. */ @@ -44,9 +47,13 @@ static struct nf_hook_ops *filter_ops __read_mostly; static bool forward = true; module_param(forward, bool, 0000); -static int __net_init ip6table_filter_net_init(struct net *net) +static int __net_init ip6table_filter_table_init(struct net *net) { struct ip6t_replace *repl; + int err; + + if (net->ipv6.ip6table_filter) + return 0; repl = ip6t_alloc_initial_table(&packet_filter); if (repl == NULL) @@ -55,15 +62,26 @@ static int __net_init ip6table_filter_net_init(struct net *net) ((struct ip6t_standard *)repl->entries)[1].target.verdict = forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; - net->ipv6.ip6table_filter = - ip6t_register_table(net, &packet_filter, repl); + err = ip6t_register_table(net, &packet_filter, repl, filter_ops, + &net->ipv6.ip6table_filter); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_filter); + return err; +} + +static int __net_init ip6table_filter_net_init(struct net *net) +{ + if (net == &init_net || !forward) + return ip6table_filter_table_init(net); + + return 0; } static void __net_exit ip6table_filter_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_filter); + if (!net->ipv6.ip6table_filter) + return; + ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops); + net->ipv6.ip6table_filter = NULL; } static struct pernet_operations ip6table_filter_net_ops = { @@ -75,28 +93,21 @@ static int __init ip6table_filter_init(void) { int ret; + filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook); + if (IS_ERR(filter_ops)) + return PTR_ERR(filter_ops); + ret = register_pernet_subsys(&ip6table_filter_net_ops); if (ret < 0) - return ret; - - /* Register hooks */ - filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook); - if (IS_ERR(filter_ops)) { - ret = PTR_ERR(filter_ops); - goto cleanup_table; - } + kfree(filter_ops); return ret; - - cleanup_table: - unregister_pernet_subsys(&ip6table_filter_net_ops); - return ret; } static void __exit ip6table_filter_fini(void) { - xt_hook_unlink(&packet_filter, filter_ops); unregister_pernet_subsys(&ip6table_filter_net_ops); + kfree(filter_ops); } module_init(ip6table_filter_init); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index abe278b07932..cb2b28883252 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -23,12 +23,15 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) +static int __net_init ip6table_mangle_table_init(struct net *net); + static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_MANGLE, + .table_init = ip6table_mangle_table_init, }; static unsigned int @@ -88,26 +91,33 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb, } static struct nf_hook_ops *mangle_ops __read_mostly; -static int __net_init ip6table_mangle_net_init(struct net *net) +static int __net_init ip6table_mangle_table_init(struct net *net) { struct ip6t_replace *repl; + int ret; + + if (net->ipv6.ip6table_mangle) + return 0; repl = ip6t_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_mangle = - ip6t_register_table(net, &packet_mangler, repl); + ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops, + &net->ipv6.ip6table_mangle); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_mangle); + return ret; } static void __net_exit ip6table_mangle_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_mangle); + if (!net->ipv6.ip6table_mangle) + return; + + ip6t_unregister_table(net, net->ipv6.ip6table_mangle, mangle_ops); + net->ipv6.ip6table_mangle = NULL; } static struct pernet_operations ip6table_mangle_net_ops = { - .init = ip6table_mangle_net_init, .exit = ip6table_mangle_net_exit, }; @@ -115,28 +125,28 @@ static int __init ip6table_mangle_init(void) { int ret; + mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); + if (IS_ERR(mangle_ops)) + return PTR_ERR(mangle_ops); + ret = register_pernet_subsys(&ip6table_mangle_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(mangle_ops); return ret; - - /* Register hooks */ - mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook); - if (IS_ERR(mangle_ops)) { - ret = PTR_ERR(mangle_ops); - goto cleanup_table; } - return ret; - - cleanup_table: - unregister_pernet_subsys(&ip6table_mangle_net_ops); + ret = ip6table_mangle_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&ip6table_mangle_net_ops); + kfree(mangle_ops); + } return ret; } static void __exit ip6table_mangle_fini(void) { - xt_hook_unlink(&packet_mangler, mangle_ops); unregister_pernet_subsys(&ip6table_mangle_net_ops); + kfree(mangle_ops); } module_init(ip6table_mangle_init); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index de2a10a565f5..7d2bd940291f 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -20,6 +20,8 @@ #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_l3proto.h> +static int __net_init ip6table_nat_table_init(struct net *net); + static const struct xt_table nf_nat_ipv6_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | @@ -28,6 +30,7 @@ static const struct xt_table nf_nat_ipv6_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV6, + .table_init = ip6table_nat_table_init, }; static unsigned int ip6table_nat_do_chain(void *priv, @@ -97,50 +100,50 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { }, }; -static int __net_init ip6table_nat_net_init(struct net *net) +static int __net_init ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; + int ret; + + if (net->ipv6.ip6table_nat) + return 0; repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl); + ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl, + nf_nat_ipv6_ops, &net->ipv6.ip6table_nat); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_nat); + return ret; } static void __net_exit ip6table_nat_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_nat); + if (!net->ipv6.ip6table_nat) + return; + ip6t_unregister_table(net, net->ipv6.ip6table_nat, nf_nat_ipv6_ops); + net->ipv6.ip6table_nat = NULL; } static struct pernet_operations ip6table_nat_net_ops = { - .init = ip6table_nat_net_init, .exit = ip6table_nat_net_exit, }; static int __init ip6table_nat_init(void) { - int err; + int ret = register_pernet_subsys(&ip6table_nat_net_ops); - err = register_pernet_subsys(&ip6table_nat_net_ops); - if (err < 0) - goto err1; + if (ret) + return ret; - err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); - if (err < 0) - goto err2; - return 0; - -err2: - unregister_pernet_subsys(&ip6table_nat_net_ops); -err1: - return err; + ret = ip6table_nat_table_init(&init_net); + if (ret) + unregister_pernet_subsys(&ip6table_nat_net_ops); + return ret; } static void __exit ip6table_nat_exit(void) { - nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); unregister_pernet_subsys(&ip6table_nat_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 9021963565c3..d4bc56443dc1 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -9,12 +9,15 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) +static int __net_init ip6table_raw_table_init(struct net *net); + static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW, + .table_init = ip6table_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -27,26 +30,32 @@ ip6table_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init ip6table_raw_net_init(struct net *net) +static int __net_init ip6table_raw_table_init(struct net *net) { struct ip6t_replace *repl; + int ret; + + if (net->ipv6.ip6table_raw) + return 0; repl = ip6t_alloc_initial_table(&packet_raw); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_raw = - ip6t_register_table(net, &packet_raw, repl); + ret = ip6t_register_table(net, &packet_raw, repl, rawtable_ops, + &net->ipv6.ip6table_raw); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_raw); + return ret; } static void __net_exit ip6table_raw_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_raw); + if (!net->ipv6.ip6table_raw) + return; + ip6t_unregister_table(net, net->ipv6.ip6table_raw, rawtable_ops); + net->ipv6.ip6table_raw = NULL; } static struct pernet_operations ip6table_raw_net_ops = { - .init = ip6table_raw_net_init, .exit = ip6table_raw_net_exit, }; @@ -54,28 +63,29 @@ static int __init ip6table_raw_init(void) { int ret; + /* Register hooks */ + rawtable_ops = xt_hook_ops_alloc(&packet_raw, ip6table_raw_hook); + if (IS_ERR(rawtable_ops)) + return PTR_ERR(rawtable_ops); + ret = register_pernet_subsys(&ip6table_raw_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(rawtable_ops); return ret; - - /* Register hooks */ - rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook); - if (IS_ERR(rawtable_ops)) { - ret = PTR_ERR(rawtable_ops); - goto cleanup_table; } - return ret; - - cleanup_table: - unregister_pernet_subsys(&ip6table_raw_net_ops); + ret = ip6table_raw_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&ip6table_raw_net_ops); + kfree(rawtable_ops); + } return ret; } static void __exit ip6table_raw_fini(void) { - xt_hook_unlink(&packet_raw, rawtable_ops); unregister_pernet_subsys(&ip6table_raw_net_ops); + kfree(rawtable_ops); } module_init(ip6table_raw_init); diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 0d856fedfeb0..cf26ccb04056 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -27,12 +27,15 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) +static int __net_init ip6table_security_table_init(struct net *net); + static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_SECURITY, + .table_init = ip6table_security_table_init, }; static unsigned int @@ -44,26 +47,32 @@ ip6table_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init ip6table_security_net_init(struct net *net) +static int __net_init ip6table_security_table_init(struct net *net) { struct ip6t_replace *repl; + int ret; + + if (net->ipv6.ip6table_security) + return 0; repl = ip6t_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; - net->ipv6.ip6table_security = - ip6t_register_table(net, &security_table, repl); + ret = ip6t_register_table(net, &security_table, repl, sectbl_ops, + &net->ipv6.ip6table_security); kfree(repl); - return PTR_ERR_OR_ZERO(net->ipv6.ip6table_security); + return ret; } static void __net_exit ip6table_security_net_exit(struct net *net) { - ip6t_unregister_table(net, net->ipv6.ip6table_security); + if (!net->ipv6.ip6table_security) + return; + ip6t_unregister_table(net, net->ipv6.ip6table_security, sectbl_ops); + net->ipv6.ip6table_security = NULL; } static struct pernet_operations ip6table_security_net_ops = { - .init = ip6table_security_net_init, .exit = ip6table_security_net_exit, }; @@ -71,27 +80,28 @@ static int __init ip6table_security_init(void) { int ret; + sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook); + if (IS_ERR(sectbl_ops)) + return PTR_ERR(sectbl_ops); + ret = register_pernet_subsys(&ip6table_security_net_ops); - if (ret < 0) + if (ret < 0) { + kfree(sectbl_ops); return ret; - - sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook); - if (IS_ERR(sectbl_ops)) { - ret = PTR_ERR(sectbl_ops); - goto cleanup_table; } - return ret; - -cleanup_table: - unregister_pernet_subsys(&ip6table_security_net_ops); + ret = ip6table_security_table_init(&init_net); + if (ret) { + unregister_pernet_subsys(&ip6table_security_net_ops); + kfree(sectbl_ops); + } return ret; } static void __exit ip6table_security_fini(void) { - xt_hook_unlink(&security_table, sectbl_ops); unregister_pernet_subsys(&ip6table_security_net_ops); + kfree(sectbl_ops); } module_init(ip6table_security_init); diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index cd1ac1637a05..9597ffb74077 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -26,7 +26,12 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; - + if (priv->sreg_proto_min) { + range.min_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_min]; + range.max_proto.all = + *(__be16 *)®s->data[priv->sreg_proto_max]; + } regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 0711f8fe4d44..fd25e447a5fa 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -922,11 +922,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ + /* a return value > 0 means to resubmit the input */ if (ret > 0) - return -ret; + return ret; return 0; } diff --git a/net/kcm/Kconfig b/net/kcm/Kconfig new file mode 100644 index 000000000000..5db94d940ecc --- /dev/null +++ b/net/kcm/Kconfig @@ -0,0 +1,10 @@ + +config AF_KCM + tristate "KCM sockets" + depends on INET + select BPF_SYSCALL + ---help--- + KCM (Kernel Connection Multiplexor) sockets provide a method + for multiplexing messages of a message based application + protocol over kernel connectons (e.g. TCP connections). + diff --git a/net/kcm/Makefile b/net/kcm/Makefile new file mode 100644 index 000000000000..71256133e677 --- /dev/null +++ b/net/kcm/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_AF_KCM) += kcm.o + +kcm-y := kcmsock.o kcmproc.o diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c new file mode 100644 index 000000000000..738008726cc6 --- /dev/null +++ b/net/kcm/kcmproc.c @@ -0,0 +1,426 @@ +#include <linux/in.h> +#include <linux/inet.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/net.h> +#include <linux/proc_fs.h> +#include <linux/rculist.h> +#include <linux/seq_file.h> +#include <linux/socket.h> +#include <net/inet_sock.h> +#include <net/kcm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/tcp.h> + +#ifdef CONFIG_PROC_FS +struct kcm_seq_muxinfo { + char *name; + const struct file_operations *seq_fops; + const struct seq_operations seq_ops; +}; + +static struct kcm_mux *kcm_get_first(struct seq_file *seq) +{ + struct net *net = seq_file_net(seq); + struct kcm_net *knet = net_generic(net, kcm_net_id); + + return list_first_or_null_rcu(&knet->mux_list, + struct kcm_mux, kcm_mux_list); +} + +static struct kcm_mux *kcm_get_next(struct kcm_mux *mux) +{ + struct kcm_net *knet = mux->knet; + + return list_next_or_null_rcu(&knet->mux_list, &mux->kcm_mux_list, + struct kcm_mux, kcm_mux_list); +} + +static struct kcm_mux *kcm_get_idx(struct seq_file *seq, loff_t pos) +{ + struct net *net = seq_file_net(seq); + struct kcm_net *knet = net_generic(net, kcm_net_id); + struct kcm_mux *m; + + list_for_each_entry_rcu(m, &knet->mux_list, kcm_mux_list) { + if (!pos) + return m; + --pos; + } + return NULL; +} + +static void *kcm_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + void *p; + + if (v == SEQ_START_TOKEN) + p = kcm_get_first(seq); + else + p = kcm_get_next(v); + ++*pos; + return p; +} + +static void *kcm_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu) +{ + rcu_read_lock(); + + if (!*pos) + return SEQ_START_TOKEN; + else + return kcm_get_idx(seq, *pos - 1); +} + +static void kcm_seq_stop(struct seq_file *seq, void *v) + __releases(rcu) +{ + rcu_read_unlock(); +} + +struct kcm_proc_mux_state { + struct seq_net_private p; + int idx; +}; + +static int kcm_seq_open(struct inode *inode, struct file *file) +{ + struct kcm_seq_muxinfo *muxinfo = PDE_DATA(inode); + int err; + + err = seq_open_net(inode, file, &muxinfo->seq_ops, + sizeof(struct kcm_proc_mux_state)); + if (err < 0) + return err; + return err; +} + +static void kcm_format_mux_header(struct seq_file *seq) +{ + struct net *net = seq_file_net(seq); + struct kcm_net *knet = net_generic(net, kcm_net_id); + + seq_printf(seq, + "*** KCM statistics (%d MUX) ****\n", + knet->count); + + seq_printf(seq, + "%-14s %-10s %-16s %-10s %-16s %-8s %-8s %-8s %-8s %s", + "Object", + "RX-Msgs", + "RX-Bytes", + "TX-Msgs", + "TX-Bytes", + "Recv-Q", + "Rmem", + "Send-Q", + "Smem", + "Status"); + + /* XXX: pdsts header stuff here */ + seq_puts(seq, "\n"); +} + +static void kcm_format_sock(struct kcm_sock *kcm, struct seq_file *seq, + int i, int *len) +{ + seq_printf(seq, + " kcm-%-7u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8s ", + kcm->index, + kcm->stats.rx_msgs, + kcm->stats.rx_bytes, + kcm->stats.tx_msgs, + kcm->stats.tx_bytes, + kcm->sk.sk_receive_queue.qlen, + sk_rmem_alloc_get(&kcm->sk), + kcm->sk.sk_write_queue.qlen, + "-"); + + if (kcm->tx_psock) + seq_printf(seq, "Psck-%u ", kcm->tx_psock->index); + + if (kcm->tx_wait) + seq_puts(seq, "TxWait "); + + if (kcm->tx_wait_more) + seq_puts(seq, "WMore "); + + if (kcm->rx_wait) + seq_puts(seq, "RxWait "); + + seq_puts(seq, "\n"); +} + +static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, + int i, int *len) +{ + seq_printf(seq, + " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ", + psock->index, + psock->stats.rx_msgs, + psock->stats.rx_bytes, + psock->stats.tx_msgs, + psock->stats.tx_bytes, + psock->sk->sk_receive_queue.qlen, + atomic_read(&psock->sk->sk_rmem_alloc), + psock->sk->sk_write_queue.qlen, + atomic_read(&psock->sk->sk_wmem_alloc)); + + if (psock->done) + seq_puts(seq, "Done "); + + if (psock->tx_stopped) + seq_puts(seq, "TxStop "); + + if (psock->rx_stopped) + seq_puts(seq, "RxStop "); + + if (psock->tx_kcm) + seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index); + + if (psock->ready_rx_msg) + seq_puts(seq, "RdyRx "); + + seq_puts(seq, "\n"); +} + +static void +kcm_format_mux(struct kcm_mux *mux, loff_t idx, struct seq_file *seq) +{ + int i, len; + struct kcm_sock *kcm; + struct kcm_psock *psock; + + /* mux information */ + seq_printf(seq, + "%-6s%-8s %-10llu %-16llu %-10llu %-16llu %-8s %-8s %-8s %-8s ", + "mux", "", + mux->stats.rx_msgs, + mux->stats.rx_bytes, + mux->stats.tx_msgs, + mux->stats.tx_bytes, + "-", "-", "-", "-"); + + seq_printf(seq, "KCMs: %d, Psocks %d\n", + mux->kcm_socks_cnt, mux->psocks_cnt); + + /* kcm sock information */ + i = 0; + spin_lock_bh(&mux->lock); + list_for_each_entry(kcm, &mux->kcm_socks, kcm_sock_list) { + kcm_format_sock(kcm, seq, i, &len); + i++; + } + i = 0; + list_for_each_entry(psock, &mux->psocks, psock_list) { + kcm_format_psock(psock, seq, i, &len); + i++; + } + spin_unlock_bh(&mux->lock); +} + +static int kcm_seq_show(struct seq_file *seq, void *v) +{ + struct kcm_proc_mux_state *mux_state; + + mux_state = seq->private; + if (v == SEQ_START_TOKEN) { + mux_state->idx = 0; + kcm_format_mux_header(seq); + } else { + kcm_format_mux(v, mux_state->idx, seq); + mux_state->idx++; + } + return 0; +} + +static const struct file_operations kcm_seq_fops = { + .owner = THIS_MODULE, + .open = kcm_seq_open, + .read = seq_read, + .llseek = seq_lseek, +}; + +static struct kcm_seq_muxinfo kcm_seq_muxinfo = { + .name = "kcm", + .seq_fops = &kcm_seq_fops, + .seq_ops = { + .show = kcm_seq_show, + .start = kcm_seq_start, + .next = kcm_seq_next, + .stop = kcm_seq_stop, + } +}; + +static int kcm_proc_register(struct net *net, struct kcm_seq_muxinfo *muxinfo) +{ + struct proc_dir_entry *p; + int rc = 0; + + p = proc_create_data(muxinfo->name, S_IRUGO, net->proc_net, + muxinfo->seq_fops, muxinfo); + if (!p) + rc = -ENOMEM; + return rc; +} +EXPORT_SYMBOL(kcm_proc_register); + +static void kcm_proc_unregister(struct net *net, + struct kcm_seq_muxinfo *muxinfo) +{ + remove_proc_entry(muxinfo->name, net->proc_net); +} +EXPORT_SYMBOL(kcm_proc_unregister); + +static int kcm_stats_seq_show(struct seq_file *seq, void *v) +{ + struct kcm_psock_stats psock_stats; + struct kcm_mux_stats mux_stats; + struct kcm_mux *mux; + struct kcm_psock *psock; + struct net *net = seq->private; + struct kcm_net *knet = net_generic(net, kcm_net_id); + + memset(&mux_stats, 0, sizeof(mux_stats)); + memset(&psock_stats, 0, sizeof(psock_stats)); + + mutex_lock(&knet->mutex); + + aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats); + aggregate_psock_stats(&knet->aggregate_psock_stats, + &psock_stats); + + list_for_each_entry_rcu(mux, &knet->mux_list, kcm_mux_list) { + spin_lock_bh(&mux->lock); + aggregate_mux_stats(&mux->stats, &mux_stats); + aggregate_psock_stats(&mux->aggregate_psock_stats, + &psock_stats); + list_for_each_entry(psock, &mux->psocks, psock_list) + aggregate_psock_stats(&psock->stats, &psock_stats); + spin_unlock_bh(&mux->lock); + } + + mutex_unlock(&knet->mutex); + + seq_printf(seq, + "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s\n", + "MUX", + "RX-Msgs", + "RX-Bytes", + "TX-Msgs", + "TX-Bytes", + "TX-Retries", + "Attach", + "Unattach", + "UnattchRsvd", + "RX-RdyDrops"); + + seq_printf(seq, + "%-8s %-10llu %-16llu %-10llu %-16llu %-10u %-10u %-10u %-10u %-10u\n", + "", + mux_stats.rx_msgs, + mux_stats.rx_bytes, + mux_stats.tx_msgs, + mux_stats.tx_bytes, + mux_stats.tx_retries, + mux_stats.psock_attach, + mux_stats.psock_unattach_rsvd, + mux_stats.psock_unattach, + mux_stats.rx_ready_drops); + + seq_printf(seq, + "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", + "Psock", + "RX-Msgs", + "RX-Bytes", + "TX-Msgs", + "TX-Bytes", + "Reserved", + "Unreserved", + "RX-Aborts", + "RX-MemFail", + "RX-NeedMor", + "RX-BadLen", + "RX-TooBig", + "RX-Timeout", + "TX-Aborts"); + + seq_printf(seq, + "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n", + "", + psock_stats.rx_msgs, + psock_stats.rx_bytes, + psock_stats.tx_msgs, + psock_stats.tx_bytes, + psock_stats.reserved, + psock_stats.unreserved, + psock_stats.rx_aborts, + psock_stats.rx_mem_fail, + psock_stats.rx_need_more_hdr, + psock_stats.rx_bad_hdr_len, + psock_stats.rx_msg_too_big, + psock_stats.rx_msg_timeouts, + psock_stats.tx_aborts); + + return 0; +} + +static int kcm_stats_seq_open(struct inode *inode, struct file *file) +{ + return single_open_net(inode, file, kcm_stats_seq_show); +} + +static const struct file_operations kcm_stats_seq_fops = { + .owner = THIS_MODULE, + .open = kcm_stats_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release_net, +}; + +static int kcm_proc_init_net(struct net *net) +{ + int err; + + if (!proc_create("kcm_stats", S_IRUGO, net->proc_net, + &kcm_stats_seq_fops)) { + err = -ENOMEM; + goto out_kcm_stats; + } + + err = kcm_proc_register(net, &kcm_seq_muxinfo); + if (err) + goto out_kcm; + + return 0; + +out_kcm: + remove_proc_entry("kcm_stats", net->proc_net); +out_kcm_stats: + return err; +} + +static void kcm_proc_exit_net(struct net *net) +{ + kcm_proc_unregister(net, &kcm_seq_muxinfo); + remove_proc_entry("kcm_stats", net->proc_net); +} + +static struct pernet_operations kcm_net_ops = { + .init = kcm_proc_init_net, + .exit = kcm_proc_exit_net, +}; + +int __init kcm_proc_init(void) +{ + return register_pernet_subsys(&kcm_net_ops); +} + +void __exit kcm_proc_exit(void) +{ + unregister_pernet_subsys(&kcm_net_ops); +} + +#endif /* CONFIG_PROC_FS */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c new file mode 100644 index 000000000000..40662d73204f --- /dev/null +++ b/net/kcm/kcmsock.c @@ -0,0 +1,2409 @@ +#include <linux/bpf.h> +#include <linux/errno.h> +#include <linux/errqueue.h> +#include <linux/file.h> +#include <linux/in.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/poll.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/uaccess.h> +#include <linux/workqueue.h> +#include <net/kcm.h> +#include <net/netns/generic.h> +#include <net/sock.h> +#include <net/tcp.h> +#include <uapi/linux/kcm.h> + +unsigned int kcm_net_id; + +static struct kmem_cache *kcm_psockp __read_mostly; +static struct kmem_cache *kcm_muxp __read_mostly; +static struct workqueue_struct *kcm_wq; + +static inline struct kcm_sock *kcm_sk(const struct sock *sk) +{ + return (struct kcm_sock *)sk; +} + +static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) +{ + return (struct kcm_tx_msg *)skb->cb; +} + +static inline struct kcm_rx_msg *kcm_rx_msg(struct sk_buff *skb) +{ + return (struct kcm_rx_msg *)((void *)skb->cb + + offsetof(struct qdisc_skb_cb, data)); +} + +static void report_csk_error(struct sock *csk, int err) +{ + csk->sk_err = EPIPE; + csk->sk_error_report(csk); +} + +/* Callback lock held */ +static void kcm_abort_rx_psock(struct kcm_psock *psock, int err, + struct sk_buff *skb) +{ + struct sock *csk = psock->sk; + + /* Unrecoverable error in receive */ + + del_timer(&psock->rx_msg_timer); + + if (psock->rx_stopped) + return; + + psock->rx_stopped = 1; + KCM_STATS_INCR(psock->stats.rx_aborts); + + /* Report an error on the lower socket */ + report_csk_error(csk, err); +} + +static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, + bool wakeup_kcm) +{ + struct sock *csk = psock->sk; + struct kcm_mux *mux = psock->mux; + + /* Unrecoverable error in transmit */ + + spin_lock_bh(&mux->lock); + + if (psock->tx_stopped) { + spin_unlock_bh(&mux->lock); + return; + } + + psock->tx_stopped = 1; + KCM_STATS_INCR(psock->stats.tx_aborts); + + if (!psock->tx_kcm) { + /* Take off psocks_avail list */ + list_del(&psock->psock_avail_list); + } else if (wakeup_kcm) { + /* In this case psock is being aborted while outside of + * write_msgs and psock is reserved. Schedule tx_work + * to handle the failure there. Need to commit tx_stopped + * before queuing work. + */ + smp_mb(); + + queue_work(kcm_wq, &psock->tx_kcm->tx_work); + } + + spin_unlock_bh(&mux->lock); + + /* Report error on lower socket */ + report_csk_error(csk, err); +} + +/* RX mux lock held. */ +static void kcm_update_rx_mux_stats(struct kcm_mux *mux, + struct kcm_psock *psock) +{ + KCM_STATS_ADD(mux->stats.rx_bytes, + psock->stats.rx_bytes - psock->saved_rx_bytes); + mux->stats.rx_msgs += + psock->stats.rx_msgs - psock->saved_rx_msgs; + psock->saved_rx_msgs = psock->stats.rx_msgs; + psock->saved_rx_bytes = psock->stats.rx_bytes; +} + +static void kcm_update_tx_mux_stats(struct kcm_mux *mux, + struct kcm_psock *psock) +{ + KCM_STATS_ADD(mux->stats.tx_bytes, + psock->stats.tx_bytes - psock->saved_tx_bytes); + mux->stats.tx_msgs += + psock->stats.tx_msgs - psock->saved_tx_msgs; + psock->saved_tx_msgs = psock->stats.tx_msgs; + psock->saved_tx_bytes = psock->stats.tx_bytes; +} + +static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +/* KCM is ready to receive messages on its queue-- either the KCM is new or + * has become unblocked after being blocked on full socket buffer. Queue any + * pending ready messages on a psock. RX mux lock held. + */ +static void kcm_rcv_ready(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + struct sk_buff *skb; + + if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled)) + return; + + while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) { + if (kcm_queue_rcv_skb(&kcm->sk, skb)) { + /* Assuming buffer limit has been reached */ + skb_queue_head(&mux->rx_hold_queue, skb); + WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); + return; + } + } + + while (!list_empty(&mux->psocks_ready)) { + psock = list_first_entry(&mux->psocks_ready, struct kcm_psock, + psock_ready_list); + + if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) { + /* Assuming buffer limit has been reached */ + WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); + return; + } + + /* Consumed the ready message on the psock. Schedule rx_work to + * get more messages. + */ + list_del(&psock->psock_ready_list); + psock->ready_rx_msg = NULL; + + /* Commit clearing of ready_rx_msg for queuing work */ + smp_mb(); + + queue_work(kcm_wq, &psock->rx_work); + } + + /* Buffer limit is okay now, add to ready list */ + list_add_tail(&kcm->wait_rx_list, + &kcm->mux->kcm_rx_waiters); + kcm->rx_wait = true; +} + +static void kcm_rfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct kcm_sock *kcm = kcm_sk(sk); + struct kcm_mux *mux = kcm->mux; + unsigned int len = skb->truesize; + + sk_mem_uncharge(sk, len); + atomic_sub(len, &sk->sk_rmem_alloc); + + /* For reading rx_wait and rx_psock without holding lock */ + smp_mb__after_atomic(); + + if (!kcm->rx_wait && !kcm->rx_psock && + sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { + spin_lock_bh(&mux->rx_lock); + kcm_rcv_ready(kcm); + spin_unlock_bh(&mux->rx_lock); + } +} + +static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + struct sk_buff_head *list = &sk->sk_receive_queue; + + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + return -ENOMEM; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return -ENOBUFS; + + skb->dev = NULL; + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = kcm_rfree; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_charge(sk, skb->truesize); + + skb_queue_tail(list, skb); + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk); + + return 0; +} + +/* Requeue received messages for a kcm socket to other kcm sockets. This is + * called with a kcm socket is receive disabled. + * RX mux lock held. + */ +static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) +{ + struct sk_buff *skb; + struct kcm_sock *kcm; + + while ((skb = __skb_dequeue(head))) { + /* Reset destructor to avoid calling kcm_rcv_ready */ + skb->destructor = sock_rfree; + skb_orphan(skb); +try_again: + if (list_empty(&mux->kcm_rx_waiters)) { + skb_queue_tail(&mux->rx_hold_queue, skb); + continue; + } + + kcm = list_first_entry(&mux->kcm_rx_waiters, + struct kcm_sock, wait_rx_list); + + if (kcm_queue_rcv_skb(&kcm->sk, skb)) { + /* Should mean socket buffer full */ + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + + /* Commit rx_wait to read in kcm_free */ + smp_wmb(); + + goto try_again; + } + } +} + +/* Lower sock lock held */ +static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, + struct sk_buff *head) +{ + struct kcm_mux *mux = psock->mux; + struct kcm_sock *kcm; + + WARN_ON(psock->ready_rx_msg); + + if (psock->rx_kcm) + return psock->rx_kcm; + + spin_lock_bh(&mux->rx_lock); + + if (psock->rx_kcm) { + spin_unlock_bh(&mux->rx_lock); + return psock->rx_kcm; + } + + kcm_update_rx_mux_stats(mux, psock); + + if (list_empty(&mux->kcm_rx_waiters)) { + psock->ready_rx_msg = head; + list_add_tail(&psock->psock_ready_list, + &mux->psocks_ready); + spin_unlock_bh(&mux->rx_lock); + return NULL; + } + + kcm = list_first_entry(&mux->kcm_rx_waiters, + struct kcm_sock, wait_rx_list); + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + + psock->rx_kcm = kcm; + kcm->rx_psock = psock; + + spin_unlock_bh(&mux->rx_lock); + + return kcm; +} + +static void kcm_done(struct kcm_sock *kcm); + +static void kcm_done_work(struct work_struct *w) +{ + kcm_done(container_of(w, struct kcm_sock, done_work)); +} + +/* Lower sock held */ +static void unreserve_rx_kcm(struct kcm_psock *psock, + bool rcv_ready) +{ + struct kcm_sock *kcm = psock->rx_kcm; + struct kcm_mux *mux = psock->mux; + + if (!kcm) + return; + + spin_lock_bh(&mux->rx_lock); + + psock->rx_kcm = NULL; + kcm->rx_psock = NULL; + + /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with + * kcm_rfree + */ + smp_mb(); + + if (unlikely(kcm->done)) { + spin_unlock_bh(&mux->rx_lock); + + /* Need to run kcm_done in a task since we need to qcquire + * callback locks which may already be held here. + */ + INIT_WORK(&kcm->done_work, kcm_done_work); + schedule_work(&kcm->done_work); + return; + } + + if (unlikely(kcm->rx_disabled)) { + requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); + } else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) { + /* Check for degenerative race with rx_wait that all + * data was dequeued (accounted for in kcm_rfree). + */ + kcm_rcv_ready(kcm); + } + spin_unlock_bh(&mux->rx_lock); +} + +static void kcm_start_rx_timer(struct kcm_psock *psock) +{ + if (psock->sk->sk_rcvtimeo) + mod_timer(&psock->rx_msg_timer, psock->sk->sk_rcvtimeo); +} + +/* Macro to invoke filter function. */ +#define KCM_RUN_FILTER(prog, ctx) \ + (*prog->bpf_func)(ctx, prog->insnsi) + +/* Lower socket lock held */ +static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, + unsigned int orig_offset, size_t orig_len) +{ + struct kcm_psock *psock = (struct kcm_psock *)desc->arg.data; + struct kcm_rx_msg *rxm; + struct kcm_sock *kcm; + struct sk_buff *head, *skb; + size_t eaten = 0, cand_len; + ssize_t extra; + int err; + bool cloned_orig = false; + + if (psock->ready_rx_msg) + return 0; + + head = psock->rx_skb_head; + if (head) { + /* Message already in progress */ + + rxm = kcm_rx_msg(head); + if (unlikely(rxm->early_eaten)) { + /* Already some number of bytes on the receive sock + * data saved in rx_skb_head, just indicate they + * are consumed. + */ + eaten = orig_len <= rxm->early_eaten ? + orig_len : rxm->early_eaten; + rxm->early_eaten -= eaten; + + return eaten; + } + + if (unlikely(orig_offset)) { + /* Getting data with a non-zero offset when a message is + * in progress is not expected. If it does happen, we + * need to clone and pull since we can't deal with + * offsets in the skbs for a message expect in the head. + */ + orig_skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!orig_skb) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); + desc->error = -ENOMEM; + return 0; + } + if (!pskb_pull(orig_skb, orig_offset)) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); + kfree_skb(orig_skb); + desc->error = -ENOMEM; + return 0; + } + cloned_orig = true; + orig_offset = 0; + } + + if (!psock->rx_skb_nextp) { + /* We are going to append to the frags_list of head. + * Need to unshare the frag_list. + */ + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); + desc->error = err; + return 0; + } + + if (unlikely(skb_shinfo(head)->frag_list)) { + /* We can't append to an sk_buff that already + * has a frag_list. We create a new head, point + * the frag_list of that to the old head, and + * then are able to use the old head->next for + * appending to the message. + */ + if (WARN_ON(head->next)) { + desc->error = -EINVAL; + return 0; + } + + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); + desc->error = -ENOMEM; + return 0; + } + skb->len = head->len; + skb->data_len = head->len; + skb->truesize = head->truesize; + *kcm_rx_msg(skb) = *kcm_rx_msg(head); + psock->rx_skb_nextp = &head->next; + skb_shinfo(skb)->frag_list = head; + psock->rx_skb_head = skb; + head = skb; + } else { + psock->rx_skb_nextp = + &skb_shinfo(head)->frag_list; + } + } + } + + while (eaten < orig_len) { + /* Always clone since we will consume something */ + skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!skb) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); + desc->error = -ENOMEM; + break; + } + + cand_len = orig_len - eaten; + + head = psock->rx_skb_head; + if (!head) { + head = skb; + psock->rx_skb_head = head; + /* Will set rx_skb_nextp on next packet if needed */ + psock->rx_skb_nextp = NULL; + rxm = kcm_rx_msg(head); + memset(rxm, 0, sizeof(*rxm)); + rxm->offset = orig_offset + eaten; + } else { + /* Unclone since we may be appending to an skb that we + * already share a frag_list with. + */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) { + KCM_STATS_INCR(psock->stats.rx_mem_fail); + desc->error = err; + break; + } + + rxm = kcm_rx_msg(head); + *psock->rx_skb_nextp = skb; + psock->rx_skb_nextp = &skb->next; + head->data_len += skb->len; + head->len += skb->len; + head->truesize += skb->truesize; + } + + if (!rxm->full_len) { + ssize_t len; + + len = KCM_RUN_FILTER(psock->bpf_prog, head); + + if (!len) { + /* Need more header to determine length */ + if (!rxm->accum_len) { + /* Start RX timer for new message */ + kcm_start_rx_timer(psock); + } + rxm->accum_len += cand_len; + eaten += cand_len; + KCM_STATS_INCR(psock->stats.rx_need_more_hdr); + WARN_ON(eaten != orig_len); + break; + } else if (len > psock->sk->sk_rcvbuf) { + /* Message length exceeds maximum allowed */ + KCM_STATS_INCR(psock->stats.rx_msg_too_big); + desc->error = -EMSGSIZE; + psock->rx_skb_head = NULL; + kcm_abort_rx_psock(psock, EMSGSIZE, head); + break; + } else if (len <= (ssize_t)head->len - + skb->len - rxm->offset) { + /* Length must be into new skb (and also + * greater than zero) + */ + KCM_STATS_INCR(psock->stats.rx_bad_hdr_len); + desc->error = -EPROTO; + psock->rx_skb_head = NULL; + kcm_abort_rx_psock(psock, EPROTO, head); + break; + } + + rxm->full_len = len; + } + + extra = (ssize_t)(rxm->accum_len + cand_len) - rxm->full_len; + + if (extra < 0) { + /* Message not complete yet. */ + if (rxm->full_len - rxm->accum_len > + tcp_inq(psock->sk)) { + /* Don't have the whole messages in the socket + * buffer. Set psock->rx_need_bytes to wait for + * the rest of the message. Also, set "early + * eaten" since we've already buffered the skb + * but don't consume yet per tcp_read_sock. + */ + + if (!rxm->accum_len) { + /* Start RX timer for new message */ + kcm_start_rx_timer(psock); + } + + psock->rx_need_bytes = rxm->full_len - + rxm->accum_len; + rxm->accum_len += cand_len; + rxm->early_eaten = cand_len; + KCM_STATS_ADD(psock->stats.rx_bytes, cand_len); + desc->count = 0; /* Stop reading socket */ + break; + } + rxm->accum_len += cand_len; + eaten += cand_len; + WARN_ON(eaten != orig_len); + break; + } + + /* Positive extra indicates ore bytes than needed for the + * message + */ + + WARN_ON(extra > cand_len); + + eaten += (cand_len - extra); + + /* Hurray, we have a new message! */ + del_timer(&psock->rx_msg_timer); + psock->rx_skb_head = NULL; + KCM_STATS_INCR(psock->stats.rx_msgs); + +try_queue: + kcm = reserve_rx_kcm(psock, head); + if (!kcm) { + /* Unable to reserve a KCM, message is held in psock. */ + break; + } + + if (kcm_queue_rcv_skb(&kcm->sk, head)) { + /* Should mean socket buffer full */ + unreserve_rx_kcm(psock, false); + goto try_queue; + } + } + + if (cloned_orig) + kfree_skb(orig_skb); + + KCM_STATS_ADD(psock->stats.rx_bytes, eaten); + + return eaten; +} + +/* Called with lock held on lower socket */ +static int psock_tcp_read_sock(struct kcm_psock *psock) +{ + read_descriptor_t desc; + + desc.arg.data = psock; + desc.error = 0; + desc.count = 1; /* give more than one skb per call */ + + /* sk should be locked here, so okay to do tcp_read_sock */ + tcp_read_sock(psock->sk, &desc, kcm_tcp_recv); + + unreserve_rx_kcm(psock, true); + + return desc.error; +} + +/* Lower sock lock held */ +static void psock_tcp_data_ready(struct sock *sk) +{ + struct kcm_psock *psock; + + read_lock_bh(&sk->sk_callback_lock); + + psock = (struct kcm_psock *)sk->sk_user_data; + if (unlikely(!psock || psock->rx_stopped)) + goto out; + + if (psock->ready_rx_msg) + goto out; + + if (psock->rx_need_bytes) { + if (tcp_inq(sk) >= psock->rx_need_bytes) + psock->rx_need_bytes = 0; + else + goto out; + } + + if (psock_tcp_read_sock(psock) == -ENOMEM) + queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); + +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static void do_psock_rx_work(struct kcm_psock *psock) +{ + read_descriptor_t rd_desc; + struct sock *csk = psock->sk; + + /* We need the read lock to synchronize with psock_tcp_data_ready. We + * need the socket lock for calling tcp_read_sock. + */ + lock_sock(csk); + read_lock_bh(&csk->sk_callback_lock); + + if (unlikely(csk->sk_user_data != psock)) + goto out; + + if (unlikely(psock->rx_stopped)) + goto out; + + if (psock->ready_rx_msg) + goto out; + + rd_desc.arg.data = psock; + + if (psock_tcp_read_sock(psock) == -ENOMEM) + queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); + +out: + read_unlock_bh(&csk->sk_callback_lock); + release_sock(csk); +} + +static void psock_rx_work(struct work_struct *w) +{ + do_psock_rx_work(container_of(w, struct kcm_psock, rx_work)); +} + +static void psock_rx_delayed_work(struct work_struct *w) +{ + do_psock_rx_work(container_of(w, struct kcm_psock, + rx_delayed_work.work)); +} + +static void psock_tcp_state_change(struct sock *sk) +{ + /* TCP only does a POLLIN for a half close. Do a POLLHUP here + * since application will normally not poll with POLLIN + * on the TCP sockets. + */ + + report_csk_error(sk, EPIPE); +} + +static void psock_tcp_write_space(struct sock *sk) +{ + struct kcm_psock *psock; + struct kcm_mux *mux; + struct kcm_sock *kcm; + + read_lock_bh(&sk->sk_callback_lock); + + psock = (struct kcm_psock *)sk->sk_user_data; + if (unlikely(!psock)) + goto out; + + mux = psock->mux; + + spin_lock_bh(&mux->lock); + + /* Check if the socket is reserved so someone is waiting for sending. */ + kcm = psock->tx_kcm; + if (kcm) + queue_work(kcm_wq, &kcm->tx_work); + + spin_unlock_bh(&mux->lock); +out: + read_unlock_bh(&sk->sk_callback_lock); +} + +static void unreserve_psock(struct kcm_sock *kcm); + +/* kcm sock is locked. */ +static struct kcm_psock *reserve_psock(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + + psock = kcm->tx_psock; + + smp_rmb(); /* Must read tx_psock before tx_wait */ + + if (psock) { + WARN_ON(kcm->tx_wait); + if (unlikely(psock->tx_stopped)) + unreserve_psock(kcm); + else + return kcm->tx_psock; + } + + spin_lock_bh(&mux->lock); + + /* Check again under lock to see if psock was reserved for this + * psock via psock_unreserve. + */ + psock = kcm->tx_psock; + if (unlikely(psock)) { + WARN_ON(kcm->tx_wait); + spin_unlock_bh(&mux->lock); + return kcm->tx_psock; + } + + if (!list_empty(&mux->psocks_avail)) { + psock = list_first_entry(&mux->psocks_avail, + struct kcm_psock, + psock_avail_list); + list_del(&psock->psock_avail_list); + if (kcm->tx_wait) { + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + } + kcm->tx_psock = psock; + psock->tx_kcm = kcm; + KCM_STATS_INCR(psock->stats.reserved); + } else if (!kcm->tx_wait) { + list_add_tail(&kcm->wait_psock_list, + &mux->kcm_tx_waiters); + kcm->tx_wait = true; + } + + spin_unlock_bh(&mux->lock); + + return psock; +} + +/* mux lock held */ +static void psock_now_avail(struct kcm_psock *psock) +{ + struct kcm_mux *mux = psock->mux; + struct kcm_sock *kcm; + + if (list_empty(&mux->kcm_tx_waiters)) { + list_add_tail(&psock->psock_avail_list, + &mux->psocks_avail); + } else { + kcm = list_first_entry(&mux->kcm_tx_waiters, + struct kcm_sock, + wait_psock_list); + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + psock->tx_kcm = kcm; + + /* Commit before changing tx_psock since that is read in + * reserve_psock before queuing work. + */ + smp_mb(); + + kcm->tx_psock = psock; + KCM_STATS_INCR(psock->stats.reserved); + queue_work(kcm_wq, &kcm->tx_work); + } +} + +/* kcm sock is locked. */ +static void unreserve_psock(struct kcm_sock *kcm) +{ + struct kcm_psock *psock; + struct kcm_mux *mux = kcm->mux; + + spin_lock_bh(&mux->lock); + + psock = kcm->tx_psock; + + if (WARN_ON(!psock)) { + spin_unlock_bh(&mux->lock); + return; + } + + smp_rmb(); /* Read tx_psock before tx_wait */ + + kcm_update_tx_mux_stats(mux, psock); + + WARN_ON(kcm->tx_wait); + + kcm->tx_psock = NULL; + psock->tx_kcm = NULL; + KCM_STATS_INCR(psock->stats.unreserved); + + if (unlikely(psock->tx_stopped)) { + if (psock->done) { + /* Deferred free */ + list_del(&psock->psock_list); + mux->psocks_cnt--; + sock_put(psock->sk); + fput(psock->sk->sk_socket->file); + kmem_cache_free(kcm_psockp, psock); + } + + /* Don't put back on available list */ + + spin_unlock_bh(&mux->lock); + + return; + } + + psock_now_avail(psock); + + spin_unlock_bh(&mux->lock); +} + +static void kcm_report_tx_retry(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + spin_lock_bh(&mux->lock); + KCM_STATS_INCR(mux->stats.tx_retries); + spin_unlock_bh(&mux->lock); +} + +/* Write any messages ready on the kcm socket. Called with kcm sock lock + * held. Return bytes actually sent or error. + */ +static int kcm_write_msgs(struct kcm_sock *kcm) +{ + struct sock *sk = &kcm->sk; + struct kcm_psock *psock; + struct sk_buff *skb, *head; + struct kcm_tx_msg *txm; + unsigned short fragidx, frag_offset; + unsigned int sent, total_sent = 0; + int ret = 0; + + kcm->tx_wait_more = false; + psock = kcm->tx_psock; + if (unlikely(psock && psock->tx_stopped)) { + /* A reserved psock was aborted asynchronously. Unreserve + * it and we'll retry the message. + */ + unreserve_psock(kcm); + kcm_report_tx_retry(kcm); + if (skb_queue_empty(&sk->sk_write_queue)) + return 0; + + kcm_tx_msg(skb_peek(&sk->sk_write_queue))->sent = 0; + + } else if (skb_queue_empty(&sk->sk_write_queue)) { + return 0; + } + + head = skb_peek(&sk->sk_write_queue); + txm = kcm_tx_msg(head); + + if (txm->sent) { + /* Send of first skbuff in queue already in progress */ + if (WARN_ON(!psock)) { + ret = -EINVAL; + goto out; + } + sent = txm->sent; + frag_offset = txm->frag_offset; + fragidx = txm->fragidx; + skb = txm->frag_skb; + + goto do_frag; + } + +try_again: + psock = reserve_psock(kcm); + if (!psock) + goto out; + + do { + skb = head; + txm = kcm_tx_msg(head); + sent = 0; + +do_frag_list: + if (WARN_ON(!skb_shinfo(skb)->nr_frags)) { + ret = -EINVAL; + goto out; + } + + for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; + fragidx++) { + skb_frag_t *frag; + + frag_offset = 0; +do_frag: + frag = &skb_shinfo(skb)->frags[fragidx]; + if (WARN_ON(!frag->size)) { + ret = -EINVAL; + goto out; + } + + ret = kernel_sendpage(psock->sk->sk_socket, + frag->page.p, + frag->page_offset + frag_offset, + frag->size - frag_offset, + MSG_DONTWAIT); + if (ret <= 0) { + if (ret == -EAGAIN) { + /* Save state to try again when there's + * write space on the socket + */ + txm->sent = sent; + txm->frag_offset = frag_offset; + txm->fragidx = fragidx; + txm->frag_skb = skb; + + ret = 0; + goto out; + } + + /* Hard failure in sending message, abort this + * psock since it has lost framing + * synchonization and retry sending the + * message from the beginning. + */ + kcm_abort_tx_psock(psock, ret ? -ret : EPIPE, + true); + unreserve_psock(kcm); + + txm->sent = 0; + kcm_report_tx_retry(kcm); + ret = 0; + + goto try_again; + } + + sent += ret; + frag_offset += ret; + KCM_STATS_ADD(psock->stats.tx_bytes, ret); + if (frag_offset < frag->size) { + /* Not finished with this frag */ + goto do_frag; + } + } + + if (skb == head) { + if (skb_has_frag_list(skb)) { + skb = skb_shinfo(skb)->frag_list; + goto do_frag_list; + } + } else if (skb->next) { + skb = skb->next; + goto do_frag_list; + } + + /* Successfully sent the whole packet, account for it. */ + skb_dequeue(&sk->sk_write_queue); + kfree_skb(head); + sk->sk_wmem_queued -= sent; + total_sent += sent; + KCM_STATS_INCR(psock->stats.tx_msgs); + } while ((head = skb_peek(&sk->sk_write_queue))); +out: + if (!head) { + /* Done with all queued messages. */ + WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); + unreserve_psock(kcm); + } + + /* Check if write space is available */ + sk->sk_write_space(sk); + + return total_sent ? : ret; +} + +static void kcm_tx_work(struct work_struct *w) +{ + struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work); + struct sock *sk = &kcm->sk; + int err; + + lock_sock(sk); + + /* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx + * aborts + */ + err = kcm_write_msgs(kcm); + if (err < 0) { + /* Hard failure in write, report error on KCM socket */ + pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err); + report_csk_error(&kcm->sk, -err); + goto out; + } + + /* Primarily for SOCK_SEQPACKET sockets */ + if (likely(sk->sk_socket) && + test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + sk->sk_write_space(sk); + } + +out: + release_sock(sk); +} + +static void kcm_push(struct kcm_sock *kcm) +{ + if (kcm->tx_wait_more) + kcm_write_msgs(kcm); +} + +static ssize_t kcm_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, int flags) + +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); + struct sk_buff *skb = NULL, *head = NULL; + long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + bool eor; + int err = 0; + int i; + + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + + /* No MSG_EOR from splice, only look at MSG_MORE */ + eor = !(flags & MSG_MORE); + + lock_sock(sk); + + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + err = -EPIPE; + if (sk->sk_err) + goto out_error; + + if (kcm->seq_skb) { + /* Previously opened message */ + head = kcm->seq_skb; + skb = kcm_tx_msg(head)->last_skb; + i = skb_shinfo(skb)->nr_frags; + + if (skb_can_coalesce(skb, i, page, offset)) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + goto coalesced; + } + + if (i >= MAX_SKB_FRAGS) { + struct sk_buff *tskb; + + tskb = alloc_skb(0, sk->sk_allocation); + while (!tskb) { + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + if (head == skb) + skb_shinfo(head)->frag_list = tskb; + else + skb->next = tskb; + + skb = tskb; + skb->ip_summed = CHECKSUM_UNNECESSARY; + i = 0; + } + } else { + /* Call the sk_stream functions to manage the sndbuf mem. */ + if (!sk_stream_memory_free(sk)) { + kcm_push(kcm); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + head = alloc_skb(0, sk->sk_allocation); + while (!head) { + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + skb = head; + i = 0; + } + + get_page(page); + skb_fill_page_desc(skb, i, page, offset, size); + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + +coalesced: + skb->len += size; + skb->data_len += size; + skb->truesize += size; + sk->sk_wmem_queued += size; + sk_mem_charge(sk, size); + + if (head != skb) { + head->len += size; + head->data_len += size; + head->truesize += size; + } + + if (eor) { + bool not_busy = skb_queue_empty(&sk->sk_write_queue); + + /* Message complete, queue it on send buffer */ + __skb_queue_tail(&sk->sk_write_queue, head); + kcm->seq_skb = NULL; + KCM_STATS_INCR(kcm->stats.tx_msgs); + + if (flags & MSG_BATCH) { + kcm->tx_wait_more = true; + } else if (kcm->tx_wait_more || not_busy) { + err = kcm_write_msgs(kcm); + if (err < 0) { + /* We got a hard error in write_msgs but have + * already queued this message. Report an error + * in the socket, but don't affect return value + * from sendmsg + */ + pr_warn("KCM: Hard failure on kcm_write_msgs\n"); + report_csk_error(&kcm->sk, -err); + } + } + } else { + /* Message not complete, save state */ + kcm->seq_skb = head; + kcm_tx_msg(head)->last_skb = skb; + } + + KCM_STATS_ADD(kcm->stats.tx_bytes, size); + + release_sock(sk); + return size; + +out_error: + kcm_push(kcm); + + err = sk_stream_error(sk, flags, err); + + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); + + release_sock(sk); + return err; +} + +static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); + struct sk_buff *skb = NULL, *head = NULL; + size_t copy, copied = 0; + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + int eor = (sock->type == SOCK_DGRAM) ? + !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); + int err = -EPIPE; + + lock_sock(sk); + + /* Per tcp_sendmsg this should be in poll */ + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + if (sk->sk_err) + goto out_error; + + if (kcm->seq_skb) { + /* Previously opened message */ + head = kcm->seq_skb; + skb = kcm_tx_msg(head)->last_skb; + goto start; + } + + /* Call the sk_stream functions to manage the sndbuf mem. */ + if (!sk_stream_memory_free(sk)) { + kcm_push(kcm); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + /* New message, alloc head skb */ + head = alloc_skb(0, sk->sk_allocation); + while (!head) { + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + + head = alloc_skb(0, sk->sk_allocation); + } + + skb = head; + + /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling + * csum_and_copy_from_iter from skb_do_copy_data_nocache. + */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + +start: + while (msg_data_left(msg)) { + bool merge = true; + int i = skb_shinfo(skb)->nr_frags; + struct page_frag *pfrag = sk_page_frag(sk); + + if (!sk_page_frag_refill(sk, pfrag)) + goto wait_for_memory; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + if (i == MAX_SKB_FRAGS) { + struct sk_buff *tskb; + + tskb = alloc_skb(0, sk->sk_allocation); + if (!tskb) + goto wait_for_memory; + + if (head == skb) + skb_shinfo(head)->frag_list = tskb; + else + skb->next = tskb; + + skb = tskb; + skb->ip_summed = CHECKSUM_UNNECESSARY; + continue; + } + merge = false; + } + + copy = min_t(int, msg_data_left(msg), + pfrag->size - pfrag->offset); + + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_memory; + + err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, + pfrag->page, + pfrag->offset, + copy); + if (err) + goto out_error; + + /* Update the skb. */ + if (merge) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); + } else { + skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, copy); + get_page(pfrag->page); + } + + pfrag->offset += copy; + copied += copy; + if (head != skb) { + head->len += copy; + head->data_len += copy; + } + + continue; + +wait_for_memory: + kcm_push(kcm); + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_error; + } + + if (eor) { + bool not_busy = skb_queue_empty(&sk->sk_write_queue); + + /* Message complete, queue it on send buffer */ + __skb_queue_tail(&sk->sk_write_queue, head); + kcm->seq_skb = NULL; + KCM_STATS_INCR(kcm->stats.tx_msgs); + + if (msg->msg_flags & MSG_BATCH) { + kcm->tx_wait_more = true; + } else if (kcm->tx_wait_more || not_busy) { + err = kcm_write_msgs(kcm); + if (err < 0) { + /* We got a hard error in write_msgs but have + * already queued this message. Report an error + * in the socket, but don't affect return value + * from sendmsg + */ + pr_warn("KCM: Hard failure on kcm_write_msgs\n"); + report_csk_error(&kcm->sk, -err); + } + } + } else { + /* Message not complete, save state */ +partial_message: + kcm->seq_skb = head; + kcm_tx_msg(head)->last_skb = skb; + } + + KCM_STATS_ADD(kcm->stats.tx_bytes, copied); + + release_sock(sk); + return copied; + +out_error: + kcm_push(kcm); + + if (copied && sock->type == SOCK_SEQPACKET) { + /* Wrote some bytes before encountering an + * error, return partial success. + */ + goto partial_message; + } + + if (head != kcm->seq_skb) + kfree_skb(head); + + err = sk_stream_error(sk, msg->msg_flags, err); + + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); + + release_sock(sk); + return err; +} + +static struct sk_buff *kcm_wait_data(struct sock *sk, int flags, + long timeo, int *err) +{ + struct sk_buff *skb; + + while (!(skb = skb_peek(&sk->sk_receive_queue))) { + if (sk->sk_err) { + *err = sock_error(sk); + return NULL; + } + + if (sock_flag(sk, SOCK_DONE)) + return NULL; + + if ((flags & MSG_DONTWAIT) || !timeo) { + *err = -EAGAIN; + return NULL; + } + + sk_wait_data(sk, &timeo, NULL); + + /* Handle signals */ + if (signal_pending(current)) { + *err = sock_intr_errno(timeo); + return NULL; + } + } + + return skb; +} + +static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); + int err = 0; + long timeo; + struct kcm_rx_msg *rxm; + int copied = 0; + struct sk_buff *skb; + + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + + lock_sock(sk); + + skb = kcm_wait_data(sk, flags, timeo, &err); + if (!skb) + goto out; + + /* Okay, have a message on the receive queue */ + + rxm = kcm_rx_msg(skb); + + if (len > rxm->full_len) + len = rxm->full_len; + + err = skb_copy_datagram_msg(skb, rxm->offset, msg, len); + if (err < 0) + goto out; + + copied = len; + if (likely(!(flags & MSG_PEEK))) { + KCM_STATS_ADD(kcm->stats.rx_bytes, copied); + if (copied < rxm->full_len) { + if (sock->type == SOCK_DGRAM) { + /* Truncated message */ + msg->msg_flags |= MSG_TRUNC; + goto msg_finished; + } + rxm->offset += copied; + rxm->full_len -= copied; + } else { +msg_finished: + /* Finished with message */ + msg->msg_flags |= MSG_EOR; + KCM_STATS_INCR(kcm->stats.rx_msgs); + skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); + } + } + +out: + release_sock(sk); + + return copied ? : err; +} + +static ssize_t kcm_sock_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd) +{ + int ret; + + release_sock(sk); + ret = splice_to_pipe(pipe, spd); + lock_sock(sk); + + return ret; +} + +static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); + long timeo; + struct kcm_rx_msg *rxm; + int err = 0; + size_t copied; + struct sk_buff *skb; + + /* Only support splice for SOCKSEQPACKET */ + + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + + lock_sock(sk); + + skb = kcm_wait_data(sk, flags, timeo, &err); + if (!skb) + goto err_out; + + /* Okay, have a message on the receive queue */ + + rxm = kcm_rx_msg(skb); + + if (len > rxm->full_len) + len = rxm->full_len; + + copied = skb_splice_bits(skb, sk, rxm->offset, pipe, len, flags, + kcm_sock_splice); + if (copied < 0) { + err = copied; + goto err_out; + } + + KCM_STATS_ADD(kcm->stats.rx_bytes, copied); + + rxm->offset += copied; + rxm->full_len -= copied; + + /* We have no way to return MSG_EOR. If all the bytes have been + * read we still leave the message in the receive socket buffer. + * A subsequent recvmsg needs to be done to return MSG_EOR and + * finish reading the message. + */ + + release_sock(sk); + + return copied; + +err_out: + release_sock(sk); + + return err; +} + +/* kcm sock lock held */ +static void kcm_recv_disable(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + if (kcm->rx_disabled) + return; + + spin_lock_bh(&mux->rx_lock); + + kcm->rx_disabled = 1; + + /* If a psock is reserved we'll do cleanup in unreserve */ + if (!kcm->rx_psock) { + if (kcm->rx_wait) { + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + } + + requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); + } + + spin_unlock_bh(&mux->rx_lock); +} + +/* kcm sock lock held */ +static void kcm_recv_enable(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + + if (!kcm->rx_disabled) + return; + + spin_lock_bh(&mux->rx_lock); + + kcm->rx_disabled = 0; + kcm_rcv_ready(kcm); + + spin_unlock_bh(&mux->rx_lock); +} + +static int kcm_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + int val, valbool; + int err = 0; + + if (level != SOL_KCM) + return -ENOPROTOOPT; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *)optval)) + return -EINVAL; + + valbool = val ? 1 : 0; + + switch (optname) { + case KCM_RECV_DISABLE: + lock_sock(&kcm->sk); + if (valbool) + kcm_recv_disable(kcm); + else + kcm_recv_enable(kcm); + release_sock(&kcm->sk); + break; + default: + err = -ENOPROTOOPT; + } + + return err; +} + +static int kcm_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + int val, len; + + if (level != SOL_KCM) + return -ENOPROTOOPT; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(int)); + if (len < 0) + return -EINVAL; + + switch (optname) { + case KCM_RECV_DISABLE: + val = kcm->rx_disabled; + break; + default: + return -ENOPROTOOPT; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; +} + +static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) +{ + struct kcm_sock *tkcm; + struct list_head *head; + int index = 0; + + /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so + * we set sk_state, otherwise epoll_wait always returns right away with + * POLLHUP + */ + kcm->sk.sk_state = TCP_ESTABLISHED; + + /* Add to mux's kcm sockets list */ + kcm->mux = mux; + spin_lock_bh(&mux->lock); + + head = &mux->kcm_socks; + list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) { + if (tkcm->index != index) + break; + head = &tkcm->kcm_sock_list; + index++; + } + + list_add(&kcm->kcm_sock_list, head); + kcm->index = index; + + mux->kcm_socks_cnt++; + spin_unlock_bh(&mux->lock); + + INIT_WORK(&kcm->tx_work, kcm_tx_work); + + spin_lock_bh(&mux->rx_lock); + kcm_rcv_ready(kcm); + spin_unlock_bh(&mux->rx_lock); +} + +static void kcm_rx_msg_timeout(unsigned long arg) +{ + struct kcm_psock *psock = (struct kcm_psock *)arg; + + /* Message assembly timed out */ + KCM_STATS_INCR(psock->stats.rx_msg_timeouts); + kcm_abort_rx_psock(psock, ETIMEDOUT, NULL); +} + +static int kcm_attach(struct socket *sock, struct socket *csock, + struct bpf_prog *prog) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + struct kcm_mux *mux = kcm->mux; + struct sock *csk; + struct kcm_psock *psock = NULL, *tpsock; + struct list_head *head; + int index = 0; + + if (csock->ops->family != PF_INET && + csock->ops->family != PF_INET6) + return -EINVAL; + + csk = csock->sk; + if (!csk) + return -EINVAL; + + /* Only support TCP for now */ + if (csk->sk_protocol != IPPROTO_TCP) + return -EINVAL; + + psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); + if (!psock) + return -ENOMEM; + + psock->mux = mux; + psock->sk = csk; + psock->bpf_prog = prog; + + setup_timer(&psock->rx_msg_timer, kcm_rx_msg_timeout, + (unsigned long)psock); + + INIT_WORK(&psock->rx_work, psock_rx_work); + INIT_DELAYED_WORK(&psock->rx_delayed_work, psock_rx_delayed_work); + + sock_hold(csk); + + write_lock_bh(&csk->sk_callback_lock); + psock->save_data_ready = csk->sk_data_ready; + psock->save_write_space = csk->sk_write_space; + psock->save_state_change = csk->sk_state_change; + csk->sk_user_data = psock; + csk->sk_data_ready = psock_tcp_data_ready; + csk->sk_write_space = psock_tcp_write_space; + csk->sk_state_change = psock_tcp_state_change; + write_unlock_bh(&csk->sk_callback_lock); + + /* Finished initialization, now add the psock to the MUX. */ + spin_lock_bh(&mux->lock); + head = &mux->psocks; + list_for_each_entry(tpsock, &mux->psocks, psock_list) { + if (tpsock->index != index) + break; + head = &tpsock->psock_list; + index++; + } + + list_add(&psock->psock_list, head); + psock->index = index; + + KCM_STATS_INCR(mux->stats.psock_attach); + mux->psocks_cnt++; + psock_now_avail(psock); + spin_unlock_bh(&mux->lock); + + /* Schedule RX work in case there are already bytes queued */ + queue_work(kcm_wq, &psock->rx_work); + + return 0; +} + +static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) +{ + struct socket *csock; + struct bpf_prog *prog; + int err; + + csock = sockfd_lookup(info->fd, &err); + if (!csock) + return -ENOENT; + + prog = bpf_prog_get(info->bpf_fd); + if (IS_ERR(prog)) { + err = PTR_ERR(prog); + goto out; + } + + if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) { + bpf_prog_put(prog); + err = -EINVAL; + goto out; + } + + err = kcm_attach(sock, csock, prog); + if (err) { + bpf_prog_put(prog); + goto out; + } + + /* Keep reference on file also */ + + return 0; +out: + fput(csock->file); + return err; +} + +static void kcm_unattach(struct kcm_psock *psock) +{ + struct sock *csk = psock->sk; + struct kcm_mux *mux = psock->mux; + + /* Stop getting callbacks from TCP socket. After this there should + * be no way to reserve a kcm for this psock. + */ + write_lock_bh(&csk->sk_callback_lock); + csk->sk_user_data = NULL; + csk->sk_data_ready = psock->save_data_ready; + csk->sk_write_space = psock->save_write_space; + csk->sk_state_change = psock->save_state_change; + psock->rx_stopped = 1; + + if (WARN_ON(psock->rx_kcm)) { + write_unlock_bh(&csk->sk_callback_lock); + return; + } + + spin_lock_bh(&mux->rx_lock); + + /* Stop receiver activities. After this point psock should not be + * able to get onto ready list either through callbacks or work. + */ + if (psock->ready_rx_msg) { + list_del(&psock->psock_ready_list); + kfree_skb(psock->ready_rx_msg); + psock->ready_rx_msg = NULL; + KCM_STATS_INCR(mux->stats.rx_ready_drops); + } + + spin_unlock_bh(&mux->rx_lock); + + write_unlock_bh(&csk->sk_callback_lock); + + del_timer_sync(&psock->rx_msg_timer); + cancel_work_sync(&psock->rx_work); + cancel_delayed_work_sync(&psock->rx_delayed_work); + + bpf_prog_put(psock->bpf_prog); + + kfree_skb(psock->rx_skb_head); + psock->rx_skb_head = NULL; + + spin_lock_bh(&mux->lock); + + aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats); + + KCM_STATS_INCR(mux->stats.psock_unattach); + + if (psock->tx_kcm) { + /* psock was reserved. Just mark it finished and we will clean + * up in the kcm paths, we need kcm lock which can not be + * acquired here. + */ + KCM_STATS_INCR(mux->stats.psock_unattach_rsvd); + spin_unlock_bh(&mux->lock); + + /* We are unattaching a socket that is reserved. Abort the + * socket since we may be out of sync in sending on it. We need + * to do this without the mux lock. + */ + kcm_abort_tx_psock(psock, EPIPE, false); + + spin_lock_bh(&mux->lock); + if (!psock->tx_kcm) { + /* psock now unreserved in window mux was unlocked */ + goto no_reserved; + } + psock->done = 1; + + /* Commit done before queuing work to process it */ + smp_mb(); + + /* Queue tx work to make sure psock->done is handled */ + queue_work(kcm_wq, &psock->tx_kcm->tx_work); + spin_unlock_bh(&mux->lock); + } else { +no_reserved: + if (!psock->tx_stopped) + list_del(&psock->psock_avail_list); + list_del(&psock->psock_list); + mux->psocks_cnt--; + spin_unlock_bh(&mux->lock); + + sock_put(csk); + fput(csk->sk_socket->file); + kmem_cache_free(kcm_psockp, psock); + } +} + +static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) +{ + struct kcm_sock *kcm = kcm_sk(sock->sk); + struct kcm_mux *mux = kcm->mux; + struct kcm_psock *psock; + struct socket *csock; + struct sock *csk; + int err; + + csock = sockfd_lookup(info->fd, &err); + if (!csock) + return -ENOENT; + + csk = csock->sk; + if (!csk) { + err = -EINVAL; + goto out; + } + + err = -ENOENT; + + spin_lock_bh(&mux->lock); + + list_for_each_entry(psock, &mux->psocks, psock_list) { + if (psock->sk != csk) + continue; + + /* Found the matching psock */ + + if (psock->unattaching || WARN_ON(psock->done)) { + err = -EALREADY; + break; + } + + psock->unattaching = 1; + + spin_unlock_bh(&mux->lock); + + kcm_unattach(psock); + + err = 0; + goto out; + } + + spin_unlock_bh(&mux->lock); + +out: + fput(csock->file); + return err; +} + +static struct proto kcm_proto = { + .name = "KCM", + .owner = THIS_MODULE, + .obj_size = sizeof(struct kcm_sock), +}; + +/* Clone a kcm socket. */ +static int kcm_clone(struct socket *osock, struct kcm_clone *info, + struct socket **newsockp) +{ + struct socket *newsock; + struct sock *newsk; + struct file *newfile; + int err, newfd; + + err = -ENFILE; + newsock = sock_alloc(); + if (!newsock) + goto out; + + newsock->type = osock->type; + newsock->ops = osock->ops; + + __module_get(newsock->ops->owner); + + newfd = get_unused_fd_flags(0); + if (unlikely(newfd < 0)) { + err = newfd; + goto out_fd_fail; + } + + newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); + if (unlikely(IS_ERR(newfile))) { + err = PTR_ERR(newfile); + goto out_sock_alloc_fail; + } + + newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, + &kcm_proto, true); + if (!newsk) { + err = -ENOMEM; + goto out_sk_alloc_fail; + } + + sock_init_data(newsock, newsk); + init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux); + + fd_install(newfd, newfile); + *newsockp = newsock; + info->fd = newfd; + + return 0; + +out_sk_alloc_fail: + fput(newfile); +out_sock_alloc_fail: + put_unused_fd(newfd); +out_fd_fail: + sock_release(newsock); +out: + return err; +} + +static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + int err; + + switch (cmd) { + case SIOCKCMATTACH: { + struct kcm_attach info; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_attach_ioctl(sock, &info); + + break; + } + case SIOCKCMUNATTACH: { + struct kcm_unattach info; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_unattach_ioctl(sock, &info); + + break; + } + case SIOCKCMCLONE: { + struct kcm_clone info; + struct socket *newsock = NULL; + + if (copy_from_user(&info, (void __user *)arg, sizeof(info))) + err = -EFAULT; + + err = kcm_clone(sock, &info, &newsock); + + if (!err) { + if (copy_to_user((void __user *)arg, &info, + sizeof(info))) { + err = -EFAULT; + sock_release(newsock); + } + } + + break; + } + default: + err = -ENOIOCTLCMD; + break; + } + + return err; +} + +static void free_mux(struct rcu_head *rcu) +{ + struct kcm_mux *mux = container_of(rcu, + struct kcm_mux, rcu); + + kmem_cache_free(kcm_muxp, mux); +} + +static void release_mux(struct kcm_mux *mux) +{ + struct kcm_net *knet = mux->knet; + struct kcm_psock *psock, *tmp_psock; + + /* Release psocks */ + list_for_each_entry_safe(psock, tmp_psock, + &mux->psocks, psock_list) { + if (!WARN_ON(psock->unattaching)) + kcm_unattach(psock); + } + + if (WARN_ON(mux->psocks_cnt)) + return; + + __skb_queue_purge(&mux->rx_hold_queue); + + mutex_lock(&knet->mutex); + aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats); + aggregate_psock_stats(&mux->aggregate_psock_stats, + &knet->aggregate_psock_stats); + list_del_rcu(&mux->kcm_mux_list); + knet->count--; + mutex_unlock(&knet->mutex); + + call_rcu(&mux->rcu, free_mux); +} + +static void kcm_done(struct kcm_sock *kcm) +{ + struct kcm_mux *mux = kcm->mux; + struct sock *sk = &kcm->sk; + int socks_cnt; + + spin_lock_bh(&mux->rx_lock); + if (kcm->rx_psock) { + /* Cleanup in unreserve_rx_kcm */ + WARN_ON(kcm->done); + kcm->rx_disabled = 1; + kcm->done = 1; + spin_unlock_bh(&mux->rx_lock); + return; + } + + if (kcm->rx_wait) { + list_del(&kcm->wait_rx_list); + kcm->rx_wait = false; + } + /* Move any pending receive messages to other kcm sockets */ + requeue_rx_msgs(mux, &sk->sk_receive_queue); + + spin_unlock_bh(&mux->rx_lock); + + if (WARN_ON(sk_rmem_alloc_get(sk))) + return; + + /* Detach from MUX */ + spin_lock_bh(&mux->lock); + + list_del(&kcm->kcm_sock_list); + mux->kcm_socks_cnt--; + socks_cnt = mux->kcm_socks_cnt; + + spin_unlock_bh(&mux->lock); + + if (!socks_cnt) { + /* We are done with the mux now. */ + release_mux(mux); + } + + WARN_ON(kcm->rx_wait); + + sock_put(&kcm->sk); +} + +/* Called by kcm_release to close a KCM socket. + * If this is the last KCM socket on the MUX, destroy the MUX. + */ +static int kcm_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm; + struct kcm_mux *mux; + struct kcm_psock *psock; + + if (!sk) + return 0; + + kcm = kcm_sk(sk); + mux = kcm->mux; + + sock_orphan(sk); + kfree_skb(kcm->seq_skb); + + lock_sock(sk); + /* Purge queue under lock to avoid race condition with tx_work trying + * to act when queue is nonempty. If tx_work runs after this point + * it will just return. + */ + __skb_queue_purge(&sk->sk_write_queue); + release_sock(sk); + + spin_lock_bh(&mux->lock); + if (kcm->tx_wait) { + /* Take of tx_wait list, after this point there should be no way + * that a psock will be assigned to this kcm. + */ + list_del(&kcm->wait_psock_list); + kcm->tx_wait = false; + } + spin_unlock_bh(&mux->lock); + + /* Cancel work. After this point there should be no outside references + * to the kcm socket. + */ + cancel_work_sync(&kcm->tx_work); + + lock_sock(sk); + psock = kcm->tx_psock; + if (psock) { + /* A psock was reserved, so we need to kill it since it + * may already have some bytes queued from a message. We + * need to do this after removing kcm from tx_wait list. + */ + kcm_abort_tx_psock(psock, EPIPE, false); + unreserve_psock(kcm); + } + release_sock(sk); + + WARN_ON(kcm->tx_wait); + WARN_ON(kcm->tx_psock); + + sock->sk = NULL; + + kcm_done(kcm); + + return 0; +} + +static const struct proto_ops kcm_dgram_ops = { + .family = PF_KCM, + .owner = THIS_MODULE, + .release = kcm_release, + .bind = sock_no_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = kcm_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = kcm_setsockopt, + .getsockopt = kcm_getsockopt, + .sendmsg = kcm_sendmsg, + .recvmsg = kcm_recvmsg, + .mmap = sock_no_mmap, + .sendpage = kcm_sendpage, +}; + +static const struct proto_ops kcm_seqpacket_ops = { + .family = PF_KCM, + .owner = THIS_MODULE, + .release = kcm_release, + .bind = sock_no_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = kcm_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = kcm_setsockopt, + .getsockopt = kcm_getsockopt, + .sendmsg = kcm_sendmsg, + .recvmsg = kcm_recvmsg, + .mmap = sock_no_mmap, + .sendpage = kcm_sendpage, + .splice_read = kcm_splice_read, +}; + +/* Create proto operation for kcm sockets */ +static int kcm_create(struct net *net, struct socket *sock, + int protocol, int kern) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + struct sock *sk; + struct kcm_mux *mux; + + switch (sock->type) { + case SOCK_DGRAM: + sock->ops = &kcm_dgram_ops; + break; + case SOCK_SEQPACKET: + sock->ops = &kcm_seqpacket_ops; + break; + default: + return -ESOCKTNOSUPPORT; + } + + if (protocol != KCMPROTO_CONNECTED) + return -EPROTONOSUPPORT; + + sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern); + if (!sk) + return -ENOMEM; + + /* Allocate a kcm mux, shared between KCM sockets */ + mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL); + if (!mux) { + sk_free(sk); + return -ENOMEM; + } + + spin_lock_init(&mux->lock); + spin_lock_init(&mux->rx_lock); + INIT_LIST_HEAD(&mux->kcm_socks); + INIT_LIST_HEAD(&mux->kcm_rx_waiters); + INIT_LIST_HEAD(&mux->kcm_tx_waiters); + + INIT_LIST_HEAD(&mux->psocks); + INIT_LIST_HEAD(&mux->psocks_ready); + INIT_LIST_HEAD(&mux->psocks_avail); + + mux->knet = knet; + + /* Add new MUX to list */ + mutex_lock(&knet->mutex); + list_add_rcu(&mux->kcm_mux_list, &knet->mux_list); + knet->count++; + mutex_unlock(&knet->mutex); + + skb_queue_head_init(&mux->rx_hold_queue); + + /* Init KCM socket */ + sock_init_data(sock, sk); + init_kcm_sock(kcm_sk(sk), mux); + + return 0; +} + +static struct net_proto_family kcm_family_ops = { + .family = PF_KCM, + .create = kcm_create, + .owner = THIS_MODULE, +}; + +static __net_init int kcm_init_net(struct net *net) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + + INIT_LIST_HEAD_RCU(&knet->mux_list); + mutex_init(&knet->mutex); + + return 0; +} + +static __net_exit void kcm_exit_net(struct net *net) +{ + struct kcm_net *knet = net_generic(net, kcm_net_id); + + /* All KCM sockets should be closed at this point, which should mean + * that all multiplexors and psocks have been destroyed. + */ + WARN_ON(!list_empty(&knet->mux_list)); +} + +static struct pernet_operations kcm_net_ops = { + .init = kcm_init_net, + .exit = kcm_exit_net, + .id = &kcm_net_id, + .size = sizeof(struct kcm_net), +}; + +static int __init kcm_init(void) +{ + int err = -ENOMEM; + + kcm_muxp = kmem_cache_create("kcm_mux_cache", + sizeof(struct kcm_mux), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + if (!kcm_muxp) + goto fail; + + kcm_psockp = kmem_cache_create("kcm_psock_cache", + sizeof(struct kcm_psock), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + if (!kcm_psockp) + goto fail; + + kcm_wq = create_singlethread_workqueue("kkcmd"); + if (!kcm_wq) + goto fail; + + err = proto_register(&kcm_proto, 1); + if (err) + goto fail; + + err = sock_register(&kcm_family_ops); + if (err) + goto sock_register_fail; + + err = register_pernet_device(&kcm_net_ops); + if (err) + goto net_ops_fail; + + err = kcm_proc_init(); + if (err) + goto proc_init_fail; + + return 0; + +proc_init_fail: + unregister_pernet_device(&kcm_net_ops); + +net_ops_fail: + sock_unregister(PF_KCM); + +sock_register_fail: + proto_unregister(&kcm_proto); + +fail: + kmem_cache_destroy(kcm_muxp); + kmem_cache_destroy(kcm_psockp); + + if (kcm_wq) + destroy_workqueue(kcm_wq); + + return err; +} + +static void __exit kcm_exit(void) +{ + kcm_proc_exit(); + unregister_pernet_device(&kcm_net_ops); + sock_unregister(PF_KCM); + proto_unregister(&kcm_proto); + destroy_workqueue(kcm_wq); + + kmem_cache_destroy(kcm_muxp); + kmem_cache_destroy(kcm_psockp); +} + +module_init(kcm_init); +module_exit(kcm_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETPROTO(PF_KCM); + diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 1b8a5caa221e..3a8f881b22f1 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -327,7 +327,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } /* prepare A-MPDU MLME for Rx aggregation */ - tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); + tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL); if (!tid_agg_rx) goto end; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 1630975c89f1..804575ff7af5 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -92,7 +92,7 @@ struct ieee80211_fragment_entry { u16 extra_len; u16 last_frag; u8 rx_queue; - bool ccmp; /* Whether fragments were encrypted with CCMP */ + bool check_sequential_pn; /* needed for CCMP/GCMP */ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ }; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 3ece7d1034c8..b54f398cda5d 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta) * computing cur_tp */ tmp_mrs = &mi->r[idx].stats; - tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma); + tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10; tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; return tmp_cur_tp; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 3928dbd24e25..370d677b547b 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -414,15 +414,16 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) (max_tp_group != MINSTREL_CCK_GROUP)) return; + max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; + max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; + if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) { cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, mrs->prob_ewma); if (cur_tp_avg > tmp_tp_avg) mi->max_prob_rate = index; - max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; - max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; - max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, max_gpr_idx, max_gpr_prob); @@ -431,7 +432,7 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) } else { if (mrs->prob_ewma > tmp_prob) mi->max_prob_rate = index; - if (mrs->prob_ewma > mg->rates[mg->max_group_prob_rate].prob_ewma) + if (mrs->prob_ewma > max_gpr_prob) mg->max_group_prob_rate = index; } } @@ -691,7 +692,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (likely(sta->ampdu_mlme.tid_tx[tid])) return; - ieee80211_start_tx_ba_session(pubsta, tid, 5000); + ieee80211_start_tx_ba_session(pubsta, tid, 0); } static void @@ -871,7 +872,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, * - if station is in dynamic SMPS (and streams > 1) * - for fallback rates, to increase chances of getting through */ - if (offset > 0 && + if (offset > 0 || (mi->sta->smps_mode == IEEE80211_SMPS_DYNAMIC && group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; @@ -1334,7 +1335,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) prob = mi->groups[i].rates[j].prob_ewma; /* convert tp_avg from pkt per second in kbps */ - tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024; + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; + tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5690e4c67486..dc27becb9b71 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1777,7 +1777,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, entry->seq = seq; entry->rx_queue = rx_queue; entry->last_frag = frag; - entry->ccmp = 0; + entry->check_sequential_pn = false; entry->extra_len = 0; return entry; @@ -1873,15 +1873,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) rx->seqno_idx, &(rx->skb)); if (rx->key && (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) && + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && ieee80211_has_protected(fc)) { int queue = rx->security_idx; - /* Store CCMP PN so that we can verify that the next - * fragment has a sequential PN value. */ - entry->ccmp = 1; + + /* Store CCMP/GCMP PN so that we can verify that the + * next fragment has a sequential PN value. + */ + entry->check_sequential_pn = true; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); + BUILD_BUG_ON(offsetof(struct ieee80211_key, + u.ccmp.rx_pn) != + offsetof(struct ieee80211_key, + u.gcmp.rx_pn)); + BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) != + sizeof(rx->key->u.gcmp.rx_pn[queue])); + BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != + IEEE80211_GCMP_PN_LEN); } return RX_QUEUED; } @@ -1896,15 +1908,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* Verify that MPDUs within one MSDU have sequential PN values. - * (IEEE 802.11i, 8.3.3.4.5) */ - if (entry->ccmp) { + /* "The receiver shall discard MSDUs and MMPDUs whose constituent + * MPDU PN values are not incrementing in steps of 1." + * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP) + * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP) + */ + if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; int queue; + if (!rx->key || (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256)) + rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) return RX_DROP_UNUSABLE; memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { @@ -3473,6 +3491,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) return false; /* ignore action frames to TDLS-peers */ if (ieee80211_is_action(hdr->frame_control) && + !is_broadcast_ether_addr(bssid) && !ether_addr_equal(bssid, hdr->addr1)) return false; } diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 0328f7250693..299edc6add5a 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -605,17 +605,13 @@ static const struct file_operations ip_vs_app_fops = { int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { - struct net *net = ipvs->net; - INIT_LIST_HEAD(&ipvs->app_list); - proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops); + proc_create("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_fops); return 0; } void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { - struct net *net = ipvs->net; - unregister_ip_vs_app(ipvs, NULL /* all */); - remove_proc_entry("ip_vs_app", net->proc_net); + remove_proc_entry("ip_vs_app", ipvs->net->proc_net); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e7c1b052c2a3..404b2a4f4b5b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1376,8 +1376,6 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) struct ip_vs_pe *old_pe; struct netns_ipvs *ipvs = svc->ipvs; - pr_info("%s: enter\n", __func__); - /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) ipvs->num_services--; @@ -3947,7 +3945,6 @@ static struct notifier_block ip_vs_dst_notifier = { int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) { - struct net *net = ipvs->net; int i, idx; /* Initialize rs_table */ @@ -3974,9 +3971,9 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) spin_lock_init(&ipvs->tot_stats.lock); - proc_create("ip_vs", 0, net->proc_net, &ip_vs_info_fops); - proc_create("ip_vs_stats", 0, net->proc_net, &ip_vs_stats_fops); - proc_create("ip_vs_stats_percpu", 0, net->proc_net, + proc_create("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_fops); + proc_create("ip_vs_stats", 0, ipvs->net->proc_net, &ip_vs_stats_fops); + proc_create("ip_vs_stats_percpu", 0, ipvs->net->proc_net, &ip_vs_stats_percpu_fops); if (ip_vs_control_net_init_sysctl(ipvs)) @@ -3991,13 +3988,11 @@ err: void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { - struct net *net = ipvs->net; - ip_vs_trash_cleanup(ipvs); ip_vs_control_net_cleanup_sysctl(ipvs); - remove_proc_entry("ip_vs_stats_percpu", net->proc_net); - remove_proc_entry("ip_vs_stats", net->proc_net); - remove_proc_entry("ip_vs", net->proc_net); + remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); + remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); + remove_proc_entry("ip_vs", ipvs->net->proc_net); free_percpu(ipvs->tot_stats.cpustats); } diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 9aea747b43ea..81b5ad6165ac 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -17,7 +17,9 @@ #include <net/netfilter/nft_masq.h> const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = { - [NFTA_MASQ_FLAGS] = { .type = NLA_U32 }, + [NFTA_MASQ_FLAGS] = { .type = NLA_U32 }, + [NFTA_MASQ_REG_PROTO_MIN] = { .type = NLA_U32 }, + [NFTA_MASQ_REG_PROTO_MAX] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(nft_masq_policy); @@ -40,6 +42,7 @@ int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { + u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); struct nft_masq *priv = nft_expr_priv(expr); int err; @@ -47,12 +50,32 @@ int nft_masq_init(const struct nft_ctx *ctx, if (err) return err; - if (tb[NFTA_MASQ_FLAGS] == NULL) - return 0; - - priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); - if (priv->flags & ~NF_NAT_RANGE_MASK) - return -EINVAL; + if (tb[NFTA_MASQ_FLAGS]) { + priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); + if (priv->flags & ~NF_NAT_RANGE_MASK) + return -EINVAL; + } + + if (tb[NFTA_MASQ_REG_PROTO_MIN]) { + priv->sreg_proto_min = + nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MIN]); + + err = nft_validate_register_load(priv->sreg_proto_min, plen); + if (err < 0) + return err; + + if (tb[NFTA_MASQ_REG_PROTO_MAX]) { + priv->sreg_proto_max = + nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MAX]); + + err = nft_validate_register_load(priv->sreg_proto_max, + plen); + if (err < 0) + return err; + } else { + priv->sreg_proto_max = priv->sreg_proto_min; + } + } return 0; } @@ -62,12 +85,18 @@ int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_masq *priv = nft_expr_priv(expr); - if (priv->flags == 0) - return 0; - - if (nla_put_be32(skb, NFTA_MASQ_FLAGS, htonl(priv->flags))) + if (priv->flags != 0 && + nla_put_be32(skb, NFTA_MASQ_FLAGS, htonl(priv->flags))) goto nla_put_failure; + if (priv->sreg_proto_min) { + if (nft_dump_register(skb, NFTA_MASQ_REG_PROTO_MIN, + priv->sreg_proto_min) || + nft_dump_register(skb, NFTA_MASQ_REG_PROTO_MAX, + priv->sreg_proto_max)) + goto nla_put_failure; + } + return 0; nla_put_failure: diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index fe885bf271c5..16c50b0dd426 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -28,6 +28,8 @@ #include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */ +static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); + void nft_meta_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -181,6 +183,11 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = sock_cgroup_classid(&sk->sk_cgrp_data); break; #endif + case NFT_META_PRANDOM: { + struct rnd_state *state = this_cpu_ptr(&nft_prandom_state); + *dest = prandom_u32_state(state); + break; + } default: WARN_ON(1); goto err; @@ -277,6 +284,10 @@ int nft_meta_get_init(const struct nft_ctx *ctx, case NFT_META_OIFNAME: len = IFNAMSIZ; break; + case NFT_META_PRANDOM: + prandom_init_once(&nft_prandom_state); + len = sizeof(u32); + break; default: return -EOPNOTSUPP; } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index c8a0b7da5ff4..d0cd2b9bf844 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -694,12 +694,45 @@ EXPORT_SYMBOL(xt_free_table_info); struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { - struct xt_table *t; + struct xt_table *t, *found = NULL; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &net->xt.tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; + + if (net == &init_net) + goto out; + + /* Table doesn't exist in this netns, re-try init */ + list_for_each_entry(t, &init_net.xt.tables[af], list) { + if (strcmp(t->name, name)) + continue; + if (!try_module_get(t->me)) + return NULL; + + mutex_unlock(&xt[af].mutex); + if (t->table_init(net) != 0) { + module_put(t->me); + return NULL; + } + + found = t; + + mutex_lock(&xt[af].mutex); + break; + } + + if (!found) + goto out; + + /* and once again: */ + list_for_each_entry(t, &net->xt.tables[af], list) + if (strcmp(t->name, name) == 0) + return t; + + module_put(found->me); + out: mutex_unlock(&xt[af].mutex); return NULL; } @@ -1170,20 +1203,20 @@ static const struct file_operations xt_target_ops = { #endif /* CONFIG_PROC_FS */ /** - * xt_hook_link - set up hooks for a new table + * xt_hook_ops_alloc - set up hooks for a new table * @table: table with metadata needed to set up hooks * @fn: Hook function * - * This function will take care of creating and registering the necessary - * Netfilter hooks for XT tables. + * This function will create the nf_hook_ops that the x_table needs + * to hand to xt_hook_link_net(). */ -struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn) +struct nf_hook_ops * +xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) { unsigned int hook_mask = table->valid_hooks; uint8_t i, num_hooks = hweight32(hook_mask); uint8_t hooknum; struct nf_hook_ops *ops; - int ret; ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL); if (ops == NULL) @@ -1200,27 +1233,9 @@ struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn) ++i; } - ret = nf_register_hooks(ops, num_hooks); - if (ret < 0) { - kfree(ops); - return ERR_PTR(ret); - } - return ops; } -EXPORT_SYMBOL_GPL(xt_hook_link); - -/** - * xt_hook_unlink - remove hooks for a table - * @ops: nf_hook_ops array as returned by nf_hook_link - * @hook_mask: the very same mask that was passed to nf_hook_link - */ -void xt_hook_unlink(const struct xt_table *table, struct nf_hook_ops *ops) -{ - nf_unregister_hooks(ops, hweight32(table->valid_hooks)); - kfree(ops); -} -EXPORT_SYMBOL_GPL(xt_hook_unlink); +EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_proto_init(struct net *net, u_int8_t af) { diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 4e3c3affd285..2455b69b5810 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -262,7 +262,6 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) if (f->opt[optnum].kind == (*optp)) { __u32 len = f->opt[optnum].length; const __u8 *optend = optp + len; - int loop_cont = 0; fmatch = FMATCH_OK; @@ -275,7 +274,6 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) mss = ntohs((__force __be16)mss); break; case OSFOPT_TS: - loop_cont = 1; break; } diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f0cb92f3ddaf..ada67422234b 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -55,8 +55,8 @@ struct netlbl_domhsh_tbl { static DEFINE_SPINLOCK(netlbl_domhsh_lock); #define netlbl_domhsh_rcu_deref(p) \ rcu_dereference_check(p, lockdep_is_held(&netlbl_domhsh_lock)) -static struct netlbl_domhsh_tbl *netlbl_domhsh = NULL; -static struct netlbl_dom_map *netlbl_domhsh_def = NULL; +static struct netlbl_domhsh_tbl *netlbl_domhsh; +static struct netlbl_dom_map *netlbl_domhsh_def; /* * Domain Hash Table Helper Functions diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index b0380927f05f..9eaa9a1e8629 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -116,11 +116,11 @@ struct netlbl_unlhsh_walk_arg { static DEFINE_SPINLOCK(netlbl_unlhsh_lock); #define netlbl_unlhsh_rcu_deref(p) \ rcu_dereference_check(p, lockdep_is_held(&netlbl_unlhsh_lock)) -static struct netlbl_unlhsh_tbl *netlbl_unlhsh = NULL; -static struct netlbl_unlhsh_iface *netlbl_unlhsh_def = NULL; +static struct netlbl_unlhsh_tbl *netlbl_unlhsh; +static struct netlbl_unlhsh_iface *netlbl_unlhsh_def; /* Accept unlabeled packets flag */ -static u8 netlabel_unlabel_acceptflg = 0; +static u8 netlabel_unlabel_acceptflg; /* NetLabel Generic NETLINK unlabeled family */ static struct genl_family netlbl_unlabel_gnl_family = { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d41b1074cb2d..1ecfa710ca98 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1915,6 +1915,10 @@ retry: goto retry; } + if (!dev_validate_header(dev, skb->data, len)) { + err = -EINVAL; + goto out_unlock; + } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; @@ -2393,18 +2397,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static bool ll_header_truncated(const struct net_device *dev, int len) -{ - /* net device doesn't like empty head */ - if (unlikely(len < dev->hard_header_len)) { - net_warn_ratelimited("%s: packet size is too short (%d < %d)\n", - current->comm, len, dev->hard_header_len); - return true; - } - - return false; -} - static void tpacket_set_protocol(const struct net_device *dev, struct sk_buff *skb) { @@ -2522,16 +2514,20 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { + int hdrlen = min_t(int, copylen, tp_len); + skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); - err = skb_store_bits(skb, 0, data, copylen); + err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; + if (!dev_validate_header(dev, skb->data, hdrlen)) + return -EINVAL; if (!skb->protocol) tpacket_set_protocol(dev, skb); - data += copylen; - to_write -= copylen; + data += hdrlen; + to_write -= hdrlen; } offset = offset_in_page(data); @@ -2703,13 +2699,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } - if (dev->hard_header_len) { - if (ll_header_truncated(dev, tp_len)) { - tp_len = -EINVAL; - goto tpacket_error; - } - copylen = max_t(int, copylen, dev->hard_header_len); - } + copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), @@ -2905,9 +2895,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; - } else { - if (ll_header_truncated(dev, len)) - goto out_free; } /* Returns -EFAULT on error */ @@ -2915,6 +2902,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (err) goto out_free; + if (sock->type == SOCK_RAW && + !dev_validate_header(dev, skb->data, len)) { + err = -EINVAL; + goto out_free; + } + sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 6e7ec257790d..c589a9ba506a 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -108,7 +108,7 @@ EXPORT_SYMBOL_GPL(ife_get_meta_u16); int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval) { - mi->metaval = kmemdup(&metaval, sizeof(u32), GFP_KERNEL); + mi->metaval = kmemdup(metaval, sizeof(u32), GFP_KERNEL); if (!mi->metaval) return -ENOMEM; @@ -118,7 +118,7 @@ EXPORT_SYMBOL_GPL(ife_alloc_meta_u32); int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval) { - mi->metaval = kmemdup(&metaval, sizeof(u16), GFP_KERNEL); + mi->metaval = kmemdup(metaval, sizeof(u16), GFP_KERNEL); if (!mi->metaval) return -ENOMEM; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 89c41a1f3589..350e134cffb3 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -66,6 +66,7 @@ static void ipt_destroy_target(struct xt_entry_target *t) struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, + .family = NFPROTO_IPV4, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -219,6 +220,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, par.hooknum = ipt->tcfi_hook; par.target = ipt->tcfi_t->u.kernel.target; par.targinfo = ipt->tcfi_t->data; + par.family = NFPROTO_IPV4; ret = par.target->target(skb, &par); switch (ret) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 95b021243233..2181ffc76638 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -165,6 +165,51 @@ static void fl_destroy_filter(struct rcu_head *head) kfree(f); } +static void fl_hw_destroy_filter(struct tcf_proto *tp, unsigned long cookie) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_flower_offload offload = {0}; + struct tc_to_netdev tc; + + if (!tc_should_offload(dev, 0)) + return; + + offload.command = TC_CLSFLOWER_DESTROY; + offload.cookie = cookie; + + tc.type = TC_SETUP_CLSFLOWER; + tc.cls_flower = &offload; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); +} + +static void fl_hw_replace_filter(struct tcf_proto *tp, + struct flow_dissector *dissector, + struct fl_flow_key *mask, + struct fl_flow_key *key, + struct tcf_exts *actions, + unsigned long cookie, u32 flags) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_flower_offload offload = {0}; + struct tc_to_netdev tc; + + if (!tc_should_offload(dev, flags)) + return; + + offload.command = TC_CLSFLOWER_REPLACE; + offload.cookie = cookie; + offload.dissector = dissector; + offload.mask = mask; + offload.key = key; + offload.exts = actions; + + tc.type = TC_SETUP_CLSFLOWER; + tc.cls_flower = &offload; + + dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); +} + static bool fl_destroy(struct tcf_proto *tp, bool force) { struct cls_fl_head *head = rtnl_dereference(tp->root); @@ -174,6 +219,7 @@ static bool fl_destroy(struct tcf_proto *tp, bool force) return false; list_for_each_entry_safe(f, next, &head->filters, list) { + fl_hw_destroy_filter(tp, (unsigned long)f); list_del_rcu(&f->list); call_rcu(&f->rcu, fl_destroy_filter); } @@ -459,6 +505,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_filter *fnew; struct nlattr *tb[TCA_FLOWER_MAX + 1]; struct fl_flow_mask mask = {}; + u32 flags = 0; int err; if (!tca[TCA_OPTIONS]) @@ -486,6 +533,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } fnew->handle = handle; + if (tb[TCA_FLOWER_FLAGS]) + flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); + err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); if (err) goto errout; @@ -498,9 +548,20 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, head->ht_params); if (err) goto errout; - if (fold) + + fl_hw_replace_filter(tp, + &head->dissector, + &mask.key, + &fnew->key, + &fnew->exts, + (unsigned long)fnew, + flags); + + if (fold) { rhashtable_remove_fast(&head->ht, &fold->ht_node, head->ht_params); + fl_hw_destroy_filter(tp, (unsigned long)fold); + } *arg = (unsigned long) fnew; @@ -527,6 +588,7 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg) rhashtable_remove_fast(&head->ht, &f->ht_node, head->ht_params); list_del_rcu(&f->list); + fl_hw_destroy_filter(tp, (unsigned long)f); tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, fl_destroy_filter); return 0; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index d0dff0cd8186..34b4ddaca27c 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -276,7 +276,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - skb = p->q->ops->dequeue(p->q); + skb = qdisc_dequeue_peeked(p->q); if (skb == NULL) return NULL; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ec529121f38a..ce46f1c7f133 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, } return 0; } + if (addr1->v6.sin6_port != addr2->v6.sin6_port) + return 0; if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ diff --git a/net/sctp/proc.c b/net/sctp/proc.c index cfc3c7101a38..5cfac8d5d3b3 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -480,7 +480,7 @@ static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v) static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) { struct sctp_association *assoc; - struct sctp_transport *tsp; + struct sctp_transport *transport, *tsp; if (v == SEQ_START_TOKEN) { seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " @@ -488,10 +488,10 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) return 0; } - tsp = (struct sctp_transport *)v; - if (!sctp_transport_hold(tsp)) + transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) return 0; - assoc = tsp->asoc; + assoc = transport->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { @@ -544,7 +544,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } - sctp_transport_put(tsp); + sctp_transport_put(transport); return 0; } diff --git a/net/socket.c b/net/socket.c index c044d1e8508c..886649c88d8f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -533,7 +533,7 @@ static const struct inode_operations sockfs_inode_ops = { * NULL is returned. */ -static struct socket *sock_alloc(void) +struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; @@ -554,6 +554,7 @@ static struct socket *sock_alloc(void) this_cpu_add(sockets_in_use, 1); return sock; } +EXPORT_SYMBOL(sock_alloc); /** * sock_release - close a socket @@ -1874,7 +1875,8 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, - struct used_address *used_address) + struct used_address *used_address, + unsigned int allowed_msghdr_flags) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; @@ -1900,6 +1902,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, if (msg_sys->msg_controllen > INT_MAX) goto out_freeiov; + flags |= (msg_sys->msg_flags & allowed_msghdr_flags); ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { err = @@ -1978,7 +1981,7 @@ long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags) if (!sock) goto out; - err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL); + err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); fput_light(sock->file, fput_needed); out: @@ -2005,6 +2008,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct used_address used_address; + unsigned int oflags = flags; if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; @@ -2019,11 +2023,15 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; err = 0; + flags |= MSG_BATCH; while (datagrams < vlen) { + if (datagrams == vlen - 1) + flags = oflags; + if (MSG_CMSG_COMPAT & flags) { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry, - &msg_sys, flags, &used_address); + &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); @@ -2031,7 +2039,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, } else { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)entry, - &msg_sys, flags, &used_address); + &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = put_user(err, &entry->msg_len); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 799e65b944b9..cabf586f47d7 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -740,7 +740,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) default: printk(KERN_CRIT "%s: bad return from " "gss_fill_context: %zd\n", __func__, err); - BUG(); + gss_msg->msg.errno = -EIO; } goto err_release_msg; } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2b32fd602669..273bc3a35425 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize) if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; - while (len < bufsize) { + while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index cc1251d07297..2dcd7640eeb5 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -341,6 +341,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, rqst->rq_reply_bytes_recvd = 0; rqst->rq_bytes_sent = 0; rqst->rq_xid = headerp->rm_xid; + + rqst->rq_private_buf.len = size; set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state); buf = &rqst->rq_rcv_buf; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 47f7da58a7f0..8b5833c1ff2e 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1093,8 +1093,11 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .cb = cb, .idx = idx, }; + int err; - switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb); + err = switchdev_port_obj_dump(dev, &dump.fdb.obj, + switchdev_port_fdb_dump_cb); + cb->args[1] = err; return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index e401108360a2..ae469b37d852 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -412,11 +412,6 @@ enomem: return -ENOMEM; } -void tipc_bcast_reinit(struct net *net) -{ - tipc_link_reinit(tipc_bc_sndlink(net), tipc_own_addr(net)); -} - void tipc_bcast_stop(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 1944c6c00bb9..d5e79b3767fd 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -46,7 +46,6 @@ struct tipc_node_map; extern const char tipc_bclink_name[]; int tipc_bcast_init(struct net *net); -void tipc_bcast_reinit(struct net *net); void tipc_bcast_stop(struct net *net); void tipc_bcast_add_peer(struct net *net, struct tipc_link *l, struct sk_buff_head *xmitq); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 802ffad3200d..27a5406213c6 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -40,6 +40,7 @@ #include "link.h" #include "discover.h" #include "bcast.h" +#include "netlink.h" #define MAX_ADDR_STR 60 @@ -54,23 +55,6 @@ static struct tipc_media * const media_info_array[] = { NULL }; -static const struct nla_policy -tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1] = { - [TIPC_NLA_BEARER_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_BEARER_NAME] = { - .type = NLA_STRING, - .len = TIPC_MAX_BEARER_NAME - }, - [TIPC_NLA_BEARER_PROP] = { .type = NLA_NESTED }, - [TIPC_NLA_BEARER_DOMAIN] = { .type = NLA_U32 } -}; - -static const struct nla_policy tipc_nl_media_policy[TIPC_NLA_MEDIA_MAX + 1] = { - [TIPC_NLA_MEDIA_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_MEDIA_NAME] = { .type = NLA_STRING }, - [TIPC_NLA_MEDIA_PROP] = { .type = NLA_NESTED } -}; - static void bearer_disable(struct net *net, struct tipc_bearer *b); /** diff --git a/net/tipc/link.c b/net/tipc/link.c index e31d92f80572..7d2bb3e70baa 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1,7 +1,7 @@ /* * net/tipc/link.c: TIPC link code * - * Copyright (c) 1996-2007, 2012-2015, Ericsson AB + * Copyright (c) 1996-2007, 2012-2016, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -127,6 +127,7 @@ struct tipc_link { /* Management and link supervision data */ u32 peer_session; + u32 session; u32 peer_bearer_id; u32 bearer_id; u32 tolerance; @@ -136,11 +137,7 @@ struct tipc_link { u16 peer_caps; bool active; u32 silent_intv_cnt; - struct { - unchar hdr[INT_H_SIZE]; - unchar body[TIPC_MAX_IF_NAME]; - } proto_msg; - struct tipc_msg *pmsg; + char if_name[TIPC_MAX_IF_NAME]; u32 priority; char net_plane; @@ -195,14 +192,6 @@ struct tipc_link { static const char *link_co_err = "Link tunneling error, "; static const char *link_rst_msg = "Resetting link "; -/* Properties valid for media, bearar and link */ -static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { - [TIPC_NLA_PROP_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 }, - [TIPC_NLA_PROP_TOL] = { .type = NLA_U32 }, - [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 } -}; - /* Send states for broadcast NACKs */ enum { @@ -215,10 +204,11 @@ enum { * Interval between NACKs when packets arrive out of order */ #define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) -/* - * Out-of-range value for link session numbers + +/* Wildcard value for link session numbers. When it is known that + * peer endpoint is down, any session number must be accepted. */ -#define WILDCARD_SESSION 0x10000 +#define ANY_SESSION 0x10000 /* Link FSM states: */ @@ -398,16 +388,6 @@ char *tipc_link_name(struct tipc_link *l) return l->name; } -static u32 link_own_addr(struct tipc_link *l) -{ - return msg_prevnode(l->pmsg); -} - -void tipc_link_reinit(struct tipc_link *l, u32 addr) -{ - msg_set_prevnode(l->pmsg, addr); -} - /** * tipc_link_create - create a new link * @n: pointer to associated node @@ -441,29 +421,22 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, struct tipc_link **link) { struct tipc_link *l; - struct tipc_msg *hdr; l = kzalloc(sizeof(*l), GFP_ATOMIC); if (!l) return false; *link = l; - l->pmsg = (struct tipc_msg *)&l->proto_msg; - hdr = l->pmsg; - tipc_msg_init(ownnode, hdr, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, peer); - msg_set_size(hdr, sizeof(l->proto_msg)); - msg_set_session(hdr, session); - msg_set_bearer_id(hdr, l->bearer_id); + l->session = session; /* Note: peer i/f name is completed by reset/activate message */ sprintf(l->name, "%u.%u.%u:%s-%u.%u.%u:unknown", tipc_zone(ownnode), tipc_cluster(ownnode), tipc_node(ownnode), if_name, tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); - strcpy((char *)msg_data(hdr), if_name); - + strcpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; - l->peer_session = WILDCARD_SESSION; + l->peer_session = ANY_SESSION; l->bearer_id = bearer_id; l->tolerance = tolerance; l->net_plane = net_plane; @@ -790,7 +763,7 @@ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) struct tipc_msg *msg = buf_msg(skb_peek(list)); int imp = msg_importance(msg); u32 oport = msg_origport(msg); - u32 addr = link_own_addr(link); + u32 addr = tipc_own_addr(link->net); struct sk_buff *skb; /* This really cannot happen... */ @@ -839,16 +812,9 @@ void link_prepare_wakeup(struct tipc_link *l) void tipc_link_reset(struct tipc_link *l) { - /* Link is down, accept any session */ - l->peer_session = WILDCARD_SESSION; - - /* If peer is up, it only accepts an incremented session number */ - msg_set_session(l->pmsg, msg_session(l->pmsg) + 1); - - /* Prepare for renewed mtu size negotiation */ + l->peer_session = ANY_SESSION; + l->session++; l->mtu = l->advertised_mtu; - - /* Clean up all queues and counters: */ __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); skb_queue_splice_init(&l->wakeupq, l->inputq); @@ -1156,7 +1122,7 @@ int tipc_link_build_ack_msg(struct tipc_link *l, struct sk_buff_head *xmitq) /* Broadcast ACK must be sent via a unicast link => defer to caller */ if (link_is_bc_rcvlink(l)) { - if (((l->rcv_nxt ^ link_own_addr(l)) & 0xf) != 0xf) + if (((l->rcv_nxt ^ tipc_own_addr(l->net)) & 0xf) != 0xf) return 0; l->rcv_unacked = 0; return TIPC_LINK_SND_BC_ACK; @@ -1268,15 +1234,30 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, u16 rcvgap, int tolerance, int priority, struct sk_buff_head *xmitq) { - struct sk_buff *skb = NULL; - struct tipc_msg *hdr = l->pmsg; + struct sk_buff *skb; + struct tipc_msg *hdr; + struct sk_buff_head *dfq = &l->deferdq; bool node_up = link_is_up(l->bc_rcvlink); /* Don't send protocol message during reset or link failover */ if (tipc_link_is_blocked(l)) return; - msg_set_type(hdr, mtyp); + if (!tipc_link_is_up(l) && (mtyp == STATE_MSG)) + return; + + if (!skb_queue_empty(dfq)) + rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; + + skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE, + TIPC_MAX_IF_NAME, l->addr, + tipc_own_addr(l->net), 0, 0, 0); + if (!skb) + return; + + hdr = buf_msg(skb); + msg_set_session(hdr, l->session); + msg_set_bearer_id(hdr, l->bearer_id); msg_set_net_plane(hdr, l->net_plane); msg_set_next_sent(hdr, l->snd_nxt); msg_set_ack(hdr, l->rcv_nxt - 1); @@ -1286,36 +1267,23 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_linkprio(hdr, priority); msg_set_redundant_link(hdr, node_up); msg_set_seq_gap(hdr, 0); - - /* Compatibility: created msg must not be in sequence with pkt flow */ msg_set_seqno(hdr, l->snd_nxt + U16_MAX / 2); if (mtyp == STATE_MSG) { - if (!tipc_link_is_up(l)) - return; - - /* Override rcvgap if there are packets in deferred queue */ - if (!skb_queue_empty(&l->deferdq)) - rcvgap = buf_seqno(skb_peek(&l->deferdq)) - l->rcv_nxt; - if (rcvgap) { - msg_set_seq_gap(hdr, rcvgap); - l->stats.sent_nacks++; - } + msg_set_seq_gap(hdr, rcvgap); + msg_set_size(hdr, INT_H_SIZE); msg_set_probe(hdr, probe); - if (probe) - l->stats.sent_probes++; l->stats.sent_states++; l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ msg_set_max_pkt(hdr, l->advertised_mtu); - msg_set_ack(hdr, l->rcv_nxt - 1); - msg_set_next_sent(hdr, 1); + strcpy(msg_data(hdr), l->if_name); } - skb = tipc_buf_acquire(msg_size(hdr)); - if (!skb) - return; - skb_copy_to_linear_data(skb, hdr, msg_size(hdr)); + if (probe) + l->stats.sent_probes++; + if (rcvgap) + l->stats.sent_nacks++; skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, skb); } @@ -1340,7 +1308,7 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, /* At least one packet required for safe algorithm => add dummy */ skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, - BASIC_H_SIZE, 0, l->addr, link_own_addr(l), + BASIC_H_SIZE, 0, l->addr, tipc_own_addr(l->net), 0, 0, TIPC_ERR_NO_PORT); if (!skb) { pr_warn("%sunable to create tunnel packet\n", link_co_err); @@ -1351,7 +1319,7 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, __skb_queue_purge(&tmpxq); /* Initialize reusable tunnel packet header */ - tipc_msg_init(link_own_addr(l), &tnlhdr, TUNNEL_PROTOCOL, + tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL, mtyp, INT_H_SIZE, l->addr); pktcnt = skb_queue_len(&l->transmq) + skb_queue_len(&l->backlogq); msg_set_msgcnt(&tnlhdr, pktcnt); @@ -1410,7 +1378,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (tipc_link_is_blocked(l) || !xmitq) goto exit; - if (link_own_addr(l) > msg_prevnode(hdr)) + if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); switch (mtyp) { @@ -1418,7 +1386,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, /* Ignore duplicate RESET with old session number */ if ((less_eq(msg_session(hdr), l->peer_session)) && - (l->peer_session != WILDCARD_SESSION)) + (l->peer_session != ANY_SESSION)) break; /* fall thru' */ @@ -1515,7 +1483,7 @@ static bool tipc_link_build_bc_proto_msg(struct tipc_link *l, bool bcast, u16 gap_to = peers_snd_nxt - 1; skb = tipc_msg_create(BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, - 0, l->addr, link_own_addr(l), 0, 0, 0); + 0, l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!skb) return false; hdr = buf_msg(skb); @@ -1670,7 +1638,7 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, if (mtyp != STATE_MSG) return 0; - if (dnode == link_own_addr(l)) { + if (dnode == tipc_own_addr(l->net)) { tipc_link_bc_ack_rcv(l, acked, xmitq); rc = tipc_link_retrans(l->bc_sndlink, from, to, xmitq); l->stats.recv_nacks++; diff --git a/net/tipc/link.h b/net/tipc/link.h index b4ee9d6e181d..6a94175ee20a 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -86,7 +86,6 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, struct sk_buff_head *namedq, struct tipc_link *bc_sndlink, struct tipc_link **link); -void tipc_link_reinit(struct tipc_link *l, u32 addr); void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq); void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 777b979b8463..e190460fe0d3 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -47,12 +47,6 @@ #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ -static const struct nla_policy -tipc_nl_name_table_policy[TIPC_NLA_NAME_TABLE_MAX + 1] = { - [TIPC_NLA_NAME_TABLE_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_NAME_TABLE_PUBL] = { .type = NLA_NESTED } -}; - /** * struct name_info - name sequence publication info * @node_list: circular list of publications made by own node diff --git a/net/tipc/net.c b/net/tipc/net.c index 77bf9113c7a7..28bf4feeb81c 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -41,11 +41,7 @@ #include "socket.h" #include "node.h" #include "bcast.h" - -static const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { - [TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_NET_ID] = { .type = NLA_U32 } -}; +#include "netlink.h" /* * The TIPC locking policy is designed to ensure a very fine locking @@ -116,7 +112,6 @@ int tipc_net_start(struct net *net, u32 addr) tn->own_addr = addr; tipc_named_reinit(net); tipc_sk_reinit(net); - tipc_bcast_reinit(net); tipc_nametbl_publish(net, TIPC_CFG_SRV, tn->own_addr, tn->own_addr, TIPC_ZONE_SCOPE, 0, tn->own_addr); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 8975b0135b76..56935df2167a 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -55,6 +55,75 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = { [TIPC_NLA_NAME_TABLE] = { .type = NLA_NESTED, } }; +const struct nla_policy +tipc_nl_name_table_policy[TIPC_NLA_NAME_TABLE_MAX + 1] = { + [TIPC_NLA_NAME_TABLE_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_NAME_TABLE_PUBL] = { .type = NLA_NESTED } +}; + +const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { + [TIPC_NLA_SOCK_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_SOCK_ADDR] = { .type = NLA_U32 }, + [TIPC_NLA_SOCK_REF] = { .type = NLA_U32 }, + [TIPC_NLA_SOCK_CON] = { .type = NLA_NESTED }, + [TIPC_NLA_SOCK_HAS_PUBL] = { .type = NLA_FLAG } +}; + +const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { + [TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_NET_ID] = { .type = NLA_U32 } +}; + +const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { + [TIPC_NLA_LINK_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_LINK_NAME] = { .type = NLA_STRING, + .len = TIPC_MAX_LINK_NAME }, + [TIPC_NLA_LINK_MTU] = { .type = NLA_U32 }, + [TIPC_NLA_LINK_BROADCAST] = { .type = NLA_FLAG }, + [TIPC_NLA_LINK_UP] = { .type = NLA_FLAG }, + [TIPC_NLA_LINK_ACTIVE] = { .type = NLA_FLAG }, + [TIPC_NLA_LINK_PROP] = { .type = NLA_NESTED }, + [TIPC_NLA_LINK_STATS] = { .type = NLA_NESTED }, + [TIPC_NLA_LINK_RX] = { .type = NLA_U32 }, + [TIPC_NLA_LINK_TX] = { .type = NLA_U32 } +}; + +const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = { + [TIPC_NLA_NODE_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_NODE_ADDR] = { .type = NLA_U32 }, + [TIPC_NLA_NODE_UP] = { .type = NLA_FLAG } +}; + +/* Properties valid for media, bearer and link */ +const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { + [TIPC_NLA_PROP_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_TOL] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 } +}; + +const struct nla_policy tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1] = { + [TIPC_NLA_BEARER_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_BEARER_NAME] = { .type = NLA_STRING, + .len = TIPC_MAX_BEARER_NAME }, + [TIPC_NLA_BEARER_PROP] = { .type = NLA_NESTED }, + [TIPC_NLA_BEARER_DOMAIN] = { .type = NLA_U32 } +}; + +const struct nla_policy tipc_nl_media_policy[TIPC_NLA_MEDIA_MAX + 1] = { + [TIPC_NLA_MEDIA_UNSPEC] = { .type = NLA_UNSPEC }, + [TIPC_NLA_MEDIA_NAME] = { .type = NLA_STRING }, + [TIPC_NLA_MEDIA_PROP] = { .type = NLA_NESTED } +}; + +const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { + [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, + [TIPC_NLA_UDP_LOCAL] = {.type = NLA_BINARY, + .len = sizeof(struct sockaddr_storage)}, + [TIPC_NLA_UDP_REMOTE] = {.type = NLA_BINARY, + .len = sizeof(struct sockaddr_storage)}, +}; + /* Users of the legacy API (tipc-config) can't handle that we add operations, * so we have a separate genl handling for the new API. */ diff --git a/net/tipc/netlink.h b/net/tipc/netlink.h index 08a1db67b927..ed1dbcb4afbd 100644 --- a/net/tipc/netlink.h +++ b/net/tipc/netlink.h @@ -35,6 +35,7 @@ #ifndef _TIPC_NETLINK_H #define _TIPC_NETLINK_H +#include <net/netlink.h> extern struct genl_family tipc_genl_family; int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***buf); @@ -45,6 +46,16 @@ struct tipc_nl_msg { u32 seq; }; +extern const struct nla_policy tipc_nl_name_table_policy[]; +extern const struct nla_policy tipc_nl_sock_policy[]; +extern const struct nla_policy tipc_nl_net_policy[]; +extern const struct nla_policy tipc_nl_link_policy[]; +extern const struct nla_policy tipc_nl_node_policy[]; +extern const struct nla_policy tipc_nl_prop_policy[]; +extern const struct nla_policy tipc_nl_bearer_policy[]; +extern const struct nla_policy tipc_nl_media_policy[]; +extern const struct nla_policy tipc_nl_udp_policy[]; + int tipc_netlink_start(void); int tipc_netlink_compat_start(void); void tipc_netlink_stop(void); diff --git a/net/tipc/node.c b/net/tipc/node.c index cdb79503d890..ace178fd3850 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -41,6 +41,7 @@ #include "socket.h" #include "bcast.h" #include "discover.h" +#include "netlink.h" #define INVALID_NODE_SIG 0x10000 @@ -164,28 +165,6 @@ struct tipc_sock_conn { struct list_head list; }; -static const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { - [TIPC_NLA_LINK_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_LINK_NAME] = { - .type = NLA_STRING, - .len = TIPC_MAX_LINK_NAME - }, - [TIPC_NLA_LINK_MTU] = { .type = NLA_U32 }, - [TIPC_NLA_LINK_BROADCAST] = { .type = NLA_FLAG }, - [TIPC_NLA_LINK_UP] = { .type = NLA_FLAG }, - [TIPC_NLA_LINK_ACTIVE] = { .type = NLA_FLAG }, - [TIPC_NLA_LINK_PROP] = { .type = NLA_NESTED }, - [TIPC_NLA_LINK_STATS] = { .type = NLA_NESTED }, - [TIPC_NLA_LINK_RX] = { .type = NLA_U32 }, - [TIPC_NLA_LINK_TX] = { .type = NLA_U32 } -}; - -static const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = { - [TIPC_NLA_NODE_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_NODE_ADDR] = { .type = NLA_U32 }, - [TIPC_NLA_NODE_UP] = { .type = NLA_FLAG } -}; - static struct tipc_link *node_active_link(struct tipc_node *n, int sel) { int bearer_id = n->active_links[sel & 1]; @@ -843,7 +822,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, memcpy(&le->maddr, maddr, sizeof(*maddr)); exit: tipc_node_write_unlock(n); - if (reset && !tipc_link_is_reset(l)) + if (reset && l && !tipc_link_is_reset(l)) tipc_node_link_down(n, b->identity, false); tipc_node_put(n); } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 69c29050f14a..3eeb50a27b89 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -42,6 +42,7 @@ #include "name_distr.h" #include "socket.h" #include "bcast.h" +#include "netlink.h" #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ @@ -126,14 +127,6 @@ static const struct proto_ops stream_ops; static const struct proto_ops msg_ops; static struct proto tipc_proto; -static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { - [TIPC_NLA_SOCK_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_SOCK_ADDR] = { .type = NLA_U32 }, - [TIPC_NLA_SOCK_REF] = { .type = NLA_U32 }, - [TIPC_NLA_SOCK_CON] = { .type = NLA_NESTED }, - [TIPC_NLA_SOCK_HAS_PUBL] = { .type = NLA_FLAG } -}; - static const struct rhashtable_params tsk_rht_params; /* @@ -673,7 +666,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct iov_iter save = msg->msg_iter; uint mtu; int rc; @@ -687,14 +680,16 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, msg_set_nameupper(mhdr, seq->upper); msg_set_hdr_sz(mhdr, MCAST_H_SIZE); + skb_queue_head_init(&pktchain); + new_mtu: mtu = tipc_bcast_get_mtu(net); - rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain); if (unlikely(rc < 0)) return rc; do { - rc = tipc_bcast_xmit(net, pktchain); + rc = tipc_bcast_xmit(net, &pktchain); if (likely(!rc)) return dsz; @@ -704,7 +699,7 @@ new_mtu: if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; @@ -863,7 +858,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; u32 dnode, dport; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct sk_buff *skb; struct tipc_name_seq *seq; struct iov_iter save; @@ -924,17 +919,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) msg_set_hdr_sz(mhdr, BASIC_H_SIZE); } + skb_queue_head_init(&pktchain); save = m->msg_iter; new_mtu: mtu = tipc_node_get_mtu(net, dnode, tsk->portid); - rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain); if (rc < 0) return rc; do { - skb = skb_peek(pktchain); + skb = skb_peek(&pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid); if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; @@ -946,7 +942,7 @@ new_mtu: if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; @@ -1016,7 +1012,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); u32 portid = tsk->portid; int rc = -EINVAL; @@ -1044,17 +1040,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); dnode = tsk_peer_node(tsk); + skb_queue_head_init(&pktchain); next: save = m->msg_iter; mtu = tsk->max_pkt; send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); - rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain); if (unlikely(rc < 0)) return rc; + do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_node_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, &pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1063,7 +1061,7 @@ next: goto next; } if (rc == -EMSGSIZE) { - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1077,7 +1075,7 @@ next: rc = tipc_wait_for_sndpkt(sock, &timeo); } while (!rc); - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); return sent ? sent : rc; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 22963cafd5ed..e6cb386fbf34 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -326,7 +326,8 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, return tipc_subscrp_cancel(s, subscriber); } - tipc_subscrp_subscribe(net, s, subscriber, swap); + if (s) + tipc_subscrp_subscribe(net, s, subscriber, swap); } /* Handle one request to establish a new subscriber */ diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index d63a911e7fe2..c94f9a15e2cd 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -48,20 +48,13 @@ #include <linux/tipc_netlink.h> #include "core.h" #include "bearer.h" +#include "netlink.h" /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 #define UDP_MIN_HEADROOM 28 -static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { - [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, - [TIPC_NLA_UDP_LOCAL] = {.type = NLA_BINARY, - .len = sizeof(struct sockaddr_storage)}, - [TIPC_NLA_UDP_REMOTE] = {.type = NLA_BINARY, - .len = sizeof(struct sockaddr_storage)}, -}; - /** * struct udp_media_addr - IP/UDP addressing information * @@ -181,6 +174,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, err = PTR_ERR(rt); goto tx_error; } + + skb->dev = rt->dst.dev; ttl = ip4_dst_hoplimit(&rt->dst); udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr, dst->ipv4.s_addr, 0, ttl, 0, src->udp_port, @@ -201,7 +196,7 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, ttl = ip6_dst_hoplimit(ndst); err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, ndst->dev, &src->ipv6, - &dst->ipv6, 0, ttl, src->udp_port, + &dst->ipv6, 0, ttl, 0, src->udp_port, dst->udp_port, false); #endif } @@ -274,7 +269,7 @@ static int parse_options(struct nlattr *attrs[], struct udp_bearer *ub, struct udp_media_addr *remote) { struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; - struct sockaddr_storage *sa_local, *sa_remote; + struct sockaddr_storage sa_local, sa_remote; if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) goto err; @@ -283,41 +278,48 @@ static int parse_options(struct nlattr *attrs[], struct udp_bearer *ub, tipc_nl_udp_policy)) goto err; if (opts[TIPC_NLA_UDP_LOCAL] && opts[TIPC_NLA_UDP_REMOTE]) { - sa_local = nla_data(opts[TIPC_NLA_UDP_LOCAL]); - sa_remote = nla_data(opts[TIPC_NLA_UDP_REMOTE]); + nla_memcpy(&sa_local, opts[TIPC_NLA_UDP_LOCAL], + sizeof(sa_local)); + nla_memcpy(&sa_remote, opts[TIPC_NLA_UDP_REMOTE], + sizeof(sa_remote)); } else { err: pr_err("Invalid UDP bearer configuration"); return -EINVAL; } - if ((sa_local->ss_family & sa_remote->ss_family) == AF_INET) { + if ((sa_local.ss_family & sa_remote.ss_family) == AF_INET) { struct sockaddr_in *ip4; - ip4 = (struct sockaddr_in *)sa_local; + ip4 = (struct sockaddr_in *)&sa_local; local->proto = htons(ETH_P_IP); local->udp_port = ip4->sin_port; local->ipv4.s_addr = ip4->sin_addr.s_addr; - ip4 = (struct sockaddr_in *)sa_remote; + ip4 = (struct sockaddr_in *)&sa_remote; remote->proto = htons(ETH_P_IP); remote->udp_port = ip4->sin_port; remote->ipv4.s_addr = ip4->sin_addr.s_addr; return 0; #if IS_ENABLED(CONFIG_IPV6) - } else if ((sa_local->ss_family & sa_remote->ss_family) == AF_INET6) { + } else if ((sa_local.ss_family & sa_remote.ss_family) == AF_INET6) { + int atype; struct sockaddr_in6 *ip6; - ip6 = (struct sockaddr_in6 *)sa_local; + ip6 = (struct sockaddr_in6 *)&sa_local; + atype = ipv6_addr_type(&ip6->sin6_addr); + if (__ipv6_addr_needs_scope_id(atype) && !ip6->sin6_scope_id) + return -EINVAL; + local->proto = htons(ETH_P_IPV6); local->udp_port = ip6->sin6_port; - local->ipv6 = ip6->sin6_addr; + memcpy(&local->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr)); ub->ifindex = ip6->sin6_scope_id; - ip6 = (struct sockaddr_in6 *)sa_remote; + ip6 = (struct sockaddr_in6 *)&sa_remote; remote->proto = htons(ETH_P_IPV6); remote->udp_port = ip6->sin6_port; - remote->ipv6 = ip6->sin6_addr; + memcpy(&remote->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr)); return 0; #endif } diff --git a/net/wireless/core.c b/net/wireless/core.c index 3a9c41bc849a..9f1c4aa851ef 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1157,6 +1157,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, return NOTIFY_DONE; } + wireless_nlevent_flush(); + return NOTIFY_OK; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 90890f183c0e..98c924260b3d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7554,7 +7554,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) && no_ht) { - kfree(connkeys); + kzfree(connkeys); return -EINVAL; } } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 79bd3a171caa..544558171787 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -917,6 +917,12 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); + /* stop critical protocol if supported */ + if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { + rdev->crit_proto_nlportid = 0; + rdev_crit_proto_stop(rdev, wdev); + } + /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c8717c1d082e..b50ee5d622e1 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -342,6 +342,40 @@ static const int compat_event_type_size[] = { /* IW event code */ +void wireless_nlevent_flush(void) +{ + struct sk_buff *skb; + struct net *net; + + ASSERT_RTNL(); + + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } +} +EXPORT_SYMBOL_GPL(wireless_nlevent_flush); + +static int wext_netdev_notifier_call(struct notifier_block *nb, + unsigned long state, void *ptr) +{ + /* + * When a netdev changes state in any way, flush all pending messages + * to avoid them going out in a strange order, e.g. RTM_NEWLINK after + * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() + * or similar - all of which could otherwise happen due to delays from + * schedule_work(). + */ + wireless_nlevent_flush(); + + return NOTIFY_OK; +} + +static struct notifier_block wext_netdev_notifier = { + .notifier_call = wext_netdev_notifier_call, +}; + static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); @@ -360,7 +394,12 @@ static struct pernet_operations wext_pernet_ops = { static int __init wireless_nlevent_init(void) { - return register_pernet_subsys(&wext_pernet_ops); + int err = register_pernet_subsys(&wext_pernet_ops); + + if (err) + return err; + + return register_netdevice_notifier(&wext_netdev_notifier); } subsys_initcall(wireless_nlevent_init); @@ -368,17 +407,8 @@ subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { - struct sk_buff *skb; - struct net *net; - rtnl_lock(); - - for_each_net(net) { - while ((skb = skb_dequeue(&net->wext_nlevents))) - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, - GFP_KERNEL); - } - + wireless_nlevent_flush(); rtnl_unlock(); } diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index c4f8ae0c8afe..502c9fc8db85 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -17,6 +17,8 @@ hostprogs-y += tracex6 hostprogs-y += trace_output hostprogs-y += lathist hostprogs-y += offwaketime +hostprogs-y += spintest +hostprogs-y += map_perf_test test_verifier-objs := test_verifier.o libbpf.o test_maps-objs := test_maps.o libbpf.o @@ -34,6 +36,8 @@ tracex6-objs := bpf_load.o libbpf.o tracex6_user.o trace_output-objs := bpf_load.o libbpf.o trace_output_user.o lathist-objs := bpf_load.o libbpf.o lathist_user.o offwaketime-objs := bpf_load.o libbpf.o offwaketime_user.o +spintest-objs := bpf_load.o libbpf.o spintest_user.o +map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -50,6 +54,8 @@ always += trace_output_kern.o always += tcbpf1_kern.o always += lathist_kern.o always += offwaketime_kern.o +always += spintest_kern.o +always += map_perf_test_kern.o HOSTCFLAGS += -I$(objtree)/usr/include @@ -67,6 +73,8 @@ HOSTLOADLIBES_tracex6 += -lelf HOSTLOADLIBES_trace_output += -lelf -lrt HOSTLOADLIBES_lathist += -lelf HOSTLOADLIBES_offwaketime += -lelf +HOSTLOADLIBES_spintest += -lelf +HOSTLOADLIBES_map_perf_test += -lelf -lrt # point this to your LLVM backend with bpf support LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 811bcca0f29d..9363500131a7 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -61,6 +61,7 @@ struct bpf_map_def { unsigned int key_size; unsigned int value_size; unsigned int max_entries; + unsigned int map_flags; }; static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) = diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index da86a8e0a95a..58f86bd11b3d 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -157,9 +157,13 @@ static int load_maps(struct bpf_map_def *maps, int len) map_fd[i] = bpf_create_map(maps[i].type, maps[i].key_size, maps[i].value_size, - maps[i].max_entries); - if (map_fd[i] < 0) + maps[i].max_entries, + maps[i].map_flags); + if (map_fd[i] < 0) { + printf("failed to create a map: %d %s\n", + errno, strerror(errno)); return 1; + } if (maps[i].type == BPF_MAP_TYPE_PROG_ARRAY) prog_array_fd = map_fd[i]; @@ -343,3 +347,65 @@ void read_trace_pipe(void) } } } + +#define MAX_SYMS 300000 +static struct ksym syms[MAX_SYMS]; +static int sym_cnt; + +static int ksym_cmp(const void *p1, const void *p2) +{ + return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; +} + +int load_kallsyms(void) +{ + FILE *f = fopen("/proc/kallsyms", "r"); + char func[256], buf[256]; + char symbol; + void *addr; + int i = 0; + + if (!f) + return -ENOENT; + + while (!feof(f)) { + if (!fgets(buf, sizeof(buf), f)) + break; + if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) + break; + if (!addr) + continue; + syms[i].addr = (long) addr; + syms[i].name = strdup(func); + i++; + } + sym_cnt = i; + qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); + return 0; +} + +struct ksym *ksym_search(long key) +{ + int start = 0, end = sym_cnt; + int result; + + while (start < end) { + size_t mid = start + (end - start) / 2; + + result = key - syms[mid].addr; + if (result < 0) + end = mid; + else if (result > 0) + start = mid + 1; + else + return &syms[mid]; + } + + if (start >= 1 && syms[start - 1].addr < key && + key < syms[start].addr) + /* valid ksym */ + return &syms[start - 1]; + + /* out of range. return _stext */ + return &syms[0]; +} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index cbd7c2b532b9..dfa57fe65c8e 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -23,5 +23,11 @@ extern int event_fd[MAX_PROGS]; int load_bpf_file(char *path); void read_trace_pipe(void); +struct ksym { + long addr; + char *name; +}; +int load_kallsyms(void); +struct ksym *ksym_search(long key); #endif diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index e2fd16c3d0f0..625e797be6ef 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -44,7 +44,7 @@ static void usage(void) static int bpf_map_create(void) { return bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(uint32_t), - sizeof(uint32_t), 1024); + sizeof(uint32_t), 1024, 0); } static int bpf_prog_create(const char *object) diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c index 65a8d48d2799..9969e35550c3 100644 --- a/samples/bpf/libbpf.c +++ b/samples/bpf/libbpf.c @@ -19,13 +19,14 @@ static __u64 ptr_to_u64(void *ptr) } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, - int max_entries) + int max_entries, int map_flags) { union bpf_attr attr = { .map_type = map_type, .key_size = key_size, .value_size = value_size, - .max_entries = max_entries + .max_entries = max_entries, + .map_flags = map_flags, }; return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h index 014aacf916e4..364582b77888 100644 --- a/samples/bpf/libbpf.h +++ b/samples/bpf/libbpf.h @@ -5,7 +5,7 @@ struct bpf_insn; int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, - int max_entries); + int max_entries, int map_flags); int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags); int bpf_lookup_elem(int fd, void *key, void *value); int bpf_delete_elem(int fd, void *key); diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c new file mode 100644 index 000000000000..311538e5a701 --- /dev/null +++ b/samples/bpf/map_perf_test_kern.c @@ -0,0 +1,100 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +#define MAX_ENTRIES 1000 + +struct bpf_map_def SEC("maps") hash_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, +}; + +struct bpf_map_def SEC("maps") percpu_hash_map = { + .type = BPF_MAP_TYPE_PERCPU_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, +}; + +struct bpf_map_def SEC("maps") hash_map_alloc = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, + .map_flags = BPF_F_NO_PREALLOC, +}; + +struct bpf_map_def SEC("maps") percpu_hash_map_alloc = { + .type = BPF_MAP_TYPE_PERCPU_HASH, + .key_size = sizeof(u32), + .value_size = sizeof(long), + .max_entries = MAX_ENTRIES, + .map_flags = BPF_F_NO_PREALLOC, +}; + +SEC("kprobe/sys_getuid") +int stress_hmap(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&hash_map, &key); + if (value) + bpf_map_delete_elem(&hash_map, &key); + return 0; +} + +SEC("kprobe/sys_geteuid") +int stress_percpu_hmap(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&percpu_hash_map, &key); + if (value) + bpf_map_delete_elem(&percpu_hash_map, &key); + return 0; +} +SEC("kprobe/sys_getgid") +int stress_hmap_alloc(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&hash_map_alloc, &key); + if (value) + bpf_map_delete_elem(&hash_map_alloc, &key); + return 0; +} + +SEC("kprobe/sys_getegid") +int stress_percpu_hmap_alloc(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key); + if (value) + bpf_map_delete_elem(&percpu_hash_map_alloc, &key); + return 0; +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c new file mode 100644 index 000000000000..95af56ec5739 --- /dev/null +++ b/samples/bpf/map_perf_test_user.c @@ -0,0 +1,155 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <sys/types.h> +#include <asm/unistd.h> +#include <unistd.h> +#include <assert.h> +#include <sys/wait.h> +#include <stdlib.h> +#include <signal.h> +#include <linux/bpf.h> +#include <string.h> +#include <time.h> +#include "libbpf.h" +#include "bpf_load.h" + +#define MAX_CNT 1000000 + +static __u64 time_get_ns(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ull + ts.tv_nsec; +} + +#define HASH_PREALLOC (1 << 0) +#define PERCPU_HASH_PREALLOC (1 << 1) +#define HASH_KMALLOC (1 << 2) +#define PERCPU_HASH_KMALLOC (1 << 3) + +static int test_flags = ~0; + +static void test_hash_prealloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getuid); + printf("%d:hash_map_perf pre-alloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_percpu_hash_prealloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_geteuid); + printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_hash_kmalloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getgid); + printf("%d:hash_map_perf kmalloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_percpu_hash_kmalloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) + syscall(__NR_getegid); + printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); +} + +static void loop(int cpu) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + sched_setaffinity(0, sizeof(cpuset), &cpuset); + + if (test_flags & HASH_PREALLOC) + test_hash_prealloc(cpu); + + if (test_flags & PERCPU_HASH_PREALLOC) + test_percpu_hash_prealloc(cpu); + + if (test_flags & HASH_KMALLOC) + test_hash_kmalloc(cpu); + + if (test_flags & PERCPU_HASH_KMALLOC) + test_percpu_hash_kmalloc(cpu); +} + +static void run_perf_test(int tasks) +{ + pid_t pid[tasks]; + int i; + + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + loop(i); + exit(0); + } else if (pid[i] == -1) { + printf("couldn't spawn #%d process\n", i); + exit(1); + } + } + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256]; + int num_cpu = 8; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + setrlimit(RLIMIT_MEMLOCK, &r); + + if (argc > 1) + test_flags = atoi(argv[1]) ? : test_flags; + + if (argc > 2) + num_cpu = atoi(argv[2]) ? : num_cpu; + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + run_perf_test(num_cpu); + + return 0; +} diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 17cf3024e22c..6f002a9c24fa 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -18,80 +18,15 @@ #include "libbpf.h" #include "bpf_load.h" -#define MAX_SYMS 300000 #define PRINT_RAW_ADDR 0 -static struct ksym { - long addr; - char *name; -} syms[MAX_SYMS]; -static int sym_cnt; - -static int ksym_cmp(const void *p1, const void *p2) -{ - return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; -} - -static int load_kallsyms(void) -{ - FILE *f = fopen("/proc/kallsyms", "r"); - char func[256], buf[256]; - char symbol; - void *addr; - int i = 0; - - if (!f) - return -ENOENT; - - while (!feof(f)) { - if (!fgets(buf, sizeof(buf), f)) - break; - if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) - break; - if (!addr) - continue; - syms[i].addr = (long) addr; - syms[i].name = strdup(func); - i++; - } - sym_cnt = i; - qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); - return 0; -} - -static void *search(long key) -{ - int start = 0, end = sym_cnt; - int result; - - while (start < end) { - size_t mid = start + (end - start) / 2; - - result = key - syms[mid].addr; - if (result < 0) - end = mid; - else if (result > 0) - start = mid + 1; - else - return &syms[mid]; - } - - if (start >= 1 && syms[start - 1].addr < key && - key < syms[start].addr) - /* valid ksym */ - return &syms[start - 1]; - - /* out of range. return _stext */ - return &syms[0]; -} - static void print_ksym(__u64 addr) { struct ksym *sym; if (!addr) return; - sym = search(addr); + sym = ksym_search(addr); if (PRINT_RAW_ADDR) printf("%s/%llx;", sym->name, addr); else diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c index a0ce251c5390..28b60baa9fa8 100644 --- a/samples/bpf/sock_example.c +++ b/samples/bpf/sock_example.c @@ -34,7 +34,7 @@ static int test_sock(void) long long value = 0, tcp_cnt, udp_cnt, icmp_cnt; map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), - 256); + 256, 0); if (map_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); goto cleanup; diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c new file mode 100644 index 000000000000..4b27619d91a4 --- /dev/null +++ b/samples/bpf/spintest_kern.c @@ -0,0 +1,68 @@ +/* Copyright (c) 2016, Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/perf_event.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") my_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(long), + .value_size = sizeof(long), + .max_entries = 1024, +}; +struct bpf_map_def SEC("maps") my_map2 = { + .type = BPF_MAP_TYPE_PERCPU_HASH, + .key_size = sizeof(long), + .value_size = sizeof(long), + .max_entries = 1024, +}; + +struct bpf_map_def SEC("maps") stackmap = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(u32), + .value_size = PERF_MAX_STACK_DEPTH * sizeof(u64), + .max_entries = 10000, +}; + +#define PROG(foo) \ +int foo(struct pt_regs *ctx) \ +{ \ + long v = ctx->ip, *val; \ +\ + val = bpf_map_lookup_elem(&my_map, &v); \ + bpf_map_update_elem(&my_map, &v, &v, BPF_ANY); \ + bpf_map_update_elem(&my_map2, &v, &v, BPF_ANY); \ + bpf_map_delete_elem(&my_map2, &v); \ + bpf_get_stackid(ctx, &stackmap, BPF_F_REUSE_STACKID); \ + return 0; \ +} + +/* add kprobes to all possible *spin* functions */ +SEC("kprobe/spin_unlock")PROG(p1) +SEC("kprobe/spin_lock")PROG(p2) +SEC("kprobe/mutex_spin_on_owner")PROG(p3) +SEC("kprobe/rwsem_spin_on_owner")PROG(p4) +SEC("kprobe/spin_unlock_irqrestore")PROG(p5) +SEC("kprobe/_raw_spin_unlock_irqrestore")PROG(p6) +SEC("kprobe/_raw_spin_unlock_bh")PROG(p7) +SEC("kprobe/_raw_spin_unlock")PROG(p8) +SEC("kprobe/_raw_spin_lock_irqsave")PROG(p9) +SEC("kprobe/_raw_spin_trylock_bh")PROG(p10) +SEC("kprobe/_raw_spin_lock_irq")PROG(p11) +SEC("kprobe/_raw_spin_trylock")PROG(p12) +SEC("kprobe/_raw_spin_lock")PROG(p13) +SEC("kprobe/_raw_spin_lock_bh")PROG(p14) +/* and to inner bpf helpers */ +SEC("kprobe/htab_map_update_elem")PROG(p15) +SEC("kprobe/__htab_percpu_map_update_elem")PROG(p16) +SEC("kprobe/htab_map_alloc")PROG(p17) + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c new file mode 100644 index 000000000000..311ede532230 --- /dev/null +++ b/samples/bpf/spintest_user.c @@ -0,0 +1,50 @@ +#include <stdio.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <string.h> +#include <assert.h> +#include <sys/resource.h> +#include "libbpf.h" +#include "bpf_load.h" + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + long key, next_key, value; + char filename[256]; + struct ksym *sym; + int i; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + setrlimit(RLIMIT_MEMLOCK, &r); + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return 2; + } + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + for (i = 0; i < 5; i++) { + key = 0; + printf("kprobing funcs:"); + while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) { + bpf_lookup_elem(map_fd[0], &next_key, &value); + assert(next_key == value); + sym = ksym_search(value); + printf(" %s", sym->name); + key = next_key; + } + if (key) + printf("\n"); + key = 0; + while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) + bpf_delete_elem(map_fd[0], &next_key); + sleep(1); + } + + return 0; +} diff --git a/samples/bpf/test_maps.c b/samples/bpf/test_maps.c index ad466ed33093..47bf0858f9e4 100644 --- a/samples/bpf/test_maps.c +++ b/samples/bpf/test_maps.c @@ -2,6 +2,7 @@ * Testsuite for eBPF maps * * Copyright (c) 2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -17,13 +18,16 @@ #include <stdlib.h> #include "libbpf.h" +static int map_flags; + /* sanity tests for map API */ static void test_hashmap_sanity(int i, void *data) { long long key, next_key, value; int map_fd; - map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), 2); + map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + 2, map_flags); if (map_fd < 0) { printf("failed to create hashmap '%s'\n", strerror(errno)); exit(1); @@ -99,7 +103,7 @@ static void test_percpu_hashmap_sanity(int task, void *data) int map_fd, i; map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), - sizeof(value[0]), 2); + sizeof(value[0]), 2, map_flags); if (map_fd < 0) { printf("failed to create hashmap '%s'\n", strerror(errno)); exit(1); @@ -188,7 +192,8 @@ static void test_arraymap_sanity(int i, void *data) int key, next_key, map_fd; long long value; - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), 2); + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), + 2, 0); if (map_fd < 0) { printf("failed to create arraymap '%s'\n", strerror(errno)); exit(1); @@ -244,7 +249,7 @@ static void test_percpu_arraymap_many_keys(void) int key, map_fd, i; map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(values[0]), nr_keys); + sizeof(values[0]), nr_keys, 0); if (map_fd < 0) { printf("failed to create per-cpu arraymap '%s'\n", strerror(errno)); @@ -275,7 +280,7 @@ static void test_percpu_arraymap_sanity(int i, void *data) int key, next_key, map_fd; map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(values[0]), 2); + sizeof(values[0]), 2, 0); if (map_fd < 0) { printf("failed to create arraymap '%s'\n", strerror(errno)); exit(1); @@ -336,7 +341,7 @@ static void test_map_large(void) /* allocate 4Mbyte of memory */ map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE); + MAP_SIZE, map_flags); if (map_fd < 0) { printf("failed to create large map '%s'\n", strerror(errno)); exit(1); @@ -421,7 +426,7 @@ static void test_map_parallel(void) int data[2]; map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE); + MAP_SIZE, map_flags); if (map_fd < 0) { printf("failed to create map for parallel test '%s'\n", strerror(errno)); @@ -463,7 +468,7 @@ static void test_map_parallel(void) assert(bpf_get_next_key(map_fd, &key, &key) == -1 && errno == ENOENT); } -int main(void) +static void run_all_tests(void) { test_hashmap_sanity(0, NULL); test_percpu_hashmap_sanity(0, NULL); @@ -474,6 +479,14 @@ int main(void) test_map_large(); test_map_parallel(); test_map_stress(); +} + +int main(void) +{ + map_flags = 0; + run_all_tests(); + map_flags = BPF_F_NO_PREALLOC; + run_all_tests(); printf("test_maps: OK\n"); return 0; } diff --git a/samples/bpf/test_verifier.c b/samples/bpf/test_verifier.c index 563c507c0a09..4b51a9039c0d 100644 --- a/samples/bpf/test_verifier.c +++ b/samples/bpf/test_verifier.c @@ -1198,7 +1198,7 @@ static int create_map(void) int map_fd; map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, - sizeof(long long), sizeof(long long), 1024); + sizeof(long long), sizeof(long long), 1024, 0); if (map_fd < 0) printf("failed to create map '%s'\n", strerror(errno)); @@ -1210,7 +1210,7 @@ static int create_prog_array(void) int map_fd; map_fd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, - sizeof(int), sizeof(int), 4); + sizeof(int), sizeof(int), 4, 0); if (map_fd < 0) printf("failed to create prog_array '%s'\n", strerror(errno)); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f8110cfd80ff..f1ab71504e1d 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3249,7 +3249,7 @@ static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t static void selinux_inode_getsecid(struct inode *inode, u32 *secid) { - struct inode_security_struct *isec = inode_security(inode); + struct inode_security_struct *isec = inode_security_novalidate(inode); *secid = isec->sid; } diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index b9c0910fb8c4..0608f216f359 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -170,6 +170,19 @@ struct snd_ctl_elem_value32 { unsigned char reserved[128]; }; +#ifdef CONFIG_X86_X32 +/* x32 has a different alignment for 64bit values from ia32 */ +struct snd_ctl_elem_value_x32 { + struct snd_ctl_elem_id id; + unsigned int indirect; /* bit-field causes misalignment */ + union { + s32 integer[128]; + unsigned char data[512]; + s64 integer64[64]; + } value; + unsigned char reserved[128]; +}; +#endif /* CONFIG_X86_X32 */ /* get the value type and count of the control */ static int get_ctl_type(struct snd_card *card, struct snd_ctl_elem_id *id, @@ -219,9 +232,11 @@ static int get_elem_size(int type, int count) static int copy_ctl_value_from_user(struct snd_card *card, struct snd_ctl_elem_value *data, - struct snd_ctl_elem_value32 __user *data32, + void __user *userdata, + void __user *valuep, int *typep, int *countp) { + struct snd_ctl_elem_value32 __user *data32 = userdata; int i, type, size; int uninitialized_var(count); unsigned int indirect; @@ -239,8 +254,9 @@ static int copy_ctl_value_from_user(struct snd_card *card, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; - if (get_user(val, &data32->value.integer[i])) + if (get_user(val, &intp[i])) return -EFAULT; data->value.integer.value[i] = val; } @@ -250,8 +266,7 @@ static int copy_ctl_value_from_user(struct snd_card *card, dev_err(card->dev, "snd_ioctl32_ctl_elem_value: unknown type %d\n", type); return -EINVAL; } - if (copy_from_user(data->value.bytes.data, - data32->value.data, size)) + if (copy_from_user(data->value.bytes.data, valuep, size)) return -EFAULT; } @@ -261,7 +276,8 @@ static int copy_ctl_value_from_user(struct snd_card *card, } /* restore the value to 32bit */ -static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, +static int copy_ctl_value_to_user(void __user *userdata, + void __user *valuep, struct snd_ctl_elem_value *data, int type, int count) { @@ -270,22 +286,22 @@ static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; val = data->value.integer.value[i]; - if (put_user(val, &data32->value.integer[i])) + if (put_user(val, &intp[i])) return -EFAULT; } } else { size = get_elem_size(type, count); - if (copy_to_user(data32->value.data, - data->value.bytes.data, size)) + if (copy_to_user(valuep, data->value.bytes.data, size)) return -EFAULT; } return 0; } -static int snd_ctl_elem_read_user_compat(struct snd_card *card, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_read_user(struct snd_card *card, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; int err, type, count; @@ -294,7 +310,9 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -303,14 +321,15 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, err = snd_ctl_elem_read(card, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } -static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_write_user(struct snd_ctl_file *file, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; struct snd_card *card = file->card; @@ -320,7 +339,9 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -329,12 +350,39 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, err = snd_ctl_elem_write(card, file, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } +static int snd_ctl_elem_read_user_compat(struct snd_card *card, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} + +#ifdef CONFIG_X86_X32 +static int snd_ctl_elem_read_user_x32(struct snd_card *card, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_x32(struct snd_ctl_file *file, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} +#endif /* CONFIG_X86_X32 */ + /* add or replace a user control */ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file, struct snd_ctl_elem_info32 __user *data32, @@ -393,6 +441,10 @@ enum { SNDRV_CTL_IOCTL_ELEM_WRITE32 = _IOWR('U', 0x13, struct snd_ctl_elem_value32), SNDRV_CTL_IOCTL_ELEM_ADD32 = _IOWR('U', 0x17, struct snd_ctl_elem_info32), SNDRV_CTL_IOCTL_ELEM_REPLACE32 = _IOWR('U', 0x18, struct snd_ctl_elem_info32), +#ifdef CONFIG_X86_X32 + SNDRV_CTL_IOCTL_ELEM_READ_X32 = _IOWR('U', 0x12, struct snd_ctl_elem_value_x32), + SNDRV_CTL_IOCTL_ELEM_WRITE_X32 = _IOWR('U', 0x13, struct snd_ctl_elem_value_x32), +#endif /* CONFIG_X86_X32 */ }; static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -431,6 +483,12 @@ static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_ctl_elem_add_compat(ctl, argp, 0); case SNDRV_CTL_IOCTL_ELEM_REPLACE32: return snd_ctl_elem_add_compat(ctl, argp, 1); +#ifdef CONFIG_X86_X32 + case SNDRV_CTL_IOCTL_ELEM_READ_X32: + return snd_ctl_elem_read_user_x32(ctl->card, argp); + case SNDRV_CTL_IOCTL_ELEM_WRITE_X32: + return snd_ctl_elem_write_user_x32(ctl, argp); +#endif /* CONFIG_X86_X32 */ } down_read(&snd_ioctl_rwsem); diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 9630e9f72b7b..1f64ab0c2a95 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -183,6 +183,14 @@ static int snd_pcm_ioctl_channel_info_compat(struct snd_pcm_substream *substream return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 for snd_pcm_channel_info */ +static int snd_pcm_channel_info_user(struct snd_pcm_substream *substream, + struct snd_pcm_channel_info __user *src); +#define snd_pcm_ioctl_channel_info_x32(s, p) \ + snd_pcm_channel_info_user(s, p) +#endif /* CONFIG_X86_X32 */ + struct snd_pcm_status32 { s32 state; struct compat_timespec trigger_tstamp; @@ -243,6 +251,71 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream, return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_status_x32 { + s32 state; + u32 rsvd; /* alignment */ + struct timespec trigger_tstamp; + struct timespec tstamp; + u32 appl_ptr; + u32 hw_ptr; + s32 delay; + u32 avail; + u32 avail_max; + u32 overrange; + s32 suspended_state; + u32 audio_tstamp_data; + struct timespec audio_tstamp; + struct timespec driver_tstamp; + u32 audio_tstamp_accuracy; + unsigned char reserved[52-2*sizeof(struct timespec)]; +} __packed; + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_pcm_status_user_x32(struct snd_pcm_substream *substream, + struct snd_pcm_status_x32 __user *src, + bool ext) +{ + struct snd_pcm_status status; + int err; + + memset(&status, 0, sizeof(status)); + /* + * with extension, parameters are read/write, + * get audio_tstamp_data from user, + * ignore rest of status structure + */ + if (ext && get_user(status.audio_tstamp_data, + (u32 __user *)(&src->audio_tstamp_data))) + return -EFAULT; + err = snd_pcm_status(substream, &status); + if (err < 0) + return err; + + if (clear_user(src, sizeof(*src))) + return -EFAULT; + if (put_user(status.state, &src->state) || + put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) || + put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.appl_ptr, &src->appl_ptr) || + put_user(status.hw_ptr, &src->hw_ptr) || + put_user(status.delay, &src->delay) || + put_user(status.avail, &src->avail) || + put_user(status.avail_max, &src->avail_max) || + put_user(status.overrange, &src->overrange) || + put_user(status.suspended_state, &src->suspended_state) || + put_user(status.audio_tstamp_data, &src->audio_tstamp_data) || + put_timespec(&status.audio_tstamp, &src->audio_tstamp) || + put_timespec(&status.driver_tstamp, &src->driver_tstamp) || + put_user(status.audio_tstamp_accuracy, &src->audio_tstamp_accuracy)) + return -EFAULT; + + return err; +} +#endif /* CONFIG_X86_X32 */ + /* both for HW_PARAMS and HW_REFINE */ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, int refine, @@ -469,6 +542,93 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_mmap_status_x32 { + s32 state; + s32 pad1; + u32 hw_ptr; + u32 pad2; /* alignment */ + struct timespec tstamp; + s32 suspended_state; + struct timespec audio_tstamp; +} __packed; + +struct snd_pcm_mmap_control_x32 { + u32 appl_ptr; + u32 avail_min; +}; + +struct snd_pcm_sync_ptr_x32 { + u32 flags; + u32 rsvd; /* alignment */ + union { + struct snd_pcm_mmap_status_x32 status; + unsigned char reserved[64]; + } s; + union { + struct snd_pcm_mmap_control_x32 control; + unsigned char reserved[64]; + } c; +} __packed; + +static int snd_pcm_ioctl_sync_ptr_x32(struct snd_pcm_substream *substream, + struct snd_pcm_sync_ptr_x32 __user *src) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + volatile struct snd_pcm_mmap_status *status; + volatile struct snd_pcm_mmap_control *control; + u32 sflags; + struct snd_pcm_mmap_control scontrol; + struct snd_pcm_mmap_status sstatus; + snd_pcm_uframes_t boundary; + int err; + + if (snd_BUG_ON(!runtime)) + return -EINVAL; + + if (get_user(sflags, &src->flags) || + get_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + get_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + if (sflags & SNDRV_PCM_SYNC_PTR_HWSYNC) { + err = snd_pcm_hwsync(substream); + if (err < 0) + return err; + } + status = runtime->status; + control = runtime->control; + boundary = recalculate_boundary(runtime); + if (!boundary) + boundary = 0x7fffffff; + snd_pcm_stream_lock_irq(substream); + /* FIXME: we should consider the boundary for the sync from app */ + if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) + control->appl_ptr = scontrol.appl_ptr; + else + scontrol.appl_ptr = control->appl_ptr % boundary; + if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) + control->avail_min = scontrol.avail_min; + else + scontrol.avail_min = control->avail_min; + sstatus.state = status->state; + sstatus.hw_ptr = status->hw_ptr % boundary; + sstatus.tstamp = status->tstamp; + sstatus.suspended_state = status->suspended_state; + sstatus.audio_tstamp = status->audio_tstamp; + snd_pcm_stream_unlock_irq(substream); + if (put_user(sstatus.state, &src->s.status.state) || + put_user(sstatus.hw_ptr, &src->s.status.hw_ptr) || + put_timespec(&sstatus.tstamp, &src->s.status.tstamp) || + put_user(sstatus.suspended_state, &src->s.status.suspended_state) || + put_timespec(&sstatus.audio_tstamp, &src->s.status.audio_tstamp) || + put_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + put_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ /* */ @@ -487,7 +647,12 @@ enum { SNDRV_PCM_IOCTL_WRITEN_FRAMES32 = _IOW('A', 0x52, struct snd_xfern32), SNDRV_PCM_IOCTL_READN_FRAMES32 = _IOR('A', 0x53, struct snd_xfern32), SNDRV_PCM_IOCTL_SYNC_PTR32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr32), - +#ifdef CONFIG_X86_X32 + SNDRV_PCM_IOCTL_CHANNEL_INFO_X32 = _IOR('A', 0x32, struct snd_pcm_channel_info), + SNDRV_PCM_IOCTL_STATUS_X32 = _IOR('A', 0x20, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_STATUS_EXT_X32 = _IOWR('A', 0x24, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_SYNC_PTR_X32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -559,6 +724,16 @@ static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned l return snd_pcm_ioctl_rewind_compat(substream, argp); case SNDRV_PCM_IOCTL_FORWARD32: return snd_pcm_ioctl_forward_compat(substream, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_PCM_IOCTL_STATUS_X32: + return snd_pcm_status_user_x32(substream, argp, false); + case SNDRV_PCM_IOCTL_STATUS_EXT_X32: + return snd_pcm_status_user_x32(substream, argp, true); + case SNDRV_PCM_IOCTL_SYNC_PTR_X32: + return snd_pcm_ioctl_sync_ptr_x32(substream, argp); + case SNDRV_PCM_IOCTL_CHANNEL_INFO_X32: + return snd_pcm_ioctl_channel_info_x32(substream, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c index 5268c1f58c25..f69764d7cdd7 100644 --- a/sound/core/rawmidi_compat.c +++ b/sound/core/rawmidi_compat.c @@ -85,8 +85,7 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile, if (err < 0) return err; - if (put_user(status.tstamp.tv_sec, &src->tstamp.tv_sec) || - put_user(status.tstamp.tv_nsec, &src->tstamp.tv_nsec) || + if (compat_put_timespec(&status.tstamp, &src->tstamp) || put_user(status.avail, &src->avail) || put_user(status.xruns, &src->xruns)) return -EFAULT; @@ -94,9 +93,58 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_rawmidi_status_x32 { + s32 stream; + u32 rsvd; /* alignment */ + struct timespec tstamp; + u32 avail; + u32 xruns; + unsigned char reserved[16]; +} __attribute__((packed)); + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile, + struct snd_rawmidi_status_x32 __user *src) +{ + int err; + struct snd_rawmidi_status status; + + if (rfile->output == NULL) + return -EINVAL; + if (get_user(status.stream, &src->stream)) + return -EFAULT; + + switch (status.stream) { + case SNDRV_RAWMIDI_STREAM_OUTPUT: + err = snd_rawmidi_output_status(rfile->output, &status); + break; + case SNDRV_RAWMIDI_STREAM_INPUT: + err = snd_rawmidi_input_status(rfile->input, &status); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + if (put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.avail, &src->avail) || + put_user(status.xruns, &src->xruns)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ + enum { SNDRV_RAWMIDI_IOCTL_PARAMS32 = _IOWR('W', 0x10, struct snd_rawmidi_params32), SNDRV_RAWMIDI_IOCTL_STATUS32 = _IOWR('W', 0x20, struct snd_rawmidi_status32), +#ifdef CONFIG_X86_X32 + SNDRV_RAWMIDI_IOCTL_STATUS_X32 = _IOWR('W', 0x20, struct snd_rawmidi_status_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -115,6 +163,10 @@ static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsign return snd_rawmidi_ioctl_params_compat(rfile, argp); case SNDRV_RAWMIDI_IOCTL_STATUS32: return snd_rawmidi_ioctl_status_compat(rfile, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_RAWMIDI_IOCTL_STATUS_X32: + return snd_rawmidi_ioctl_status_x32(rfile, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c index 8db156b207f1..8cdf489df80e 100644 --- a/sound/core/seq/oss/seq_oss.c +++ b/sound/core/seq/oss/seq_oss.c @@ -149,8 +149,6 @@ odev_release(struct inode *inode, struct file *file) if ((dp = file->private_data) == NULL) return 0; - snd_seq_oss_drain_write(dp); - mutex_lock(®ister_mutex); snd_seq_oss_release(dp); mutex_unlock(®ister_mutex); diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h index b43924325249..d7b4d016b547 100644 --- a/sound/core/seq/oss/seq_oss_device.h +++ b/sound/core/seq/oss/seq_oss_device.h @@ -127,7 +127,6 @@ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int co unsigned int snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait); void snd_seq_oss_reset(struct seq_oss_devinfo *dp); -void snd_seq_oss_drain_write(struct seq_oss_devinfo *dp); /* */ void snd_seq_oss_process_queue(struct seq_oss_devinfo *dp, abstime_t time); diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index 6779e82b46dd..92c96a95a903 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -436,22 +436,6 @@ snd_seq_oss_release(struct seq_oss_devinfo *dp) /* - * Wait until the queue is empty (if we don't have nonblock) - */ -void -snd_seq_oss_drain_write(struct seq_oss_devinfo *dp) -{ - if (! dp->timer->running) - return; - if (is_write_mode(dp->file_mode) && !is_nonblock_mode(dp->file_mode) && - dp->writeq) { - while (snd_seq_oss_writeq_sync(dp->writeq)) - ; - } -} - - -/* * reset sequencer devices */ void diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c index e05802ae6e1b..2e908225d754 100644 --- a/sound/core/timer_compat.c +++ b/sound/core/timer_compat.c @@ -70,13 +70,14 @@ static int snd_timer_user_status_compat(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; - struct snd_timer_status status; + struct snd_timer_status32 status; tu = file->private_data; if (snd_BUG_ON(!tu->timeri)) return -ENXIO; memset(&status, 0, sizeof(status)); - status.tstamp = tu->tstamp; + status.tstamp.tv_sec = tu->tstamp.tv_sec; + status.tstamp.tv_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; @@ -88,12 +89,21 @@ static int snd_timer_user_status_compat(struct file *file, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 */ +#define snd_timer_user_status_x32(file, s) \ + snd_timer_user_status(file, s) +#endif /* CONFIG_X86_X32 */ + /* */ enum { SNDRV_TIMER_IOCTL_INFO32 = _IOR('T', 0x11, struct snd_timer_info32), SNDRV_TIMER_IOCTL_STATUS32 = _IOW('T', 0x14, struct snd_timer_status32), +#ifdef CONFIG_X86_X32 + SNDRV_TIMER_IOCTL_STATUS_X32 = _IOW('T', 0x14, struct snd_timer_status), +#endif /* CONFIG_X86_X32 */ }; static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -122,6 +132,10 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_timer_user_info_compat(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status_compat(file, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_TIMER_IOCTL_STATUS_X32: + return snd_timer_user_status_x32(file, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index b5a17cb510a0..8c486235c905 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -426,18 +426,22 @@ EXPORT_SYMBOL_GPL(snd_hdac_bus_stop_chip); * @bus: HD-audio core bus * @status: INTSTS register value * @ask: callback to be called for woken streams + * + * Returns the bits of handled streams, or zero if no stream is handled. */ -void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, +int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, void (*ack)(struct hdac_bus *, struct hdac_stream *)) { struct hdac_stream *azx_dev; u8 sd_status; + int handled = 0; list_for_each_entry(azx_dev, &bus->stream_list, list) { if (status & azx_dev->sd_int_sta_mask) { sd_status = snd_hdac_stream_readb(azx_dev, SD_STS); snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK); + handled |= 1 << azx_dev->index; if (!azx_dev->substream || !azx_dev->running || !(sd_status & SD_INT_COMPLETE)) continue; @@ -445,6 +449,7 @@ void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, ack(bus, azx_dev); } } + return handled; } EXPORT_SYMBOL_GPL(snd_hdac_bus_handle_stream_irq); diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 37cf9cee9835..27de8015717d 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -930,6 +930,8 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) struct azx *chip = dev_id; struct hdac_bus *bus = azx_bus(chip); u32 status; + bool active, handled = false; + int repeat = 0; /* count for avoiding endless loop */ #ifdef CONFIG_PM if (azx_has_pm_runtime(chip)) @@ -939,33 +941,36 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) spin_lock(&bus->reg_lock); - if (chip->disabled) { - spin_unlock(&bus->reg_lock); - return IRQ_NONE; - } - - status = azx_readl(chip, INTSTS); - if (status == 0 || status == 0xffffffff) { - spin_unlock(&bus->reg_lock); - return IRQ_NONE; - } + if (chip->disabled) + goto unlock; - snd_hdac_bus_handle_stream_irq(bus, status, stream_update); + do { + status = azx_readl(chip, INTSTS); + if (status == 0 || status == 0xffffffff) + break; - /* clear rirb int */ - status = azx_readb(chip, RIRBSTS); - if (status & RIRB_INT_MASK) { - if (status & RIRB_INT_RESPONSE) { - if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) - udelay(80); - snd_hdac_bus_update_rirb(bus); + handled = true; + active = false; + if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update)) + active = true; + + /* clear rirb int */ + status = azx_readb(chip, RIRBSTS); + if (status & RIRB_INT_MASK) { + active = true; + if (status & RIRB_INT_RESPONSE) { + if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) + udelay(80); + snd_hdac_bus_update_rirb(bus); + } + azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); } - azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); - } + } while (active && ++repeat < 10); + unlock: spin_unlock(&bus->reg_lock); - return IRQ_HANDLED; + return IRQ_RETVAL(handled); } EXPORT_SYMBOL_GPL(azx_interrupt); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index ce6b97f31390..e5240cb3749f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -363,7 +363,10 @@ enum { ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c)) -#define IS_BROXTON(pci) ((pci)->device == 0x5a98) +#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) +#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) +#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", @@ -540,13 +543,13 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); - if (IS_BROXTON(pci)) { + if (IS_SKL_PLUS(pci)) { pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); val = val & ~INTEL_HDA_CGCTL_MISCBDCGE; pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); } azx_init_chip(chip, full_reset); - if (IS_BROXTON(pci)) { + if (IS_SKL_PLUS(pci)) { pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); val = val | INTEL_HDA_CGCTL_MISCBDCGE; pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); @@ -555,7 +558,7 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) snd_hdac_set_codec_wakeup(bus, false); /* reduce dma latency to avoid noise */ - if (IS_BROXTON(pci)) + if (IS_BXT(pci)) bxt_reduce_dma_latency(chip); } @@ -977,11 +980,6 @@ static int azx_resume(struct device *dev) /* put codec down to D3 at hibernation for Intel SKL+; * otherwise BIOS may still access the codec and screw up the driver */ -#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) -#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) -#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) -#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) - static int azx_freeze_noirq(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 8ee78dbd4c60..bcbc4ee10130 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2477,13 +2477,6 @@ static int patch_generic_hdmi(struct hda_codec *codec) is_broxton(codec)) codec->core.link_power_control = 1; - if (codec_has_acomp(codec)) { - codec->depop_delay = 0; - spec->i915_audio_ops.audio_ptr = codec; - spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; - snd_hdac_i915_register_notifier(&spec->i915_audio_ops); - } - if (hdmi_parse_codec(codec) < 0) { if (spec->i915_bound) snd_hdac_i915_exit(&codec->bus->core); @@ -2505,6 +2498,18 @@ static int patch_generic_hdmi(struct hda_codec *codec) init_channel_allocations(); + if (codec_has_acomp(codec)) { + codec->depop_delay = 0; + spec->i915_audio_ops.audio_ptr = codec; + /* intel_audio_codec_enable() or intel_audio_codec_disable() + * will call pin_eld_notify with using audio_ptr pointer + * We need make sure audio_ptr is really setup + */ + wmb(); + spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; + snd_hdac_i915_register_notifier(&spec->i915_audio_ops); + } + return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index efd4980cffb8..93d2156b6241 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3801,6 +3801,10 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, static void alc_headset_mode_default(struct hda_codec *codec) { + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + {} + }; static struct coef_fw coef0255[] = { WRITE_COEF(0x45, 0xc089), WRITE_COEF(0x45, 0xc489), @@ -3842,6 +3846,9 @@ static void alc_headset_mode_default(struct hda_codec *codec) }; switch (codec->core.vendor_id) { + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; case 0x10ec0255: case 0x10ec0256: alc_process_coef_fw(codec, coef0255); @@ -4749,6 +4756,9 @@ enum { ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, + ALC255_FIXUP_DELL_SPK_NOISE, + ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC280_FIXUP_HP_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -5368,6 +5378,29 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_fixup_lenovo_line2_mic_hotkey, }, + [ALC255_FIXUP_DELL_SPK_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, + [ALC225_FIXUP_DELL1_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Disable pass-through path for FRONT 14h */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x36 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE + }, + [ALC280_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MIC, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5379,6 +5412,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK), SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK), + SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK), @@ -5410,6 +5444,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { 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", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -5470,6 +5505,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -5638,10 +5674,10 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {0x21, 0x03211020} static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { - SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x14, 0x901701a0}), - SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x14, 0x901701b0}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 2875b4f6d8c9..7c8941b8b2de 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -2879,7 +2879,7 @@ static int snd_hdsp_get_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl { struct hdsp *hdsp = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdsp_dds_offset(hdsp); + ucontrol->value.integer.value[0] = hdsp_dds_offset(hdsp); return 0; } @@ -2891,7 +2891,7 @@ static int snd_hdsp_put_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl if (!snd_hdsp_use_is_exclusive(hdsp)) return -EBUSY; - val = ucontrol->value.enumerated.item[0]; + val = ucontrol->value.integer.value[0]; spin_lock_irq(&hdsp->lock); if (val != hdsp_dds_offset(hdsp)) change = (hdsp_set_dds_offset(hdsp, val) == 0) ? 1 : 0; diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index 8bc8016c173d..a4a999a0317e 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -1601,6 +1601,9 @@ static void hdspm_set_dds_value(struct hdspm *hdspm, int rate) { u64 n; + if (snd_BUG_ON(rate <= 0)) + return; + if (rate >= 112000) rate /= 4; else if (rate >= 56000) @@ -2215,6 +2218,8 @@ static int hdspm_get_system_sample_rate(struct hdspm *hdspm) } else { /* slave mode, return external sample rate */ rate = hdspm_external_sample_rate(hdspm); + if (!rate) + rate = hdspm->system_sample_rate; } } @@ -2260,8 +2265,11 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol, ucontrol) { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); + int rate = ucontrol->value.integer.value[0]; - hdspm_set_dds_value(hdspm, ucontrol->value.enumerated.item[0]); + if (rate < 27000 || rate > 207000) + return -EINVAL; + hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]); return 0; } @@ -4449,7 +4457,7 @@ static int snd_hdspm_get_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdspm->tco->term; + ucontrol->value.integer.value[0] = hdspm->tco->term; return 0; } @@ -4460,8 +4468,8 @@ static int snd_hdspm_put_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - if (hdspm->tco->term != ucontrol->value.enumerated.item[0]) { - hdspm->tco->term = ucontrol->value.enumerated.item[0]; + if (hdspm->tco->term != ucontrol->value.integer.value[0]) { + hdspm->tco->term = ucontrol->value.integer.value[0]; hdspm_tco_write(hdspm); diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 4f6ce1cac8e2..c458d60d5030 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1124,6 +1124,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ + case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */ diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 90bd2ea41032..b3281dcd4a5d 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -217,13 +217,16 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd, return rc; } +#define NFIT_TEST_ARS_RECORDS 4 + static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd, unsigned int buf_len) { if (buf_len < sizeof(*nd_cmd)) return -EINVAL; - nd_cmd->max_ars_out = 256; + nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status) + + NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record); nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16; return 0; @@ -246,7 +249,8 @@ static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd, if (buf_len < sizeof(*nd_cmd)) return -EINVAL; - nd_cmd->out_length = 256; + nd_cmd->out_length = sizeof(struct nd_cmd_ars_status); + /* TODO: emit error records */ nd_cmd->num_records = 0; nd_cmd->address = 0; nd_cmd->length = -1ULL; diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance.tc b/tools/testing/selftests/ftrace/test.d/instances/instance.tc index 773e276ff90b..1e1abe0ad354 100644 --- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc +++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc @@ -39,28 +39,23 @@ instance_slam() { } instance_slam & -x=`jobs -l` -p1=`echo $x | cut -d' ' -f2` +p1=$! echo $p1 instance_slam & -x=`jobs -l | tail -1` -p2=`echo $x | cut -d' ' -f2` +p2=$! echo $p2 instance_slam & -x=`jobs -l | tail -1` -p3=`echo $x | cut -d' ' -f2` +p3=$! echo $p3 instance_slam & -x=`jobs -l | tail -1` -p4=`echo $x | cut -d' ' -f2` +p4=$! echo $p4 instance_slam & -x=`jobs -l | tail -1` -p5=`echo $x | cut -d' ' -f2` +p5=$! echo $p5 ls -lR >/dev/null diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 043032c6a5a4..00429b392c61 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1875,8 +1875,8 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8; + int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS); + int sz = nr_longs * sizeof(unsigned long); vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL); diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 353159922456..db2dd3335c6a 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -172,7 +172,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, * do alloc nowait since if we are going to sleep anyway we * may as well sleep faulting in page */ - work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT); + work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN); if (!work) return 0; |