diff options
778 files changed, 14329 insertions, 7665 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net index beb8ec4dabbc..5ecfd72ba684 100644 --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -188,6 +188,14 @@ Description: Indicates the interface unique physical port identifier within the NIC, as a string. +What: /sys/class/net/<iface>/phys_port_name +Date: March 2015 +KernelVersion: 4.0 +Contact: netdev@vger.kernel.org +Description: + Indicates the interface physical port name within the NIC, + as a string. + What: /sys/class/net/<iface>/speed Date: October 2009 KernelVersion: 2.6.33 diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 5e9aeb91d355..0c0df91b1516 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -24,6 +24,14 @@ Description: Indicates the number of transmit timeout events seen by this network interface transmit queue. +What: /sys/class/<iface>/queues/tx-<queue>/tx_maxrate +Date: March 2015 +KernelVersion: 4.1 +Contact: netdev@vger.kernel.org +Description: + A Mbps max-rate set for the queue, a value of zero means disabled, + default is disabled. + What: /sys/class/<iface>/queues/tx-<queue>/xps_cpus Date: November 2010 KernelVersion: 2.6.38 diff --git a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt index f4445e5a2bbb..1e097037349c 100644 --- a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt +++ b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt @@ -22,6 +22,8 @@ Optional Properties: - pclkN, clkN: Pairs of parent of input clock and input clock to the devices in this power domain. Maximum of 4 pairs (N = 0 to 3) are supported currently. +- power-domains: phandle pointing to the parent power domain, for more details + see Documentation/devicetree/bindings/power/power_domain.txt Node of a device using power domains must have a power-domains property defined with a phandle to respective power domain. diff --git a/Documentation/devicetree/bindings/arm/sti.txt b/Documentation/devicetree/bindings/arm/sti.txt index d70ec358736c..8d27f6b084c7 100644 --- a/Documentation/devicetree/bindings/arm/sti.txt +++ b/Documentation/devicetree/bindings/arm/sti.txt @@ -13,6 +13,10 @@ Boards with the ST STiH407 SoC shall have the following properties: Required root node property: compatible = "st,stih407"; +Boards with the ST STiH410 SoC shall have the following properties: +Required root node property: +compatible = "st,stih410"; + Boards with the ST STiH418 SoC shall have the following properties: Required root node property: compatible = "st,stih418"; diff --git a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt index 6151999c5dca..f55aa280d34f 100644 --- a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt +++ b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt @@ -14,7 +14,11 @@ Required properties for all the ethernet interfaces: - "enet_csr": Ethernet control and status register address space - "ring_csr": Descriptor ring control and status register address space - "ring_cmd": Descriptor ring command register address space -- interrupts: Ethernet main interrupt +- interrupts: Two interrupt specifiers can be specified. + - First is the Rx interrupt. This irq is mandatory. + - Second is the Tx completion interrupt. + This is supported only on SGMII based 1GbE and 10GbE interfaces. +- port-id: Port number (0 or 1) - clocks: Reference to the clock entry. - local-mac-address: MAC address assigned to this device - phy-connection-type: Interface type between ethernet device and PHY device @@ -49,6 +53,7 @@ Example: <0x0 0X10000000 0x0 0X200>; reg-names = "enet_csr", "ring_csr", "ring_cmd"; interrupts = <0x0 0x3c 0x4>; + port-id = <0>; clocks = <&menetclk 0>; local-mac-address = [00 01 73 00 00 01]; phy-connection-type = "rgmii"; diff --git a/Documentation/devicetree/bindings/net/keystone-netcp.txt b/Documentation/devicetree/bindings/net/keystone-netcp.txt index f9c07710478d..d0e6fa38f335 100644 --- a/Documentation/devicetree/bindings/net/keystone-netcp.txt +++ b/Documentation/devicetree/bindings/net/keystone-netcp.txt @@ -49,6 +49,7 @@ Required properties: - compatible: Should be "ti,netcp-1.0" - clocks: phandle to the reference clocks for the subsystem. - dma-id: Navigator packet dma instance id. +- ranges: address range of NetCP (includes, Ethernet SS, PA and SA) Optional properties: - reg: register location and the size for the following register @@ -64,10 +65,30 @@ NetCP device properties: Device specification for NetCP sub-modules. 1Gb/10Gb (gbe/xgbe) ethernet switch sub-module specifications. Required properties: - label: Must be "netcp-gbe" for 1Gb & "netcp-xgbe" for 10Gb. +- compatible: Must be one of below:- + "ti,netcp-gbe" for 1GbE on NetCP 1.4 + "ti,netcp-gbe-5" for 1GbE N NetCP 1.5 (N=5) + "ti,netcp-gbe-9" for 1GbE N NetCP 1.5 (N=9) + "ti,netcp-gbe-2" for 1GbE N NetCP 1.5 (N=2) + "ti,netcp-xgbe" for 10 GbE + - reg: register location and the size for the following register regions in the specified order. - - subsystem registers - - serdes registers + - switch subsystem registers + - sgmii port3/4 module registers (only for NetCP 1.4) + - switch module registers + - serdes registers (only for 10G) + + NetCP 1.4 ethss, here is the order + index #0 - switch subsystem registers + index #1 - sgmii port3/4 module registers + index #2 - switch module registers + + NetCP 1.5 ethss 9 port, 5 port and 2 port + index #0 - switch subsystem registers + index #1 - switch module registers + index #2 - serdes registers + - tx-channel: the navigator packet dma channel name for tx. - tx-queue: the navigator queue number associated with the tx dma channel. - interfaces: specification for each of the switch port to be registered as a @@ -120,14 +141,13 @@ Optional properties: Example binding: -netcp: netcp@2090000 { +netcp: netcp@2000000 { reg = <0x2620110 0x8>; reg-names = "efuse"; compatible = "ti,netcp-1.0"; #address-cells = <1>; #size-cells = <1>; - ranges; - + ranges = <0 0x2000000 0xfffff>; clocks = <&papllclk>, <&clkcpgmac>, <&chipclk12>; dma-coherent; /* big-endian; */ @@ -137,9 +157,9 @@ netcp: netcp@2090000 { #address-cells = <1>; #size-cells = <1>; ranges; - gbe@0x2090000 { + gbe@90000 { label = "netcp-gbe"; - reg = <0x2090000 0xf00>; + reg = <0x90000 0x300>, <0x90400 0x400>, <0x90800 0x700>; /* enable-ale; */ tx-queue = <648>; tx-channel = <8>; diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt index 98c16672ab5f..0f8ed3710c66 100644 --- a/Documentation/devicetree/bindings/power/power_domain.txt +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -19,6 +19,16 @@ Required properties: providing multiple PM domains (e.g. power controllers), but can be any value as specified by device tree binding documentation of particular provider. +Optional properties: + - power-domains : A phandle and PM domain specifier as defined by bindings of + the power controller specified by phandle. + Some power domains might be powered from another power domain (or have + other hardware specific dependencies). For representing such dependency + a standard PM domain consumer binding is used. When provided, all domains + created by the given provider should be subdomains of the domain + specified by this binding. More details about power domain specifier are + available in the next section. + Example: power: power-controller@12340000 { @@ -30,6 +40,25 @@ Example: The node above defines a power controller that is a PM domain provider and expects one cell as its phandle argument. +Example 2: + + parent: power-controller@12340000 { + compatible = "foo,power-controller"; + reg = <0x12340000 0x1000>; + #power-domain-cells = <1>; + }; + + child: power-controller@12340000 { + compatible = "foo,power-controller"; + reg = <0x12341000 0x1000>; + power-domains = <&parent 0>; + #power-domain-cells = <1>; + }; + +The nodes above define two power controllers: 'parent' and 'child'. +Domains created by the 'child' power controller are subdomains of '0' power +domain provided by the 'parent' power controller. + ==PM domain consumers== Required properties: diff --git a/Documentation/devicetree/bindings/serial/of-serial.txt b/Documentation/devicetree/bindings/serial/8250.txt index 91d5ab0e60fc..91d5ab0e60fc 100644 --- a/Documentation/devicetree/bindings/serial/of-serial.txt +++ b/Documentation/devicetree/bindings/serial/8250.txt diff --git a/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt b/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt new file mode 100644 index 000000000000..ebcbb62c0a76 --- /dev/null +++ b/Documentation/devicetree/bindings/serial/axis,etraxfs-uart.txt @@ -0,0 +1,19 @@ +ETRAX FS UART + +Required properties: +- compatible : "axis,etraxfs-uart" +- reg: offset and length of the register set for the device. +- interrupts: device interrupt + +Optional properties: +- {dtr,dsr,ri,cd}-gpios: specify a GPIO for DTR/DSR/RI/CD + line respectively. + +Example: + +serial@b00260000 { + compatible = "axis,etraxfs-uart"; + reg = <0xb0026000 0x1000>; + interrupts = <68>; + status = "disabled"; +}; diff --git a/Documentation/devicetree/bindings/submitting-patches.txt b/Documentation/devicetree/bindings/submitting-patches.txt index 56742bc70218..7d44eae7ab0b 100644 --- a/Documentation/devicetree/bindings/submitting-patches.txt +++ b/Documentation/devicetree/bindings/submitting-patches.txt @@ -12,6 +12,9 @@ I. For patch submitters devicetree@vger.kernel.org + and Cc: the DT maintainers. Use scripts/get_maintainer.pl to identify + all of the DT maintainers. + 3) The Documentation/ portion of the patch should come in the series before the code implementing the binding. diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 389ca1347a77..fae26d014aaf 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -20,6 +20,7 @@ amlogic Amlogic, Inc. ams AMS AG amstaos AMS-Taos Inc. apm Applied Micro Circuits Corporation (APM) +arasan Arasan Chip Systems arm ARM Ltd. armadeus ARMadeus Systems SARL asahi-kasei Asahi Kasei Corp. @@ -27,6 +28,7 @@ atmel Atmel Corporation auo AU Optronics Corporation avago Avago Technologies avic Shanghai AVIC Optoelectronics Co., Ltd. +axis Axis Communications AB bosch Bosch Sensortec GmbH brcm Broadcom Corporation buffalo Buffalo, Inc. diff --git a/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt b/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt index f90e294d7631..a4d869744f59 100644 --- a/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt +++ b/Documentation/devicetree/bindings/watchdog/atmel-wdt.txt @@ -26,6 +26,11 @@ Optional properties: - atmel,disable : Should be present if you want to disable the watchdog. - atmel,idle-halt : Should be present if you want to stop the watchdog when entering idle state. + CAUTION: This property should be used with care, it actually makes the + watchdog not counting when the CPU is in idle state, therefore the + watchdog reset time depends on mean CPU usage and will not reset at all + if the CPU stop working while it is in idle state, which is probably + not what you want. - atmel,dbg-halt : Should be present if you want to stop the watchdog when entering debug state. diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index 9930ecfbb465..135581f015e1 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -280,7 +280,8 @@ Possible BPF extensions are shown in the following table: rxhash skb->hash cpu raw_smp_processor_id() vlan_tci skb_vlan_tag_get(skb) - vlan_pr skb_vlan_tag_present(skb) + vlan_avail skb_vlan_tag_present(skb) + vlan_tpid skb->vlan_proto rand prandom_u32() These extensions can also be prefixed with '#'. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 4412f695a62f..071fb18dc57c 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1126,11 +1126,23 @@ arp_accept - BOOLEAN gratuitous arp frame, the arp table will be updated regardless if this setting is on or off. +mcast_solicit - INTEGER + The maximum number of multicast probes in INCOMPLETE state, + when the associated hardware address is unknown. Defaults + to 3. + +ucast_solicit - INTEGER + The maximum number of unicast probes in PROBE state, when + the hardware address is being reconfirmed. Defaults to 3. app_solicit - INTEGER The maximum number of probes to send to the user space ARP daemon via netlink before dropping back to multicast probes (see - mcast_solicit). Defaults to 0. + mcast_resolicit). Defaults to 0. + +mcast_resolicit - INTEGER + The maximum number of multicast probes after unicast and + app probes in PROBE state. Defaults to 0. disable_policy - BOOLEAN Disable IPSEC policy (SPD) for this interface @@ -1208,6 +1220,17 @@ anycast_src_echo_reply - BOOLEAN FALSE: disabled Default: FALSE +idgen_delay - INTEGER + Controls the delay in seconds after which time to retry + privacy stable address generation if a DAD conflict is + detected. + Default: 1 (as specified in RFC7217) + +idgen_retries - INTEGER + Controls the number of retries to generate a stable privacy + address if a DAD conflict is detected. + Default: 3 (as specified in RFC7217) + mld_qrv - INTEGER Controls the MLD query robustness variable (see RFC3810 9.1). Default: 2 (as specified by RFC3810 9.1) @@ -1528,6 +1551,20 @@ use_optimistic - BOOLEAN 0: disabled (default) 1: enabled +stable_secret - IPv6 address + This IPv6 address will be used as a secret to generate IPv6 + addresses for link-local addresses and autoconfigured + ones. All addresses generated after setting this secret will + be stable privacy ones by default. This can be changed via the + addrgenmode ip-link. conf/default/stable_secret is used as the + secret for the namespace, the interface specific ones can + overwrite that. Writes to conf/all/stable_secret are refused. + + It is recommended to generate this secret during installation + of a system and keep it stable after that. + + By default the stable secret is unset. + icmp/*: ratelimit - INTEGER Limit the maximal rates for sending ICMPv6 packets. diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index a6d7cb91069e..daa015af16a0 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -440,9 +440,10 @@ and the following flags apply: +++ Capture process: from include/linux/if_packet.h - #define TP_STATUS_COPY 2 - #define TP_STATUS_LOSING 4 - #define TP_STATUS_CSUMNOTREADY 8 + #define TP_STATUS_COPY (1 << 1) + #define TP_STATUS_LOSING (1 << 2) + #define TP_STATUS_CSUMNOTREADY (1 << 3) + #define TP_STATUS_CSUM_VALID (1 << 7) TP_STATUS_COPY : This flag indicates that the frame (and associated meta information) has been truncated because it's @@ -466,6 +467,12 @@ TP_STATUS_CSUMNOTREADY: currently it's used for outgoing IP packets which reading the packet we should not try to check the checksum. +TP_STATUS_CSUM_VALID : This flag indicates that at least the transport + header checksum of the packet has been already + validated on the kernel side. If the flag is not set + then we are free to check the checksum by ourselves + provided that TP_STATUS_CSUMNOTREADY is also not set. + for convenience there are also the following defines: #define TP_STATUS_KERNEL 0 diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt index 99ca40e8e810..cbfac0949635 100644 --- a/Documentation/networking/scaling.txt +++ b/Documentation/networking/scaling.txt @@ -421,6 +421,15 @@ best CPUs to share a given queue are probably those that share the cache with the CPU that processes transmit completions for that queue (transmit interrupts). +Per TX Queue rate limitation: +============================= + +These are rate-limitation mechanisms implemented by HW, where currently +a max-rate attribute is supported, by setting a Mbps value to + +/sys/class/net/<dev>/queues/tx-<n>/tx_maxrate + +A value of zero means disabled, and this is the default. Further Information =================== diff --git a/MAINTAINERS b/MAINTAINERS index 42e221c48776..c2016557b294 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1030,6 +1030,16 @@ F: arch/arm/mach-mxs/ F: arch/arm/boot/dts/imx* F: arch/arm/configs/imx*_defconfig +ARM/FREESCALE VYBRID ARM ARCHITECTURE +M: Shawn Guo <shawn.guo@linaro.org> +M: Sascha Hauer <kernel@pengutronix.de> +R: Stefan Agner <stefan@agner.ch> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git +F: arch/arm/mach-imx/*vf610* +F: arch/arm/boot/dts/vf* + ARM/GLOMATION GESBC9312SX MACHINE SUPPORT M: Lennert Buytenhek <kernel@wantstofly.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -1188,6 +1198,7 @@ ARM/Marvell Dove/MV78xx0/Orion SOC support M: Jason Cooper <jason@lakedaemon.net> M: Andrew Lunn <andrew@lunn.ch> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> +M: Gregory Clement <gregory.clement@free-electrons.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-dove/ @@ -1730,7 +1741,7 @@ S: Maintained F: drivers/net/ethernet/atheros/ ATM -M: Chas Williams <chas@cmf.nrl.navy.mil> +M: Chas Williams <3chas3@gmail.com> L: linux-atm-general@lists.sourceforge.net (moderated for non-subscribers) L: netdev@vger.kernel.org W: http://linux-atm.sourceforge.net @@ -2107,7 +2118,6 @@ F: drivers/net/ethernet/broadcom/bnx2x/ BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE M: Christian Daudt <bcm@fixthebug.org> -M: Matt Porter <mporter@linaro.org> M: Florian Fainelli <f.fainelli@gmail.com> L: bcm-kernel-feedback-list@broadcom.com T: git git://github.com/broadcom/mach-bcm @@ -10196,6 +10206,13 @@ S: Maintained F: Documentation/usb/ohci.txt F: drivers/usb/host/ohci* +USB OTG FSM (Finite State Machine) +M: Peter Chen <Peter.Chen@freescale.com> +T: git git://github.com/hzpeterchen/linux-usb.git +L: linux-usb@vger.kernel.org +S: Maintained +F: drivers/usb/common/usb-otg-fsm.c + USB OVER IP DRIVER M: Valentina Manea <valentina.manea.m@gmail.com> M: Shuah Khan <shuah.kh@samsung.com> @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc5 NAME = Hurr durr I'ma sheep # *DOCUMENTATION* diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 7f99cd652203..eb7bb511f853 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -150,6 +150,7 @@ machine-$(CONFIG_ARCH_BERLIN) += berlin machine-$(CONFIG_ARCH_CLPS711X) += clps711x machine-$(CONFIG_ARCH_CNS3XXX) += cns3xxx machine-$(CONFIG_ARCH_DAVINCI) += davinci +machine-$(CONFIG_ARCH_DIGICOLOR) += digicolor machine-$(CONFIG_ARCH_DOVE) += dove machine-$(CONFIG_ARCH_EBSA110) += ebsa110 machine-$(CONFIG_ARCH_EFM32) += efm32 diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index 2c6248d9a9ef..c3255e0c90aa 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -301,3 +301,11 @@ cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; cd-inverted; }; + +&aes { + status = "okay"; +}; + +&sham { + status = "okay"; +}; diff --git a/arch/arm/boot/dts/am335x-bone.dts b/arch/arm/boot/dts/am335x-bone.dts index 83d40f7655e5..6b8493720424 100644 --- a/arch/arm/boot/dts/am335x-bone.dts +++ b/arch/arm/boot/dts/am335x-bone.dts @@ -24,11 +24,3 @@ &mmc1 { vmmc-supply = <&ldo3_reg>; }; - -&sham { - status = "okay"; -}; - -&aes { - status = "okay"; -}; diff --git a/arch/arm/boot/dts/am335x-lxm.dts b/arch/arm/boot/dts/am335x-lxm.dts index 7266a00aab2e..5c5667a3624d 100644 --- a/arch/arm/boot/dts/am335x-lxm.dts +++ b/arch/arm/boot/dts/am335x-lxm.dts @@ -328,6 +328,10 @@ dual_emac_res_vlan = <3>; }; +&phy_sel { + rmii-clock-ext; +}; + &mac { pinctrl-names = "default", "sleep"; pinctrl-0 = <&cpsw_default>; diff --git a/arch/arm/boot/dts/am33xx-clocks.dtsi b/arch/arm/boot/dts/am33xx-clocks.dtsi index 712edce7d6fb..071b56aa0c7e 100644 --- a/arch/arm/boot/dts/am33xx-clocks.dtsi +++ b/arch/arm/boot/dts/am33xx-clocks.dtsi @@ -99,7 +99,7 @@ ehrpwm0_tbclk: ehrpwm0_tbclk@44e10664 { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <0>; reg = <0x0664>; }; @@ -107,7 +107,7 @@ ehrpwm1_tbclk: ehrpwm1_tbclk@44e10664 { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <1>; reg = <0x0664>; }; @@ -115,7 +115,7 @@ ehrpwm2_tbclk: ehrpwm2_tbclk@44e10664 { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <2>; reg = <0x0664>; }; diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi index c7dc9dab93a4..cfb49686ab6a 100644 --- a/arch/arm/boot/dts/am43xx-clocks.dtsi +++ b/arch/arm/boot/dts/am43xx-clocks.dtsi @@ -107,7 +107,7 @@ ehrpwm0_tbclk: ehrpwm0_tbclk { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <0>; reg = <0x0664>; }; @@ -115,7 +115,7 @@ ehrpwm1_tbclk: ehrpwm1_tbclk { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <1>; reg = <0x0664>; }; @@ -123,7 +123,7 @@ ehrpwm2_tbclk: ehrpwm2_tbclk { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <2>; reg = <0x0664>; }; @@ -131,7 +131,7 @@ ehrpwm3_tbclk: ehrpwm3_tbclk { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <4>; reg = <0x0664>; }; @@ -139,7 +139,7 @@ ehrpwm4_tbclk: ehrpwm4_tbclk { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <5>; reg = <0x0664>; }; @@ -147,7 +147,7 @@ ehrpwm5_tbclk: ehrpwm5_tbclk { #clock-cells = <0>; compatible = "ti,gate-clock"; - clocks = <&dpll_per_m2_ck>; + clocks = <&l4ls_gclk>; ti,bit-shift = <6>; reg = <0x0664>; }; diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi index 9f7c7376f2cf..62d25b14deb8 100644 --- a/arch/arm/boot/dts/at91sam9260.dtsi +++ b/arch/arm/boot/dts/at91sam9260.dtsi @@ -494,12 +494,12 @@ pinctrl_usart3_rts: usart3_rts-0 { atmel,pins = - <AT91_PIOB 8 AT91_PERIPH_B AT91_PINCTRL_NONE>; /* PC8 periph B */ + <AT91_PIOC 8 AT91_PERIPH_B AT91_PINCTRL_NONE>; }; pinctrl_usart3_cts: usart3_cts-0 { atmel,pins = - <AT91_PIOB 10 AT91_PERIPH_B AT91_PINCTRL_NONE>; /* PC10 periph B */ + <AT91_PIOC 10 AT91_PERIPH_B AT91_PINCTRL_NONE>; }; }; @@ -853,7 +853,7 @@ }; usb1: gadget@fffa4000 { - compatible = "atmel,at91rm9200-udc"; + compatible = "atmel,at91sam9260-udc"; reg = <0xfffa4000 0x4000>; interrupts = <10 IRQ_TYPE_LEVEL_HIGH 2>; clocks = <&udc_clk>, <&udpck>; @@ -976,7 +976,6 @@ atmel,watchdog-type = "hardware"; atmel,reset-type = "all"; atmel,dbg-halt; - atmel,idle-halt; status = "disabled"; }; diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi index e247b0b5fdab..d55fdf2487ef 100644 --- a/arch/arm/boot/dts/at91sam9261.dtsi +++ b/arch/arm/boot/dts/at91sam9261.dtsi @@ -124,11 +124,12 @@ }; usb1: gadget@fffa4000 { - compatible = "atmel,at91rm9200-udc"; + compatible = "atmel,at91sam9261-udc"; reg = <0xfffa4000 0x4000>; interrupts = <10 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&udc_clk>, <&udpck>; - clock-names = "usb_clk", "udc_clk", "udpck"; + clocks = <&udc_clk>, <&udpck>; + clock-names = "pclk", "hclk"; + atmel,matrix = <&matrix>; status = "disabled"; }; @@ -262,7 +263,7 @@ }; matrix: matrix@ffffee00 { - compatible = "atmel,at91sam9260-bus-matrix"; + compatible = "atmel,at91sam9260-bus-matrix", "syscon"; reg = <0xffffee00 0x200>; }; diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index 340179ef6ba0..e4f61a979a57 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -69,7 +69,7 @@ sram1: sram@00500000 { compatible = "mmio-sram"; - reg = <0x00300000 0x4000>; + reg = <0x00500000 0x4000>; }; ahb { @@ -856,7 +856,7 @@ }; usb1: gadget@fff78000 { - compatible = "atmel,at91rm9200-udc"; + compatible = "atmel,at91sam9263-udc"; reg = <0xfff78000 0x4000>; interrupts = <24 IRQ_TYPE_LEVEL_HIGH 2>; clocks = <&udc_clk>, <&udpck>; @@ -905,7 +905,6 @@ atmel,watchdog-type = "hardware"; atmel,reset-type = "all"; atmel,dbg-halt; - atmel,idle-halt; status = "disabled"; }; diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi index 586eab7b653d..8ec05b11298a 100644 --- a/arch/arm/boot/dts/at91sam9g45.dtsi +++ b/arch/arm/boot/dts/at91sam9g45.dtsi @@ -1116,7 +1116,6 @@ atmel,watchdog-type = "hardware"; atmel,reset-type = "all"; atmel,dbg-halt; - atmel,idle-halt; status = "disabled"; }; @@ -1301,7 +1300,7 @@ compatible = "atmel,at91sam9g45-ehci", "usb-ehci"; reg = <0x00800000 0x100000>; interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>; + clocks = <&utmi>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ehci_clk", "hclk", "uhpck"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi index c2666a7cb5b1..0c53a375ba99 100644 --- a/arch/arm/boot/dts/at91sam9n12.dtsi +++ b/arch/arm/boot/dts/at91sam9n12.dtsi @@ -894,7 +894,6 @@ atmel,watchdog-type = "hardware"; atmel,reset-type = "all"; atmel,dbg-halt; - atmel,idle-halt; status = "disabled"; }; diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 818dabdd8c0e..d221179d0f1a 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -1066,7 +1066,7 @@ reg = <0x00500000 0x80000 0xf803c000 0x400>; interrupts = <23 IRQ_TYPE_LEVEL_HIGH 0>; - clocks = <&usb>, <&udphs_clk>; + clocks = <&utmi>, <&udphs_clk>; clock-names = "hclk", "pclk"; status = "disabled"; @@ -1130,7 +1130,6 @@ atmel,watchdog-type = "hardware"; atmel,reset-type = "all"; atmel,dbg-halt; - atmel,idle-halt; status = "disabled"; }; @@ -1186,7 +1185,7 @@ compatible = "atmel,at91sam9g45-ehci", "usb-ehci"; reg = <0x00700000 0x100000>; interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&uhpck>; + clocks = <&utmi>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ehci_clk", "uhpck"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index 3290a96ba586..7563d7ce01bb 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -263,17 +263,15 @@ dcan1_pins_default: dcan1_pins_default { pinctrl-single,pins = < - 0x3d0 (PIN_OUTPUT | MUX_MODE0) /* dcan1_tx */ - 0x3d4 (MUX_MODE15) /* dcan1_rx.off */ - 0x418 (PULL_DIS | MUX_MODE1) /* wakeup0.dcan1_rx */ + 0x3d0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* dcan1_tx */ + 0x418 (PULL_UP | MUX_MODE1) /* wakeup0.dcan1_rx */ >; }; dcan1_pins_sleep: dcan1_pins_sleep { pinctrl-single,pins = < - 0x3d0 (MUX_MODE15) /* dcan1_tx.off */ - 0x3d4 (MUX_MODE15) /* dcan1_rx.off */ - 0x418 (MUX_MODE15) /* wakeup0.off */ + 0x3d0 (MUX_MODE15 | PULL_UP) /* dcan1_tx.off */ + 0x418 (MUX_MODE15 | PULL_UP) /* wakeup0.off */ >; }; }; diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts index e0264d0bf7b9..40ed539ce474 100644 --- a/arch/arm/boot/dts/dra72-evm.dts +++ b/arch/arm/boot/dts/dra72-evm.dts @@ -119,17 +119,15 @@ dcan1_pins_default: dcan1_pins_default { pinctrl-single,pins = < - 0x3d0 (PIN_OUTPUT | MUX_MODE0) /* dcan1_tx */ - 0x3d4 (MUX_MODE15) /* dcan1_rx.off */ - 0x418 (PULL_DIS | MUX_MODE1) /* wakeup0.dcan1_rx */ + 0x3d0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* dcan1_tx */ + 0x418 (PULL_UP | MUX_MODE1) /* wakeup0.dcan1_rx */ >; }; dcan1_pins_sleep: dcan1_pins_sleep { pinctrl-single,pins = < - 0x3d0 (MUX_MODE15) /* dcan1_tx.off */ - 0x3d4 (MUX_MODE15) /* dcan1_rx.off */ - 0x418 (MUX_MODE15) /* wakeup0.off */ + 0x3d0 (MUX_MODE15 | PULL_UP) /* dcan1_tx.off */ + 0x418 (MUX_MODE15 | PULL_UP) /* wakeup0.off */ >; }; diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index 4bdcbd61ce47..99b09a44e269 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -243,10 +243,18 @@ ti,invert-autoidle-bit; }; + dpll_core_byp_mux: dpll_core_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x012c>; + }; + dpll_core_ck: dpll_core_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-core-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_core_byp_mux>; reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>; }; @@ -309,10 +317,18 @@ clock-div = <1>; }; + dpll_dsp_byp_mux: dpll_dsp_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x0240>; + }; + dpll_dsp_ck: dpll_dsp_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_dsp_byp_mux>; reg = <0x0234>, <0x0238>, <0x0240>, <0x023c>; }; @@ -335,10 +351,18 @@ clock-div = <1>; }; + dpll_iva_byp_mux: dpll_iva_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x01ac>; + }; + dpll_iva_ck: dpll_iva_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_iva_byp_mux>; reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>; }; @@ -361,10 +385,18 @@ clock-div = <1>; }; + dpll_gpu_byp_mux: dpll_gpu_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x02e4>; + }; + dpll_gpu_ck: dpll_gpu_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_gpu_byp_mux>; reg = <0x02d8>, <0x02dc>, <0x02e4>, <0x02e0>; }; @@ -398,10 +430,18 @@ clock-div = <1>; }; + dpll_ddr_byp_mux: dpll_ddr_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x021c>; + }; + dpll_ddr_ck: dpll_ddr_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_ddr_byp_mux>; reg = <0x0210>, <0x0214>, <0x021c>, <0x0218>; }; @@ -416,10 +456,18 @@ ti,invert-autoidle-bit; }; + dpll_gmac_byp_mux: dpll_gmac_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x02b4>; + }; + dpll_gmac_ck: dpll_gmac_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin1>, <&dpll_gmac_byp_mux>; reg = <0x02a8>, <0x02ac>, <0x02b4>, <0x02b0>; }; @@ -482,10 +530,18 @@ clock-div = <1>; }; + dpll_eve_byp_mux: dpll_eve_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x0290>; + }; + dpll_eve_ck: dpll_eve_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_eve_byp_mux>; reg = <0x0284>, <0x0288>, <0x0290>, <0x028c>; }; @@ -1249,10 +1305,18 @@ clock-div = <1>; }; + dpll_per_byp_mux: dpll_per_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x014c>; + }; + dpll_per_ck: dpll_per_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_per_byp_mux>; reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>; }; @@ -1275,10 +1339,18 @@ clock-div = <1>; }; + dpll_usb_byp_mux: dpll_usb_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x018c>; + }; + dpll_usb_ck: dpll_usb_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-j-type-clock"; - clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>; + clocks = <&sys_clkin1>, <&dpll_usb_byp_mux>; reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>; }; diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi index 277b48b0b6f9..ac6b0ae42caf 100644 --- a/arch/arm/boot/dts/exynos3250.dtsi +++ b/arch/arm/boot/dts/exynos3250.dtsi @@ -18,6 +18,7 @@ */ #include "skeleton.dtsi" +#include "exynos4-cpu-thermal.dtsi" #include <dt-bindings/clock/exynos3250.h> / { @@ -193,6 +194,7 @@ interrupts = <0 216 0>; clocks = <&cmu CLK_TMU_APBIF>; clock-names = "tmu_apbif"; + #include "exynos4412-tmu-sensor-conf.dtsi" status = "disabled"; }; diff --git a/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi new file mode 100644 index 000000000000..735cb2f10817 --- /dev/null +++ b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi @@ -0,0 +1,52 @@ +/* + * Device tree sources for Exynos4 thermal zone + * + * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.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. + * + */ + +#include <dt-bindings/thermal/thermal.h> + +/ { +thermal-zones { + cpu_thermal: cpu-thermal { + thermal-sensors = <&tmu 0>; + polling-delay-passive = <0>; + polling-delay = <0>; + trips { + cpu_alert0: cpu-alert-0 { + temperature = <70000>; /* millicelsius */ + hysteresis = <10000>; /* millicelsius */ + type = "active"; + }; + cpu_alert1: cpu-alert-1 { + temperature = <95000>; /* millicelsius */ + hysteresis = <10000>; /* millicelsius */ + type = "active"; + }; + cpu_alert2: cpu-alert-2 { + temperature = <110000>; /* millicelsius */ + hysteresis = <10000>; /* millicelsius */ + type = "active"; + }; + cpu_crit0: cpu-crit-0 { + temperature = <120000>; /* millicelsius */ + hysteresis = <0>; /* millicelsius */ + type = "critical"; + }; + }; + cooling-maps { + map0 { + trip = <&cpu_alert0>; + }; + map1 { + trip = <&cpu_alert1>; + }; + }; + }; +}; +}; diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi index 76173cacd450..77ea547768f4 100644 --- a/arch/arm/boot/dts/exynos4.dtsi +++ b/arch/arm/boot/dts/exynos4.dtsi @@ -38,6 +38,7 @@ i2c5 = &i2c_5; i2c6 = &i2c_6; i2c7 = &i2c_7; + i2c8 = &i2c_8; csis0 = &csis_0; csis1 = &csis_1; fimc0 = &fimc_0; @@ -104,6 +105,7 @@ compatible = "samsung,exynos4210-pd"; reg = <0x10023C20 0x20>; #power-domain-cells = <0>; + power-domains = <&pd_lcd0>; }; pd_cam: cam-power-domain@10023C00 { @@ -554,6 +556,22 @@ status = "disabled"; }; + i2c_8: i2c@138E0000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "samsung,s3c2440-hdmiphy-i2c"; + reg = <0x138E0000 0x100>; + interrupts = <0 93 0>; + clocks = <&clock CLK_I2C_HDMI>; + clock-names = "i2c"; + status = "disabled"; + + hdmi_i2c_phy: hdmiphy@38 { + compatible = "exynos4210-hdmiphy"; + reg = <0x38>; + }; + }; + spi_0: spi@13920000 { compatible = "samsung,exynos4210-spi"; reg = <0x13920000 0x100>; @@ -663,6 +681,33 @@ status = "disabled"; }; + tmu: tmu@100C0000 { + #include "exynos4412-tmu-sensor-conf.dtsi" + }; + + hdmi: hdmi@12D00000 { + compatible = "samsung,exynos4210-hdmi"; + reg = <0x12D00000 0x70000>; + interrupts = <0 92 0>; + clock-names = "hdmi", "sclk_hdmi", "sclk_pixel", "sclk_hdmiphy", + "mout_hdmi"; + clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>, + <&clock CLK_SCLK_PIXEL>, <&clock CLK_SCLK_HDMIPHY>, + <&clock CLK_MOUT_HDMI>; + phy = <&hdmi_i2c_phy>; + power-domains = <&pd_tv>; + samsung,syscon-phandle = <&pmu_system_controller>; + status = "disabled"; + }; + + mixer: mixer@12C10000 { + compatible = "samsung,exynos4210-mixer"; + interrupts = <0 91 0>; + reg = <0x12C10000 0x2100>, <0x12c00000 0x300>; + power-domains = <&pd_tv>; + status = "disabled"; + }; + ppmu_dmc0: ppmu_dmc0@106a0000 { compatible = "samsung,exynos-ppmu"; reg = <0x106a0000 0x2000>; diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts index 3d6652a4b6cb..32c5fd8f6269 100644 --- a/arch/arm/boot/dts/exynos4210-trats.dts +++ b/arch/arm/boot/dts/exynos4210-trats.dts @@ -426,6 +426,25 @@ status = "okay"; }; + tmu@100C0000 { + status = "okay"; + }; + + thermal-zones { + cpu_thermal: cpu-thermal { + cooling-maps { + map0 { + /* Corresponds to 800MHz at freq_table */ + cooling-device = <&cpu0 2 2>; + }; + map1 { + /* Corresponds to 200MHz at freq_table */ + cooling-device = <&cpu0 4 4>; + }; + }; + }; + }; + camera { pinctrl-names = "default"; pinctrl-0 = <>; diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts index b57e6b82ea20..d4f2b11319dd 100644 --- a/arch/arm/boot/dts/exynos4210-universal_c210.dts +++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts @@ -505,6 +505,63 @@ assigned-clock-rates = <0>, <160000000>; }; }; + + hdmi_en: voltage-regulator-hdmi-5v { + compatible = "regulator-fixed"; + regulator-name = "HDMI_5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpe0 1 0>; + enable-active-high; + }; + + hdmi_ddc: i2c-ddc { + compatible = "i2c-gpio"; + gpios = <&gpe4 2 0 &gpe4 3 0>; + i2c-gpio,delay-us = <100>; + #address-cells = <1>; + #size-cells = <0>; + + pinctrl-0 = <&i2c_ddc_bus>; + pinctrl-names = "default"; + status = "okay"; + }; + + mixer@12C10000 { + status = "okay"; + }; + + hdmi@12D00000 { + hpd-gpio = <&gpx3 7 0>; + pinctrl-names = "default"; + pinctrl-0 = <&hdmi_hpd>; + hdmi-en-supply = <&hdmi_en>; + vdd-supply = <&ldo3_reg>; + vdd_osc-supply = <&ldo4_reg>; + vdd_pll-supply = <&ldo3_reg>; + ddc = <&hdmi_ddc>; + status = "okay"; + }; + + i2c@138E0000 { + status = "okay"; + }; +}; + +&pinctrl_1 { + hdmi_hpd: hdmi-hpd { + samsung,pins = "gpx3-7"; + samsung,pin-pud = <0>; + }; +}; + +&pinctrl_0 { + i2c_ddc_bus: i2c-ddc-bus { + samsung,pins = "gpe4-2", "gpe4-3"; + samsung,pin-function = <2>; + samsung,pin-pud = <3>; + samsung,pin-drv = <0>; + }; }; &mdma1 { diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi index 67c832c9dcf1..be89f83f70e7 100644 --- a/arch/arm/boot/dts/exynos4210.dtsi +++ b/arch/arm/boot/dts/exynos4210.dtsi @@ -21,6 +21,7 @@ #include "exynos4.dtsi" #include "exynos4210-pinctrl.dtsi" +#include "exynos4-cpu-thermal.dtsi" / { compatible = "samsung,exynos4210", "samsung,exynos4"; @@ -35,10 +36,13 @@ #address-cells = <1>; #size-cells = <0>; - cpu@900 { + cpu0: cpu@900 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <0x900>; + cooling-min-level = <4>; + cooling-max-level = <2>; + #cooling-cells = <2>; /* min followed by max */ }; cpu@901 { @@ -153,16 +157,38 @@ reg = <0x03860000 0x1000>; }; - tmu@100C0000 { + tmu: tmu@100C0000 { compatible = "samsung,exynos4210-tmu"; interrupt-parent = <&combiner>; reg = <0x100C0000 0x100>; interrupts = <2 4>; clocks = <&clock CLK_TMU_APBIF>; clock-names = "tmu_apbif"; + samsung,tmu_gain = <15>; + samsung,tmu_reference_voltage = <7>; status = "disabled"; }; + thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&tmu 0>; + + trips { + cpu_alert0: cpu-alert-0 { + temperature = <85000>; /* millicelsius */ + }; + cpu_alert1: cpu-alert-1 { + temperature = <100000>; /* millicelsius */ + }; + cpu_alert2: cpu-alert-2 { + temperature = <110000>; /* millicelsius */ + }; + }; + }; + }; + g2d@12800000 { compatible = "samsung,s5pv210-g2d"; reg = <0x12800000 0x1000>; @@ -203,6 +229,14 @@ }; }; + mixer: mixer@12C10000 { + clock-names = "mixer", "hdmi", "sclk_hdmi", "vp", "mout_mixer", + "sclk_mixer"; + clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>, + <&clock CLK_SCLK_HDMI>, <&clock CLK_VP>, + <&clock CLK_MOUT_MIXER>, <&clock CLK_SCLK_MIXER>; + }; + ppmu_lcd1: ppmu_lcd1@12240000 { compatible = "samsung,exynos-ppmu"; reg = <0x12240000 0x2000>; diff --git a/arch/arm/boot/dts/exynos4212.dtsi b/arch/arm/boot/dts/exynos4212.dtsi index dd0a43ec56da..5be03288f1ee 100644 --- a/arch/arm/boot/dts/exynos4212.dtsi +++ b/arch/arm/boot/dts/exynos4212.dtsi @@ -26,10 +26,13 @@ #address-cells = <1>; #size-cells = <0>; - cpu@A00 { + cpu0: cpu@A00 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <0xA00>; + cooling-min-level = <13>; + cooling-max-level = <7>; + #cooling-cells = <2>; /* min followed by max */ }; cpu@A01 { diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index de80b5bba204..adb4f6a97a1d 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -249,6 +249,20 @@ regulator-always-on; }; + ldo8_reg: ldo@8 { + regulator-compatible = "LDO8"; + regulator-name = "VDD10_HDMI_1.0V"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + }; + + ldo10_reg: ldo@10 { + regulator-compatible = "LDO10"; + regulator-name = "VDDQ_MIPIHSI_1.8V"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + ldo11_reg: LDO11 { regulator-name = "VDD18_ABB1_1.8V"; regulator-min-microvolt = <1800000>; @@ -411,6 +425,51 @@ ehci: ehci@12580000 { status = "okay"; }; + + tmu@100C0000 { + vtmu-supply = <&ldo10_reg>; + status = "okay"; + }; + + thermal-zones { + cpu_thermal: cpu-thermal { + cooling-maps { + map0 { + /* Corresponds to 800MHz at freq_table */ + cooling-device = <&cpu0 7 7>; + }; + map1 { + /* Corresponds to 200MHz at freq_table */ + cooling-device = <&cpu0 13 13>; + }; + }; + }; + }; + + mixer: mixer@12C10000 { + status = "okay"; + }; + + hdmi@12D00000 { + hpd-gpio = <&gpx3 7 0>; + pinctrl-names = "default"; + pinctrl-0 = <&hdmi_hpd>; + vdd-supply = <&ldo8_reg>; + vdd_osc-supply = <&ldo10_reg>; + vdd_pll-supply = <&ldo8_reg>; + ddc = <&hdmi_ddc>; + status = "okay"; + }; + + hdmi_ddc: i2c@13880000 { + status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_bus>; + }; + + i2c@138E0000 { + status = "okay"; + }; }; &pinctrl_1 { @@ -425,4 +484,9 @@ samsung,pin-pud = <0>; samsung,pin-drv = <0>; }; + + hdmi_hpd: hdmi-hpd { + samsung,pins = "gpx3-7"; + samsung,pin-pud = <1>; + }; }; diff --git a/arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi new file mode 100644 index 000000000000..e3f7934d19d0 --- /dev/null +++ b/arch/arm/boot/dts/exynos4412-tmu-sensor-conf.dtsi @@ -0,0 +1,24 @@ +/* + * Device tree sources for Exynos4412 TMU sensor configuration + * + * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.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. + * + */ + +#include <dt-bindings/thermal/thermal_exynos.h> + +#thermal-sensor-cells = <0>; +samsung,tmu_gain = <8>; +samsung,tmu_reference_voltage = <16>; +samsung,tmu_noise_cancel_mode = <4>; +samsung,tmu_efuse_value = <55>; +samsung,tmu_min_efuse_value = <40>; +samsung,tmu_max_efuse_value = <100>; +samsung,tmu_first_point_trim = <25>; +samsung,tmu_second_point_trim = <85>; +samsung,tmu_default_temp_offset = <50>; +samsung,tmu_cal_type = <TYPE_ONE_POINT_TRIMMING>; diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts index 21f748083586..173ffa479ad3 100644 --- a/arch/arm/boot/dts/exynos4412-trats2.dts +++ b/arch/arm/boot/dts/exynos4412-trats2.dts @@ -927,6 +927,21 @@ pulldown-ohm = <100000>; /* 100K */ io-channels = <&adc 2>; /* Battery temperature */ }; + + thermal-zones { + cpu_thermal: cpu-thermal { + cooling-maps { + map0 { + /* Corresponds to 800MHz at freq_table */ + cooling-device = <&cpu0 7 7>; + }; + map1 { + /* Corresponds to 200MHz at freq_table */ + cooling-device = <&cpu0 13 13>; + }; + }; + }; + }; }; &pmu_system_controller { diff --git a/arch/arm/boot/dts/exynos4412.dtsi b/arch/arm/boot/dts/exynos4412.dtsi index 0f6ec93bb1d8..68ad43b391ae 100644 --- a/arch/arm/boot/dts/exynos4412.dtsi +++ b/arch/arm/boot/dts/exynos4412.dtsi @@ -26,10 +26,13 @@ #address-cells = <1>; #size-cells = <0>; - cpu@A00 { + cpu0: cpu@A00 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <0xA00>; + cooling-min-level = <13>; + cooling-max-level = <7>; + #cooling-cells = <2>; /* min followed by max */ }; cpu@A01 { diff --git a/arch/arm/boot/dts/exynos4x12.dtsi b/arch/arm/boot/dts/exynos4x12.dtsi index f5e0ae780d6c..6a6abe14fd9b 100644 --- a/arch/arm/boot/dts/exynos4x12.dtsi +++ b/arch/arm/boot/dts/exynos4x12.dtsi @@ -19,6 +19,7 @@ #include "exynos4.dtsi" #include "exynos4x12-pinctrl.dtsi" +#include "exynos4-cpu-thermal.dtsi" / { aliases { @@ -297,4 +298,15 @@ clock-names = "tmu_apbif"; status = "disabled"; }; + + hdmi: hdmi@12D00000 { + compatible = "samsung,exynos4212-hdmi"; + }; + + mixer: mixer@12C10000 { + compatible = "samsung,exynos4212-mixer"; + clock-names = "mixer", "hdmi", "sclk_hdmi", "vp"; + clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>, + <&clock CLK_SCLK_HDMI>, <&clock CLK_VP>; + }; }; diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi index 9bb1b0b738f5..adbde1adad95 100644 --- a/arch/arm/boot/dts/exynos5250.dtsi +++ b/arch/arm/boot/dts/exynos5250.dtsi @@ -20,7 +20,7 @@ #include <dt-bindings/clock/exynos5250.h> #include "exynos5.dtsi" #include "exynos5250-pinctrl.dtsi" - +#include "exynos4-cpu-thermal.dtsi" #include <dt-bindings/clock/exynos-audss-clk.h> / { @@ -58,11 +58,14 @@ #address-cells = <1>; #size-cells = <0>; - cpu@0 { + cpu0: cpu@0 { device_type = "cpu"; compatible = "arm,cortex-a15"; reg = <0>; clock-frequency = <1700000000>; + cooling-min-level = <15>; + cooling-max-level = <9>; + #cooling-cells = <2>; /* min followed by max */ }; cpu@1 { device_type = "cpu"; @@ -102,6 +105,12 @@ #power-domain-cells = <0>; }; + pd_disp1: disp1-power-domain@100440A0 { + compatible = "samsung,exynos4210-pd"; + reg = <0x100440A0 0x20>; + #power-domain-cells = <0>; + }; + clock: clock-controller@10010000 { compatible = "samsung,exynos5250-clock"; reg = <0x10010000 0x30000>; @@ -235,12 +244,32 @@ status = "disabled"; }; - tmu@10060000 { + tmu: tmu@10060000 { compatible = "samsung,exynos5250-tmu"; reg = <0x10060000 0x100>; interrupts = <0 65 0>; clocks = <&clock CLK_TMU>; clock-names = "tmu_apbif"; + #include "exynos4412-tmu-sensor-conf.dtsi" + }; + + thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&tmu 0>; + + cooling-maps { + map0 { + /* Corresponds to 800MHz at freq_table */ + cooling-device = <&cpu0 9 9>; + }; + map1 { + /* Corresponds to 200MHz at freq_table */ + cooling-device = <&cpu0 15 15>; + }; + }; + }; }; serial@12C00000 { @@ -719,6 +748,7 @@ hdmi: hdmi { compatible = "samsung,exynos4212-hdmi"; reg = <0x14530000 0x70000>; + power-domains = <&pd_disp1>; interrupts = <0 95 0>; clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>, <&clock CLK_SCLK_PIXEL>, <&clock CLK_SCLK_HDMIPHY>, @@ -731,9 +761,11 @@ mixer { compatible = "samsung,exynos5250-mixer"; reg = <0x14450000 0x10000>; + power-domains = <&pd_disp1>; interrupts = <0 94 0>; - clocks = <&clock CLK_MIXER>, <&clock CLK_SCLK_HDMI>; - clock-names = "mixer", "sclk_hdmi"; + clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>, + <&clock CLK_SCLK_HDMI>; + clock-names = "mixer", "hdmi", "sclk_hdmi"; }; dp_phy: video-phy@10040720 { @@ -743,6 +775,7 @@ }; dp: dp-controller@145B0000 { + power-domains = <&pd_disp1>; clocks = <&clock CLK_DP>; clock-names = "dp"; phys = <&dp_phy>; @@ -750,6 +783,7 @@ }; fimd: fimd@14400000 { + power-domains = <&pd_disp1>; clocks = <&clock CLK_SCLK_FIMD1>, <&clock CLK_FIMD1>; clock-names = "sclk_fimd", "fimd"; }; diff --git a/arch/arm/boot/dts/exynos5420-trip-points.dtsi b/arch/arm/boot/dts/exynos5420-trip-points.dtsi new file mode 100644 index 000000000000..5d31fc140823 --- /dev/null +++ b/arch/arm/boot/dts/exynos5420-trip-points.dtsi @@ -0,0 +1,35 @@ +/* + * Device tree sources for default Exynos5420 thermal zone definition + * + * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.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. + * + */ + +polling-delay-passive = <0>; +polling-delay = <0>; +trips { + cpu-alert-0 { + temperature = <85000>; /* millicelsius */ + hysteresis = <10000>; /* millicelsius */ + type = "active"; + }; + cpu-alert-1 { + temperature = <103000>; /* millicelsius */ + hysteresis = <10000>; /* millicelsius */ + type = "active"; + }; + cpu-alert-2 { + temperature = <110000>; /* millicelsius */ + hysteresis = <10000>; /* millicelsius */ + type = "active"; + }; + cpu-crit-0 { + temperature = <1200000>; /* millicelsius */ + hysteresis = <0>; /* millicelsius */ + type = "critical"; + }; +}; diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi index 9dc2e9773b30..c0e98cf3514f 100644 --- a/arch/arm/boot/dts/exynos5420.dtsi +++ b/arch/arm/boot/dts/exynos5420.dtsi @@ -740,8 +740,9 @@ compatible = "samsung,exynos5420-mixer"; reg = <0x14450000 0x10000>; interrupts = <0 94 0>; - clocks = <&clock CLK_MIXER>, <&clock CLK_SCLK_HDMI>; - clock-names = "mixer", "sclk_hdmi"; + clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>, + <&clock CLK_SCLK_HDMI>; + clock-names = "mixer", "hdmi", "sclk_hdmi"; power-domains = <&disp_pd>; }; @@ -782,6 +783,7 @@ interrupts = <0 65 0>; clocks = <&clock CLK_TMU>; clock-names = "tmu_apbif"; + #include "exynos4412-tmu-sensor-conf.dtsi" }; tmu_cpu1: tmu@10064000 { @@ -790,6 +792,7 @@ interrupts = <0 183 0>; clocks = <&clock CLK_TMU>; clock-names = "tmu_apbif"; + #include "exynos4412-tmu-sensor-conf.dtsi" }; tmu_cpu2: tmu@10068000 { @@ -798,6 +801,7 @@ interrupts = <0 184 0>; clocks = <&clock CLK_TMU>, <&clock CLK_TMU>; clock-names = "tmu_apbif", "tmu_triminfo_apbif"; + #include "exynos4412-tmu-sensor-conf.dtsi" }; tmu_cpu3: tmu@1006c000 { @@ -806,6 +810,7 @@ interrupts = <0 185 0>; clocks = <&clock CLK_TMU>, <&clock CLK_TMU_GPU>; clock-names = "tmu_apbif", "tmu_triminfo_apbif"; + #include "exynos4412-tmu-sensor-conf.dtsi" }; tmu_gpu: tmu@100a0000 { @@ -814,6 +819,30 @@ interrupts = <0 215 0>; clocks = <&clock CLK_TMU_GPU>, <&clock CLK_TMU>; clock-names = "tmu_apbif", "tmu_triminfo_apbif"; + #include "exynos4412-tmu-sensor-conf.dtsi" + }; + + thermal-zones { + cpu0_thermal: cpu0-thermal { + thermal-sensors = <&tmu_cpu0>; + #include "exynos5420-trip-points.dtsi" + }; + cpu1_thermal: cpu1-thermal { + thermal-sensors = <&tmu_cpu1>; + #include "exynos5420-trip-points.dtsi" + }; + cpu2_thermal: cpu2-thermal { + thermal-sensors = <&tmu_cpu2>; + #include "exynos5420-trip-points.dtsi" + }; + cpu3_thermal: cpu3-thermal { + thermal-sensors = <&tmu_cpu3>; + #include "exynos5420-trip-points.dtsi" + }; + gpu_thermal: gpu-thermal { + thermal-sensors = <&tmu_gpu>; + #include "exynos5420-trip-points.dtsi" + }; }; watchdog: watchdog@101D0000 { diff --git a/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi b/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi new file mode 100644 index 000000000000..7b2fba0ae92b --- /dev/null +++ b/arch/arm/boot/dts/exynos5440-tmu-sensor-conf.dtsi @@ -0,0 +1,24 @@ +/* + * Device tree sources for Exynos5440 TMU sensor configuration + * + * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.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. + * + */ + +#include <dt-bindings/thermal/thermal_exynos.h> + +#thermal-sensor-cells = <0>; +samsung,tmu_gain = <5>; +samsung,tmu_reference_voltage = <16>; +samsung,tmu_noise_cancel_mode = <4>; +samsung,tmu_efuse_value = <0x5d2d>; +samsung,tmu_min_efuse_value = <16>; +samsung,tmu_max_efuse_value = <76>; +samsung,tmu_first_point_trim = <25>; +samsung,tmu_second_point_trim = <70>; +samsung,tmu_default_temp_offset = <25>; +samsung,tmu_cal_type = <TYPE_ONE_POINT_TRIMMING>; diff --git a/arch/arm/boot/dts/exynos5440-trip-points.dtsi b/arch/arm/boot/dts/exynos5440-trip-points.dtsi new file mode 100644 index 000000000000..48adfa8f4300 --- /dev/null +++ b/arch/arm/boot/dts/exynos5440-trip-points.dtsi @@ -0,0 +1,25 @@ +/* + * Device tree sources for default Exynos5440 thermal zone definition + * + * Copyright (c) 2014 Lukasz Majewski <l.majewski@samsung.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. + * + */ + +polling-delay-passive = <0>; +polling-delay = <0>; +trips { + cpu-alert-0 { + temperature = <100000>; /* millicelsius */ + hysteresis = <0>; /* millicelsius */ + type = "active"; + }; + cpu-crit-0 { + temperature = <1050000>; /* millicelsius */ + hysteresis = <0>; /* millicelsius */ + type = "critical"; + }; +}; diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi index 8f3373cd7b87..59d9416b3b03 100644 --- a/arch/arm/boot/dts/exynos5440.dtsi +++ b/arch/arm/boot/dts/exynos5440.dtsi @@ -219,6 +219,7 @@ interrupts = <0 58 0>; clocks = <&clock CLK_B_125>; clock-names = "tmu_apbif"; + #include "exynos5440-tmu-sensor-conf.dtsi" }; tmuctrl_1: tmuctrl@16011C { @@ -227,6 +228,7 @@ interrupts = <0 58 0>; clocks = <&clock CLK_B_125>; clock-names = "tmu_apbif"; + #include "exynos5440-tmu-sensor-conf.dtsi" }; tmuctrl_2: tmuctrl@160120 { @@ -235,6 +237,22 @@ interrupts = <0 58 0>; clocks = <&clock CLK_B_125>; clock-names = "tmu_apbif"; + #include "exynos5440-tmu-sensor-conf.dtsi" + }; + + thermal-zones { + cpu0_thermal: cpu0-thermal { + thermal-sensors = <&tmuctrl_0>; + #include "exynos5440-trip-points.dtsi" + }; + cpu1_thermal: cpu1-thermal { + thermal-sensors = <&tmuctrl_1>; + #include "exynos5440-trip-points.dtsi" + }; + cpu2_thermal: cpu2-thermal { + thermal-sensors = <&tmuctrl_2>; + #include "exynos5440-trip-points.dtsi" + }; }; sata@210000 { diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi index f1cd2147421d..a626e6dd8022 100644 --- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi @@ -35,6 +35,7 @@ regulator-max-microvolt = <5000000>; gpio = <&gpio3 22 0>; enable-active-high; + vin-supply = <&swbst_reg>; }; reg_usb_h1_vbus: regulator@1 { @@ -45,6 +46,7 @@ regulator-max-microvolt = <5000000>; gpio = <&gpio1 29 0>; enable-active-high; + vin-supply = <&swbst_reg>; }; reg_audio: regulator@2 { diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts index fda4932faefd..945887d3fdb3 100644 --- a/arch/arm/boot/dts/imx6sl-evk.dts +++ b/arch/arm/boot/dts/imx6sl-evk.dts @@ -52,6 +52,7 @@ regulator-max-microvolt = <5000000>; gpio = <&gpio4 0 0>; enable-active-high; + vin-supply = <&swbst_reg>; }; reg_usb_otg2_vbus: regulator@1 { @@ -62,6 +63,7 @@ regulator-max-microvolt = <5000000>; gpio = <&gpio4 2 0>; enable-active-high; + vin-supply = <&swbst_reg>; }; reg_aud3v: regulator@2 { diff --git a/arch/arm/boot/dts/omap5-core-thermal.dtsi b/arch/arm/boot/dts/omap5-core-thermal.dtsi index 19212ac6eef0..de8a3d456cf7 100644 --- a/arch/arm/boot/dts/omap5-core-thermal.dtsi +++ b/arch/arm/boot/dts/omap5-core-thermal.dtsi @@ -13,7 +13,7 @@ core_thermal: core_thermal { polling-delay-passive = <250>; /* milliseconds */ - polling-delay = <1000>; /* milliseconds */ + polling-delay = <500>; /* milliseconds */ /* sensor ID */ thermal-sensors = <&bandgap 2>; diff --git a/arch/arm/boot/dts/omap5-gpu-thermal.dtsi b/arch/arm/boot/dts/omap5-gpu-thermal.dtsi index 1b87aca88b77..bc3090f2e84b 100644 --- a/arch/arm/boot/dts/omap5-gpu-thermal.dtsi +++ b/arch/arm/boot/dts/omap5-gpu-thermal.dtsi @@ -13,7 +13,7 @@ gpu_thermal: gpu_thermal { polling-delay-passive = <250>; /* milliseconds */ - polling-delay = <1000>; /* milliseconds */ + polling-delay = <500>; /* milliseconds */ /* sensor ID */ thermal-sensors = <&bandgap 1>; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index ddff674bd05e..4a485b63a141 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -1079,4 +1079,8 @@ }; }; +&cpu_thermal { + polling-delay = <500>; /* milliseconds */ +}; + /include/ "omap54xx-clocks.dtsi" diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi index 58c27466f012..83b425fb3ac2 100644 --- a/arch/arm/boot/dts/omap54xx-clocks.dtsi +++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi @@ -167,10 +167,18 @@ ti,index-starts-at-one; }; + dpll_core_byp_mux: dpll_core_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin>, <&dpll_abe_m3x2_ck>; + ti,bit-shift = <23>; + reg = <0x012c>; + }; + dpll_core_ck: dpll_core_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-core-clock"; - clocks = <&sys_clkin>, <&dpll_abe_m3x2_ck>; + clocks = <&sys_clkin>, <&dpll_core_byp_mux>; reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>; }; @@ -294,10 +302,18 @@ clock-div = <1>; }; + dpll_iva_byp_mux: dpll_iva_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin>, <&iva_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x01ac>; + }; + dpll_iva_ck: dpll_iva_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin>, <&iva_dpll_hs_clk_div>; + clocks = <&sys_clkin>, <&dpll_iva_byp_mux>; reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>; }; @@ -599,10 +615,19 @@ }; }; &cm_core_clocks { + + dpll_per_byp_mux: dpll_per_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin>, <&per_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x014c>; + }; + dpll_per_ck: dpll_per_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-clock"; - clocks = <&sys_clkin>, <&per_dpll_hs_clk_div>; + clocks = <&sys_clkin>, <&dpll_per_byp_mux>; reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>; }; @@ -714,10 +739,18 @@ ti,index-starts-at-one; }; + dpll_usb_byp_mux: dpll_usb_byp_mux { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clkin>, <&usb_dpll_hs_clk_div>; + ti,bit-shift = <23>; + reg = <0x018c>; + }; + dpll_usb_ck: dpll_usb_ck { #clock-cells = <0>; compatible = "ti,omap4-dpll-j-type-clock"; - clocks = <&sys_clkin>, <&usb_dpll_hs_clk_div>; + clocks = <&sys_clkin>, <&dpll_usb_byp_mux>; reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>; }; diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi index 261311bdf65b..367af53c1b84 100644 --- a/arch/arm/boot/dts/sama5d3.dtsi +++ b/arch/arm/boot/dts/sama5d3.dtsi @@ -1248,7 +1248,6 @@ atmel,watchdog-type = "hardware"; atmel,reset-type = "all"; atmel,dbg-halt; - atmel,idle-halt; status = "disabled"; }; @@ -1416,7 +1415,7 @@ compatible = "atmel,at91sam9g45-ehci", "usb-ehci"; reg = <0x00700000 0x100000>; interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&uhpck>; + clocks = <&utmi>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ehci_clk", "uhpck"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index d986b41b9654..4303874889c6 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -66,6 +66,7 @@ gpio4 = &pioE; tcb0 = &tcb0; tcb1 = &tcb1; + i2c0 = &i2c0; i2c2 = &i2c2; }; cpus { @@ -259,7 +260,7 @@ compatible = "atmel,at91sam9g45-ehci", "usb-ehci"; reg = <0x00600000 0x100000>; interrupts = <46 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&uhpck>; + clocks = <&utmi>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ehci_clk", "uhpck"; status = "disabled"; }; @@ -461,8 +462,8 @@ lcdck: lcdck { #clock-cells = <0>; - reg = <4>; - clocks = <&smd>; + reg = <3>; + clocks = <&mck>; }; smdck: smdck { @@ -770,7 +771,7 @@ reg = <50>; }; - lcd_clk: lcd_clk { + lcdc_clk: lcdc_clk { #clock-cells = <0>; reg = <51>; }; diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi index 252c3d1bda50..9d8760956752 100644 --- a/arch/arm/boot/dts/socfpga.dtsi +++ b/arch/arm/boot/dts/socfpga.dtsi @@ -713,6 +713,9 @@ reg-shift = <2>; reg-io-width = <4>; clocks = <&l4_sp_clk>; + dmas = <&pdma 28>, + <&pdma 29>; + dma-names = "tx", "rx"; }; uart1: serial1@ffc03000 { @@ -722,6 +725,9 @@ reg-shift = <2>; reg-io-width = <4>; clocks = <&l4_sp_clk>; + dmas = <&pdma 30>, + <&pdma 31>; + dma-names = "tx", "rx"; }; rst: rstmgr@ffd05000 { diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig index f2670f638e97..811e72bbe642 100644 --- a/arch/arm/configs/at91_dt_defconfig +++ b/arch/arm/configs/at91_dt_defconfig @@ -70,6 +70,7 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_NETDEVICES=y +CONFIG_ARM_AT91_ETHER=y CONFIG_MACB=y # CONFIG_NET_VENDOR_BROADCOM is not set CONFIG_DM9000=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index b7e6b6fba5e0..06075b6d2463 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -99,7 +99,7 @@ CONFIG_PCI_RCAR_GEN2=y CONFIG_PCI_RCAR_GEN2_PCIE=y CONFIG_PCIEPORTBUS=y CONFIG_SMP=y -CONFIG_NR_CPUS=8 +CONFIG_NR_CPUS=16 CONFIG_HIGHPTE=y CONFIG_CMA=y CONFIG_ARM_APPENDED_DTB=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index a097cffa1231..8e108599e1af 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -377,6 +377,7 @@ CONFIG_PWM_TWL=m CONFIG_PWM_TWL_LED=m CONFIG_OMAP_USB2=m CONFIG_TI_PIPE3=y +CONFIG_TWL4030_USB=m CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y # CONFIG_EXT3_FS_XATTR is not set diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index 41d856effe6c..510c747c65b4 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -3,8 +3,6 @@ CONFIG_SYSVIPC=y CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SYSFS_DEPRECATED=y -CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_BLK_DEV_INITRD=y CONFIG_EMBEDDED=y CONFIG_SLAB=y diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 38840a812924..8f6a5702b696 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -4,6 +4,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_PERF_EVENTS=y CONFIG_ARCH_SUNXI=y CONFIG_SMP=y +CONFIG_NR_CPUS=8 CONFIG_AEABI=y CONFIG_HIGHMEM=y CONFIG_HIGHPTE=y diff --git a/arch/arm/configs/vexpress_defconfig b/arch/arm/configs/vexpress_defconfig index f489fdaa19b8..37fe607a4ede 100644 --- a/arch/arm/configs/vexpress_defconfig +++ b/arch/arm/configs/vexpress_defconfig @@ -118,8 +118,8 @@ CONFIG_HID_ZEROPLUS=y CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y -CONFIG_USB_ISP1760_HCD=y CONFIG_USB_STORAGE=y +CONFIG_USB_ISP1760=y CONFIG_MMC=y CONFIG_MMC_ARMMMCI=y CONFIG_NEW_LEDS=y diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped index 71e5fc7cfb18..1d1800f71c5b 100644 --- a/arch/arm/crypto/aesbs-core.S_shipped +++ b/arch/arm/crypto/aesbs-core.S_shipped @@ -58,14 +58,18 @@ # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ 7 +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 #endif #ifdef __thumb__ # define adrl adr #endif -#if __ARM_ARCH__>=7 +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + .text .syntax unified @ ARMv7-capable assembler is expected to handle this #ifdef __thumb2__ @@ -74,8 +78,6 @@ .code 32 #endif -.fpu neon - .type _bsaes_decrypt8,%function .align 4 _bsaes_decrypt8: @@ -2095,9 +2097,11 @@ bsaes_xts_decrypt: vld1.8 {q8}, [r0] @ initial tweak adr r2, .Lxts_magic +#ifndef XTS_CHAIN_TWEAK tst r9, #0xf @ if not multiple of 16 it ne @ Thumb2 thing, sanity check in ARM subne r9, #0x10 @ subtract another 16 bytes +#endif subs r9, #0x80 blo .Lxts_dec_short diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl index be068db960ee..a4d3856e7d24 100644 --- a/arch/arm/crypto/bsaes-armv7.pl +++ b/arch/arm/crypto/bsaes-armv7.pl @@ -701,14 +701,18 @@ $code.=<<___; # define VFP_ABI_FRAME 0 # define BSAES_ASM_EXTENDED_KEY # define XTS_CHAIN_TWEAK -# define __ARM_ARCH__ 7 +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 #endif #ifdef __thumb__ # define adrl adr #endif -#if __ARM_ARCH__>=7 +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + .text .syntax unified @ ARMv7-capable assembler is expected to handle this #ifdef __thumb2__ @@ -717,8 +721,6 @@ $code.=<<___; .code 32 #endif -.fpu neon - .type _bsaes_decrypt8,%function .align 4 _bsaes_decrypt8: @@ -2076,9 +2078,11 @@ bsaes_xts_decrypt: vld1.8 {@XMM[8]}, [r0] @ initial tweak adr $magic, .Lxts_magic +#ifndef XTS_CHAIN_TWEAK tst $len, #0xf @ if not multiple of 16 it ne @ Thumb2 thing, sanity check in ARM subne $len, #0x10 @ subtract another 16 bytes +#endif subs $len, #0x80 blo .Lxts_dec_short diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index bf0fe99e8ca9..4cf48c3aca13 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -149,29 +149,28 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) +#define kvm_pgd_index(addr) pgd_index(addr) + static inline bool kvm_page_empty(void *ptr) { struct page *ptr_page = virt_to_page(ptr); return page_count(ptr_page) == 1; } - #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) #define kvm_pud_table_empty(kvm, pudp) (0) #define KVM_PREALLOC_LEVEL 0 -static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) +static inline void *kvm_get_hwpgd(struct kvm *kvm) { - return 0; + return kvm->arch.pgd; } -static inline void kvm_free_hwpgd(struct kvm *kvm) { } - -static inline void *kvm_get_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - return kvm->arch.pgd; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } struct kvm; diff --git a/arch/arm/include/debug/at91.S b/arch/arm/include/debug/at91.S index 80a6501b4d50..c3c45e628e33 100644 --- a/arch/arm/include/debug/at91.S +++ b/arch/arm/include/debug/at91.S @@ -18,8 +18,11 @@ #define AT91_DBGU 0xfc00c000 /* SAMA5D4_BASE_USART3 */ #endif -/* Keep in sync with mach-at91/include/mach/hardware.h */ +#ifdef CONFIG_MMU #define AT91_IO_P2V(x) ((x) - 0x01000000) +#else +#define AT91_IO_P2V(x) (x) +#endif #define AT91_DBGU_SR (0x14) /* Status Register */ #define AT91_DBGU_THR (0x1c) /* Transmitter Holding Register */ diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index e55408e96559..1d60bebea4b8 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -246,12 +246,9 @@ static int __get_cpu_architecture(void) if (cpu_arch) cpu_arch += CPU_ARCH_ARMv3; } else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) { - unsigned int mmfr0; - /* Revised CPUID format. Read the Memory Model Feature * Register 0 and check for VMSAv7 or PMSAv7 */ - asm("mrc p15, 0, %0, c0, c1, 4" - : "=r" (mmfr0)); + unsigned int mmfr0 = read_cpuid_ext(CPUID_EXT_MMFR0); if ((mmfr0 & 0x0000000f) >= 0x00000003 || (mmfr0 & 0x000000f0) >= 0x00000030) cpu_arch = CPU_ARCH_ARMv7; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 3e6859bc3e11..5656d79c5a44 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -290,7 +290,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, phys_addr_t addr = start, end = start + size; phys_addr_t next; - pgd = pgdp + pgd_index(addr); + pgd = pgdp + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); if (!pgd_none(*pgd)) @@ -355,7 +355,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t next; pgd_t *pgd; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); stage2_flush_puds(kvm, pgd, addr, next); @@ -632,6 +632,20 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE); } +/* Free the HW pgd, one page at a time */ +static void kvm_free_hwpgd(void *hwpgd) +{ + free_pages_exact(hwpgd, kvm_get_hwpgd_size()); +} + +/* Allocate the HW PGD, making sure that each page gets its own refcount */ +static void *kvm_alloc_hwpgd(void) +{ + unsigned int size = kvm_get_hwpgd_size(); + + return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); +} + /** * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. * @kvm: The KVM struct pointer for the VM. @@ -645,15 +659,31 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) */ int kvm_alloc_stage2_pgd(struct kvm *kvm) { - int ret; pgd_t *pgd; + void *hwpgd; if (kvm->arch.pgd != NULL) { kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } + hwpgd = kvm_alloc_hwpgd(); + if (!hwpgd) + return -ENOMEM; + + /* When the kernel uses more levels of page tables than the + * guest, we allocate a fake PGD and pre-populate it to point + * to the next-level page table, which will be the real + * initial page table pointed to by the VTTBR. + * + * When KVM_PREALLOC_LEVEL==2, we allocate a single page for + * the PMD and the kernel will use folded pud. + * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD + * pages. + */ if (KVM_PREALLOC_LEVEL > 0) { + int i; + /* * Allocate fake pgd for the page table manipulation macros to * work. This is not used by the hardware and we have no @@ -661,30 +691,32 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) */ pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), GFP_KERNEL | __GFP_ZERO); + + if (!pgd) { + kvm_free_hwpgd(hwpgd); + return -ENOMEM; + } + + /* Plug the HW PGD into the fake one. */ + for (i = 0; i < PTRS_PER_S2_PGD; i++) { + if (KVM_PREALLOC_LEVEL == 1) + pgd_populate(NULL, pgd + i, + (pud_t *)hwpgd + i * PTRS_PER_PUD); + else if (KVM_PREALLOC_LEVEL == 2) + pud_populate(NULL, pud_offset(pgd, 0) + i, + (pmd_t *)hwpgd + i * PTRS_PER_PMD); + } } else { /* * Allocate actual first-level Stage-2 page table used by the * hardware for Stage-2 page table walks. */ - pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER); + pgd = (pgd_t *)hwpgd; } - if (!pgd) - return -ENOMEM; - - ret = kvm_prealloc_hwpgd(kvm, pgd); - if (ret) - goto out_err; - kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; return 0; -out_err: - if (KVM_PREALLOC_LEVEL > 0) - kfree(pgd); - else - free_pages((unsigned long)pgd, S2_PGD_ORDER); - return ret; } /** @@ -785,11 +817,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) return; unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); - kvm_free_hwpgd(kvm); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); if (KVM_PREALLOC_LEVEL > 0) kfree(kvm->arch.pgd); - else - free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER); + kvm->arch.pgd = NULL; } @@ -799,7 +830,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pgd_t *pgd; pud_t *pud; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); if (WARN_ON(pgd_none(*pgd))) { if (!cache) return NULL; @@ -1089,7 +1120,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) pgd_t *pgd; phys_addr_t next; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { /* * Release kvm_mmu_lock periodically if the memory region is diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 5e34fb143309..aa4116e9452f 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -270,37 +270,35 @@ static void __init at91_pm_sram_init(void) phys_addr_t sram_pbase; unsigned long sram_base; struct device_node *node; - struct platform_device *pdev; + struct platform_device *pdev = NULL; - node = of_find_compatible_node(NULL, NULL, "mmio-sram"); - if (!node) { - pr_warn("%s: failed to find sram node!\n", __func__); - return; + for_each_compatible_node(node, NULL, "mmio-sram") { + pdev = of_find_device_by_node(node); + if (pdev) { + of_node_put(node); + break; + } } - pdev = of_find_device_by_node(node); if (!pdev) { pr_warn("%s: failed to find sram device!\n", __func__); - goto put_node; + return; } sram_pool = dev_get_gen_pool(&pdev->dev); if (!sram_pool) { pr_warn("%s: sram pool unavailable!\n", __func__); - goto put_node; + return; } sram_base = gen_pool_alloc(sram_pool, at91_slow_clock_sz); if (!sram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); - goto put_node; + return; } sram_pbase = gen_pool_virt_to_phys(sram_pool, sram_base); slow_clock = __arm_ioremap_exec(sram_pbase, at91_slow_clock_sz, false); - -put_node: - of_node_put(node); } #endif diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h index d2c89963af2d..86c0aa819d25 100644 --- a/arch/arm/mach-at91/pm.h +++ b/arch/arm/mach-at91/pm.h @@ -44,7 +44,7 @@ static inline void at91rm9200_standby(void) " mcr p15, 0, %0, c7, c0, 4\n\t" " str %5, [%1, %2]" : - : "r" (0), "r" (AT91_BASE_SYS), "r" (AT91RM9200_SDRAMC_LPR), + : "r" (0), "r" (at91_ramc_base[0]), "r" (AT91RM9200_SDRAMC_LPR), "r" (1), "r" (AT91RM9200_SDRAMC_SRR), "r" (lpr)); } diff --git a/arch/arm/mach-at91/pm_slowclock.S b/arch/arm/mach-at91/pm_slowclock.S index 556151e85ec4..931f0e302c03 100644 --- a/arch/arm/mach-at91/pm_slowclock.S +++ b/arch/arm/mach-at91/pm_slowclock.S @@ -25,11 +25,6 @@ */ #undef SLOWDOWN_MASTER_CLOCK -#define MCKRDY_TIMEOUT 1000 -#define MOSCRDY_TIMEOUT 1000 -#define PLLALOCK_TIMEOUT 1000 -#define PLLBLOCK_TIMEOUT 1000 - pmc .req r0 sdramc .req r1 ramc1 .req r2 @@ -41,60 +36,42 @@ tmp2 .req r5 * Wait until master clock is ready (after switching master clock source) */ .macro wait_mckrdy - mov tmp2, #MCKRDY_TIMEOUT -1: sub tmp2, tmp2, #1 - cmp tmp2, #0 - beq 2f - ldr tmp1, [pmc, #AT91_PMC_SR] +1: ldr tmp1, [pmc, #AT91_PMC_SR] tst tmp1, #AT91_PMC_MCKRDY beq 1b -2: .endm /* * Wait until master oscillator has stabilized. */ .macro wait_moscrdy - mov tmp2, #MOSCRDY_TIMEOUT -1: sub tmp2, tmp2, #1 - cmp tmp2, #0 - beq 2f - ldr tmp1, [pmc, #AT91_PMC_SR] +1: ldr tmp1, [pmc, #AT91_PMC_SR] tst tmp1, #AT91_PMC_MOSCS beq 1b -2: .endm /* * Wait until PLLA has locked. */ .macro wait_pllalock - mov tmp2, #PLLALOCK_TIMEOUT -1: sub tmp2, tmp2, #1 - cmp tmp2, #0 - beq 2f - ldr tmp1, [pmc, #AT91_PMC_SR] +1: ldr tmp1, [pmc, #AT91_PMC_SR] tst tmp1, #AT91_PMC_LOCKA beq 1b -2: .endm /* * Wait until PLLB has locked. */ .macro wait_pllblock - mov tmp2, #PLLBLOCK_TIMEOUT -1: sub tmp2, tmp2, #1 - cmp tmp2, #0 - beq 2f - ldr tmp1, [pmc, #AT91_PMC_SR] +1: ldr tmp1, [pmc, #AT91_PMC_SR] tst tmp1, #AT91_PMC_LOCKB beq 1b -2: .endm .text + .arm + /* void at91_slow_clock(void __iomem *pmc, void __iomem *sdramc, * void __iomem *ramc1, int memctrl) */ @@ -134,6 +111,16 @@ ddr_sr_enable: cmp memctrl, #AT91_MEMCTRL_DDRSDR bne sdr_sr_enable + /* LPDDR1 --> force DDR2 mode during self-refresh */ + ldr tmp1, [sdramc, #AT91_DDRSDRC_MDR] + str tmp1, .saved_sam9_mdr + bic tmp1, tmp1, #~AT91_DDRSDRC_MD + cmp tmp1, #AT91_DDRSDRC_MD_LOW_POWER_DDR + ldreq tmp1, [sdramc, #AT91_DDRSDRC_MDR] + biceq tmp1, tmp1, #AT91_DDRSDRC_MD + orreq tmp1, tmp1, #AT91_DDRSDRC_MD_DDR2 + streq tmp1, [sdramc, #AT91_DDRSDRC_MDR] + /* prepare for DDRAM self-refresh mode */ ldr tmp1, [sdramc, #AT91_DDRSDRC_LPR] str tmp1, .saved_sam9_lpr @@ -142,14 +129,26 @@ ddr_sr_enable: /* figure out if we use the second ram controller */ cmp ramc1, #0 - ldrne tmp2, [ramc1, #AT91_DDRSDRC_LPR] - strne tmp2, .saved_sam9_lpr1 - bicne tmp2, #AT91_DDRSDRC_LPCB - orrne tmp2, #AT91_DDRSDRC_LPCB_SELF_REFRESH + beq ddr_no_2nd_ctrl + + ldr tmp2, [ramc1, #AT91_DDRSDRC_MDR] + str tmp2, .saved_sam9_mdr1 + bic tmp2, tmp2, #~AT91_DDRSDRC_MD + cmp tmp2, #AT91_DDRSDRC_MD_LOW_POWER_DDR + ldreq tmp2, [ramc1, #AT91_DDRSDRC_MDR] + biceq tmp2, tmp2, #AT91_DDRSDRC_MD + orreq tmp2, tmp2, #AT91_DDRSDRC_MD_DDR2 + streq tmp2, [ramc1, #AT91_DDRSDRC_MDR] + + ldr tmp2, [ramc1, #AT91_DDRSDRC_LPR] + str tmp2, .saved_sam9_lpr1 + bic tmp2, #AT91_DDRSDRC_LPCB + orr tmp2, #AT91_DDRSDRC_LPCB_SELF_REFRESH /* Enable DDRAM self-refresh mode */ + str tmp2, [ramc1, #AT91_DDRSDRC_LPR] +ddr_no_2nd_ctrl: str tmp1, [sdramc, #AT91_DDRSDRC_LPR] - strne tmp2, [ramc1, #AT91_DDRSDRC_LPR] b sdr_sr_done @@ -208,6 +207,7 @@ sdr_sr_done: /* Turn off the main oscillator */ ldr tmp1, [pmc, #AT91_CKGR_MOR] bic tmp1, tmp1, #AT91_PMC_MOSCEN + orr tmp1, tmp1, #AT91_PMC_KEY str tmp1, [pmc, #AT91_CKGR_MOR] /* Wait for interrupt */ @@ -216,6 +216,7 @@ sdr_sr_done: /* Turn on the main oscillator */ ldr tmp1, [pmc, #AT91_CKGR_MOR] orr tmp1, tmp1, #AT91_PMC_MOSCEN + orr tmp1, tmp1, #AT91_PMC_KEY str tmp1, [pmc, #AT91_CKGR_MOR] wait_moscrdy @@ -280,12 +281,17 @@ sdr_sr_done: */ cmp memctrl, #AT91_MEMCTRL_DDRSDR bne sdr_en_restore + /* Restore MDR in case of LPDDR1 */ + ldr tmp1, .saved_sam9_mdr + str tmp1, [sdramc, #AT91_DDRSDRC_MDR] /* Restore LPR on AT91 with DDRAM */ ldr tmp1, .saved_sam9_lpr str tmp1, [sdramc, #AT91_DDRSDRC_LPR] /* if we use the second ram controller */ cmp ramc1, #0 + ldrne tmp2, .saved_sam9_mdr1 + strne tmp2, [ramc1, #AT91_DDRSDRC_MDR] ldrne tmp2, .saved_sam9_lpr1 strne tmp2, [ramc1, #AT91_DDRSDRC_LPR] @@ -319,5 +325,11 @@ ram_restored: .saved_sam9_lpr1: .word 0 +.saved_sam9_mdr: + .word 0 + +.saved_sam9_mdr1: + .word 0 + ENTRY(at91_slow_clock_sz) .word .-at91_slow_clock diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index 3f32c47a6d74..d2e9f12d12f1 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -126,8 +126,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious) */ void exynos_cpu_power_down(int cpu) { - if (cpu == 0 && (of_machine_is_compatible("samsung,exynos5420") || - of_machine_is_compatible("samsung,exynos5800"))) { + if (cpu == 0 && (soc_is_exynos5420() || soc_is_exynos5800())) { /* * Bypass power down for CPU0 during suspend. Check for * the SYS_PWR_REG value to decide if we are suspending diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 20f267121b3e..37266a826437 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -161,6 +161,34 @@ no_clk: of_genpd_add_provider_simple(np, &pd->pd); } + /* Assign the child power domains to their parents */ + for_each_compatible_node(np, NULL, "samsung,exynos4210-pd") { + struct generic_pm_domain *child_domain, *parent_domain; + struct of_phandle_args args; + + args.np = np; + args.args_count = 0; + child_domain = of_genpd_get_from_provider(&args); + if (!child_domain) + continue; + + if (of_parse_phandle_with_args(np, "power-domains", + "#power-domain-cells", 0, &args) != 0) + continue; + + parent_domain = of_genpd_get_from_provider(&args); + if (!parent_domain) + continue; + + if (pm_genpd_add_subdomain(parent_domain, child_domain)) + pr_warn("%s failed to add subdomain: %s\n", + parent_domain->name, child_domain->name); + else + pr_info("%s has as child subdomain: %s.\n", + parent_domain->name, child_domain->name); + of_node_put(np); + } + return 0; } arch_initcall(exynos4_pm_init_power_domain); diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c index 52e2b1a2fddb..318d127df147 100644 --- a/arch/arm/mach-exynos/suspend.c +++ b/arch/arm/mach-exynos/suspend.c @@ -87,8 +87,8 @@ static unsigned int exynos_pmu_spare3; static u32 exynos_irqwake_intmask = 0xffffffff; static const struct exynos_wkup_irq exynos3250_wkup_irq[] = { - { 73, BIT(1) }, /* RTC alarm */ - { 74, BIT(2) }, /* RTC tick */ + { 105, BIT(1) }, /* RTC alarm */ + { 106, BIT(2) }, /* RTC tick */ { /* sentinel */ }, }; diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c index 4ad6e473cf83..9de3412af406 100644 --- a/arch/arm/mach-imx/mach-imx6q.c +++ b/arch/arm/mach-imx/mach-imx6q.c @@ -211,8 +211,9 @@ static void __init imx6q_1588_init(void) * set bit IOMUXC_GPR1[21]. Or the PTP clock must be from pad * (external OSC), and we need to clear the bit. */ - clksel = ptp_clk == enet_ref ? IMX6Q_GPR1_ENET_CLK_SEL_ANATOP : - IMX6Q_GPR1_ENET_CLK_SEL_PAD; + clksel = clk_is_match(ptp_clk, enet_ref) ? + IMX6Q_GPR1_ENET_CLK_SEL_ANATOP : + IMX6Q_GPR1_ENET_CLK_SEL_PAD; gpr = syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr"); if (!IS_ERR(gpr)) regmap_update_bits(gpr, IOMUXC_GPR1, diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 92afb723dcfc..355b08936871 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1692,16 +1692,15 @@ static int _deassert_hardreset(struct omap_hwmod *oh, const char *name) if (ret == -EBUSY) pr_warn("omap_hwmod: %s: failed to hardreset\n", oh->name); - if (!ret) { + if (oh->clkdm) { /* * Set the clockdomain to HW_AUTO, assuming that the * previous state was HW_AUTO. */ - if (oh->clkdm && hwsup) + if (hwsup) clkdm_allow_idle(oh->clkdm); - } else { - if (oh->clkdm) - clkdm_hwmod_disable(oh->clkdm, oh); + + clkdm_hwmod_disable(oh->clkdm, oh); } return ret; @@ -2698,6 +2697,7 @@ static int __init _register(struct omap_hwmod *oh) INIT_LIST_HEAD(&oh->master_ports); INIT_LIST_HEAD(&oh->slave_ports); spin_lock_init(&oh->_lock); + lockdep_set_class(&oh->_lock, &oh->hwmod_key); oh->_state = _HWMOD_STATE_REGISTERED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 9d4bec6ee742..9611c91d9b82 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -674,6 +674,7 @@ struct omap_hwmod { u32 _sysc_cache; void __iomem *_mpu_rt_va; spinlock_t _lock; + struct lock_class_key hwmod_key; /* unique lock class */ struct list_head node; struct omap_hwmod_ocp_if *_mpu_port; unsigned int (*xlate_irq)(unsigned int); diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index e8692e7675b8..16fe7a1b7a35 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -1466,55 +1466,18 @@ static struct omap_hwmod dra7xx_ocp2scp3_hwmod = { * */ -static struct omap_hwmod_class dra7xx_pcie_hwmod_class = { +static struct omap_hwmod_class dra7xx_pciess_hwmod_class = { .name = "pcie", }; /* pcie1 */ -static struct omap_hwmod dra7xx_pcie1_hwmod = { +static struct omap_hwmod dra7xx_pciess1_hwmod = { .name = "pcie1", - .class = &dra7xx_pcie_hwmod_class, + .class = &dra7xx_pciess_hwmod_class, .clkdm_name = "pcie_clkdm", .main_clk = "l4_root_clk_div", .prcm = { .omap4 = { - .clkctrl_offs = DRA7XX_CM_PCIE_CLKSTCTRL_OFFSET, - .modulemode = MODULEMODE_SWCTRL, - }, - }, -}; - -/* pcie2 */ -static struct omap_hwmod dra7xx_pcie2_hwmod = { - .name = "pcie2", - .class = &dra7xx_pcie_hwmod_class, - .clkdm_name = "pcie_clkdm", - .main_clk = "l4_root_clk_div", - .prcm = { - .omap4 = { - .clkctrl_offs = DRA7XX_CM_PCIE_CLKSTCTRL_OFFSET, - .modulemode = MODULEMODE_SWCTRL, - }, - }, -}; - -/* - * 'PCIE PHY' class - * - */ - -static struct omap_hwmod_class dra7xx_pcie_phy_hwmod_class = { - .name = "pcie-phy", -}; - -/* pcie1 phy */ -static struct omap_hwmod dra7xx_pcie1_phy_hwmod = { - .name = "pcie1-phy", - .class = &dra7xx_pcie_phy_hwmod_class, - .clkdm_name = "l3init_clkdm", - .main_clk = "l4_root_clk_div", - .prcm = { - .omap4 = { .clkctrl_offs = DRA7XX_CM_L3INIT_PCIESS1_CLKCTRL_OFFSET, .context_offs = DRA7XX_RM_L3INIT_PCIESS1_CONTEXT_OFFSET, .modulemode = MODULEMODE_SWCTRL, @@ -1522,11 +1485,11 @@ static struct omap_hwmod dra7xx_pcie1_phy_hwmod = { }, }; -/* pcie2 phy */ -static struct omap_hwmod dra7xx_pcie2_phy_hwmod = { - .name = "pcie2-phy", - .class = &dra7xx_pcie_phy_hwmod_class, - .clkdm_name = "l3init_clkdm", +/* pcie2 */ +static struct omap_hwmod dra7xx_pciess2_hwmod = { + .name = "pcie2", + .class = &dra7xx_pciess_hwmod_class, + .clkdm_name = "pcie_clkdm", .main_clk = "l4_root_clk_div", .prcm = { .omap4 = { @@ -2877,50 +2840,34 @@ static struct omap_hwmod_ocp_if dra7xx_l4_cfg__ocp2scp3 = { .user = OCP_USER_MPU | OCP_USER_SDMA, }; -/* l3_main_1 -> pcie1 */ -static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pcie1 = { +/* l3_main_1 -> pciess1 */ +static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pciess1 = { .master = &dra7xx_l3_main_1_hwmod, - .slave = &dra7xx_pcie1_hwmod, + .slave = &dra7xx_pciess1_hwmod, .clk = "l3_iclk_div", .user = OCP_USER_MPU | OCP_USER_SDMA, }; -/* l4_cfg -> pcie1 */ -static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie1 = { +/* l4_cfg -> pciess1 */ +static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pciess1 = { .master = &dra7xx_l4_cfg_hwmod, - .slave = &dra7xx_pcie1_hwmod, + .slave = &dra7xx_pciess1_hwmod, .clk = "l4_root_clk_div", .user = OCP_USER_MPU | OCP_USER_SDMA, }; -/* l3_main_1 -> pcie2 */ -static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pcie2 = { +/* l3_main_1 -> pciess2 */ +static struct omap_hwmod_ocp_if dra7xx_l3_main_1__pciess2 = { .master = &dra7xx_l3_main_1_hwmod, - .slave = &dra7xx_pcie2_hwmod, + .slave = &dra7xx_pciess2_hwmod, .clk = "l3_iclk_div", .user = OCP_USER_MPU | OCP_USER_SDMA, }; -/* l4_cfg -> pcie2 */ -static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie2 = { - .master = &dra7xx_l4_cfg_hwmod, - .slave = &dra7xx_pcie2_hwmod, - .clk = "l4_root_clk_div", - .user = OCP_USER_MPU | OCP_USER_SDMA, -}; - -/* l4_cfg -> pcie1 phy */ -static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie1_phy = { - .master = &dra7xx_l4_cfg_hwmod, - .slave = &dra7xx_pcie1_phy_hwmod, - .clk = "l4_root_clk_div", - .user = OCP_USER_MPU | OCP_USER_SDMA, -}; - -/* l4_cfg -> pcie2 phy */ -static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pcie2_phy = { +/* l4_cfg -> pciess2 */ +static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pciess2 = { .master = &dra7xx_l4_cfg_hwmod, - .slave = &dra7xx_pcie2_phy_hwmod, + .slave = &dra7xx_pciess2_hwmod, .clk = "l4_root_clk_div", .user = OCP_USER_MPU | OCP_USER_SDMA, }; @@ -3327,12 +3274,10 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { &dra7xx_l4_cfg__mpu, &dra7xx_l4_cfg__ocp2scp1, &dra7xx_l4_cfg__ocp2scp3, - &dra7xx_l3_main_1__pcie1, - &dra7xx_l4_cfg__pcie1, - &dra7xx_l3_main_1__pcie2, - &dra7xx_l4_cfg__pcie2, - &dra7xx_l4_cfg__pcie1_phy, - &dra7xx_l4_cfg__pcie2_phy, + &dra7xx_l3_main_1__pciess1, + &dra7xx_l4_cfg__pciess1, + &dra7xx_l3_main_1__pciess2, + &dra7xx_l4_cfg__pciess2, &dra7xx_l3_main_1__qspi, &dra7xx_l4_per3__rtcss, &dra7xx_l4_cfg__sata, diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index 190fa43e7479..e642b079e9f3 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -173,6 +173,7 @@ static void __init omap3_igep0030_rev_g_legacy_init(void) static void __init omap3_evm_legacy_init(void) { + hsmmc2_internal_input_clk(); legacy_init_wl12xx(WL12XX_REFCLOCK_38, 0, 149); } diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c index a08a617a6c11..d6d6bc39e05c 100644 --- a/arch/arm/mach-omap2/prm44xx.c +++ b/arch/arm/mach-omap2/prm44xx.c @@ -252,10 +252,10 @@ static void omap44xx_prm_save_and_clear_irqen(u32 *saved_mask) { saved_mask[0] = omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST, - OMAP4_PRM_IRQSTATUS_MPU_OFFSET); + OMAP4_PRM_IRQENABLE_MPU_OFFSET); saved_mask[1] = omap4_prm_read_inst_reg(OMAP4430_PRM_OCP_SOCKET_INST, - OMAP4_PRM_IRQSTATUS_MPU_2_OFFSET); + OMAP4_PRM_IRQENABLE_MPU_2_OFFSET); omap4_prm_write_inst_reg(0, OMAP4430_PRM_OCP_SOCKET_INST, OMAP4_PRM_IRQENABLE_MPU_OFFSET); diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h index 483cb467bf65..a0f3b1cd497c 100644 --- a/arch/arm/mach-socfpga/core.h +++ b/arch/arm/mach-socfpga/core.h @@ -45,6 +45,6 @@ extern char secondary_trampoline, secondary_trampoline_end; extern unsigned long socfpga_cpu1start_addr; -#define SOCFPGA_SCU_VIRT_BASE 0xfffec000 +#define SOCFPGA_SCU_VIRT_BASE 0xfee00000 #endif diff --git a/arch/arm/mach-socfpga/socfpga.c b/arch/arm/mach-socfpga/socfpga.c index 383d61e138af..f5e597c207b9 100644 --- a/arch/arm/mach-socfpga/socfpga.c +++ b/arch/arm/mach-socfpga/socfpga.c @@ -23,6 +23,7 @@ #include <asm/hardware/cache-l2x0.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> +#include <asm/cacheflush.h> #include "core.h" @@ -73,6 +74,10 @@ void __init socfpga_sysmgr_init(void) (u32 *) &socfpga_cpu1start_addr)) pr_err("SMP: Need cpu1-start-addr in device tree.\n"); + /* Ensure that socfpga_cpu1start_addr is visible to other CPUs */ + smp_wmb(); + sync_cache_w(&socfpga_cpu1start_addr); + sys_manager_base_addr = of_iomap(np, 0); np = of_find_compatible_node(NULL, NULL, "altr,rst-mgr"); diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c index b067390cef4e..b373acade338 100644 --- a/arch/arm/mach-sti/board-dt.c +++ b/arch/arm/mach-sti/board-dt.c @@ -18,6 +18,7 @@ static const char *stih41x_dt_match[] __initdata = { "st,stih415", "st,stih416", "st,stih407", + "st,stih410", "st,stih418", NULL }; diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index c6c7696b8db9..8f15f70622a6 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -1131,23 +1131,22 @@ static void __init l2c310_of_parse(const struct device_node *np, } ret = l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_512K); - if (ret) - return; - - switch (assoc) { - case 16: - *aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK; - *aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16; - *aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK; - break; - case 8: - *aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK; - *aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK; - break; - default: - pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n", - assoc); - break; + if (!ret) { + switch (assoc) { + case 16: + *aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK; + *aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16; + *aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK; + break; + case 8: + *aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK; + *aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK; + break; + default: + pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n", + assoc); + break; + } } prefetch = l2x0_saved_regs.prefetch_ctrl; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 170a116d1b29..c27447653903 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -171,7 +171,7 @@ static int __dma_supported(struct device *dev, u64 mask, bool warn) */ if (sizeof(mask) != sizeof(dma_addr_t) && mask > (dma_addr_t)~0 && - dma_to_pfn(dev, ~0) < max_pfn) { + dma_to_pfn(dev, ~0) < max_pfn - 1) { if (warn) { dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n", mask); diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a982dc3190df..6333d9c17875 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -552,6 +552,7 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs) pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n", inf->name, fsr, addr); + show_pte(current->mm, addr); info.si_signo = inf->sig; info.si_errno = 0; diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c index 004e35cdcfff..cf30daff8932 100644 --- a/arch/arm/mm/pageattr.c +++ b/arch/arm/mm/pageattr.c @@ -49,7 +49,10 @@ static int change_memory_common(unsigned long addr, int numpages, WARN_ON_ONCE(1); } - if (!is_module_address(start) || !is_module_address(end - 1)) + if (start < MODULES_VADDR || start >= MODULES_END) + return -EINVAL; + + if (end < MODULES_VADDR || start >= MODULES_END) return -EINVAL; data.set_mask = set_mask; diff --git a/arch/arm64/boot/dts/apm/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts index 2e25de0800b9..83578e766b94 100644 --- a/arch/arm64/boot/dts/apm/apm-mustang.dts +++ b/arch/arm64/boot/dts/apm/apm-mustang.dts @@ -45,6 +45,10 @@ status = "ok"; }; +&sgenet1 { + status = "ok"; +}; + &xgenet { status = "ok"; }; diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi index a857794432d6..e74f6e0a208c 100644 --- a/arch/arm64/boot/dts/apm/apm-storm.dtsi +++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi @@ -186,6 +186,16 @@ clock-output-names = "sge0clk"; }; + sge1clk: sge1clk@1f21c000 { + compatible = "apm,xgene-device-clock"; + #clock-cells = <1>; + clocks = <&socplldiv2 0>; + reg = <0x0 0x1f21c000 0x0 0x1000>; + reg-names = "csr-reg"; + csr-mask = <0xc>; + clock-output-names = "sge1clk"; + }; + xge0clk: xge0clk@1f61c000 { compatible = "apm,xgene-device-clock"; #clock-cells = <1>; @@ -628,13 +638,30 @@ <0x0 0x1f200000 0x0 0Xc300>, <0x0 0x1B000000 0x0 0X200>; reg-names = "enet_csr", "ring_csr", "ring_cmd"; - interrupts = <0x0 0xA0 0x4>; + interrupts = <0x0 0xA0 0x4>, + <0x0 0xA1 0x4>; dma-coherent; clocks = <&sge0clk 0>; local-mac-address = [00 00 00 00 00 00]; phy-connection-type = "sgmii"; }; + sgenet1: ethernet@1f210030 { + compatible = "apm,xgene1-sgenet"; + status = "disabled"; + reg = <0x0 0x1f210030 0x0 0xd100>, + <0x0 0x1f200000 0x0 0Xc300>, + <0x0 0x1B000000 0x0 0X8000>; + reg-names = "enet_csr", "ring_csr", "ring_cmd"; + interrupts = <0x0 0xAC 0x4>, + <0x0 0xAD 0x4>; + port-id = <1>; + dma-coherent; + clocks = <&sge1clk 0>; + local-mac-address = [00 00 00 00 00 00]; + phy-connection-type = "sgmii"; + }; + xgenet: ethernet@1f610000 { compatible = "apm,xgene1-xgenet"; status = "disabled"; @@ -642,7 +669,8 @@ <0x0 0x1f600000 0x0 0Xc300>, <0x0 0x18000000 0x0 0X200>; reg-names = "enet_csr", "ring_csr", "ring_cmd"; - interrupts = <0x0 0x60 0x4>; + interrupts = <0x0 0x60 0x4>, + <0x0 0x61 0x4>; dma-coherent; clocks = <&xge0clk 0>; /* mac address will be overwritten by the bootloader */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 94674eb7e7bb..54bb4ba97441 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -129,6 +129,9 @@ * 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are * not known to exist and will break with this configuration. * + * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time + * (see hyp-init.S). + * * Note that when using 4K pages, we concatenate two first level page tables * together. * @@ -138,7 +141,6 @@ #ifdef CONFIG_ARM64_64K_PAGES /* * Stage2 translation configuration: - * 40bits output (PS = 2) * 40bits input (T0SZ = 24) * 64kB pages (TG0 = 1) * 2 level page tables (SL = 1) @@ -150,7 +152,6 @@ #else /* * Stage2 translation configuration: - * 40bits output (PS = 2) * 40bits input (T0SZ = 24) * 4kB pages (TG0 = 0) * 3 level page tables (SL = 1) diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 6458b5373142..bbfb600fa822 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -158,6 +158,8 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) #define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT) #define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) +#define kvm_pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1)) + /* * If we are concatenating first level stage-2 page tables, we would have less * than or equal to 16 pointers in the fake PGD, because that's what the @@ -171,43 +173,6 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) #define KVM_PREALLOC_LEVEL (0) #endif -/** - * kvm_prealloc_hwpgd - allocate inital table for VTTBR - * @kvm: The KVM struct pointer for the VM. - * @pgd: The kernel pseudo pgd - * - * When the kernel uses more levels of page tables than the guest, we allocate - * a fake PGD and pre-populate it to point to the next-level page table, which - * will be the real initial page table pointed to by the VTTBR. - * - * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and - * the kernel will use folded pud. When KVM_PREALLOC_LEVEL==1, we - * allocate 2 consecutive PUD pages. - */ -static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) -{ - unsigned int i; - unsigned long hwpgd; - - if (KVM_PREALLOC_LEVEL == 0) - return 0; - - hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT); - if (!hwpgd) - return -ENOMEM; - - for (i = 0; i < PTRS_PER_S2_PGD; i++) { - if (KVM_PREALLOC_LEVEL == 1) - pgd_populate(NULL, pgd + i, - (pud_t *)hwpgd + i * PTRS_PER_PUD); - else if (KVM_PREALLOC_LEVEL == 2) - pud_populate(NULL, pud_offset(pgd, 0) + i, - (pmd_t *)hwpgd + i * PTRS_PER_PMD); - } - - return 0; -} - static inline void *kvm_get_hwpgd(struct kvm *kvm) { pgd_t *pgd = kvm->arch.pgd; @@ -224,12 +189,11 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm) return pmd_offset(pud, 0); } -static inline void kvm_free_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - if (KVM_PREALLOC_LEVEL > 0) { - unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm); - free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT); - } + if (KVM_PREALLOC_LEVEL > 0) + return PTRS_PER_S2_PGD * PAGE_SIZE; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } static inline bool kvm_page_empty(void *ptr) diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h index 9a8fd84f8fb2..941c375616e2 100644 --- a/arch/arm64/include/asm/proc-fns.h +++ b/arch/arm64/include/asm/proc-fns.h @@ -39,7 +39,11 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr); #include <asm/memory.h> -#define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm) +#define cpu_switch_mm(pgd,mm) \ +do { \ + BUG_ON(pgd == swapper_pg_dir); \ + cpu_do_switch_mm(virt_to_phys(pgd),mm); \ +} while (0) #define cpu_get_pgd() \ ({ \ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index c028fe37456f..53d9c354219f 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -48,6 +48,7 @@ static inline void tlb_flush(struct mmu_gather *tlb) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { + __flush_tlb_pgtable(tlb->mm, addr); pgtable_page_dtor(pte); tlb_remove_entry(tlb, pte); } @@ -56,6 +57,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { + __flush_tlb_pgtable(tlb->mm, addr); tlb_remove_entry(tlb, virt_to_page(pmdp)); } #endif @@ -64,6 +66,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { + __flush_tlb_pgtable(tlb->mm, addr); tlb_remove_entry(tlb, virt_to_page(pudp)); } #endif diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 4abe9b945f77..c3bb05b98616 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -144,6 +144,19 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end } /* + * Used to invalidate the TLB (walk caches) corresponding to intermediate page + * table levels (pgd/pud/pmd). + */ +static inline void __flush_tlb_pgtable(struct mm_struct *mm, + unsigned long uaddr) +{ + unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48); + + dsb(ishst); + asm("tlbi vae1is, %0" : : "r" (addr)); + dsb(ish); +} +/* * On AArch64, the cache coherency is handled via the set_pte_at() function. */ static inline void update_mmu_cache(struct vm_area_struct *vma, diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index b42c7b480e1e..ab21e0d58278 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -337,7 +337,11 @@ core_initcall(arm64_dmi_init); static void efi_set_pgd(struct mm_struct *mm) { - cpu_switch_mm(mm->pgd, mm); + if (mm == &init_mm) + cpu_set_reserved_ttbr0(); + else + cpu_switch_mm(mm->pgd, mm); + flush_tlb_all(); if (icache_is_aivivt()) __flush_icache_all(); @@ -354,3 +358,12 @@ void efi_virtmap_unload(void) efi_set_pgd(current->active_mm); preempt_enable(); } + +/* + * UpdateCapsule() depends on the system being shutdown via + * ResetSystem(). + */ +bool efi_poweroff_required(void) +{ + return efi_enabled(EFI_RUNTIME_SERVICES); +} diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 8ce88e08c030..07f930540f4a 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -585,8 +585,8 @@ ENDPROC(set_cpu_boot_mode_flag) * zeroing of .bss would clobber it. */ .pushsection .data..cacheline_aligned -ENTRY(__boot_cpu_mode) .align L1_CACHE_SHIFT +ENTRY(__boot_cpu_mode) .long BOOT_CPU_MODE_EL2 .long 0 .popsection diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index fde9923af859..c6b1f3b96f45 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -21,6 +21,7 @@ #include <stdarg.h> #include <linux/compat.h> +#include <linux/efi.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/kernel.h> @@ -150,6 +151,13 @@ void machine_restart(char *cmd) local_irq_disable(); smp_send_stop(); + /* + * UpdateCapsule() depends on the system being reset via + * ResetSystem(). + */ + if (efi_enabled(EFI_RUNTIME_SERVICES)) + efi_reboot(reboot_mode, NULL); + /* Now call the architecture specific reboot code. */ if (arm_pm_restart) arm_pm_restart(reboot_mode, cmd); diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 58e0c2bdde04..ef7d112f5ce0 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -51,7 +51,7 @@ static int __init early_coherent_pool(char *p) } early_param("coherent_pool", early_coherent_pool); -static void *__alloc_from_pool(size_t size, struct page **ret_page) +static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) { unsigned long val; void *ptr = NULL; @@ -67,6 +67,8 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page) *ret_page = phys_to_page(phys); ptr = (void *)val; + if (flags & __GFP_ZERO) + memset(ptr, 0, size); } return ptr; @@ -101,6 +103,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, flags |= GFP_DMA; if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) { struct page *page; + void *addr; size = PAGE_ALIGN(size); page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, @@ -109,7 +112,10 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, return NULL; *dma_handle = phys_to_dma(dev, page_to_phys(page)); - return page_address(page); + addr = page_address(page); + if (flags & __GFP_ZERO) + memset(addr, 0, size); + return addr; } else { return swiotlb_alloc_coherent(dev, size, dma_handle, flags); } @@ -146,7 +152,7 @@ static void *__dma_alloc(struct device *dev, size_t size, if (!coherent && !(flags & __GFP_WAIT)) { struct page *page = NULL; - void *addr = __alloc_from_pool(size, &page); + void *addr = __alloc_from_pool(size, &page, flags); if (addr) *dma_handle = phys_to_dma(dev, page_to_phys(page)); diff --git a/arch/c6x/include/asm/pgtable.h b/arch/c6x/include/asm/pgtable.h index 78d4483ba40c..ec4db6df5e0d 100644 --- a/arch/c6x/include/asm/pgtable.h +++ b/arch/c6x/include/asm/pgtable.h @@ -67,6 +67,11 @@ extern unsigned long empty_zero_page; */ #define pgtable_cache_init() do { } while (0) +/* + * c6x is !MMU, so define the simpliest implementation + */ +#define pgprot_writecombine pgprot_noncached + #include <asm-generic/pgtable.h> #endif /* _ASM_C6X_PGTABLE_H */ diff --git a/arch/microblaze/kernel/entry.S b/arch/microblaze/kernel/entry.S index 0536bc021cc6..ef548510b951 100644 --- a/arch/microblaze/kernel/entry.S +++ b/arch/microblaze/kernel/entry.S @@ -348,8 +348,9 @@ C_ENTRY(_user_exception): * The LP register should point to the location where the called function * should return. [note that MAKE_SYS_CALL uses label 1] */ /* See if the system call number is valid */ + blti r12, 5f addi r11, r12, -__NR_syscalls; - bgei r11,5f; + bgei r11, 5f; /* Figure out which function to use for this system call. */ /* Note Microblaze barrel shift is optional, so don't rely on it */ add r12, r12, r12; /* convert num -> ptr */ @@ -375,7 +376,7 @@ C_ENTRY(_user_exception): /* The syscall number is invalid, return an error. */ 5: - rtsd r15, 8; /* looks like a normal subroutine return */ + braid ret_from_trap addi r3, r0, -ENOSYS; /* Entry point used to return from a syscall/trap */ @@ -411,7 +412,7 @@ C_ENTRY(ret_from_trap): bri 1b /* Maybe handle a signal */ -5: +5: andi r11, r19, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME; beqi r11, 4f; /* Signals to handle, handle them */ diff --git a/arch/nios2/include/asm/ptrace.h b/arch/nios2/include/asm/ptrace.h index 20fb1cf2dab6..642462144872 100644 --- a/arch/nios2/include/asm/ptrace.h +++ b/arch/nios2/include/asm/ptrace.h @@ -15,7 +15,54 @@ #include <uapi/asm/ptrace.h> +/* This struct defines the way the registers are stored on the + stack during a system call. */ + #ifndef __ASSEMBLY__ +struct pt_regs { + unsigned long r8; /* r8-r15 Caller-saved GP registers */ + unsigned long r9; + unsigned long r10; + unsigned long r11; + unsigned long r12; + unsigned long r13; + unsigned long r14; + unsigned long r15; + unsigned long r1; /* Assembler temporary */ + unsigned long r2; /* Retval LS 32bits */ + unsigned long r3; /* Retval MS 32bits */ + unsigned long r4; /* r4-r7 Register arguments */ + unsigned long r5; + unsigned long r6; + unsigned long r7; + unsigned long orig_r2; /* Copy of r2 ?? */ + unsigned long ra; /* Return address */ + unsigned long fp; /* Frame pointer */ + unsigned long sp; /* Stack pointer */ + unsigned long gp; /* Global pointer */ + unsigned long estatus; + unsigned long ea; /* Exception return address (pc) */ + unsigned long orig_r7; +}; + +/* + * This is the extended stack used by signal handlers and the context + * switcher: it's pushed after the normal "struct pt_regs". + */ +struct switch_stack { + unsigned long r16; /* r16-r23 Callee-saved GP registers */ + unsigned long r17; + unsigned long r18; + unsigned long r19; + unsigned long r20; + unsigned long r21; + unsigned long r22; + unsigned long r23; + unsigned long fp; + unsigned long gp; + unsigned long ra; +}; + #define user_mode(regs) (((regs)->estatus & ESTATUS_EU)) #define instruction_pointer(regs) ((regs)->ra) diff --git a/arch/nios2/include/asm/ucontext.h b/arch/nios2/include/asm/ucontext.h deleted file mode 100644 index 2c87614b0f6e..000000000000 --- a/arch/nios2/include/asm/ucontext.h +++ /dev/null @@ -1,32 +0,0 @@ -/* - * Copyright (C) 2010 Tobias Klauser <tklauser@distanz.ch> - * Copyright (C) 2004 Microtronix Datacom Ltd - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#ifndef _ASM_NIOS2_UCONTEXT_H -#define _ASM_NIOS2_UCONTEXT_H - -typedef int greg_t; -#define NGREG 32 -typedef greg_t gregset_t[NGREG]; - -struct mcontext { - int version; - gregset_t gregs; -}; - -#define MCONTEXT_VERSION 2 - -struct ucontext { - unsigned long uc_flags; - struct ucontext *uc_link; - stack_t uc_stack; - struct mcontext uc_mcontext; - sigset_t uc_sigmask; /* mask last for extensibility */ -}; - -#endif diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild index 4f07ca3f8d10..e0bb972a50d7 100644 --- a/arch/nios2/include/uapi/asm/Kbuild +++ b/arch/nios2/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ include include/uapi/asm-generic/Kbuild.asm header-y += elf.h -header-y += ucontext.h + +generic-y += ucontext.h diff --git a/arch/nios2/include/uapi/asm/elf.h b/arch/nios2/include/uapi/asm/elf.h index a5b91ae5cf56..6f06d3b2949e 100644 --- a/arch/nios2/include/uapi/asm/elf.h +++ b/arch/nios2/include/uapi/asm/elf.h @@ -50,9 +50,7 @@ typedef unsigned long elf_greg_t; -#define ELF_NGREG \ - ((sizeof(struct pt_regs) + sizeof(struct switch_stack)) / \ - sizeof(elf_greg_t)) +#define ELF_NGREG 49 typedef elf_greg_t elf_gregset_t[ELF_NGREG]; typedef unsigned long elf_fpregset_t; diff --git a/arch/nios2/include/uapi/asm/ptrace.h b/arch/nios2/include/uapi/asm/ptrace.h index e83a7c9d1c36..71a330597adf 100644 --- a/arch/nios2/include/uapi/asm/ptrace.h +++ b/arch/nios2/include/uapi/asm/ptrace.h @@ -67,53 +67,9 @@ #define NUM_PTRACE_REG (PTR_TLBMISC + 1) -/* this struct defines the way the registers are stored on the - stack during a system call. - - There is a fake_regs in setup.c that has to match pt_regs.*/ - -struct pt_regs { - unsigned long r8; /* r8-r15 Caller-saved GP registers */ - unsigned long r9; - unsigned long r10; - unsigned long r11; - unsigned long r12; - unsigned long r13; - unsigned long r14; - unsigned long r15; - unsigned long r1; /* Assembler temporary */ - unsigned long r2; /* Retval LS 32bits */ - unsigned long r3; /* Retval MS 32bits */ - unsigned long r4; /* r4-r7 Register arguments */ - unsigned long r5; - unsigned long r6; - unsigned long r7; - unsigned long orig_r2; /* Copy of r2 ?? */ - unsigned long ra; /* Return address */ - unsigned long fp; /* Frame pointer */ - unsigned long sp; /* Stack pointer */ - unsigned long gp; /* Global pointer */ - unsigned long estatus; - unsigned long ea; /* Exception return address (pc) */ - unsigned long orig_r7; -}; - -/* - * This is the extended stack used by signal handlers and the context - * switcher: it's pushed after the normal "struct pt_regs". - */ -struct switch_stack { - unsigned long r16; /* r16-r23 Callee-saved GP registers */ - unsigned long r17; - unsigned long r18; - unsigned long r19; - unsigned long r20; - unsigned long r21; - unsigned long r22; - unsigned long r23; - unsigned long fp; - unsigned long gp; - unsigned long ra; +/* User structures for general purpose registers. */ +struct user_pt_regs { + __u32 regs[49]; }; #endif /* __ASSEMBLY__ */ diff --git a/arch/nios2/include/uapi/asm/sigcontext.h b/arch/nios2/include/uapi/asm/sigcontext.h index 7b8bb41867d4..b67944a50927 100644 --- a/arch/nios2/include/uapi/asm/sigcontext.h +++ b/arch/nios2/include/uapi/asm/sigcontext.h @@ -15,14 +15,16 @@ * details. */ -#ifndef _ASM_NIOS2_SIGCONTEXT_H -#define _ASM_NIOS2_SIGCONTEXT_H +#ifndef _UAPI__ASM_SIGCONTEXT_H +#define _UAPI__ASM_SIGCONTEXT_H -#include <asm/ptrace.h> +#include <linux/types.h> + +#define MCONTEXT_VERSION 2 struct sigcontext { - struct pt_regs regs; - unsigned long sc_mask; /* old sigmask */ + int version; + unsigned long gregs[32]; }; #endif diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c index 2d0ea25be171..dda41e4fe707 100644 --- a/arch/nios2/kernel/signal.c +++ b/arch/nios2/kernel/signal.c @@ -39,7 +39,7 @@ static inline int rt_restore_ucontext(struct pt_regs *regs, struct ucontext *uc, int *pr2) { int temp; - greg_t *gregs = uc->uc_mcontext.gregs; + unsigned long *gregs = uc->uc_mcontext.gregs; int err; /* Always make any pending restarted system calls return -EINTR */ @@ -127,7 +127,7 @@ badframe: static inline int rt_setup_ucontext(struct ucontext *uc, struct pt_regs *regs) { struct switch_stack *sw = (struct switch_stack *)regs - 1; - greg_t *gregs = uc->uc_mcontext.gregs; + unsigned long *gregs = uc->uc_mcontext.gregs; int err = 0; err |= __put_user(MCONTEXT_VERSION, &uc->uc_mcontext.version); diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 0d231adfe576..0c9b6afe69e9 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -126,7 +126,6 @@ good_area: break; } -survive: /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo @@ -220,11 +219,6 @@ no_context: */ out_of_memory: up_read(&mm->mmap_sem); - if (is_global_init(tsk)) { - yield(); - down_read(&mm->mmap_sem); - goto survive; - } if (!user_mode(regs)) goto no_context; pagefault_out_of_memory(); diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index 343ea7c987aa..ff95d15a2384 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -57,7 +57,6 @@ enum interruption_class { IRQIO_TAP, IRQIO_VMR, IRQIO_LCS, - IRQIO_CLW, IRQIO_CTC, IRQIO_APB, IRQIO_ADM, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f6579cfde2df..19e17bd7aec0 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -165,7 +165,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: case KVM_CAP_S390_CSS_SUPPORT: - case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_ENABLE_CAP_VM: diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 96ac69c5eba0..efb00ec75805 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -86,6 +86,9 @@ config ARCH_DEFCONFIG default "arch/sparc/configs/sparc32_defconfig" if SPARC32 default "arch/sparc/configs/sparc64_defconfig" if SPARC64 +config ARCH_PROC_KCORE_TEXT + def_bool y + config IOMMU_HELPER bool default y if SPARC64 diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 4f6725ff4c33..f5b6537306f0 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2957,6 +2957,17 @@ unsigned long sun4v_t5_set_perfreg(unsigned long reg_num, unsigned long reg_val); #endif + +#define HV_FAST_M7_GET_PERFREG 0x43 +#define HV_FAST_M7_SET_PERFREG 0x44 + +#ifndef __ASSEMBLY__ +unsigned long sun4v_m7_get_perfreg(unsigned long reg_num, + unsigned long *reg_val); +unsigned long sun4v_m7_set_perfreg(unsigned long reg_num, + unsigned long reg_val); +#endif + /* Function numbers for HV_CORE_TRAP. */ #define HV_CORE_SET_VER 0x00 #define HV_CORE_PUTCHAR 0x01 @@ -2981,6 +2992,7 @@ unsigned long sun4v_t5_set_perfreg(unsigned long reg_num, #define HV_GRP_SDIO 0x0108 #define HV_GRP_SDIO_ERR 0x0109 #define HV_GRP_REBOOT_DATA 0x0110 +#define HV_GRP_M7_PERF 0x0114 #define HV_GRP_NIAG_PERF 0x0200 #define HV_GRP_FIRE_PERF 0x0201 #define HV_GRP_N2_CPU 0x0202 diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h index 9b672be70dda..50d4840d9aeb 100644 --- a/arch/sparc/include/asm/io_64.h +++ b/arch/sparc/include/asm/io_64.h @@ -407,16 +407,16 @@ static inline void iounmap(volatile void __iomem *addr) { } -#define ioread8(X) readb(X) -#define ioread16(X) readw(X) -#define ioread16be(X) __raw_readw(X) -#define ioread32(X) readl(X) -#define ioread32be(X) __raw_readl(X) -#define iowrite8(val,X) writeb(val,X) -#define iowrite16(val,X) writew(val,X) -#define iowrite16be(val,X) __raw_writew(val,X) -#define iowrite32(val,X) writel(val,X) -#define iowrite32be(val,X) __raw_writel(val,X) +#define ioread8 readb +#define ioread16 readw +#define ioread16be __raw_readw +#define ioread32 readl +#define ioread32be __raw_readl +#define iowrite8 writeb +#define iowrite16 writew +#define iowrite16be __raw_writew +#define iowrite32 writel +#define iowrite32be __raw_writel /* Create a virtual mapping cookie for an IO port range */ void __iomem *ioport_map(unsigned long port, unsigned int nr); diff --git a/arch/sparc/include/asm/starfire.h b/arch/sparc/include/asm/starfire.h index c100dc27a0a9..176fa0ad19f1 100644 --- a/arch/sparc/include/asm/starfire.h +++ b/arch/sparc/include/asm/starfire.h @@ -12,7 +12,6 @@ extern int this_is_starfire; void check_if_starfire(void); -int starfire_hard_smp_processor_id(void); void starfire_hookup(int); unsigned int starfire_translate(unsigned long imap, unsigned int upaid); diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index 88d322b67fac..07cc49e541f4 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -98,11 +98,7 @@ void sun4v_do_mna(struct pt_regs *regs, void do_privop(struct pt_regs *regs); void do_privact(struct pt_regs *regs); void do_cee(struct pt_regs *regs); -void do_cee_tl1(struct pt_regs *regs); -void do_dae_tl1(struct pt_regs *regs); -void do_iae_tl1(struct pt_regs *regs); void do_div0_tl1(struct pt_regs *regs); -void do_fpdis_tl1(struct pt_regs *regs); void do_fpieee_tl1(struct pt_regs *regs); void do_fpother_tl1(struct pt_regs *regs); void do_ill_tl1(struct pt_regs *regs); diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index 5c55145bfbf0..662500fa555f 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -48,6 +48,7 @@ static struct api_info api_table[] = { { .group = HV_GRP_VT_CPU, }, { .group = HV_GRP_T5_CPU, }, { .group = HV_GRP_DIAG, .flags = FLAG_PRE_API }, + { .group = HV_GRP_M7_PERF, }, }; static DEFINE_SPINLOCK(hvapi_lock); diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index caedf8320416..afbaba52d2f1 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -837,3 +837,19 @@ ENTRY(sun4v_t5_set_perfreg) retl nop ENDPROC(sun4v_t5_set_perfreg) + +ENTRY(sun4v_m7_get_perfreg) + mov %o1, %o4 + mov HV_FAST_M7_GET_PERFREG, %o5 + ta HV_FAST_TRAP + stx %o1, [%o4] + retl + nop +ENDPROC(sun4v_m7_get_perfreg) + +ENTRY(sun4v_m7_set_perfreg) + mov HV_FAST_M7_SET_PERFREG, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(sun4v_m7_set_perfreg) diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 7e967c8018c8..eb978c77c76a 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -217,6 +217,31 @@ static const struct pcr_ops n5_pcr_ops = { .pcr_nmi_disable = PCR_N4_PICNPT, }; +static u64 m7_pcr_read(unsigned long reg_num) +{ + unsigned long val; + + (void) sun4v_m7_get_perfreg(reg_num, &val); + + return val; +} + +static void m7_pcr_write(unsigned long reg_num, u64 val) +{ + (void) sun4v_m7_set_perfreg(reg_num, val); +} + +static const struct pcr_ops m7_pcr_ops = { + .read_pcr = m7_pcr_read, + .write_pcr = m7_pcr_write, + .read_pic = n4_pic_read, + .write_pic = n4_pic_write, + .nmi_picl_value = n4_picl_value, + .pcr_nmi_enable = (PCR_N4_PICNPT | PCR_N4_STRACE | + PCR_N4_UTRACE | PCR_N4_TOE | + (26 << PCR_N4_SL_SHIFT)), + .pcr_nmi_disable = PCR_N4_PICNPT, +}; static unsigned long perf_hsvc_group; static unsigned long perf_hsvc_major; @@ -248,6 +273,10 @@ static int __init register_perf_hsvc(void) perf_hsvc_group = HV_GRP_T5_CPU; break; + case SUN4V_CHIP_SPARC_M7: + perf_hsvc_group = HV_GRP_M7_PERF; + break; + default: return -ENODEV; } @@ -293,6 +322,10 @@ static int __init setup_sun4v_pcr_ops(void) pcr_ops = &n5_pcr_ops; break; + case SUN4V_CHIP_SPARC_M7: + pcr_ops = &m7_pcr_ops; + break; + default: ret = -ENODEV; break; diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 46a5e4508752..86eebfa3b158 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -792,6 +792,42 @@ static const struct sparc_pmu niagara4_pmu = { .num_pic_regs = 4, }; +static void sparc_m7_write_pmc(int idx, u64 val) +{ + u64 pcr; + + pcr = pcr_ops->read_pcr(idx); + /* ensure ov and ntc are reset */ + pcr &= ~(PCR_N4_OV | PCR_N4_NTC); + + pcr_ops->write_pic(idx, val & 0xffffffff); + + pcr_ops->write_pcr(idx, pcr); +} + +static const struct sparc_pmu sparc_m7_pmu = { + .event_map = niagara4_event_map, + .cache_map = &niagara4_cache_map, + .max_events = ARRAY_SIZE(niagara4_perfmon_event_map), + .read_pmc = sparc_vt_read_pmc, + .write_pmc = sparc_m7_write_pmc, + .upper_shift = 5, + .lower_shift = 5, + .event_mask = 0x7ff, + .user_bit = PCR_N4_UTRACE, + .priv_bit = PCR_N4_STRACE, + + /* We explicitly don't support hypervisor tracing. */ + .hv_bit = 0, + + .irq_bit = PCR_N4_TOE, + .upper_nop = 0, + .lower_nop = 0, + .flags = 0, + .max_hw_events = 4, + .num_pcrs = 4, + .num_pic_regs = 4, +}; static const struct sparc_pmu *sparc_pmu __read_mostly; static u64 event_encoding(u64 event_id, int idx) @@ -960,6 +996,8 @@ out: cpuc->pcr[0] |= cpuc->event[0]->hw.config_base; } +static void sparc_pmu_start(struct perf_event *event, int flags); + /* On this PMU each PIC has it's own PCR control register. */ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) { @@ -972,20 +1010,13 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc) struct perf_event *cp = cpuc->event[i]; struct hw_perf_event *hwc = &cp->hw; int idx = hwc->idx; - u64 enc; if (cpuc->current_idx[i] != PIC_NO_INDEX) continue; - sparc_perf_event_set_period(cp, hwc, idx); cpuc->current_idx[i] = idx; - enc = perf_event_get_enc(cpuc->events[i]); - cpuc->pcr[idx] &= ~mask_for_index(idx); - if (hwc->state & PERF_HES_STOPPED) - cpuc->pcr[idx] |= nop_for_index(idx); - else - cpuc->pcr[idx] |= event_encoding(enc, idx); + sparc_pmu_start(cp, PERF_EF_RELOAD); } out: for (i = 0; i < cpuc->n_events; i++) { @@ -1101,7 +1132,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) int i; local_irq_save(flags); - perf_pmu_disable(event->pmu); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event[i]) { @@ -1127,7 +1157,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags) } } - perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -1361,7 +1390,6 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags) unsigned long flags; local_irq_save(flags); - perf_pmu_disable(event->pmu); n0 = cpuc->n_events; if (n0 >= sparc_pmu->max_hw_events) @@ -1394,7 +1422,6 @@ nocheck: ret = 0; out: - perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } @@ -1667,6 +1694,10 @@ static bool __init supported_pmu(void) sparc_pmu = &niagara4_pmu; return true; } + if (!strcmp(sparc_pmu_type, "sparc-m7")) { + sparc_pmu = &sparc_m7_pmu; + return true; + } return false; } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 0be7bf978cb1..46a59643bb1c 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -287,6 +287,8 @@ void arch_trigger_all_cpu_backtrace(bool include_self) printk(" TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n", gp->tpc, gp->o7, gp->i7, gp->rpc); } + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); @@ -362,6 +364,8 @@ static void pmu_snapshot_all_cpus(void) (cpu == this_cpu ? '*' : ' '), cpu, pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3], pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]); + + touch_nmi_watchdog(); } memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index da6f1a7fc4db..61139d9924ca 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1406,11 +1406,32 @@ void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) scheduler_ipi(); } -/* This is a nop because we capture all other cpus - * anyways when making the PROM active. - */ +static void stop_this_cpu(void *dummy) +{ + prom_stopself(); +} + void smp_send_stop(void) { + int cpu; + + if (tlb_type == hypervisor) { + for_each_online_cpu(cpu) { + if (cpu == smp_processor_id()) + continue; +#ifdef CONFIG_SUN_LDOMS + if (ldom_domaining_enabled) { + unsigned long hv_err; + hv_err = sun4v_cpu_stop(cpu); + if (hv_err) + printk(KERN_ERR "sun4v_cpu_stop() " + "failed err=%lu\n", hv_err); + } else +#endif + prom_stopcpu_cpuid(cpu); + } + } else + smp_call_function(stop_this_cpu, NULL, 0); } /** diff --git a/arch/sparc/kernel/starfire.c b/arch/sparc/kernel/starfire.c index 82281a566bb8..167fdfd9c837 100644 --- a/arch/sparc/kernel/starfire.c +++ b/arch/sparc/kernel/starfire.c @@ -28,11 +28,6 @@ void check_if_starfire(void) this_is_starfire = 1; } -int starfire_hard_smp_processor_id(void) -{ - return upa_readl(0x1fff40000d0UL); -} - /* * Each Starfire board has 32 registers which perform translation * and delivery of traditional interrupt packets into the extended diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index c85403d0496c..30e7ddb27a3a 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -333,7 +333,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second long err; /* No need for backward compatibility. We can start fresh... */ - if (call <= SEMCTL) { + if (call <= SEMTIMEDOP) { switch (call) { case SEMOP: err = sys_semtimedop(first, ptr, diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index a27651e866e7..0e699745d643 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2427,6 +2427,8 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } user_instruction_dump ((unsigned int __user *) regs->tpc); } + if (panic_on_oops) + panic("Fatal exception"); if (regs->tstate & TSTATE_PRIV) do_exit(SIGKILL); do_exit(SIGSEGV); @@ -2564,27 +2566,6 @@ void do_cee(struct pt_regs *regs) die_if_kernel("TL0: Cache Error Exception", regs); } -void do_cee_tl1(struct pt_regs *regs) -{ - exception_enter(); - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); - die_if_kernel("TL1: Cache Error Exception", regs); -} - -void do_dae_tl1(struct pt_regs *regs) -{ - exception_enter(); - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); - die_if_kernel("TL1: Data Access Exception", regs); -} - -void do_iae_tl1(struct pt_regs *regs) -{ - exception_enter(); - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); - die_if_kernel("TL1: Instruction Access Exception", regs); -} - void do_div0_tl1(struct pt_regs *regs) { exception_enter(); @@ -2592,13 +2573,6 @@ void do_div0_tl1(struct pt_regs *regs) die_if_kernel("TL1: DIV0 Exception", regs); } -void do_fpdis_tl1(struct pt_regs *regs) -{ - exception_enter(); - dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); - die_if_kernel("TL1: FPU Disabled", regs); -} - void do_fpieee_tl1(struct pt_regs *regs) { exception_enter(); diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S index b7f6334e159f..857ad4f8905f 100644 --- a/arch/sparc/lib/memmove.S +++ b/arch/sparc/lib/memmove.S @@ -8,9 +8,11 @@ .text ENTRY(memmove) /* o0=dst o1=src o2=len */ - mov %o0, %g1 + brz,pn %o2, 99f + mov %o0, %g1 + cmp %o0, %o1 - bleu,pt %xcc, memcpy + bleu,pt %xcc, 2f add %o1, %o2, %g7 cmp %g7, %o0 bleu,pt %xcc, memcpy @@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */ stb %g7, [%o0] bne,pt %icc, 1b sub %o0, 1, %o0 - +99: retl mov %g1, %o0 + + /* We can't just call memcpy for these memmove cases. On some + * chips the memcpy uses cache initializing stores and when dst + * and src are close enough, those can clobber the source data + * before we've loaded it in. + */ +2: or %o0, %o1, %g7 + or %o2, %g7, %g7 + andcc %g7, 0x7, %g0 + bne,pn %xcc, 4f + nop + +3: ldx [%o1], %g7 + add %o1, 8, %o1 + subcc %o2, 8, %o2 + add %o0, 8, %o0 + bne,pt %icc, 3b + stx %g7, [%o0 - 0x8] + ba,a,pt %xcc, 99b + +4: ldub [%o1], %g7 + add %o1, 1, %o1 + subcc %o2, 1, %o2 + add %o0, 1, %o0 + bne,pt %icc, 4b + stb %g7, [%o0 - 0x1] + ba,a,pt %xcc, 99b ENDPROC(memmove) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 3ea267c53320..4ca0d6ba5ec8 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2820,7 +2820,7 @@ static int __init report_memory(void) return 0; } -device_initcall(report_memory); +arch_initcall(report_memory); #ifdef CONFIG_SMP #define do_flush_tlb_kernel_range smp_flush_tlb_kernel_range diff --git a/arch/tile/gxio/mpipe.c b/arch/tile/gxio/mpipe.c index 6f00e9850636..ee186e13dfe6 100644 --- a/arch/tile/gxio/mpipe.c +++ b/arch/tile/gxio/mpipe.c @@ -456,7 +456,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, EXPORT_SYMBOL_GPL(gxio_mpipe_equeue_init); int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context, - const struct timespec *ts) + const struct timespec64 *ts) { cycles_t cycles = get_cycles(); return gxio_mpipe_set_timestamp_aux(context, (uint64_t)ts->tv_sec, @@ -466,7 +466,7 @@ int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context, EXPORT_SYMBOL_GPL(gxio_mpipe_set_timestamp); int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context, - struct timespec *ts) + struct timespec64 *ts) { int ret; cycles_t cycles_prev, cycles_now, clock_rate; diff --git a/arch/tile/include/gxio/mpipe.h b/arch/tile/include/gxio/mpipe.h index e37cf4f0cffd..73e83a187866 100644 --- a/arch/tile/include/gxio/mpipe.h +++ b/arch/tile/include/gxio/mpipe.h @@ -1830,7 +1830,7 @@ extern int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr, * code. */ extern int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context, - struct timespec *ts); + struct timespec64 *ts); /* Set the timestamp of mPIPE. * @@ -1840,7 +1840,7 @@ extern int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context, * code. */ extern int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context, - const struct timespec *ts); + const struct timespec64 *ts); /* Adjust the timestamp of mPIPE. * diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 7083c16cccba..bb1376381985 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -14,13 +14,6 @@ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; -struct kaslr_setup_data { - __u64 next; - __u32 type; - __u32 len; - __u8 data[1]; -} kaslr_setup_data; - #define I8254_PORT_CONTROL 0x43 #define I8254_PORT_COUNTER0 0x40 #define I8254_CMD_READBACK 0xC0 @@ -302,29 +295,7 @@ static unsigned long find_random_addr(unsigned long minimum, return slots_fetch_random(); } -static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled) -{ - struct setup_data *data; - - kaslr_setup_data.type = SETUP_KASLR; - kaslr_setup_data.len = 1; - kaslr_setup_data.next = 0; - kaslr_setup_data.data[0] = enabled; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - if (data) - data->next = (unsigned long)&kaslr_setup_data; - else - params->hdr.setup_data = (unsigned long)&kaslr_setup_data; - -} - -unsigned char *choose_kernel_location(struct boot_params *params, - unsigned char *input, +unsigned char *choose_kernel_location(unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size) @@ -335,17 +306,14 @@ unsigned char *choose_kernel_location(struct boot_params *params, #ifdef CONFIG_HIBERNATION if (!cmdline_find_option_bool("kaslr")) { debug_putstr("KASLR disabled by default...\n"); - add_kaslr_setup_data(params, 0); goto out; } #else if (cmdline_find_option_bool("nokaslr")) { debug_putstr("KASLR disabled by cmdline...\n"); - add_kaslr_setup_data(params, 0); goto out; } #endif - add_kaslr_setup_data(params, 1); /* Record the various known unsafe memory ranges. */ mem_avoid_init((unsigned long)input, input_size, diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 5903089c818f..a950864a64da 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -401,8 +401,7 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, * the entire decompressed kernel plus relocation table, or the * entire decompressed kernel plus .bss and .brk sections. */ - output = choose_kernel_location(real_mode, input_data, input_len, - output, + output = choose_kernel_location(input_data, input_len, output, output_len > run_size ? output_len : run_size); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index ee3576b2666b..04477d68403f 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -57,8 +57,7 @@ int cmdline_find_option_bool(const char *option); #if CONFIG_RANDOMIZE_BASE /* aslr.c */ -unsigned char *choose_kernel_location(struct boot_params *params, - unsigned char *input, +unsigned char *choose_kernel_location(unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size); @@ -66,8 +65,7 @@ unsigned char *choose_kernel_location(struct boot_params *params, bool has_cpuflag(int flag); #else static inline -unsigned char *choose_kernel_location(struct boot_params *params, - unsigned char *input, +unsigned char *choose_kernel_location(unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size) diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 947c6bf52c33..54f60ab41c63 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1155,7 +1155,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); if (!src) return -ENOMEM; - assoc = (src + req->cryptlen + auth_tag_len); + assoc = (src + req->cryptlen); scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); scatterwalk_map_and_copy(assoc, req->assoc, 0, req->assoclen, 0); @@ -1180,7 +1180,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) scatterwalk_done(&src_sg_walk, 0, 0); scatterwalk_done(&assoc_sg_walk, 0, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1); + scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1); kfree(src); } return retval; diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 0dbc08282291..72ba21a8b5fc 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -370,7 +370,7 @@ static inline void drop_fpu(struct task_struct *tsk) preempt_disable(); tsk->thread.fpu_counter = 0; __drop_fpu(tsk); - clear_used_math(); + clear_stopped_child_used_math(tsk); preempt_enable(); } diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 95e11f79f123..f97fbe3abb67 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -51,8 +51,6 @@ extern int devmem_is_allowed(unsigned long pagenr); extern unsigned long max_low_pfn_mapped; extern unsigned long max_pfn_mapped; -extern bool kaslr_enabled; - static inline phys_addr_t get_max_mapped(void) { return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT; diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index fa1195dae425..164e3f8d3c3d 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/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 44e6dd7e36a2..225b0988043a 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -7,7 +7,6 @@ #define SETUP_DTB 2 #define SETUP_PCI 3 #define SETUP_EFI 4 -#define SETUP_KASLR 5 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 3d525c6124f6..803b684676ff 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1338,6 +1338,26 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) } /* + * ACPI offers an alternative platform interface model that removes + * ACPI hardware requirements for platforms that do not implement + * the PC Architecture. + * + * We initialize the Hardware-reduced ACPI model here: + */ +static void __init acpi_reduced_hw_init(void) +{ + if (acpi_gbl_reduced_hardware) { + /* + * Override x86_init functions and bypass legacy pic + * in Hardware-reduced ACPI mode + */ + x86_init.timers.timer_init = x86_init_noop; + x86_init.irqs.pre_vector_init = x86_init_noop; + legacy_pic = &null_legacy_pic; + } +} + +/* * If your system is blacklisted here, but you find that acpi=force * works for you, please contact linux-acpi@vger.kernel.org */ @@ -1536,6 +1556,11 @@ int __init early_acpi_boot_init(void) */ early_acpi_process_madt(); + /* + * Hardware-reduced ACPI mode initialization: + */ + acpi_reduced_hw_init(); + return 0; } diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index c2fd21fed002..017149cded07 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -37,10 +37,12 @@ static const struct apic apic_numachip; static unsigned int get_apic_id(unsigned long x) { unsigned long value; - unsigned int id; + unsigned int id = (x >> 24) & 0xff; - rdmsrl(MSR_FAM10H_NODE_ID, value); - id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U); + if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) { + rdmsrl(MSR_FAM10H_NODE_ID, value); + id |= (value << 2) & 0xff00; + } return id; } @@ -155,10 +157,18 @@ static int __init numachip_probe(void) static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) { - if (c->phys_proc_id != node) { - c->phys_proc_id = node; - per_cpu(cpu_llc_id, smp_processor_id()) = node; + u64 val; + u32 nodes = 1; + + this_cpu_write(cpu_llc_id, node); + + /* Account for nodes per socket in multi-core-module processors */ + if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) { + rdmsrl(MSR_FAM10H_NODE_ID, val); + nodes = ((val >> 3) & 7) + 1; } + + c->phys_proc_id = node / nodes; } static int __init numachip_system_init(void) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 9bbb9b35c144..d1ac80b72c72 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -47,13 +47,21 @@ do { \ #ifdef CONFIG_RANDOMIZE_BASE static unsigned long module_load_offset; +static int randomize_modules = 1; /* Mutex protects the module_load_offset. */ static DEFINE_MUTEX(module_kaslr_mutex); +static int __init parse_nokaslr(char *p) +{ + randomize_modules = 0; + return 0; +} +early_param("nokaslr", parse_nokaslr); + static unsigned long int get_module_load_offset(void) { - if (kaslr_enabled) { + if (randomize_modules) { mutex_lock(&module_kaslr_mutex); /* * Calculate the module_load_offset the first time this diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 98dc9317286e..0a2421cca01f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -122,8 +122,6 @@ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; -bool __read_mostly kaslr_enabled = false; - #ifdef CONFIG_DMI RESERVE_BRK(dmi_alloc, 65536); #endif @@ -427,11 +425,6 @@ static void __init reserve_initrd(void) } #endif /* CONFIG_BLK_DEV_INITRD */ -static void __init parse_kaslr_setup(u64 pa_data, u32 data_len) -{ - kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data)); -} - static void __init parse_setup_data(void) { struct setup_data *data; @@ -457,9 +450,6 @@ static void __init parse_setup_data(void) case SETUP_EFI: parse_efi_setup(pa_data, data_len); break; - case SETUP_KASLR: - parse_kaslr_setup(pa_data, data_len); - break; default: break; } @@ -842,14 +832,10 @@ static void __init trim_low_memory_range(void) static int dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) { - if (kaslr_enabled) - pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n", - (unsigned long)&_text - __START_KERNEL, - __START_KERNEL, - __START_KERNEL_map, - MODULES_VADDR-1); - else - pr_emerg("Kernel Offset: disabled\n"); + pr_emerg("Kernel Offset: 0x%lx from 0x%lx " + "(relocation range: 0x%lx-0x%lx)\n", + (unsigned long)&_text - __START_KERNEL, __START_KERNEL, + __START_KERNEL_map, MODULES_VADDR-1); return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 9d2073e2ecc9..4ff5d162ff9f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -384,7 +384,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) goto exit; conditional_sti(regs); - if (!user_mode(regs)) + if (!user_mode_vm(regs)) die("bounds", regs, error_code); if (!cpu_feature_enabled(X86_FEATURE_MPX)) { @@ -637,7 +637,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) * then it's very likely the result of an icebp/int01 trap. * User wants a sigtrap for that. */ - if (!dr6 && user_mode(regs)) + if (!dr6 && user_mode_vm(regs)) user_icebp = 1; /* Catch kmemcheck conditions first of all! */ diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 34f66e58a896..cdc6cf903078 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -379,7 +379,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) * thread's fpu state, reconstruct fxstate from the fsave * header. Sanitize the copied state etc. */ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; @@ -393,14 +393,15 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) */ drop_fpu(tsk); - if (__copy_from_user(xsave, buf_fx, state_size) || + if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || __copy_from_user(&env, buf, sizeof(env))) { + fpu_finit(fpu); err = -1; } else { sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - set_used_math(); } + set_used_math(); if (use_eager_fpu()) { preempt_disable(); math_state_restore(); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index cc31f7c06d3d..9541ba34126b 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -507,6 +507,7 @@ static int picdev_read(struct kvm_pic *s, return -EOPNOTSUPP; if (len != 1) { + memset(val, 0, len); pr_pic_unimpl("non byte read\n"); return 0; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f7b20b417a3a..10a481b7674d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2168,7 +2168,10 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) { unsigned long *msr_bitmap; - if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) { + if (is_guest_mode(vcpu)) + msr_bitmap = vmx_msr_bitmap_nested; + else if (irqchip_in_kernel(vcpu->kvm) && + apic_x2apic_mode(vcpu->arch.apic)) { if (is_long_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_longmode_x2apic; else @@ -9218,9 +9221,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS && - nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) { - vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_nested)); + exec_control & CPU_BASED_USE_MSR_BITMAPS) { + nested_vmx_merge_msr_bitmap(vcpu, vmcs12); + /* MSR_BITMAP will be set by following vmx_set_efer. */ } else exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bd7a70be41b3..32bf19ef3115 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2744,7 +2744,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_USER_NMI: case KVM_CAP_REINJECT_CONTROL: case KVM_CAP_IRQ_INJECT_STATUS: - case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: case KVM_CAP_IOEVENTFD_NO_LENGTH: case KVM_CAP_PIT2: diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 3d2612b68694..2fb384724ebb 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -513,31 +513,6 @@ void __init pcibios_set_cache_line_size(void) } } -/* - * Some device drivers assume dev->irq won't change after calling - * pci_disable_device(). So delay releasing of IRQ resource to driver - * unbinding time. Otherwise it will break PM subsystem and drivers - * like xen-pciback etc. - */ -static int pci_irq_notifier(struct notifier_block *nb, unsigned long action, - void *data) -{ - struct pci_dev *dev = to_pci_dev(data); - - if (action != BUS_NOTIFY_UNBOUND_DRIVER) - return NOTIFY_DONE; - - if (pcibios_disable_irq) - pcibios_disable_irq(dev); - - return NOTIFY_OK; -} - -static struct notifier_block pci_irq_nb = { - .notifier_call = pci_irq_notifier, - .priority = INT_MIN, -}; - int __init pcibios_init(void) { if (!raw_pci_ops) { @@ -550,9 +525,6 @@ int __init pcibios_init(void) if (pci_bf_sort >= pci_force_bf) pci_sort_breadthfirst(); - - bus_register_notifier(&pci_bus_type, &pci_irq_nb); - return 0; } @@ -711,6 +683,12 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return 0; } +void pcibios_disable_device (struct pci_dev *dev) +{ + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); +} + int pci_ext_cfg_avail(void) { if (raw_pci_ext_ops) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index efb849323c74..852aa4c92da0 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -234,10 +234,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (dev->irq_managed && dev->irq > 0) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - dev->irq = 0; } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index e71b3dbd87b8..5dc6ca5e1741 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1256,9 +1256,22 @@ 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 && dev->irq_managed && dev->irq) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); dev->irq = 0; dev->irq_managed = 0; diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S index 31776d0efc8c..d7ec4e251c0a 100644 --- a/arch/x86/vdso/vdso32/sigreturn.S +++ b/arch/x86/vdso/vdso32/sigreturn.S @@ -17,6 +17,7 @@ .text .globl __kernel_sigreturn .type __kernel_sigreturn,@function + nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */ ALIGN __kernel_sigreturn: .LSTART_sigreturn: diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 740ae3026a14..9f93af56a5fc 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -563,7 +563,7 @@ static bool alloc_p2m(unsigned long pfn) if (p2m_pfn == PFN_DOWN(__pa(p2m_missing))) p2m_init(p2m); else - p2m_init_identity(p2m, pfn); + p2m_init_identity(p2m, pfn & ~(P2M_PER_PAGE - 1)); spin_lock_irqsave(&p2m_update_lock, flags); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 7f8b7edcadca..26089d182cb7 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -358,8 +358,8 @@ int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len) npages = (off + n + PAGE_SIZE - 1) >> PAGE_SHIFT; if (WARN_ON(npages == 0)) return -EINVAL; - - sg_init_table(sgl->sg, npages); + /* Add one extra for linking */ + sg_init_table(sgl->sg, npages + 1); for (i = 0, len = n; i < npages; i++) { int plen = min_t(int, len, PAGE_SIZE - off); @@ -369,18 +369,26 @@ int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len) off = 0; len -= plen; } + sg_mark_end(sgl->sg + npages - 1); + sgl->npages = npages; + return n; } EXPORT_SYMBOL_GPL(af_alg_make_sg); +void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new) +{ + sg_unmark_end(sgl_prev->sg + sgl_prev->npages - 1); + sg_chain(sgl_prev->sg, sgl_prev->npages + 1, sgl_new->sg); +} +EXPORT_SYMBOL(af_alg_link_sg); + void af_alg_free_sg(struct af_alg_sgl *sgl) { int i; - i = 0; - do { + for (i = 0; i < sgl->npages; i++) put_page(sgl->pages[i]); - } while (!sg_is_last(sgl->sg + (i++))); } EXPORT_SYMBOL_GPL(af_alg_free_sg); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index b9743dc35801..60496d405ebf 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -39,6 +39,7 @@ struct skcipher_ctx { struct af_alg_completion completion; + atomic_t inflight; unsigned used; unsigned int len; @@ -49,9 +50,65 @@ struct skcipher_ctx { struct ablkcipher_request req; }; +struct skcipher_async_rsgl { + struct af_alg_sgl sgl; + struct list_head list; +}; + +struct skcipher_async_req { + struct kiocb *iocb; + struct skcipher_async_rsgl first_sgl; + struct list_head list; + struct scatterlist *tsg; + char iv[]; +}; + +#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \ + crypto_ablkcipher_reqsize(crypto_ablkcipher_reqtfm(&ctx->req))) + +#define GET_REQ_SIZE(ctx) \ + crypto_ablkcipher_reqsize(crypto_ablkcipher_reqtfm(&ctx->req)) + +#define GET_IV_SIZE(ctx) \ + crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(&ctx->req)) + #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) +static void skcipher_free_async_sgls(struct skcipher_async_req *sreq) +{ + struct skcipher_async_rsgl *rsgl, *tmp; + struct scatterlist *sgl; + struct scatterlist *sg; + int i, n; + + list_for_each_entry_safe(rsgl, tmp, &sreq->list, list) { + af_alg_free_sg(&rsgl->sgl); + if (rsgl != &sreq->first_sgl) + kfree(rsgl); + } + sgl = sreq->tsg; + n = sg_nents(sgl); + for_each_sg(sgl, sg, n, i) + put_page(sg_page(sg)); + + kfree(sreq->tsg); +} + +static void skcipher_async_cb(struct crypto_async_request *req, int err) +{ + struct sock *sk = req->data; + struct alg_sock *ask = alg_sk(sk); + struct skcipher_ctx *ctx = ask->private; + struct skcipher_async_req *sreq = GET_SREQ(req, ctx); + struct kiocb *iocb = sreq->iocb; + + atomic_dec(&ctx->inflight); + skcipher_free_async_sgls(sreq); + kfree(req); + aio_complete(iocb, err, err); +} + static inline int skcipher_sndbuf(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); @@ -96,7 +153,7 @@ static int skcipher_alloc_sgl(struct sock *sk) return 0; } -static void skcipher_pull_sgl(struct sock *sk, int used) +static void skcipher_pull_sgl(struct sock *sk, int used, int put) { struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; @@ -123,8 +180,8 @@ static void skcipher_pull_sgl(struct sock *sk, int used) if (sg[i].length) return; - - put_page(sg_page(sg + i)); + if (put) + put_page(sg_page(sg + i)); sg_assign_page(sg + i, NULL); } @@ -143,7 +200,7 @@ static void skcipher_free_sgl(struct sock *sk) struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; - skcipher_pull_sgl(sk, ctx->used); + skcipher_pull_sgl(sk, ctx->used, 1); } static int skcipher_wait_for_wmem(struct sock *sk, unsigned flags) @@ -424,8 +481,149 @@ unlock: return err ?: size; } -static int skcipher_recvmsg(struct socket *sock, struct msghdr *msg, - size_t ignored, int flags) +static int skcipher_all_sg_nents(struct skcipher_ctx *ctx) +{ + struct skcipher_sg_list *sgl; + struct scatterlist *sg; + int nents = 0; + + list_for_each_entry(sgl, &ctx->tsgl, list) { + sg = sgl->sg; + + while (!sg->length) + sg++; + + nents += sg_nents(sg); + } + return nents; +} + +static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, + int flags) +{ + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + struct skcipher_ctx *ctx = ask->private; + struct skcipher_sg_list *sgl; + struct scatterlist *sg; + struct skcipher_async_req *sreq; + struct ablkcipher_request *req; + struct skcipher_async_rsgl *last_rsgl = NULL; + unsigned int len = 0, tx_nents = skcipher_all_sg_nents(ctx); + unsigned int reqlen = sizeof(struct skcipher_async_req) + + GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx); + int i = 0; + int err = -ENOMEM; + + lock_sock(sk); + req = kmalloc(reqlen, GFP_KERNEL); + if (unlikely(!req)) + goto unlock; + + sreq = GET_SREQ(req, ctx); + sreq->iocb = msg->msg_iocb; + memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl)); + INIT_LIST_HEAD(&sreq->list); + sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL); + if (unlikely(!sreq->tsg)) { + kfree(req); + goto unlock; + } + sg_init_table(sreq->tsg, tx_nents); + memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx)); + ablkcipher_request_set_tfm(req, crypto_ablkcipher_reqtfm(&ctx->req)); + ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_async_cb, sk); + + while (iov_iter_count(&msg->msg_iter)) { + struct skcipher_async_rsgl *rsgl; + int used; + + if (!ctx->used) { + err = skcipher_wait_for_data(sk, flags); + if (err) + goto free; + } + sgl = list_first_entry(&ctx->tsgl, + struct skcipher_sg_list, list); + sg = sgl->sg; + + while (!sg->length) + sg++; + + used = min_t(unsigned long, ctx->used, + iov_iter_count(&msg->msg_iter)); + used = min_t(unsigned long, used, sg->length); + + if (i == tx_nents) { + struct scatterlist *tmp; + int x; + /* Ran out of tx slots in async request + * need to expand */ + tmp = kcalloc(tx_nents * 2, sizeof(*tmp), + GFP_KERNEL); + if (!tmp) + goto free; + + sg_init_table(tmp, tx_nents * 2); + for (x = 0; x < tx_nents; x++) + sg_set_page(&tmp[x], sg_page(&sreq->tsg[x]), + sreq->tsg[x].length, + sreq->tsg[x].offset); + kfree(sreq->tsg); + sreq->tsg = tmp; + tx_nents *= 2; + } + /* Need to take over the tx sgl from ctx + * to the asynch req - these sgls will be freed later */ + sg_set_page(sreq->tsg + i++, sg_page(sg), sg->length, + sg->offset); + + if (list_empty(&sreq->list)) { + rsgl = &sreq->first_sgl; + list_add_tail(&rsgl->list, &sreq->list); + } else { + rsgl = kzalloc(sizeof(*rsgl), GFP_KERNEL); + if (!rsgl) { + err = -ENOMEM; + goto free; + } + list_add_tail(&rsgl->list, &sreq->list); + } + + used = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, used); + err = used; + if (used < 0) + goto free; + if (last_rsgl) + af_alg_link_sg(&last_rsgl->sgl, &rsgl->sgl); + + last_rsgl = rsgl; + len += used; + skcipher_pull_sgl(sk, used, 0); + iov_iter_advance(&msg->msg_iter, used); + } + + ablkcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, + len, sreq->iv); + err = ctx->enc ? crypto_ablkcipher_encrypt(req) : + crypto_ablkcipher_decrypt(req); + if (err == -EINPROGRESS) { + atomic_inc(&ctx->inflight); + err = -EIOCBQUEUED; + goto unlock; + } +free: + skcipher_free_async_sgls(sreq); + kfree(req); +unlock: + skcipher_wmem_wakeup(sk); + release_sock(sk); + return err; +} + +static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, + int flags) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); @@ -484,7 +682,7 @@ free: goto unlock; copied += used; - skcipher_pull_sgl(sk, used); + skcipher_pull_sgl(sk, used, 1); iov_iter_advance(&msg->msg_iter, used); } @@ -497,6 +695,13 @@ unlock: return copied ?: err; } +static int skcipher_recvmsg(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + return (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) ? + skcipher_recvmsg_async(sock, msg, flags) : + skcipher_recvmsg_sync(sock, msg, flags); +} static unsigned int skcipher_poll(struct file *file, struct socket *sock, poll_table *wait) @@ -555,12 +760,25 @@ static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) return crypto_ablkcipher_setkey(private, key, keylen); } +static void skcipher_wait(struct sock *sk) +{ + struct alg_sock *ask = alg_sk(sk); + struct skcipher_ctx *ctx = ask->private; + int ctr = 0; + + while (atomic_read(&ctx->inflight) && ctr++ < 100) + msleep(100); +} + static void skcipher_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req); + if (atomic_read(&ctx->inflight)) + skcipher_wait(sk); + skcipher_free_sgl(sk); sock_kzfree_s(sk, ctx->iv, crypto_ablkcipher_ivsize(tfm)); sock_kfree_s(sk, ctx, ctx->len); @@ -592,6 +810,7 @@ static int skcipher_accept_parent(void *private, struct sock *sk) ctx->more = 0; ctx->merge = 0; ctx->enc = 0; + atomic_set(&ctx->inflight, 0); af_alg_init_completion(&ctx->completion); ask->private = ctx; diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 657964e8ab7e..37fb19047603 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -65,6 +65,7 @@ struct lpss_private_data; struct lpss_device_desc { unsigned int flags; + const char *clk_con_id; unsigned int prv_offset; size_t prv_size_override; void (*setup)(struct lpss_private_data *pdata); @@ -140,6 +141,7 @@ static struct lpss_device_desc lpt_i2c_dev_desc = { static struct lpss_device_desc lpt_uart_dev_desc = { .flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR, + .clk_con_id = "baudclk", .prv_offset = 0x800, .setup = lpss_uart_setup, }; @@ -156,6 +158,7 @@ static struct lpss_device_desc byt_pwm_dev_desc = { static struct lpss_device_desc byt_uart_dev_desc = { .flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX, + .clk_con_id = "baudclk", .prv_offset = 0x800, .setup = lpss_uart_setup, }; @@ -313,7 +316,7 @@ out: return PTR_ERR(clk); pdata->clk = clk; - clk_register_clkdev(clk, NULL, devname); + clk_register_clkdev(clk, dev_desc->clk_con_id, devname); return 0; } diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index e7f718d6918a..b1def411c0b8 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -485,6 +485,14 @@ void acpi_pci_irq_disable(struct pci_dev *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; @@ -505,6 +513,5 @@ void acpi_pci_irq_disable(struct pci_dev *dev) if (gsi >= 0) { acpi_unregister_gsi(gsi); dev->irq_managed = 0; - dev->irq = 0; } } diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index d453a2c98ad0..81751a49d8bf 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -307,7 +307,7 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, if (pos == 0) { memmove(blk + offset * map->cache_word_size, blk, rbnode->blklen * map->cache_word_size); - bitmap_shift_right(present, present, offset, blklen); + bitmap_shift_left(present, present, offset, blklen); } /* update the rbnode block, its size and the base register */ diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index f373c35f9e1d..da84f544c544 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -608,7 +608,8 @@ static int regcache_sync_block_single(struct regmap *map, void *block, for (i = start; i < end; i++) { regtmp = block_base + (i * map->reg_stride); - if (!regcache_reg_present(cache_present, i)) + if (!regcache_reg_present(cache_present, i) || + !regmap_writeable(map, regtmp)) continue; val = regcache_get_val(map, block, i); @@ -677,7 +678,8 @@ static int regcache_sync_block_raw(struct regmap *map, void *block, for (i = start; i < end; i++) { regtmp = block_base + (i * map->reg_stride); - if (!regcache_reg_present(cache_present, i)) { + if (!regcache_reg_present(cache_present, i) || + !regmap_writeable(map, regtmp)) { ret = regcache_sync_block_raw_flush(map, &data, base, regtmp); if (ret != 0) diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 6299a50a5960..a6c3f75b4b01 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -499,7 +499,8 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, goto err_alloc; } - ret = request_threaded_irq(irq, NULL, regmap_irq_thread, irq_flags, + ret = request_threaded_irq(irq, NULL, regmap_irq_thread, + irq_flags | IRQF_ONESHOT, chip->name, d); if (ret != 0) { dev_err(map->dev, "Failed to request IRQ %d for %s: %d\n", diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index fae2dbbf5745..72d7028f779b 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -142,6 +142,7 @@ struct ports_device { * notification */ struct work_struct control_work; + struct work_struct config_work; struct list_head ports; @@ -1837,10 +1838,21 @@ static void config_intr(struct virtio_device *vdev) portdev = vdev->priv; + if (!use_multiport(portdev)) + schedule_work(&portdev->config_work); +} + +static void config_work_handler(struct work_struct *work) +{ + struct ports_device *portdev; + + portdev = container_of(work, struct ports_device, control_work); if (!use_multiport(portdev)) { + struct virtio_device *vdev; struct port *port; u16 rows, cols; + vdev = portdev->vdev; virtio_cread(vdev, struct virtio_console_config, cols, &cols); virtio_cread(vdev, struct virtio_console_config, rows, &rows); @@ -2040,12 +2052,14 @@ static int virtcons_probe(struct virtio_device *vdev) virtio_device_ready(portdev->vdev); + INIT_WORK(&portdev->config_work, &config_work_handler); + INIT_WORK(&portdev->control_work, &control_work_handler); + if (multiport) { unsigned int nr_added_bufs; spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); - INIT_WORK(&portdev->control_work, &control_work_handler); nr_added_bufs = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); @@ -2113,6 +2127,8 @@ static void virtcons_remove(struct virtio_device *vdev) /* Finish up work that's lined up */ if (use_multiport(portdev)) cancel_work_sync(&portdev->control_work); + else + cancel_work_sync(&portdev->config_work); list_for_each_entry_safe(port, port2, &portdev->ports, list) unplug_port(port); @@ -2164,6 +2180,7 @@ static int virtcons_freeze(struct virtio_device *vdev) virtqueue_disable_cb(portdev->c_ivq); cancel_work_sync(&portdev->control_work); + cancel_work_sync(&portdev->config_work); /* * Once more: if control_work_handler() was running, it would * enable the cb as the last step. diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index db7f8bce7467..25006a8bb8e6 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -144,12 +144,6 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw, divider->flags); } -/* - * The reverse of DIV_ROUND_UP: The maximum number which - * divided by m is r - */ -#define MULT_ROUND_UP(r, m) ((r) * (m) + (m) - 1) - static bool _is_valid_table_div(const struct clk_div_table *table, unsigned int div) { @@ -225,19 +219,24 @@ static int _div_round_closest(const struct clk_div_table *table, unsigned long parent_rate, unsigned long rate, unsigned long flags) { - int up, down, div; + int up, down; + unsigned long up_rate, down_rate; - up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate); + up = DIV_ROUND_UP(parent_rate, rate); + down = parent_rate / rate; if (flags & CLK_DIVIDER_POWER_OF_TWO) { - up = __roundup_pow_of_two(div); - down = __rounddown_pow_of_two(div); + up = __roundup_pow_of_two(up); + down = __rounddown_pow_of_two(down); } else if (table) { - up = _round_up_table(table, div); - down = _round_down_table(table, div); + up = _round_up_table(table, up); + down = _round_down_table(table, down); } - return (up - div) <= (div - down) ? up : down; + up_rate = DIV_ROUND_UP(parent_rate, up); + down_rate = DIV_ROUND_UP(parent_rate, down); + + return (rate - up_rate) <= (down_rate - rate) ? up : down; } static int _div_round(const struct clk_div_table *table, @@ -313,7 +312,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate, return i; } parent_rate = __clk_round_rate(__clk_get_parent(hw->clk), - MULT_ROUND_UP(rate, i)); + rate * i); now = DIV_ROUND_UP(parent_rate, i); if (_is_best_div(rate, now, best, flags)) { bestdiv = i; @@ -353,7 +352,7 @@ static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate, bestdiv = readl(divider->reg) >> divider->shift; bestdiv &= div_mask(divider->width); bestdiv = _get_div(divider->table, bestdiv, divider->flags); - return bestdiv; + return DIV_ROUND_UP(*prate, bestdiv); } return divider_round_rate(hw, rate, prate, divider->table, diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index eb0152961d3c..237f23f68bfc 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1350,7 +1350,6 @@ static unsigned long clk_core_get_rate(struct clk_core *clk) return rate; } -EXPORT_SYMBOL_GPL(clk_core_get_rate); /** * clk_get_rate - return the rate of clk @@ -2171,6 +2170,32 @@ int clk_get_phase(struct clk *clk) } /** + * clk_is_match - check if two clk's point to the same hardware clock + * @p: clk compared against q + * @q: clk compared against p + * + * Returns true if the two struct clk pointers both point to the same hardware + * clock node. Put differently, returns true if struct clk *p and struct clk *q + * share the same struct clk_core object. + * + * Returns false otherwise. Note that two NULL clks are treated as matching. + */ +bool clk_is_match(const struct clk *p, const struct clk *q) +{ + /* trivial case: identical struct clk's or both NULL */ + if (p == q) + return true; + + /* true if clk->core pointers match. Avoid derefing garbage */ + if (!IS_ERR_OR_NULL(p) && !IS_ERR_OR_NULL(q)) + if (p->core == q->core) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(clk_is_match); + +/** * __clk_init - initialize the data structures in a struct clk * @dev: device initializing this clk, placeholder for now * @clk: clk being initialized diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c index b0b562b9ce0e..e60feffc10a1 100644 --- a/drivers/clk/qcom/gcc-msm8960.c +++ b/drivers/clk/qcom/gcc-msm8960.c @@ -48,6 +48,17 @@ static struct clk_pll pll3 = { }, }; +static struct clk_regmap pll4_vote = { + .enable_reg = 0x34c0, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "pll4_vote", + .parent_names = (const char *[]){ "pll4" }, + .num_parents = 1, + .ops = &clk_pll_vote_ops, + }, +}; + static struct clk_pll pll8 = { .l_reg = 0x3144, .m_reg = 0x3148, @@ -3023,6 +3034,7 @@ static struct clk_branch rpm_msg_ram_h_clk = { static struct clk_regmap *gcc_msm8960_clks[] = { [PLL3] = &pll3.clkr, + [PLL4_VOTE] = &pll4_vote, [PLL8] = &pll8.clkr, [PLL8_VOTE] = &pll8_vote, [PLL14] = &pll14.clkr, @@ -3247,6 +3259,7 @@ static const struct qcom_reset_map gcc_msm8960_resets[] = { static struct clk_regmap *gcc_apq8064_clks[] = { [PLL3] = &pll3.clkr, + [PLL4_VOTE] = &pll4_vote, [PLL8] = &pll8.clkr, [PLL8_VOTE] = &pll8_vote, [PLL14] = &pll14.clkr, diff --git a/drivers/clk/qcom/lcc-ipq806x.c b/drivers/clk/qcom/lcc-ipq806x.c index 121ffde25dc3..c9ff27b4648b 100644 --- a/drivers/clk/qcom/lcc-ipq806x.c +++ b/drivers/clk/qcom/lcc-ipq806x.c @@ -462,7 +462,6 @@ static struct platform_driver lcc_ipq806x_driver = { .remove = lcc_ipq806x_remove, .driver = { .name = "lcc-ipq806x", - .owner = THIS_MODULE, .of_match_table = lcc_ipq806x_match_table, }, }; diff --git a/drivers/clk/qcom/lcc-msm8960.c b/drivers/clk/qcom/lcc-msm8960.c index a75a408cfccd..e2c863295f00 100644 --- a/drivers/clk/qcom/lcc-msm8960.c +++ b/drivers/clk/qcom/lcc-msm8960.c @@ -417,8 +417,8 @@ static struct clk_rcg slimbus_src = { .mnctr_en_bit = 8, .mnctr_reset_bit = 7, .mnctr_mode_shift = 5, - .n_val_shift = 16, - .m_val_shift = 16, + .n_val_shift = 24, + .m_val_shift = 8, .width = 8, }, .p = { @@ -547,7 +547,7 @@ static int lcc_msm8960_probe(struct platform_device *pdev) return PTR_ERR(regmap); /* Use the correct frequency plan depending on speed of PLL4 */ - val = regmap_read(regmap, 0x4, &val); + regmap_read(regmap, 0x4, &val); if (val == 0x12) { slimbus_src.freq_tbl = clk_tbl_aif_osr_492; mi2s_osr_src.freq_tbl = clk_tbl_aif_osr_492; @@ -574,7 +574,6 @@ static struct platform_driver lcc_msm8960_driver = { .remove = lcc_msm8960_remove, .driver = { .name = "lcc-msm8960", - .owner = THIS_MODULE, .of_match_table = lcc_msm8960_match_table, }, }; diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c index 6ef89639a9f6..d21640634adf 100644 --- a/drivers/clk/ti/fapll.c +++ b/drivers/clk/ti/fapll.c @@ -84,7 +84,7 @@ static int ti_fapll_enable(struct clk_hw *hw) struct fapll_data *fd = to_fapll(hw); u32 v = readl_relaxed(fd->base); - v |= (1 << FAPLL_MAIN_PLLEN); + v |= FAPLL_MAIN_PLLEN; writel_relaxed(v, fd->base); return 0; @@ -95,7 +95,7 @@ static void ti_fapll_disable(struct clk_hw *hw) struct fapll_data *fd = to_fapll(hw); u32 v = readl_relaxed(fd->base); - v &= ~(1 << FAPLL_MAIN_PLLEN); + v &= ~FAPLL_MAIN_PLLEN; writel_relaxed(v, fd->base); } @@ -104,7 +104,7 @@ static int ti_fapll_is_enabled(struct clk_hw *hw) struct fapll_data *fd = to_fapll(hw); u32 v = readl_relaxed(fd->base); - return v & (1 << FAPLL_MAIN_PLLEN); + return v & FAPLL_MAIN_PLLEN; } static unsigned long ti_fapll_recalc_rate(struct clk_hw *hw, diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c index bba62f9deefb..ec57ba2bbd87 100644 --- a/drivers/clocksource/time-efm32.c +++ b/drivers/clocksource/time-efm32.c @@ -225,12 +225,12 @@ static int __init efm32_clockevent_init(struct device_node *np) clock_event_ddata.base = base; clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ); - setup_irq(irq, &efm32_clock_event_irq); - clockevents_config_and_register(&clock_event_ddata.evtdev, DIV_ROUND_CLOSEST(rate, 1024), 0xf, 0xffff); + setup_irq(irq, &efm32_clock_event_irq); + return 0; err_get_irq: diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index 02268448dc85..5dcbf90b8015 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -178,10 +178,6 @@ static void __init sun5i_timer_init(struct device_node *node) ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); - ret = setup_irq(irq, &sun5i_timer_irq); - if (ret) - pr_warn("failed to setup irq %d\n", irq); - /* Enable timer0 interrupt */ val = readl(timer_base + TIMER_IRQ_EN_REG); writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG); @@ -191,6 +187,10 @@ static void __init sun5i_timer_init(struct device_node *node) clockevents_config_and_register(&sun5i_clockevent, rate, TIMER_SYNC_TICKS, 0xffffffff); + + ret = setup_irq(irq, &sun5i_timer_irq); + if (ret) + pr_warn("failed to setup irq %d\n", irq); } CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer", sun5i_timer_init); diff --git a/drivers/cpuidle/cpuidle-mvebu-v7.c b/drivers/cpuidle/cpuidle-mvebu-v7.c index 38e68618513a..980151f34707 100644 --- a/drivers/cpuidle/cpuidle-mvebu-v7.c +++ b/drivers/cpuidle/cpuidle-mvebu-v7.c @@ -37,11 +37,11 @@ static int mvebu_v7_enter_idle(struct cpuidle_device *dev, deepidle = true; ret = mvebu_v7_cpu_suspend(deepidle); + cpu_pm_exit(); + if (ret) return ret; - cpu_pm_exit(); - return index; } @@ -50,17 +50,17 @@ static struct cpuidle_driver armadaxp_idle_driver = { .states[0] = ARM_CPUIDLE_WFI_STATE, .states[1] = { .enter = mvebu_v7_enter_idle, - .exit_latency = 10, + .exit_latency = 100, .power_usage = 50, - .target_residency = 100, + .target_residency = 1000, .name = "MV CPU IDLE", .desc = "CPU power down", }, .states[2] = { .enter = mvebu_v7_enter_idle, - .exit_latency = 100, + .exit_latency = 1000, .power_usage = 5, - .target_residency = 1000, + .target_residency = 10000, .flags = MVEBU_V7_FLAG_DEEP_IDLE, .name = "MV CPU DEEP IDLE", .desc = "CPU and L2 Fabric power down", diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 4a5fd245014e..83aa55d6fa5d 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -97,6 +97,12 @@ #define DRIVER_NAME "pl08xdmac" +#define PL80X_DMA_BUSWIDTHS \ + BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \ + BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) + static struct amba_driver pl08x_amba_driver; struct pl08x_driver_data; @@ -2070,6 +2076,10 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) pl08x->memcpy.device_pause = pl08x_pause; pl08x->memcpy.device_resume = pl08x_resume; pl08x->memcpy.device_terminate_all = pl08x_terminate_all; + pl08x->memcpy.src_addr_widths = PL80X_DMA_BUSWIDTHS; + pl08x->memcpy.dst_addr_widths = PL80X_DMA_BUSWIDTHS; + pl08x->memcpy.directions = BIT(DMA_MEM_TO_MEM); + pl08x->memcpy.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; /* Initialize slave engine */ dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask); @@ -2086,6 +2096,10 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) pl08x->slave.device_pause = pl08x_pause; pl08x->slave.device_resume = pl08x_resume; pl08x->slave.device_terminate_all = pl08x_terminate_all; + pl08x->slave.src_addr_widths = PL80X_DMA_BUSWIDTHS; + pl08x->slave.dst_addr_widths = PL80X_DMA_BUSWIDTHS; + pl08x->slave.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + pl08x->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; /* Get the platform data */ pl08x->pd = dev_get_platdata(&adev->dev); diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 1e1a4c567542..0b4fc6fb48ce 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -238,93 +238,126 @@ static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first) } /* - * atc_get_current_descriptors - - * locate the descriptor which equal to physical address in DSCR - * @atchan: the channel we want to start - * @dscr_addr: physical descriptor address in DSCR + * atc_get_desc_by_cookie - get the descriptor of a cookie + * @atchan: the DMA channel + * @cookie: the cookie to get the descriptor for */ -static struct at_desc *atc_get_current_descriptors(struct at_dma_chan *atchan, - u32 dscr_addr) +static struct at_desc *atc_get_desc_by_cookie(struct at_dma_chan *atchan, + dma_cookie_t cookie) { - struct at_desc *desc, *_desc, *child, *desc_cur = NULL; + struct at_desc *desc, *_desc; - list_for_each_entry_safe(desc, _desc, &atchan->active_list, desc_node) { - if (desc->lli.dscr == dscr_addr) { - desc_cur = desc; - break; - } + list_for_each_entry_safe(desc, _desc, &atchan->queue, desc_node) { + if (desc->txd.cookie == cookie) + return desc; + } - list_for_each_entry(child, &desc->tx_list, desc_node) { - if (child->lli.dscr == dscr_addr) { - desc_cur = child; - break; - } - } + list_for_each_entry_safe(desc, _desc, &atchan->active_list, desc_node) { + if (desc->txd.cookie == cookie) + return desc; } - return desc_cur; + return NULL; } -/* - * atc_get_bytes_left - - * Get the number of bytes residue in dma buffer, - * @chan: the channel we want to start +/** + * atc_calc_bytes_left - calculates the number of bytes left according to the + * value read from CTRLA. + * + * @current_len: the number of bytes left before reading CTRLA + * @ctrla: the value of CTRLA + * @desc: the descriptor containing the transfer width + */ +static inline int atc_calc_bytes_left(int current_len, u32 ctrla, + struct at_desc *desc) +{ + return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width); +} + +/** + * atc_calc_bytes_left_from_reg - calculates the number of bytes left according + * to the current value of CTRLA. + * + * @current_len: the number of bytes left before reading CTRLA + * @atchan: the channel to read CTRLA for + * @desc: the descriptor containing the transfer width + */ +static inline int atc_calc_bytes_left_from_reg(int current_len, + struct at_dma_chan *atchan, struct at_desc *desc) +{ + u32 ctrla = channel_readl(atchan, CTRLA); + + return atc_calc_bytes_left(current_len, ctrla, desc); +} + +/** + * atc_get_bytes_left - get the number of bytes residue for a cookie + * @chan: DMA channel + * @cookie: transaction identifier to check status of */ -static int atc_get_bytes_left(struct dma_chan *chan) +static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie) { struct at_dma_chan *atchan = to_at_dma_chan(chan); - struct at_dma *atdma = to_at_dma(chan->device); - int chan_id = atchan->chan_common.chan_id; struct at_desc *desc_first = atc_first_active(atchan); - struct at_desc *desc_cur; - int ret = 0, count = 0; + struct at_desc *desc; + int ret; + u32 ctrla, dscr; /* - * Initialize necessary values in the first time. - * remain_desc record remain desc length. + * If the cookie doesn't match to the currently running transfer then + * we can return the total length of the associated DMA transfer, + * because it is still queued. */ - if (atchan->remain_desc == 0) - /* First descriptor embedds the transaction length */ - atchan->remain_desc = desc_first->len; + desc = atc_get_desc_by_cookie(atchan, cookie); + if (desc == NULL) + return -EINVAL; + else if (desc != desc_first) + return desc->total_len; - /* - * This happens when current descriptor transfer complete. - * The residual buffer size should reduce current descriptor length. - */ - if (unlikely(test_bit(ATC_IS_BTC, &atchan->status))) { - clear_bit(ATC_IS_BTC, &atchan->status); - desc_cur = atc_get_current_descriptors(atchan, - channel_readl(atchan, DSCR)); - if (!desc_cur) { - ret = -EINVAL; - goto out; - } + /* cookie matches to the currently running transfer */ + ret = desc_first->total_len; - count = (desc_cur->lli.ctrla & ATC_BTSIZE_MAX) - << desc_first->tx_width; - if (atchan->remain_desc < count) { - ret = -EINVAL; - goto out; + if (desc_first->lli.dscr) { + /* hardware linked list transfer */ + + /* + * Calculate the residue by removing the length of the child + * descriptors already transferred from the total length. + * To get the current child descriptor we can use the value of + * the channel's DSCR register and compare it against the value + * of the hardware linked list structure of each child + * descriptor. + */ + + ctrla = channel_readl(atchan, CTRLA); + rmb(); /* ensure CTRLA is read before DSCR */ + dscr = channel_readl(atchan, DSCR); + + /* for the first descriptor we can be more accurate */ + if (desc_first->lli.dscr == dscr) + return atc_calc_bytes_left(ret, ctrla, desc_first); + + ret -= desc_first->len; + list_for_each_entry(desc, &desc_first->tx_list, desc_node) { + if (desc->lli.dscr == dscr) + break; + + ret -= desc->len; } - atchan->remain_desc -= count; - ret = atchan->remain_desc; - } else { /* - * Get residual bytes when current - * descriptor transfer in progress. + * For the last descriptor in the chain we can calculate + * the remaining bytes using the channel's register. + * Note that the transfer width of the first and last + * descriptor may differ. */ - count = (channel_readl(atchan, CTRLA) & ATC_BTSIZE_MAX) - << (desc_first->tx_width); - ret = atchan->remain_desc - count; + if (!desc->lli.dscr) + ret = atc_calc_bytes_left_from_reg(ret, atchan, desc); + } else { + /* single transfer */ + ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first); } - /* - * Check fifo empty. - */ - if (!(dma_readl(atdma, CHSR) & AT_DMA_EMPT(chan_id))) - atc_issue_pending(chan); -out: return ret; } @@ -539,8 +572,6 @@ static irqreturn_t at_dma_interrupt(int irq, void *dev_id) /* Give information to tasklet */ set_bit(ATC_IS_ERROR, &atchan->status); } - if (pending & AT_DMA_BTC(i)) - set_bit(ATC_IS_BTC, &atchan->status); tasklet_schedule(&atchan->tasklet); ret = IRQ_HANDLED; } @@ -653,14 +684,18 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, desc->lli.ctrlb = ctrlb; desc->txd.cookie = 0; + desc->len = xfer_count << src_width; atc_desc_chain(&first, &prev, desc); } /* First descriptor of the chain embedds additional information */ first->txd.cookie = -EBUSY; - first->len = len; + first->total_len = len; + + /* set transfer width for the calculation of the residue */ first->tx_width = src_width; + prev->tx_width = src_width; /* set end-of-link to the last link descriptor of list*/ set_desc_eol(desc); @@ -752,6 +787,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, | ATC_SRC_WIDTH(mem_width) | len >> mem_width; desc->lli.ctrlb = ctrlb; + desc->len = len; atc_desc_chain(&first, &prev, desc); total_len += len; @@ -792,6 +828,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, | ATC_DST_WIDTH(mem_width) | len >> reg_width; desc->lli.ctrlb = ctrlb; + desc->len = len; atc_desc_chain(&first, &prev, desc); total_len += len; @@ -806,8 +843,11 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, /* First descriptor of the chain embedds additional information */ first->txd.cookie = -EBUSY; - first->len = total_len; + first->total_len = total_len; + + /* set transfer width for the calculation of the residue */ first->tx_width = reg_width; + prev->tx_width = reg_width; /* first link descriptor of list is responsible of flags */ first->txd.flags = flags; /* client is in control of this ack */ @@ -872,6 +912,7 @@ atc_dma_cyclic_fill_desc(struct dma_chan *chan, struct at_desc *desc, | ATC_FC_MEM2PER | ATC_SIF(atchan->mem_if) | ATC_DIF(atchan->per_if); + desc->len = period_len; break; case DMA_DEV_TO_MEM: @@ -883,6 +924,7 @@ atc_dma_cyclic_fill_desc(struct dma_chan *chan, struct at_desc *desc, | ATC_FC_PER2MEM | ATC_SIF(atchan->per_if) | ATC_DIF(atchan->mem_if); + desc->len = period_len; break; default: @@ -964,7 +1006,7 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, /* First descriptor of the chain embedds additional information */ first->txd.cookie = -EBUSY; - first->len = buf_len; + first->total_len = buf_len; first->tx_width = reg_width; return &first->txd; @@ -1118,7 +1160,7 @@ atc_tx_status(struct dma_chan *chan, spin_lock_irqsave(&atchan->lock, flags); /* Get number of bytes left in the active transactions */ - bytes = atc_get_bytes_left(chan); + bytes = atc_get_bytes_left(chan, cookie); spin_unlock_irqrestore(&atchan->lock, flags); @@ -1214,7 +1256,6 @@ static int atc_alloc_chan_resources(struct dma_chan *chan) spin_lock_irqsave(&atchan->lock, flags); atchan->descs_allocated = i; - atchan->remain_desc = 0; list_splice(&tmp_list, &atchan->free_list); dma_cookie_init(chan); spin_unlock_irqrestore(&atchan->lock, flags); @@ -1257,7 +1298,6 @@ static void atc_free_chan_resources(struct dma_chan *chan) list_splice_init(&atchan->free_list, &list); atchan->descs_allocated = 0; atchan->status = 0; - atchan->remain_desc = 0; dev_vdbg(chan2dev(chan), "free_chan_resources: done\n"); } diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h index d6bba6c636c2..2727ca560572 100644 --- a/drivers/dma/at_hdmac_regs.h +++ b/drivers/dma/at_hdmac_regs.h @@ -181,8 +181,9 @@ struct at_lli { * @at_lli: hardware lli structure * @txd: support for the async_tx api * @desc_node: node on the channed descriptors list - * @len: total transaction bytecount + * @len: descriptor byte count * @tx_width: transfer width + * @total_len: total transaction byte count */ struct at_desc { /* FIRST values the hardware uses */ @@ -194,6 +195,7 @@ struct at_desc { struct list_head desc_node; size_t len; u32 tx_width; + size_t total_len; }; static inline struct at_desc * @@ -213,7 +215,6 @@ txd_to_at_desc(struct dma_async_tx_descriptor *txd) enum atc_status { ATC_IS_ERROR = 0, ATC_IS_PAUSED = 1, - ATC_IS_BTC = 2, ATC_IS_CYCLIC = 24, }; @@ -231,7 +232,6 @@ enum atc_status { * @save_cfg: configuration register that is saved on suspend/resume cycle * @save_dscr: for cyclic operations, preserve next descriptor address in * the cyclic list on suspend/resume cycle - * @remain_desc: to save remain desc length * @dma_sconfig: configuration for slave transfers, passed via * .device_config * @lock: serializes enqueue/dequeue operations to descriptors lists @@ -251,7 +251,6 @@ struct at_dma_chan { struct tasklet_struct tasklet; u32 save_cfg; u32 save_dscr; - u32 remain_desc; struct dma_slave_config dma_sconfig; spinlock_t lock; diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index 6565a361e7e5..b2c3ae071429 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -26,6 +26,8 @@ #include "internal.h" +#define DRV_NAME "dw_dmac" + static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { @@ -284,7 +286,7 @@ static struct platform_driver dw_driver = { .remove = dw_remove, .shutdown = dw_shutdown, .driver = { - .name = "dw_dmac", + .name = DRV_NAME, .pm = &dw_dev_pm_ops, .of_match_table = of_match_ptr(dw_dma_of_id_table), .acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table), @@ -305,3 +307,4 @@ module_exit(dw_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 18c0a131e4e4..66a0efb9651d 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -531,6 +531,10 @@ static int sdma_run_channel0(struct sdma_engine *sdma) dev_err(sdma->dev, "Timeout waiting for CH0 ready\n"); } + /* Set bits of CONFIG register with dynamic context switching */ + if (readl(sdma->regs + SDMA_H_CONFIG) == 0) + writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG); + return ret ? 0 : -ETIMEDOUT; } @@ -1394,9 +1398,6 @@ static int sdma_init(struct sdma_engine *sdma) writel_relaxed(ccb_phys, sdma->regs + SDMA_H_C0PTR); - /* Set bits of CONFIG register with given context switching mode */ - writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG); - /* Initializes channel's priorities */ sdma_set_channel_priority(&sdma->channel[0], 7); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 910ff8ab9c9c..d8135adb2238 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -645,6 +645,7 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm, pr_debug(" sdma queue id: %d\n", q->properties.sdma_queue_id); pr_debug(" sdma engine id: %d\n", q->properties.sdma_engine_id); + init_sdma_vm(dqm, q, qpd); retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj, &q->gart_mqd_addr, &q->properties); if (retval != 0) { @@ -652,7 +653,14 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm, return retval; } - init_sdma_vm(dqm, q, qpd); + retval = mqd->load_mqd(mqd, q->mqd, 0, + 0, NULL); + if (retval != 0) { + deallocate_sdma_queue(dqm, q->sdma_id); + mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj); + return retval; + } + return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index e415a2a9207e..c7d298e62c96 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -44,7 +44,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev, BUG_ON(!kq || !dev); BUG_ON(type != KFD_QUEUE_TYPE_DIQ && type != KFD_QUEUE_TYPE_HIQ); - pr_debug("kfd: In func %s initializing queue type %d size %d\n", + pr_debug("amdkfd: In func %s initializing queue type %d size %d\n", __func__, KFD_QUEUE_TYPE_HIQ, queue_size); nop.opcode = IT_NOP; @@ -69,12 +69,16 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev, prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off); - if (prop.doorbell_ptr == NULL) + if (prop.doorbell_ptr == NULL) { + pr_err("amdkfd: error init doorbell"); goto err_get_kernel_doorbell; + } retval = kfd_gtt_sa_allocate(dev, queue_size, &kq->pq); - if (retval != 0) + if (retval != 0) { + pr_err("amdkfd: error init pq queues size (%d)\n", queue_size); goto err_pq_allocate_vidmem; + } kq->pq_kernel_addr = kq->pq->cpu_ptr; kq->pq_gpu_addr = kq->pq->gpu_addr; @@ -165,10 +169,8 @@ err_rptr_allocate_vidmem: err_eop_allocate_vidmem: kfd_gtt_sa_free(dev, kq->pq); err_pq_allocate_vidmem: - pr_err("kfd: error init pq\n"); kfd_release_kernel_doorbell(dev, prop.doorbell_ptr); err_get_kernel_doorbell: - pr_err("kfd: error init doorbell"); return false; } @@ -187,6 +189,8 @@ static void uninitialize(struct kernel_queue *kq) else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ) kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj); + kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj); + kfd_gtt_sa_free(kq->dev, kq->rptr_mem); kfd_gtt_sa_free(kq->dev, kq->wptr_mem); kq->ops_asic_specific.uninitialize(kq); @@ -211,7 +215,7 @@ static int acquire_packet_buffer(struct kernel_queue *kq, queue_address = (unsigned int *)kq->pq_kernel_addr; queue_size_dwords = kq->queue->properties.queue_size / sizeof(uint32_t); - pr_debug("kfd: In func %s\nrptr: %d\nwptr: %d\nqueue_address 0x%p\n", + pr_debug("amdkfd: In func %s\nrptr: %d\nwptr: %d\nqueue_address 0x%p\n", __func__, rptr, wptr, queue_address); available_size = (rptr - 1 - wptr + queue_size_dwords) % @@ -296,7 +300,7 @@ struct kernel_queue *kernel_queue_init(struct kfd_dev *dev, } if (kq->ops.initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE) == false) { - pr_err("kfd: failed to init kernel queue\n"); + pr_err("amdkfd: failed to init kernel queue\n"); kfree(kq); return NULL; } @@ -319,7 +323,7 @@ static __attribute__((unused)) void test_kq(struct kfd_dev *dev) BUG_ON(!dev); - pr_err("kfd: starting kernel queue test\n"); + pr_err("amdkfd: starting kernel queue test\n"); kq = kernel_queue_init(dev, KFD_QUEUE_TYPE_HIQ); BUG_ON(!kq); @@ -330,7 +334,7 @@ static __attribute__((unused)) void test_kq(struct kfd_dev *dev) buffer[i] = kq->nop_packet; kq->ops.submit_packet(kq); - pr_err("kfd: ending kernel queue test\n"); + pr_err("amdkfd: ending kernel queue test\n"); } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 6b6b07ff720b..f6d04c7b5115 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -43,9 +43,10 @@ #include "drm_crtc_internal.h" #include "drm_internal.h" -static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, - struct drm_mode_fb_cmd2 *r, - struct drm_file *file_priv); +static struct drm_framebuffer * +internal_framebuffer_create(struct drm_device *dev, + struct drm_mode_fb_cmd2 *r, + struct drm_file *file_priv); /* Avoid boilerplate. I'm tired of typing. */ #define DRM_ENUM_NAME_FN(fnname, list) \ @@ -2908,13 +2909,11 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc, */ if (req->flags & DRM_MODE_CURSOR_BO) { if (req->handle) { - fb = add_framebuffer_internal(dev, &fbreq, file_priv); + fb = internal_framebuffer_create(dev, &fbreq, file_priv); if (IS_ERR(fb)) { DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n"); return PTR_ERR(fb); } - - drm_framebuffer_reference(fb); } else { fb = NULL; } @@ -3267,9 +3266,10 @@ static int framebuffer_check(const struct drm_mode_fb_cmd2 *r) return 0; } -static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, - struct drm_mode_fb_cmd2 *r, - struct drm_file *file_priv) +static struct drm_framebuffer * +internal_framebuffer_create(struct drm_device *dev, + struct drm_mode_fb_cmd2 *r, + struct drm_file *file_priv) { struct drm_mode_config *config = &dev->mode_config; struct drm_framebuffer *fb; @@ -3301,12 +3301,6 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, return fb; } - mutex_lock(&file_priv->fbs_lock); - r->fb_id = fb->base.id; - list_add(&fb->filp_head, &file_priv->fbs); - DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id); - mutex_unlock(&file_priv->fbs_lock); - return fb; } @@ -3328,15 +3322,24 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev, int drm_mode_addfb2(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct drm_mode_fb_cmd2 *r = data; struct drm_framebuffer *fb; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; - fb = add_framebuffer_internal(dev, data, file_priv); + fb = internal_framebuffer_create(dev, r, file_priv); if (IS_ERR(fb)) return PTR_ERR(fb); + /* Transfer ownership to the filp for reaping on close */ + + DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id); + mutex_lock(&file_priv->fbs_lock); + r->fb_id = fb->base.id; + list_add(&fb->filp_head, &file_priv->fbs); + mutex_unlock(&file_priv->fbs_lock); + return 0; } diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 9a5b68717ec8..379ab4555756 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -733,10 +733,14 @@ static bool check_txmsg_state(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_sideband_msg_tx *txmsg) { bool ret; - mutex_lock(&mgr->qlock); + + /* + * All updates to txmsg->state are protected by mgr->qlock, and the two + * cases we check here are terminal states. For those the barriers + * provided by the wake_up/wait_event pair are enough. + */ ret = (txmsg->state == DRM_DP_SIDEBAND_TX_RX || txmsg->state == DRM_DP_SIDEBAND_TX_TIMEOUT); - mutex_unlock(&mgr->qlock); return ret; } @@ -1363,12 +1367,13 @@ static int process_single_tx_qlock(struct drm_dp_mst_topology_mgr *mgr, return 0; } -/* must be called holding qlock */ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) { struct drm_dp_sideband_msg_tx *txmsg; int ret; + WARN_ON(!mutex_is_locked(&mgr->qlock)); + /* construct a chunk from the first msg in the tx_msg queue */ if (list_empty(&mgr->tx_msg_downq)) { mgr->tx_down_in_progress = false; diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 7fc6f8bd4821..1134526286c8 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -403,7 +403,7 @@ static int check_free_hole(u64 start, u64 end, u64 size, unsigned alignment) unsigned rem; rem = do_div(tmp, alignment); - if (tmp) + if (rem) start += alignment - rem; } diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index a5e74612100e..0a6780367d28 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -50,7 +50,7 @@ config DRM_EXYNOS_DSI config DRM_EXYNOS_DP bool "EXYNOS DRM DP driver support" - depends on (DRM_EXYNOS_FIMD || DRM_EXYNOS7DECON) && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS) + depends on (DRM_EXYNOS_FIMD || DRM_EXYNOS7_DECON) && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS) default DRM_EXYNOS select DRM_PANEL help diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index 63f02e2380ae..970046199608 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -888,8 +888,8 @@ static int decon_probe(struct platform_device *pdev) of_node_put(i80_if_timings); ctx->regs = of_iomap(dev->of_node, 0); - if (IS_ERR(ctx->regs)) { - ret = PTR_ERR(ctx->regs); + if (!ctx->regs) { + ret = -ENOMEM; goto err_del_component; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c deleted file mode 100644 index ba9b3d5ed672..000000000000 --- a/drivers/gpu/drm/exynos/exynos_drm_connector.c +++ /dev/null @@ -1,245 +0,0 @@ -/* - * Copyright (c) 2011 Samsung Electronics Co., Ltd. - * Authors: - * Inki Dae <inki.dae@samsung.com> - * Joonyoung Shim <jy0922.shim@samsung.com> - * Seung-Woo Kim <sw0312.kim@samsung.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. - */ - -#include <drm/drmP.h> -#include <drm/drm_crtc_helper.h> - -#include <drm/exynos_drm.h> -#include "exynos_drm_drv.h" -#include "exynos_drm_encoder.h" -#include "exynos_drm_connector.h" - -#define to_exynos_connector(x) container_of(x, struct exynos_drm_connector,\ - drm_connector) - -struct exynos_drm_connector { - struct drm_connector drm_connector; - uint32_t encoder_id; - struct exynos_drm_display *display; -}; - -static int exynos_drm_connector_get_modes(struct drm_connector *connector) -{ - struct exynos_drm_connector *exynos_connector = - to_exynos_connector(connector); - struct exynos_drm_display *display = exynos_connector->display; - struct edid *edid = NULL; - unsigned int count = 0; - int ret; - - /* - * if get_edid() exists then get_edid() callback of hdmi side - * is called to get edid data through i2c interface else - * get timing from the FIMD driver(display controller). - * - * P.S. in case of lcd panel, count is always 1 if success - * because lcd panel has only one mode. - */ - if (display->ops->get_edid) { - edid = display->ops->get_edid(display, connector); - if (IS_ERR_OR_NULL(edid)) { - ret = PTR_ERR(edid); - edid = NULL; - DRM_ERROR("Panel operation get_edid failed %d\n", ret); - goto out; - } - - count = drm_add_edid_modes(connector, edid); - if (!count) { - DRM_ERROR("Add edid modes failed %d\n", count); - goto out; - } - - drm_mode_connector_update_edid_property(connector, edid); - } else { - struct exynos_drm_panel_info *panel; - struct drm_display_mode *mode = drm_mode_create(connector->dev); - if (!mode) { - DRM_ERROR("failed to create a new display mode.\n"); - return 0; - } - - if (display->ops->get_panel) - panel = display->ops->get_panel(display); - else { - drm_mode_destroy(connector->dev, mode); - return 0; - } - - drm_display_mode_from_videomode(&panel->vm, mode); - mode->width_mm = panel->width_mm; - mode->height_mm = panel->height_mm; - connector->display_info.width_mm = mode->width_mm; - connector->display_info.height_mm = mode->height_mm; - - mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; - drm_mode_set_name(mode); - drm_mode_probed_add(connector, mode); - - count = 1; - } - -out: - kfree(edid); - return count; -} - -static int exynos_drm_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - struct exynos_drm_connector *exynos_connector = - to_exynos_connector(connector); - struct exynos_drm_display *display = exynos_connector->display; - int ret = MODE_BAD; - - DRM_DEBUG_KMS("%s\n", __FILE__); - - if (display->ops->check_mode) - if (!display->ops->check_mode(display, mode)) - ret = MODE_OK; - - return ret; -} - -static struct drm_encoder *exynos_drm_best_encoder( - struct drm_connector *connector) -{ - struct drm_device *dev = connector->dev; - struct exynos_drm_connector *exynos_connector = - to_exynos_connector(connector); - return drm_encoder_find(dev, exynos_connector->encoder_id); -} - -static struct drm_connector_helper_funcs exynos_connector_helper_funcs = { - .get_modes = exynos_drm_connector_get_modes, - .mode_valid = exynos_drm_connector_mode_valid, - .best_encoder = exynos_drm_best_encoder, -}; - -static int exynos_drm_connector_fill_modes(struct drm_connector *connector, - unsigned int max_width, unsigned int max_height) -{ - struct exynos_drm_connector *exynos_connector = - to_exynos_connector(connector); - struct exynos_drm_display *display = exynos_connector->display; - unsigned int width, height; - - width = max_width; - height = max_height; - - /* - * if specific driver want to find desired_mode using maxmum - * resolution then get max width and height from that driver. - */ - if (display->ops->get_max_resol) - display->ops->get_max_resol(display, &width, &height); - - return drm_helper_probe_single_connector_modes(connector, width, - height); -} - -/* get detection status of display device. */ -static enum drm_connector_status -exynos_drm_connector_detect(struct drm_connector *connector, bool force) -{ - struct exynos_drm_connector *exynos_connector = - to_exynos_connector(connector); - struct exynos_drm_display *display = exynos_connector->display; - enum drm_connector_status status = connector_status_disconnected; - - if (display->ops->is_connected) { - if (display->ops->is_connected(display)) - status = connector_status_connected; - else - status = connector_status_disconnected; - } - - return status; -} - -static void exynos_drm_connector_destroy(struct drm_connector *connector) -{ - struct exynos_drm_connector *exynos_connector = - to_exynos_connector(connector); - - drm_connector_unregister(connector); - drm_connector_cleanup(connector); - kfree(exynos_connector); -} - -static struct drm_connector_funcs exynos_connector_funcs = { - .dpms = drm_helper_connector_dpms, - .fill_modes = exynos_drm_connector_fill_modes, - .detect = exynos_drm_connector_detect, - .destroy = exynos_drm_connector_destroy, -}; - -struct drm_connector *exynos_drm_connector_create(struct drm_device *dev, - struct drm_encoder *encoder) -{ - struct exynos_drm_connector *exynos_connector; - struct exynos_drm_display *display = exynos_drm_get_display(encoder); - struct drm_connector *connector; - int type; - int err; - - exynos_connector = kzalloc(sizeof(*exynos_connector), GFP_KERNEL); - if (!exynos_connector) - return NULL; - - connector = &exynos_connector->drm_connector; - - switch (display->type) { - case EXYNOS_DISPLAY_TYPE_HDMI: - type = DRM_MODE_CONNECTOR_HDMIA; - connector->interlace_allowed = true; - connector->polled = DRM_CONNECTOR_POLL_HPD; - break; - case EXYNOS_DISPLAY_TYPE_VIDI: - type = DRM_MODE_CONNECTOR_VIRTUAL; - connector->polled = DRM_CONNECTOR_POLL_HPD; - break; - default: - type = DRM_MODE_CONNECTOR_Unknown; - break; - } - - drm_connector_init(dev, connector, &exynos_connector_funcs, type); - drm_connector_helper_add(connector, &exynos_connector_helper_funcs); - - err = drm_connector_register(connector); - if (err) - goto err_connector; - - exynos_connector->encoder_id = encoder->base.id; - exynos_connector->display = display; - connector->dpms = DRM_MODE_DPMS_OFF; - connector->encoder = encoder; - - err = drm_mode_connector_attach_encoder(connector, encoder); - if (err) { - DRM_ERROR("failed to attach a connector to a encoder\n"); - goto err_sysfs; - } - - DRM_DEBUG_KMS("connector has been created\n"); - - return connector; - -err_sysfs: - drm_connector_unregister(connector); -err_connector: - drm_connector_cleanup(connector); - kfree(exynos_connector); - return NULL; -} diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.h b/drivers/gpu/drm/exynos/exynos_drm_connector.h deleted file mode 100644 index 4eb20d78379a..000000000000 --- a/drivers/gpu/drm/exynos/exynos_drm_connector.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Copyright (c) 2011 Samsung Electronics Co., Ltd. - * Authors: - * Inki Dae <inki.dae@samsung.com> - * Joonyoung Shim <jy0922.shim@samsung.com> - * Seung-Woo Kim <sw0312.kim@samsung.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. - */ - -#ifndef _EXYNOS_DRM_CONNECTOR_H_ -#define _EXYNOS_DRM_CONNECTOR_H_ - -struct drm_connector *exynos_drm_connector_create(struct drm_device *dev, - struct drm_encoder *encoder); - -#endif diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 925fc69af1a0..c300e22da8ac 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -284,14 +284,9 @@ static void fimd_clear_channel(struct fimd_context *ctx) } } -static int fimd_ctx_initialize(struct fimd_context *ctx, +static int fimd_iommu_attach_devices(struct fimd_context *ctx, struct drm_device *drm_dev) { - struct exynos_drm_private *priv; - priv = drm_dev->dev_private; - - ctx->drm_dev = drm_dev; - ctx->pipe = priv->pipe++; /* attach this sub driver to iommu mapping if supported. */ if (is_drm_iommu_supported(ctx->drm_dev)) { @@ -313,7 +308,7 @@ static int fimd_ctx_initialize(struct fimd_context *ctx, return 0; } -static void fimd_ctx_remove(struct fimd_context *ctx) +static void fimd_iommu_detach_devices(struct fimd_context *ctx) { /* detach this sub driver from iommu mapping if supported. */ if (is_drm_iommu_supported(ctx->drm_dev)) @@ -1056,25 +1051,23 @@ static int fimd_bind(struct device *dev, struct device *master, void *data) { struct fimd_context *ctx = dev_get_drvdata(dev); struct drm_device *drm_dev = data; + struct exynos_drm_private *priv = drm_dev->dev_private; int ret; - ret = fimd_ctx_initialize(ctx, drm_dev); - if (ret) { - DRM_ERROR("fimd_ctx_initialize failed.\n"); - return ret; - } + ctx->drm_dev = drm_dev; + ctx->pipe = priv->pipe++; ctx->crtc = exynos_drm_crtc_create(drm_dev, ctx->pipe, EXYNOS_DISPLAY_TYPE_LCD, &fimd_crtc_ops, ctx); - if (IS_ERR(ctx->crtc)) { - fimd_ctx_remove(ctx); - return PTR_ERR(ctx->crtc); - } if (ctx->display) exynos_drm_create_enc_conn(drm_dev, ctx->display); + ret = fimd_iommu_attach_devices(ctx, drm_dev); + if (ret) + return ret; + return 0; } @@ -1086,10 +1079,10 @@ static void fimd_unbind(struct device *dev, struct device *master, fimd_dpms(ctx->crtc, DRM_MODE_DPMS_OFF); + fimd_iommu_detach_devices(ctx); + if (ctx->display) exynos_dpi_remove(ctx->display); - - fimd_ctx_remove(ctx); } static const struct component_ops fimd_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c index a5616872eee7..8ad5b7294eb4 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_plane.c +++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c @@ -175,7 +175,7 @@ static int exynos_disable_plane(struct drm_plane *plane) struct exynos_drm_plane *exynos_plane = to_exynos_plane(plane); struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(plane->crtc); - if (exynos_crtc->ops->win_disable) + if (exynos_crtc && exynos_crtc->ops->win_disable) exynos_crtc->ops->win_disable(exynos_crtc, exynos_plane->zpos); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index e5daad5f75fb..5b205863b659 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2936,9 +2936,9 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) req = obj->last_read_req; /* Do this after OLR check to make sure we make forward progress polling - * on this IOCTL with a timeout <=0 (like busy ioctl) + * on this IOCTL with a timeout == 0 (like busy ioctl) */ - if (args->timeout_ns <= 0) { + if (args->timeout_ns == 0) { ret = -ETIME; goto out; } @@ -2948,7 +2948,8 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) i915_gem_request_reference(req); mutex_unlock(&dev->struct_mutex); - ret = __i915_wait_request(req, reset_counter, true, &args->timeout_ns, + ret = __i915_wait_request(req, reset_counter, true, + args->timeout_ns > 0 ? &args->timeout_ns : NULL, file->driver_priv); mutex_lock(&dev->struct_mutex); i915_gem_request_unreference(req); @@ -4792,6 +4793,9 @@ i915_gem_init_hw(struct drm_device *dev) if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt()) return -EIO; + /* Double layer security blanket, see i915_gem_init() */ + intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + if (dev_priv->ellc_size) I915_WRITE(HSW_IDICR, I915_READ(HSW_IDICR) | IDIHASHMSK(0xf)); @@ -4824,7 +4828,7 @@ i915_gem_init_hw(struct drm_device *dev) for_each_ring(ring, dev_priv, i) { ret = ring->init_hw(ring); if (ret) - return ret; + goto out; } for (i = 0; i < NUM_L3_SLICES(dev); i++) @@ -4841,9 +4845,11 @@ i915_gem_init_hw(struct drm_device *dev) DRM_ERROR("Context enable failed %d\n", ret); i915_gem_cleanup_ringbuffer(dev); - return ret; + goto out; } +out: + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); return ret; } @@ -4877,6 +4883,14 @@ int i915_gem_init(struct drm_device *dev) dev_priv->gt.stop_ring = intel_logical_ring_stop; } + /* This is just a security blanket to placate dragons. + * On some systems, we very sporadically observe that the first TLBs + * used by the CS may be stale, despite us poking the TLB reset. If + * we hold the forcewake during initialisation these problems + * just magically go away. + */ + intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + ret = i915_gem_init_userptr(dev); if (ret) goto out_unlock; @@ -4903,6 +4917,7 @@ int i915_gem_init(struct drm_device *dev) } out_unlock: + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); mutex_unlock(&dev->struct_mutex); return ret; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index e730789b53b7..6d22128d97b1 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -37,6 +37,7 @@ #include <drm/i915_drm.h> #include "i915_drv.h" #include "i915_trace.h" +#include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_dp_helper.h> #include <drm/drm_crtc_helper.h> @@ -2416,6 +2417,14 @@ out_unref_obj: return false; } +/* Update plane->state->fb to match plane->fb after driver-internal updates */ +static void +update_state_fb(struct drm_plane *plane) +{ + if (plane->fb != plane->state->fb) + drm_atomic_set_fb_for_plane(plane->state, plane->fb); +} + static void intel_find_plane_obj(struct intel_crtc *intel_crtc, struct intel_initial_plane_config *plane_config) @@ -2462,6 +2471,8 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc, break; } } + + update_state_fb(intel_crtc->base.primary); } static void i9xx_update_primary_plane(struct drm_crtc *crtc, @@ -6602,6 +6613,10 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc, struct drm_framebuffer *fb; struct intel_framebuffer *intel_fb; + val = I915_READ(DSPCNTR(plane)); + if (!(val & DISPLAY_PLANE_ENABLE)) + return; + intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL); if (!intel_fb) { DRM_DEBUG_KMS("failed to alloc fb\n"); @@ -6610,8 +6625,6 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc, fb = &intel_fb->base; - val = I915_READ(DSPCNTR(plane)); - if (INTEL_INFO(dev)->gen >= 4) if (val & DISPPLANE_TILED) plane_config->tiling = I915_TILING_X; @@ -6650,6 +6663,7 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc, plane_config->size); crtc->base.primary->fb = fb; + update_state_fb(crtc->base.primary); } static void chv_crtc_clock_get(struct intel_crtc *crtc, @@ -7643,6 +7657,9 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc, fb = &intel_fb->base; val = I915_READ(PLANE_CTL(pipe, 0)); + if (!(val & PLANE_CTL_ENABLE)) + goto error; + if (val & PLANE_CTL_TILED_MASK) plane_config->tiling = I915_TILING_X; @@ -7687,6 +7704,7 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc, plane_config->size); crtc->base.primary->fb = fb; + update_state_fb(crtc->base.primary); return; error: @@ -7730,6 +7748,10 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc, struct drm_framebuffer *fb; struct intel_framebuffer *intel_fb; + val = I915_READ(DSPCNTR(pipe)); + if (!(val & DISPLAY_PLANE_ENABLE)) + return; + intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL); if (!intel_fb) { DRM_DEBUG_KMS("failed to alloc fb\n"); @@ -7738,8 +7760,6 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc, fb = &intel_fb->base; - val = I915_READ(DSPCNTR(pipe)); - if (INTEL_INFO(dev)->gen >= 4) if (val & DISPPLANE_TILED) plane_config->tiling = I915_TILING_X; @@ -7778,6 +7798,7 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc, plane_config->size); crtc->base.primary->fb = fb; + update_state_fb(crtc->base.primary); } static bool ironlake_get_pipe_config(struct intel_crtc *crtc, @@ -9716,7 +9737,7 @@ void intel_check_page_flip(struct drm_device *dev, int pipe) struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - WARN_ON(!in_irq()); + WARN_ON(!in_interrupt()); if (crtc == NULL) return; @@ -9816,6 +9837,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, drm_gem_object_reference(&obj->base); crtc->primary->fb = fb; + update_state_fb(crtc->primary); work->pending_flip_obj = obj; @@ -9884,6 +9906,7 @@ cleanup_unpin: cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); crtc->primary->fb = old_fb; + update_state_fb(crtc->primary); drm_gem_object_unreference(&work->old_fb_obj->base); drm_gem_object_unreference(&obj->base); mutex_unlock(&dev->struct_mutex); @@ -13718,6 +13741,7 @@ void intel_modeset_gem_init(struct drm_device *dev) to_intel_crtc(c)->pipe); drm_framebuffer_unreference(c->primary->fb); c->primary->fb = NULL; + update_state_fb(c->primary); } } mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index c47a3baa53d5..4e8fb891d4ea 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1048,8 +1048,14 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev) /* We need to init first for ECOBUS access and then * determine later if we want to reinit, in case of MT access is - * not working + * not working. In this stage we don't know which flavour this + * ivb is, so it is better to reset also the gen6 fw registers + * before the ecobus check. */ + + __raw_i915_write32(dev_priv, FORCEWAKE, 0); + __raw_posting_read(dev_priv, ECOBUS); + fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_MT, FORCEWAKE_MT_ACK); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 29bd539af183..6efa8f38ff54 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -340,11 +340,13 @@ nvkm_devobj_ctor(struct nvkm_object *parent, struct nvkm_object *engine, /* switch mmio to cpu's native endianness */ #ifndef __BIG_ENDIAN - if (ioread32_native(map + 0x000004) != 0x00000000) + if (ioread32_native(map + 0x000004) != 0x00000000) { #else - if (ioread32_native(map + 0x000004) == 0x00000000) + if (ioread32_native(map + 0x000004) == 0x00000000) { #endif iowrite32_native(0x01000001, map + 0x000004); + ioread32_native(map); + } /* read boot0 and strapping information */ boot0 = ioread32_native(map + 0x000000); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c index 539561ed3281..108d048da764 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c @@ -142,6 +142,49 @@ gm100_identify(struct nvkm_device *device) device->oclass[NVDEV_ENGINE_MSPPP ] = &gf100_msppp_oclass; #endif break; + case 0x126: + device->cname = "GM206"; + device->oclass[NVDEV_SUBDEV_VBIOS ] = &nvkm_bios_oclass; + device->oclass[NVDEV_SUBDEV_GPIO ] = gk104_gpio_oclass; + device->oclass[NVDEV_SUBDEV_I2C ] = gm204_i2c_oclass; + device->oclass[NVDEV_SUBDEV_FUSE ] = &gm107_fuse_oclass; +#if 0 + /* looks to be some non-trivial changes */ + device->oclass[NVDEV_SUBDEV_CLK ] = &gk104_clk_oclass; + /* priv ring says no to 0x10eb14 writes */ + device->oclass[NVDEV_SUBDEV_THERM ] = &gm107_therm_oclass; +#endif + device->oclass[NVDEV_SUBDEV_MXM ] = &nv50_mxm_oclass; + device->oclass[NVDEV_SUBDEV_DEVINIT] = gm204_devinit_oclass; + device->oclass[NVDEV_SUBDEV_MC ] = gk20a_mc_oclass; + device->oclass[NVDEV_SUBDEV_BUS ] = gf100_bus_oclass; + device->oclass[NVDEV_SUBDEV_TIMER ] = &gk20a_timer_oclass; + device->oclass[NVDEV_SUBDEV_FB ] = gm107_fb_oclass; + device->oclass[NVDEV_SUBDEV_LTC ] = gm107_ltc_oclass; + device->oclass[NVDEV_SUBDEV_IBUS ] = &gk104_ibus_oclass; + device->oclass[NVDEV_SUBDEV_INSTMEM] = nv50_instmem_oclass; + device->oclass[NVDEV_SUBDEV_MMU ] = &gf100_mmu_oclass; + device->oclass[NVDEV_SUBDEV_BAR ] = &gf100_bar_oclass; + device->oclass[NVDEV_SUBDEV_PMU ] = gk208_pmu_oclass; +#if 0 + device->oclass[NVDEV_SUBDEV_VOLT ] = &nv40_volt_oclass; +#endif + device->oclass[NVDEV_ENGINE_DMAOBJ ] = gf110_dmaeng_oclass; +#if 0 + device->oclass[NVDEV_ENGINE_FIFO ] = gk208_fifo_oclass; + device->oclass[NVDEV_ENGINE_SW ] = gf100_sw_oclass; + device->oclass[NVDEV_ENGINE_GR ] = gm107_gr_oclass; +#endif + device->oclass[NVDEV_ENGINE_DISP ] = gm204_disp_oclass; +#if 0 + device->oclass[NVDEV_ENGINE_CE0 ] = &gm204_ce0_oclass; + device->oclass[NVDEV_ENGINE_CE1 ] = &gm204_ce1_oclass; + device->oclass[NVDEV_ENGINE_CE2 ] = &gm204_ce2_oclass; + device->oclass[NVDEV_ENGINE_MSVLD ] = &gk104_msvld_oclass; + device->oclass[NVDEV_ENGINE_MSPDEC ] = &gk104_mspdec_oclass; + device->oclass[NVDEV_ENGINE_MSPPP ] = &gf100_msppp_oclass; +#endif + break; default: nv_fatal(device, "unknown Maxwell chipset\n"); return -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c index b038b6eb51db..043e4296084c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c @@ -502,72 +502,57 @@ nv04_fifo_intr(struct nvkm_subdev *subdev) { struct nvkm_device *device = nv_device(subdev); struct nv04_fifo_priv *priv = (void *)subdev; - uint32_t status, reassign; - int cnt = 0; + u32 mask = nv_rd32(priv, NV03_PFIFO_INTR_EN_0); + u32 stat = nv_rd32(priv, NV03_PFIFO_INTR_0) & mask; + u32 reassign, chid, get, sem; reassign = nv_rd32(priv, NV03_PFIFO_CACHES) & 1; - while ((status = nv_rd32(priv, NV03_PFIFO_INTR_0)) && (cnt++ < 100)) { - uint32_t chid, get; - - nv_wr32(priv, NV03_PFIFO_CACHES, 0); - - chid = nv_rd32(priv, NV03_PFIFO_CACHE1_PUSH1) & priv->base.max; - get = nv_rd32(priv, NV03_PFIFO_CACHE1_GET); + nv_wr32(priv, NV03_PFIFO_CACHES, 0); - if (status & NV_PFIFO_INTR_CACHE_ERROR) { - nv04_fifo_cache_error(device, priv, chid, get); - status &= ~NV_PFIFO_INTR_CACHE_ERROR; - } + chid = nv_rd32(priv, NV03_PFIFO_CACHE1_PUSH1) & priv->base.max; + get = nv_rd32(priv, NV03_PFIFO_CACHE1_GET); - if (status & NV_PFIFO_INTR_DMA_PUSHER) { - nv04_fifo_dma_pusher(device, priv, chid); - status &= ~NV_PFIFO_INTR_DMA_PUSHER; - } + if (stat & NV_PFIFO_INTR_CACHE_ERROR) { + nv04_fifo_cache_error(device, priv, chid, get); + stat &= ~NV_PFIFO_INTR_CACHE_ERROR; + } - if (status & NV_PFIFO_INTR_SEMAPHORE) { - uint32_t sem; + if (stat & NV_PFIFO_INTR_DMA_PUSHER) { + nv04_fifo_dma_pusher(device, priv, chid); + stat &= ~NV_PFIFO_INTR_DMA_PUSHER; + } - status &= ~NV_PFIFO_INTR_SEMAPHORE; - nv_wr32(priv, NV03_PFIFO_INTR_0, - NV_PFIFO_INTR_SEMAPHORE); + if (stat & NV_PFIFO_INTR_SEMAPHORE) { + stat &= ~NV_PFIFO_INTR_SEMAPHORE; + nv_wr32(priv, NV03_PFIFO_INTR_0, NV_PFIFO_INTR_SEMAPHORE); - sem = nv_rd32(priv, NV10_PFIFO_CACHE1_SEMAPHORE); - nv_wr32(priv, NV10_PFIFO_CACHE1_SEMAPHORE, sem | 0x1); + sem = nv_rd32(priv, NV10_PFIFO_CACHE1_SEMAPHORE); + nv_wr32(priv, NV10_PFIFO_CACHE1_SEMAPHORE, sem | 0x1); - nv_wr32(priv, NV03_PFIFO_CACHE1_GET, get + 4); - nv_wr32(priv, NV04_PFIFO_CACHE1_PULL0, 1); - } + nv_wr32(priv, NV03_PFIFO_CACHE1_GET, get + 4); + nv_wr32(priv, NV04_PFIFO_CACHE1_PULL0, 1); + } - if (device->card_type == NV_50) { - if (status & 0x00000010) { - status &= ~0x00000010; - nv_wr32(priv, 0x002100, 0x00000010); - } - - if (status & 0x40000000) { - nv_wr32(priv, 0x002100, 0x40000000); - nvkm_fifo_uevent(&priv->base); - status &= ~0x40000000; - } + if (device->card_type == NV_50) { + if (stat & 0x00000010) { + stat &= ~0x00000010; + nv_wr32(priv, 0x002100, 0x00000010); } - if (status) { - nv_warn(priv, "unknown intr 0x%08x, ch %d\n", - status, chid); - nv_wr32(priv, NV03_PFIFO_INTR_0, status); - status = 0; + if (stat & 0x40000000) { + nv_wr32(priv, 0x002100, 0x40000000); + nvkm_fifo_uevent(&priv->base); + stat &= ~0x40000000; } - - nv_wr32(priv, NV03_PFIFO_CACHES, reassign); } - if (status) { - nv_error(priv, "still angry after %d spins, halt\n", cnt); - nv_wr32(priv, 0x002140, 0); - nv_wr32(priv, 0x000140, 0); + if (stat) { + nv_warn(priv, "unknown intr 0x%08x\n", stat); + nv_mask(priv, NV03_PFIFO_INTR_EN_0, stat, 0x00000000); + nv_wr32(priv, NV03_PFIFO_INTR_0, stat); } - nv_wr32(priv, 0x000100, 0x00000100); + nv_wr32(priv, NV03_PFIFO_CACHES, reassign); } static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c index 2e7ec389eea7..57e2c5b13123 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c @@ -1032,9 +1032,9 @@ gf100_grctx_generate_bundle(struct gf100_grctx *info) const int s = 8; const int b = mmio_vram(info, impl->bundle_size, (1 << s), access); mmio_refn(info, 0x408004, 0x00000000, s, b); - mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b); + mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s)); mmio_refn(info, 0x418808, 0x00000000, s, b); - mmio_refn(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s), 0, b); + mmio_wr32(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s)); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c index b52300d8861a..5e9454ba158f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c @@ -851,9 +851,9 @@ gk104_grctx_generate_bundle(struct gf100_grctx *info) const int s = 8; const int b = mmio_vram(info, impl->bundle_size, (1 << s), access); mmio_refn(info, 0x408004, 0x00000000, s, b); - mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b); + mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s)); mmio_refn(info, 0x418808, 0x00000000, s, b); - mmio_refn(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s), 0, b); + mmio_wr32(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s)); mmio_wr32(info, 0x4064c8, (state_limit << 16) | token_limit); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c index 956f4dce960c..b2fae6e389e2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c @@ -871,9 +871,9 @@ gm107_grctx_generate_bundle(struct gf100_grctx *info) const int s = 8; const int b = mmio_vram(info, impl->bundle_size, (1 << s), access); mmio_refn(info, 0x408004, 0x00000000, s, b); - mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b); + mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s)); mmio_refn(info, 0x418e24, 0x00000000, s, b); - mmio_refn(info, 0x418e28, 0x80000000 | (impl->bundle_size >> s), 0, b); + mmio_wr32(info, 0x418e28, 0x80000000 | (impl->bundle_size >> s)); mmio_wr32(info, 0x4064c8, (state_limit << 16) | token_limit); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c index d1a89b2bd5c1..c4e1f085ee10 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c @@ -74,7 +74,11 @@ dcb_i2c_parse(struct nvkm_bios *bios, u8 idx, struct dcb_i2c_entry *info) u16 ent = dcb_i2c_entry(bios, idx, &ver, &len); if (ent) { if (ver >= 0x41) { - if (!(nv_ro32(bios, ent) & 0x80000000)) + u32 ent_value = nv_ro32(bios, ent); + u8 i2c_port = (ent_value >> 27) & 0x1f; + u8 dpaux_port = (ent_value >> 22) & 0x1f; + /* value 0x1f means unused according to DCB 4.x spec */ + if (i2c_port == 0x1f && dpaux_port == 0x1f) info->type = DCB_I2C_UNUSED; else info->type = DCB_I2C_PMGR; diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index d13d1b5a859f..df09ca7c4889 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -1030,37 +1030,59 @@ static inline bool radeon_test_signaled(struct radeon_fence *fence) return test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags); } +struct radeon_wait_cb { + struct fence_cb base; + struct task_struct *task; +}; + +static void +radeon_fence_wait_cb(struct fence *fence, struct fence_cb *cb) +{ + struct radeon_wait_cb *wait = + container_of(cb, struct radeon_wait_cb, base); + + wake_up_process(wait->task); +} + static signed long radeon_fence_default_wait(struct fence *f, bool intr, signed long t) { struct radeon_fence *fence = to_radeon_fence(f); struct radeon_device *rdev = fence->rdev; - bool signaled; + struct radeon_wait_cb cb; - fence_enable_sw_signaling(&fence->base); + cb.task = current; - /* - * This function has to return -EDEADLK, but cannot hold - * exclusive_lock during the wait because some callers - * may already hold it. This means checking needs_reset without - * lock, and not fiddling with any gpu internals. - * - * The callback installed with fence_enable_sw_signaling will - * run before our wait_event_*timeout call, so we will see - * both the signaled fence and the changes to needs_reset. - */ + if (fence_add_callback(f, &cb.base, radeon_fence_wait_cb)) + return t; + + while (t > 0) { + if (intr) + set_current_state(TASK_INTERRUPTIBLE); + else + set_current_state(TASK_UNINTERRUPTIBLE); + + /* + * radeon_test_signaled must be called after + * set_current_state to prevent a race with wake_up_process + */ + if (radeon_test_signaled(fence)) + break; + + if (rdev->needs_reset) { + t = -EDEADLK; + break; + } + + t = schedule_timeout(t); + + if (t > 0 && intr && signal_pending(current)) + t = -ERESTARTSYS; + } + + __set_current_state(TASK_RUNNING); + fence_remove_callback(f, &cb.base); - if (intr) - t = wait_event_interruptible_timeout(rdev->fence_queue, - ((signaled = radeon_test_signaled(fence)) || - rdev->needs_reset), t); - else - t = wait_event_timeout(rdev->fence_queue, - ((signaled = radeon_test_signaled(fence)) || - rdev->needs_reset), t); - - if (t > 0 && !signaled) - return -EDEADLK; return t; } diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c index 061eaa9c19c7..122eb5693ba1 100644 --- a/drivers/gpu/drm/radeon/radeon_kfd.c +++ b/drivers/gpu/drm/radeon/radeon_kfd.c @@ -153,7 +153,7 @@ void radeon_kfd_device_init(struct radeon_device *rdev) .compute_vmid_bitmap = 0xFF00, .first_compute_pipe = 1, - .compute_pipe_count = 8 - 1, + .compute_pipe_count = 4 - 1, }; radeon_doorbell_get_kfd_info(rdev, diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 43e09942823e..318165d4855c 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -173,17 +173,6 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain) else rbo->placements[i].lpfn = 0; } - - /* - * Use two-ended allocation depending on the buffer size to - * improve fragmentation quality. - * 512kb was measured as the most optimal number. - */ - if (rbo->tbo.mem.size > 512 * 1024) { - for (i = 0; i < c; i++) { - rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN; - } - } } int radeon_bo_create(struct radeon_device *rdev, diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index e088e5558da0..a7fb2735d4a9 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -7130,8 +7130,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~UPLL_BYPASS_EN_MASK); if (!vclk || !dclk) { - /* keep the Bypass mode, put PLL to sleep */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* keep the Bypass mode */ return 0; } @@ -7147,8 +7146,7 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk) /* set VCO_MODE to 1 */ WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_VCO_MODE_MASK, ~UPLL_VCO_MODE_MASK); - /* toggle UPLL_SLEEP to 1 then back to 0 */ - WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK); + /* disable sleep mode */ WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_SLEEP_MASK); /* deassert UPLL_RESET */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 6c6b655defcf..e13b9cbc304e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -725,32 +725,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_err1; } - ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, - (dev_priv->vram_size >> PAGE_SHIFT)); - if (unlikely(ret != 0)) { - DRM_ERROR("Failed initializing memory manager for VRAM.\n"); - goto out_err2; - } - - dev_priv->has_gmr = true; - if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || - refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, - VMW_PL_GMR) != 0) { - DRM_INFO("No GMR memory available. " - "Graphics memory resources are very limited.\n"); - dev_priv->has_gmr = false; - } - - if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { - dev_priv->has_mob = true; - if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, - VMW_PL_MOB) != 0) { - DRM_INFO("No MOB memory available. " - "3D will be disabled.\n"); - dev_priv->has_mob = false; - } - } - dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start, dev_priv->mmio_size); @@ -813,6 +787,33 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) goto out_no_fman; } + + ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM, + (dev_priv->vram_size >> PAGE_SHIFT)); + if (unlikely(ret != 0)) { + DRM_ERROR("Failed initializing memory manager for VRAM.\n"); + goto out_no_vram; + } + + dev_priv->has_gmr = true; + if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) || + refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR, + VMW_PL_GMR) != 0) { + DRM_INFO("No GMR memory available. " + "Graphics memory resources are very limited.\n"); + dev_priv->has_gmr = false; + } + + if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { + dev_priv->has_mob = true; + if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB, + VMW_PL_MOB) != 0) { + DRM_INFO("No MOB memory available. " + "3D will be disabled.\n"); + dev_priv->has_mob = false; + } + } + vmw_kms_save_vga(dev_priv); /* Start kms and overlay systems, needs fifo. */ @@ -838,6 +839,12 @@ out_no_fifo: vmw_kms_close(dev_priv); out_no_kms: vmw_kms_restore_vga(dev_priv); + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); +out_no_vram: vmw_fence_manager_takedown(dev_priv->fman); out_no_fman: if (dev_priv->capabilities & SVGA_CAP_IRQMASK) @@ -853,12 +860,6 @@ out_err4: iounmap(dev_priv->mmio_virt); out_err3: arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); -out_err2: (void)ttm_bo_device_release(&dev_priv->bdev); out_err1: vmw_ttm_global_release(dev_priv); @@ -887,6 +888,13 @@ static int vmw_driver_unload(struct drm_device *dev) } vmw_kms_close(dev_priv); vmw_overlay_close(dev_priv); + + if (dev_priv->has_mob) + (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); + if (dev_priv->has_gmr) + (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); + (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); + vmw_fence_manager_takedown(dev_priv->fman); if (dev_priv->capabilities & SVGA_CAP_IRQMASK) drm_irq_uninstall(dev_priv->dev); @@ -898,11 +906,6 @@ static int vmw_driver_unload(struct drm_device *dev) ttm_object_device_release(&dev_priv->tdev); iounmap(dev_priv->mmio_virt); arch_phys_wc_del(dev_priv->mmio_mtrr); - if (dev_priv->has_mob) - (void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB); - if (dev_priv->has_gmr) - (void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR); - (void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM); (void)ttm_bo_device_release(&dev_priv->bdev); vmw_ttm_global_release(dev_priv); @@ -1235,6 +1238,7 @@ static void vmw_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); + pci_disable_device(pdev); drm_put_dev(dev); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 33176d05db35..654c8daeb5ab 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -890,7 +890,8 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo); if (unlikely(ret != 0)) { DRM_ERROR("Could not find or use MOB buffer.\n"); - return -EINVAL; + ret = -EINVAL; + goto out_no_reloc; } bo = &vmw_bo->base; @@ -914,7 +915,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, out_no_reloc: vmw_dmabuf_unreference(&vmw_bo); - vmw_bo_p = NULL; + *vmw_bo_p = NULL; return ret; } @@ -951,7 +952,8 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo); if (unlikely(ret != 0)) { DRM_ERROR("Could not find or use GMR region.\n"); - return -EINVAL; + ret = -EINVAL; + goto out_no_reloc; } bo = &vmw_bo->base; @@ -974,7 +976,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, out_no_reloc: vmw_dmabuf_unreference(&vmw_bo); - vmw_bo_p = NULL; + *vmw_bo_p = NULL; return ret; } @@ -2780,13 +2782,11 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data, NULL, arg->command_size, arg->throttle_us, (void __user *)(unsigned long)arg->fence_rep, NULL); - + ttm_read_unlock(&dev_priv->reservation_sem); if (unlikely(ret != 0)) - goto out_unlock; + return ret; vmw_kms_cursor_post_execbuf(dev_priv); -out_unlock: - ttm_read_unlock(&dev_priv->reservation_sem); - return ret; + return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 8725b79e7847..07cda8cbbddb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -2033,23 +2033,17 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, int i; struct drm_mode_config *mode_config = &dev->mode_config; - ret = ttm_read_lock(&dev_priv->reservation_sem, true); - if (unlikely(ret != 0)) - return ret; - if (!arg->num_outputs) { struct drm_vmw_rect def_rect = {0, 0, 800, 600}; vmw_du_update_layout(dev_priv, 1, &def_rect); - goto out_unlock; + return 0; } rects_size = arg->num_outputs * sizeof(struct drm_vmw_rect); rects = kcalloc(arg->num_outputs, sizeof(struct drm_vmw_rect), GFP_KERNEL); - if (unlikely(!rects)) { - ret = -ENOMEM; - goto out_unlock; - } + if (unlikely(!rects)) + return -ENOMEM; user_rects = (void __user *)(unsigned long)arg->rects; ret = copy_from_user(rects, user_rects, rects_size); @@ -2074,7 +2068,5 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, out_free: kfree(rects); -out_unlock: - ttm_read_unlock(&dev_priv->reservation_sem); return ret; } diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 7c669c328c4c..56ce8c2b5530 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1959,6 +1959,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb65a) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_BT) }, { HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE) }, + { HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_PRO) }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPSEED, USB_DEVICE_ID_TOPSEED_CYBERLINK) }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPSEED2, USB_DEVICE_ID_TOPSEED2_RF_COMBO) }, { HID_USB_DEVICE(USB_VENDOR_ID_TWINHAN, USB_DEVICE_ID_TWINHAN_IR_REMOTE) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 204312bfab2c..9c4786759f16 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -586,6 +586,7 @@ #define USB_VENDOR_ID_LOGITECH 0x046d #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e #define USB_DEVICE_ID_LOGITECH_T651 0xb00c +#define USB_DEVICE_ID_LOGITECH_C077 0xc007 #define USB_DEVICE_ID_LOGITECH_RECEIVER 0xc101 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST 0xc110 #define USB_DEVICE_ID_LOGITECH_HARMONY_LAST 0xc14f @@ -898,6 +899,7 @@ #define USB_VENDOR_ID_TIVO 0x150a #define USB_DEVICE_ID_TIVO_SLIDE_BT 0x1200 #define USB_DEVICE_ID_TIVO_SLIDE 0x1201 +#define USB_DEVICE_ID_TIVO_SLIDE_PRO 0x1203 #define USB_VENDOR_ID_TOPSEED 0x0766 #define USB_DEVICE_ID_TOPSEED_CYBERLINK 0x0204 diff --git a/drivers/hid/hid-tivo.c b/drivers/hid/hid-tivo.c index d790d8d71f7f..d98696927453 100644 --- a/drivers/hid/hid-tivo.c +++ b/drivers/hid/hid-tivo.c @@ -64,6 +64,7 @@ static const struct hid_device_id tivo_devices[] = { /* TiVo Slide Bluetooth remote, pairs with a Broadcom dongle */ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_BT) }, { HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE) }, + { HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_PRO) }, { } }; MODULE_DEVICE_TABLE(hid, tivo_devices); diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 9be99a67bfe2..a82127753461 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -78,6 +78,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET }, { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET }, { USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP, HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 046351cf17f3..bbe32d66e500 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -551,9 +551,13 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) (features->type == CINTIQ && !(data[1] & 0x40))) return 1; - if (features->quirks & WACOM_QUIRK_MULTI_INPUT) + if (wacom->shared) { wacom->shared->stylus_in_proximity = true; + if (wacom->shared->touch_down) + return 1; + } + /* in Range while exiting */ if (((data[1] & 0xfe) == 0x20) && wacom->reporting_data) { input_report_key(input, BTN_TOUCH, 0); @@ -1043,27 +1047,28 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom) struct input_dev *input = wacom->input; unsigned char *data = wacom->data; int i; - int current_num_contacts = 0; + int current_num_contacts = data[61]; int contacts_to_send = 0; int num_contacts_left = 4; /* maximum contacts per packet */ int byte_per_packet = WACOM_BYTES_PER_24HDT_PACKET; int y_offset = 2; + static int contact_with_no_pen_down_count = 0; if (wacom->features.type == WACOM_27QHDT) { current_num_contacts = data[63]; num_contacts_left = 10; byte_per_packet = WACOM_BYTES_PER_QHDTHID_PACKET; y_offset = 0; - } else { - current_num_contacts = data[61]; } /* * First packet resets the counter since only the first * packet in series will have non-zero current_num_contacts. */ - if (current_num_contacts) + if (current_num_contacts) { wacom->num_contacts_left = current_num_contacts; + contact_with_no_pen_down_count = 0; + } contacts_to_send = min(num_contacts_left, wacom->num_contacts_left); @@ -1096,15 +1101,16 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom) input_report_abs(input, ABS_MT_WIDTH_MINOR, min(w, h)); input_report_abs(input, ABS_MT_ORIENTATION, w > h); } + contact_with_no_pen_down_count++; } } input_mt_report_pointer_emulation(input, true); wacom->num_contacts_left -= contacts_to_send; - if (wacom->num_contacts_left <= 0) + if (wacom->num_contacts_left <= 0) { wacom->num_contacts_left = 0; - - wacom->shared->touch_down = (wacom->num_contacts_left > 0); + wacom->shared->touch_down = (contact_with_no_pen_down_count > 0); + } return 1; } @@ -1116,6 +1122,7 @@ static int wacom_mt_touch(struct wacom_wac *wacom) int current_num_contacts = data[2]; int contacts_to_send = 0; int x_offset = 0; + static int contact_with_no_pen_down_count = 0; /* MTTPC does not support Height and Width */ if (wacom->features.type == MTTPC || wacom->features.type == MTTPC_B) @@ -1125,8 +1132,10 @@ static int wacom_mt_touch(struct wacom_wac *wacom) * First packet resets the counter since only the first * packet in series will have non-zero current_num_contacts. */ - if (current_num_contacts) + if (current_num_contacts) { wacom->num_contacts_left = current_num_contacts; + contact_with_no_pen_down_count = 0; + } /* There are at most 5 contacts per packet */ contacts_to_send = min(5, wacom->num_contacts_left); @@ -1147,15 +1156,16 @@ static int wacom_mt_touch(struct wacom_wac *wacom) int y = get_unaligned_le16(&data[offset + x_offset + 9]); input_report_abs(input, ABS_MT_POSITION_X, x); input_report_abs(input, ABS_MT_POSITION_Y, y); + contact_with_no_pen_down_count++; } } input_mt_report_pointer_emulation(input, true); wacom->num_contacts_left -= contacts_to_send; - if (wacom->num_contacts_left < 0) + if (wacom->num_contacts_left <= 0) { wacom->num_contacts_left = 0; - - wacom->shared->touch_down = (wacom->num_contacts_left > 0); + wacom->shared->touch_down = (contact_with_no_pen_down_count > 0); + } return 1; } @@ -1193,29 +1203,25 @@ static int wacom_tpc_single_touch(struct wacom_wac *wacom, size_t len) { unsigned char *data = wacom->data; struct input_dev *input = wacom->input; - bool prox; + bool prox = !wacom->shared->stylus_in_proximity; int x = 0, y = 0; if (wacom->features.touch_max > 1 || len > WACOM_PKGLEN_TPC2FG) return 0; - if (!wacom->shared->stylus_in_proximity) { - if (len == WACOM_PKGLEN_TPC1FG) { - prox = data[0] & 0x01; - x = get_unaligned_le16(&data[1]); - y = get_unaligned_le16(&data[3]); - } else if (len == WACOM_PKGLEN_TPC1FG_B) { - prox = data[2] & 0x01; - x = get_unaligned_le16(&data[3]); - y = get_unaligned_le16(&data[5]); - } else { - prox = data[1] & 0x01; - x = le16_to_cpup((__le16 *)&data[2]); - y = le16_to_cpup((__le16 *)&data[4]); - } - } else - /* force touch out when pen is in prox */ - prox = 0; + if (len == WACOM_PKGLEN_TPC1FG) { + prox = prox && (data[0] & 0x01); + x = get_unaligned_le16(&data[1]); + y = get_unaligned_le16(&data[3]); + } else if (len == WACOM_PKGLEN_TPC1FG_B) { + prox = prox && (data[2] & 0x01); + x = get_unaligned_le16(&data[3]); + y = get_unaligned_le16(&data[5]); + } else { + prox = prox && (data[1] & 0x01); + x = le16_to_cpup((__le16 *)&data[2]); + y = le16_to_cpup((__le16 *)&data[4]); + } if (prox) { input_report_abs(input, ABS_X, x); @@ -1613,6 +1619,7 @@ static int wacom_bpt_touch(struct wacom_wac *wacom) struct input_dev *pad_input = wacom->pad_input; unsigned char *data = wacom->data; int i; + int contact_with_no_pen_down_count = 0; if (data[0] != 0x02) return 0; @@ -1640,6 +1647,7 @@ static int wacom_bpt_touch(struct wacom_wac *wacom) } input_report_abs(input, ABS_MT_POSITION_X, x); input_report_abs(input, ABS_MT_POSITION_Y, y); + contact_with_no_pen_down_count++; } } @@ -1649,11 +1657,12 @@ static int wacom_bpt_touch(struct wacom_wac *wacom) input_report_key(pad_input, BTN_FORWARD, (data[1] & 0x04) != 0); input_report_key(pad_input, BTN_BACK, (data[1] & 0x02) != 0); input_report_key(pad_input, BTN_RIGHT, (data[1] & 0x01) != 0); + wacom->shared->touch_down = (contact_with_no_pen_down_count > 0); return 1; } -static void wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data) +static int wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data, int last_touch_count) { struct wacom_features *features = &wacom->features; struct input_dev *input = wacom->input; @@ -1661,7 +1670,7 @@ static void wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data) int slot = input_mt_get_slot_by_key(input, data[0]); if (slot < 0) - return; + return 0; touch = touch && !wacom->shared->stylus_in_proximity; @@ -1693,7 +1702,9 @@ static void wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data) input_report_abs(input, ABS_MT_POSITION_Y, y); input_report_abs(input, ABS_MT_TOUCH_MAJOR, width); input_report_abs(input, ABS_MT_TOUCH_MINOR, height); + last_touch_count++; } + return last_touch_count; } static void wacom_bpt3_button_msg(struct wacom_wac *wacom, unsigned char *data) @@ -1718,6 +1729,7 @@ static int wacom_bpt3_touch(struct wacom_wac *wacom) unsigned char *data = wacom->data; int count = data[1] & 0x07; int i; + int contact_with_no_pen_down_count = 0; if (data[0] != 0x02) return 0; @@ -1728,12 +1740,15 @@ static int wacom_bpt3_touch(struct wacom_wac *wacom) int msg_id = data[offset]; if (msg_id >= 2 && msg_id <= 17) - wacom_bpt3_touch_msg(wacom, data + offset); + contact_with_no_pen_down_count = + wacom_bpt3_touch_msg(wacom, data + offset, + contact_with_no_pen_down_count); else if (msg_id == 128) wacom_bpt3_button_msg(wacom, data + offset); } input_mt_report_pointer_emulation(input, true); + wacom->shared->touch_down = (contact_with_no_pen_down_count > 0); return 1; } @@ -1759,6 +1774,9 @@ static int wacom_bpt_pen(struct wacom_wac *wacom) return 0; } + if (wacom->shared->touch_down) + return 0; + prox = (data[1] & 0x20) == 0x20; /* diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 210cf4874cb7..edf274cabe81 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -679,9 +679,6 @@ static int i2c_device_remove(struct device *dev) status = driver->remove(client); } - if (dev->of_node) - irq_dispose_mapping(client->irq); - dev_pm_domain_detach(&client->dev, true); return status; } diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index 1793aea4a7d2..6eb738ca6d2f 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -1793,11 +1793,11 @@ static void idetape_setup(ide_drive_t *drive, idetape_tape_t *tape, int minor) tape->best_dsc_rw_freq = clamp_t(unsigned long, t, IDETAPE_DSC_RW_MIN, IDETAPE_DSC_RW_MAX); printk(KERN_INFO "ide-tape: %s <-> %s: %dKBps, %d*%dkB buffer, " - "%lums tDSC%s\n", + "%ums tDSC%s\n", drive->name, tape->name, *(u16 *)&tape->caps[14], (*(u16 *)&tape->caps[16] * 512) / tape->buffer_size, tape->buffer_size / 1024, - tape->best_dsc_rw_freq * 1000 / HZ, + jiffies_to_msecs(tape->best_dsc_rw_freq), (drive->dev_flags & IDE_DFLAG_USING_DMA) ? ", DMA" : ""); ide_proc_register_driver(drive, tape->driver); diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index c7619716c31d..59040265e361 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -64,6 +64,14 @@ enum { #define GUID_TBL_BLK_NUM_ENTRIES 8 #define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES) +/* Counters should be saturate once they reach their maximum value */ +#define ASSIGN_32BIT_COUNTER(counter, value) do {\ + if ((value) > U32_MAX) \ + counter = cpu_to_be32(U32_MAX); \ + else \ + counter = cpu_to_be32(value); \ +} while (0) + struct mlx4_mad_rcv_buf { struct ib_grh grh; u8 payload[256]; @@ -806,10 +814,14 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, static void edit_counter(struct mlx4_counter *cnt, struct ib_pma_portcounters *pma_cnt) { - pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2)); - pma_cnt->port_rcv_data = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2)); - pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames)); - pma_cnt->port_rcv_packets = cpu_to_be32(be64_to_cpu(cnt->rx_frames)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data, + (be64_to_cpu(cnt->tx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data, + (be64_to_cpu(cnt->rx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets, + be64_to_cpu(cnt->tx_frames)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets, + be64_to_cpu(cnt->rx_frames)); } static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index ac6e2b710ea6..b972c0b41799 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2697,8 +2697,12 @@ static void handle_bonded_port_state_event(struct work_struct *work) spin_lock_bh(&ibdev->iboe.lock); for (i = 0; i < MLX4_MAX_PORTS; ++i) { struct net_device *curr_netdev = ibdev->iboe.netdevs[i]; + enum ib_port_state curr_port_state; - enum ib_port_state curr_port_state = + if (!curr_netdev) + continue; + + curr_port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index f2cceb6493a0..dda605836546 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -67,9 +67,6 @@ #define X_MAX_POSITIVE 8176 #define Y_MAX_POSITIVE 8176 -/* maximum ABS_MT_POSITION displacement (in mm) */ -#define DMAX 10 - /***************************************************************************** * Stuff we need even when we do not want native Synaptics support ****************************************************************************/ @@ -123,32 +120,41 @@ void synaptics_reset(struct psmouse *psmouse) static bool cr48_profile_sensor; +#define ANY_BOARD_ID 0 struct min_max_quirk { const char * const *pnp_ids; + struct { + unsigned long int min, max; + } board_id; int x_min, x_max, y_min, y_max; }; static const struct min_max_quirk min_max_pnpid_table[] = { { (const char * const []){"LEN0033", NULL}, + {ANY_BOARD_ID, ANY_BOARD_ID}, 1024, 5052, 2258, 4832 }, { - (const char * const []){"LEN0035", "LEN0042", NULL}, + (const char * const []){"LEN0042", NULL}, + {ANY_BOARD_ID, ANY_BOARD_ID}, 1232, 5710, 1156, 4696 }, { (const char * const []){"LEN0034", "LEN0036", "LEN0037", "LEN0039", "LEN2002", "LEN2004", NULL}, + {ANY_BOARD_ID, 2961}, 1024, 5112, 2024, 4832 }, { (const char * const []){"LEN2001", NULL}, + {ANY_BOARD_ID, ANY_BOARD_ID}, 1024, 5022, 2508, 4832 }, { (const char * const []){"LEN2006", NULL}, + {ANY_BOARD_ID, ANY_BOARD_ID}, 1264, 5675, 1171, 4688 }, { } @@ -175,9 +181,7 @@ static const char * const topbuttonpad_pnp_ids[] = { "LEN0041", "LEN0042", /* Yoga */ "LEN0045", - "LEN0046", "LEN0047", - "LEN0048", "LEN0049", "LEN2000", "LEN2001", /* Edge E431 */ @@ -235,18 +239,39 @@ static int synaptics_model_id(struct psmouse *psmouse) return 0; } +static int synaptics_more_extended_queries(struct psmouse *psmouse) +{ + struct synaptics_data *priv = psmouse->private; + unsigned char buf[3]; + + if (synaptics_send_cmd(psmouse, SYN_QUE_MEXT_CAPAB_10, buf)) + return -1; + + priv->ext_cap_10 = (buf[0]<<16) | (buf[1]<<8) | buf[2]; + + return 0; +} + /* - * Read the board id from the touchpad + * Read the board id and the "More Extended Queries" from the touchpad * The board id is encoded in the "QUERY MODES" response */ -static int synaptics_board_id(struct psmouse *psmouse) +static int synaptics_query_modes(struct psmouse *psmouse) { struct synaptics_data *priv = psmouse->private; unsigned char bid[3]; + /* firmwares prior 7.5 have no board_id encoded */ + if (SYN_ID_FULL(priv->identity) < 0x705) + return 0; + if (synaptics_send_cmd(psmouse, SYN_QUE_MODES, bid)) return -1; priv->board_id = ((bid[0] & 0xfc) << 6) | bid[1]; + + if (SYN_MEXT_CAP_BIT(bid[0])) + return synaptics_more_extended_queries(psmouse); + return 0; } @@ -346,7 +371,6 @@ static int synaptics_resolution(struct psmouse *psmouse) { struct synaptics_data *priv = psmouse->private; unsigned char resp[3]; - int i; if (SYN_ID_MAJOR(priv->identity) < 4) return 0; @@ -358,17 +382,6 @@ static int synaptics_resolution(struct psmouse *psmouse) } } - for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) { - if (psmouse_matches_pnp_id(psmouse, - min_max_pnpid_table[i].pnp_ids)) { - priv->x_min = min_max_pnpid_table[i].x_min; - priv->x_max = min_max_pnpid_table[i].x_max; - priv->y_min = min_max_pnpid_table[i].y_min; - priv->y_max = min_max_pnpid_table[i].y_max; - return 0; - } - } - if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 5 && SYN_CAP_MAX_DIMENSIONS(priv->ext_cap_0c)) { if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MAX_COORDS, resp)) { @@ -377,23 +390,69 @@ static int synaptics_resolution(struct psmouse *psmouse) } else { priv->x_max = (resp[0] << 5) | ((resp[1] & 0x0f) << 1); priv->y_max = (resp[2] << 5) | ((resp[1] & 0xf0) >> 3); + psmouse_info(psmouse, + "queried max coordinates: x [..%d], y [..%d]\n", + priv->x_max, priv->y_max); } } - if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 7 && - SYN_CAP_MIN_DIMENSIONS(priv->ext_cap_0c)) { + if (SYN_CAP_MIN_DIMENSIONS(priv->ext_cap_0c) && + (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 7 || + /* + * Firmware v8.1 does not report proper number of extended + * capabilities, but has been proven to report correct min + * coordinates. + */ + SYN_ID_FULL(priv->identity) == 0x801)) { if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MIN_COORDS, resp)) { psmouse_warn(psmouse, "device claims to have min coordinates query, but I'm not able to read it.\n"); } else { priv->x_min = (resp[0] << 5) | ((resp[1] & 0x0f) << 1); priv->y_min = (resp[2] << 5) | ((resp[1] & 0xf0) >> 3); + psmouse_info(psmouse, + "queried min coordinates: x [%d..], y [%d..]\n", + priv->x_min, priv->y_min); } } return 0; } +/* + * Apply quirk(s) if the hardware matches + */ + +static void synaptics_apply_quirks(struct psmouse *psmouse) +{ + struct synaptics_data *priv = psmouse->private; + int i; + + for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) { + if (!psmouse_matches_pnp_id(psmouse, + min_max_pnpid_table[i].pnp_ids)) + continue; + + if (min_max_pnpid_table[i].board_id.min != ANY_BOARD_ID && + priv->board_id < min_max_pnpid_table[i].board_id.min) + continue; + + if (min_max_pnpid_table[i].board_id.max != ANY_BOARD_ID && + priv->board_id > min_max_pnpid_table[i].board_id.max) + continue; + + priv->x_min = min_max_pnpid_table[i].x_min; + priv->x_max = min_max_pnpid_table[i].x_max; + priv->y_min = min_max_pnpid_table[i].y_min; + priv->y_max = min_max_pnpid_table[i].y_max; + psmouse_info(psmouse, + "quirked min/max coordinates: x [%d..%d], y [%d..%d]\n", + priv->x_min, priv->x_max, + priv->y_min, priv->y_max); + break; + } +} + static int synaptics_query_hardware(struct psmouse *psmouse) { if (synaptics_identify(psmouse)) @@ -402,13 +461,15 @@ static int synaptics_query_hardware(struct psmouse *psmouse) return -1; if (synaptics_firmware_id(psmouse)) return -1; - if (synaptics_board_id(psmouse)) + if (synaptics_query_modes(psmouse)) return -1; if (synaptics_capability(psmouse)) return -1; if (synaptics_resolution(psmouse)) return -1; + synaptics_apply_quirks(psmouse); + return 0; } @@ -516,18 +577,22 @@ static int synaptics_is_pt_packet(unsigned char *buf) return (buf[0] & 0xFC) == 0x84 && (buf[3] & 0xCC) == 0xC4; } -static void synaptics_pass_pt_packet(struct serio *ptport, unsigned char *packet) +static void synaptics_pass_pt_packet(struct psmouse *psmouse, + struct serio *ptport, + unsigned char *packet) { + struct synaptics_data *priv = psmouse->private; struct psmouse *child = serio_get_drvdata(ptport); if (child && child->state == PSMOUSE_ACTIVATED) { - serio_interrupt(ptport, packet[1], 0); + serio_interrupt(ptport, packet[1] | priv->pt_buttons, 0); serio_interrupt(ptport, packet[4], 0); serio_interrupt(ptport, packet[5], 0); if (child->pktsize == 4) serio_interrupt(ptport, packet[2], 0); - } else + } else { serio_interrupt(ptport, packet[1], 0); + } } static void synaptics_pt_activate(struct psmouse *psmouse) @@ -605,6 +670,18 @@ static void synaptics_parse_agm(const unsigned char buf[], } } +static void synaptics_parse_ext_buttons(const unsigned char buf[], + struct synaptics_data *priv, + struct synaptics_hw_state *hw) +{ + unsigned int ext_bits = + (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) + 1) >> 1; + unsigned int ext_mask = GENMASK(ext_bits - 1, 0); + + hw->ext_buttons = buf[4] & ext_mask; + hw->ext_buttons |= (buf[5] & ext_mask) << ext_bits; +} + static bool is_forcepad; static int synaptics_parse_hw_state(const unsigned char buf[], @@ -691,28 +768,9 @@ static int synaptics_parse_hw_state(const unsigned char buf[], hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0; } - if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) && + if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) > 0 && ((buf[0] ^ buf[3]) & 0x02)) { - switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) { - default: - /* - * if nExtBtn is greater than 8 it should be - * considered invalid and treated as 0 - */ - break; - case 8: - hw->ext_buttons |= ((buf[5] & 0x08)) ? 0x80 : 0; - hw->ext_buttons |= ((buf[4] & 0x08)) ? 0x40 : 0; - case 6: - hw->ext_buttons |= ((buf[5] & 0x04)) ? 0x20 : 0; - hw->ext_buttons |= ((buf[4] & 0x04)) ? 0x10 : 0; - case 4: - hw->ext_buttons |= ((buf[5] & 0x02)) ? 0x08 : 0; - hw->ext_buttons |= ((buf[4] & 0x02)) ? 0x04 : 0; - case 2: - hw->ext_buttons |= ((buf[5] & 0x01)) ? 0x02 : 0; - hw->ext_buttons |= ((buf[4] & 0x01)) ? 0x01 : 0; - } + synaptics_parse_ext_buttons(buf, priv, hw); } } else { hw->x = (((buf[1] & 0x1f) << 8) | buf[2]); @@ -774,12 +832,54 @@ static void synaptics_report_semi_mt_data(struct input_dev *dev, } } +static void synaptics_report_ext_buttons(struct psmouse *psmouse, + const struct synaptics_hw_state *hw) +{ + struct input_dev *dev = psmouse->dev; + struct synaptics_data *priv = psmouse->private; + int ext_bits = (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) + 1) >> 1; + char buf[6] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + int i; + + if (!SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap)) + return; + + /* Bug in FW 8.1, buttons are reported only when ExtBit is 1 */ + if (SYN_ID_FULL(priv->identity) == 0x801 && + !((psmouse->packet[0] ^ psmouse->packet[3]) & 0x02)) + return; + + if (!SYN_CAP_EXT_BUTTONS_STICK(priv->ext_cap_10)) { + for (i = 0; i < ext_bits; i++) { + input_report_key(dev, BTN_0 + 2 * i, + hw->ext_buttons & (1 << i)); + input_report_key(dev, BTN_1 + 2 * i, + hw->ext_buttons & (1 << (i + ext_bits))); + } + return; + } + + /* + * This generation of touchpads has the trackstick buttons + * physically wired to the touchpad. Re-route them through + * the pass-through interface. + */ + if (!priv->pt_port) + return; + + /* The trackstick expects at most 3 buttons */ + priv->pt_buttons = SYN_CAP_EXT_BUTTON_STICK_L(hw->ext_buttons) | + SYN_CAP_EXT_BUTTON_STICK_R(hw->ext_buttons) << 1 | + SYN_CAP_EXT_BUTTON_STICK_M(hw->ext_buttons) << 2; + + synaptics_pass_pt_packet(psmouse, priv->pt_port, buf); +} + static void synaptics_report_buttons(struct psmouse *psmouse, const struct synaptics_hw_state *hw) { struct input_dev *dev = psmouse->dev; struct synaptics_data *priv = psmouse->private; - int i; input_report_key(dev, BTN_LEFT, hw->left); input_report_key(dev, BTN_RIGHT, hw->right); @@ -792,8 +892,7 @@ static void synaptics_report_buttons(struct psmouse *psmouse, input_report_key(dev, BTN_BACK, hw->down); } - for (i = 0; i < SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap); i++) - input_report_key(dev, BTN_0 + i, hw->ext_buttons & (1 << i)); + synaptics_report_ext_buttons(psmouse, hw); } static void synaptics_report_mt_data(struct psmouse *psmouse, @@ -813,7 +912,7 @@ static void synaptics_report_mt_data(struct psmouse *psmouse, pos[i].y = synaptics_invert_y(hw[i]->y); } - input_mt_assign_slots(dev, slot, pos, nsemi, DMAX * priv->x_res); + input_mt_assign_slots(dev, slot, pos, nsemi, 0); for (i = 0; i < nsemi; i++) { input_mt_slot(dev, slot[i]); @@ -1014,7 +1113,8 @@ static psmouse_ret_t synaptics_process_byte(struct psmouse *psmouse) if (SYN_CAP_PASS_THROUGH(priv->capabilities) && synaptics_is_pt_packet(psmouse->packet)) { if (priv->pt_port) - synaptics_pass_pt_packet(priv->pt_port, psmouse->packet); + synaptics_pass_pt_packet(psmouse, priv->pt_port, + psmouse->packet); } else synaptics_process_packet(psmouse); @@ -1116,8 +1216,9 @@ static void set_input_params(struct psmouse *psmouse, __set_bit(BTN_BACK, dev->keybit); } - for (i = 0; i < SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap); i++) - __set_bit(BTN_0 + i, dev->keybit); + if (!SYN_CAP_EXT_BUTTONS_STICK(priv->ext_cap_10)) + for (i = 0; i < SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap); i++) + __set_bit(BTN_0 + i, dev->keybit); __clear_bit(EV_REL, dev->evbit); __clear_bit(REL_X, dev->relbit); @@ -1125,7 +1226,8 @@ static void set_input_params(struct psmouse *psmouse, if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) { __set_bit(INPUT_PROP_BUTTONPAD, dev->propbit); - if (psmouse_matches_pnp_id(psmouse, topbuttonpad_pnp_ids)) + if (psmouse_matches_pnp_id(psmouse, topbuttonpad_pnp_ids) && + !SYN_CAP_EXT_BUTTONS_STICK(priv->ext_cap_10)) __set_bit(INPUT_PROP_TOPBUTTONPAD, dev->propbit); /* Clickpads report only left button */ __clear_bit(BTN_RIGHT, dev->keybit); diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h index aedc3299b14e..ee4bd0d12b26 100644 --- a/drivers/input/mouse/synaptics.h +++ b/drivers/input/mouse/synaptics.h @@ -22,6 +22,7 @@ #define SYN_QUE_EXT_CAPAB_0C 0x0c #define SYN_QUE_EXT_MAX_COORDS 0x0d #define SYN_QUE_EXT_MIN_COORDS 0x0f +#define SYN_QUE_MEXT_CAPAB_10 0x10 /* synatics modes */ #define SYN_BIT_ABSOLUTE_MODE (1 << 7) @@ -53,6 +54,7 @@ #define SYN_EXT_CAP_REQUESTS(c) (((c) & 0x700000) >> 20) #define SYN_CAP_MULTI_BUTTON_NO(ec) (((ec) & 0x00f000) >> 12) #define SYN_CAP_PRODUCT_ID(ec) (((ec) & 0xff0000) >> 16) +#define SYN_MEXT_CAP_BIT(m) ((m) & (1 << 1)) /* * The following describes response for the 0x0c query. @@ -89,6 +91,30 @@ #define SYN_CAP_REDUCED_FILTERING(ex0c) ((ex0c) & 0x000400) #define SYN_CAP_IMAGE_SENSOR(ex0c) ((ex0c) & 0x000800) +/* + * The following descibes response for the 0x10 query. + * + * byte mask name meaning + * ---- ---- ------- ------------ + * 1 0x01 ext buttons are stick buttons exported in the extended + * capability are actually meant to be used + * by the tracktick (pass-through). + * 1 0x02 SecurePad the touchpad is a SecurePad, so it + * contains a built-in fingerprint reader. + * 1 0xe0 more ext count how many more extented queries are + * available after this one. + * 2 0xff SecurePad width the width of the SecurePad fingerprint + * reader. + * 3 0xff SecurePad height the height of the SecurePad fingerprint + * reader. + */ +#define SYN_CAP_EXT_BUTTONS_STICK(ex10) ((ex10) & 0x010000) +#define SYN_CAP_SECUREPAD(ex10) ((ex10) & 0x020000) + +#define SYN_CAP_EXT_BUTTON_STICK_L(eb) (!!((eb) & 0x01)) +#define SYN_CAP_EXT_BUTTON_STICK_M(eb) (!!((eb) & 0x02)) +#define SYN_CAP_EXT_BUTTON_STICK_R(eb) (!!((eb) & 0x04)) + /* synaptics modes query bits */ #define SYN_MODE_ABSOLUTE(m) ((m) & (1 << 7)) #define SYN_MODE_RATE(m) ((m) & (1 << 6)) @@ -143,6 +169,7 @@ struct synaptics_data { unsigned long int capabilities; /* Capabilities */ unsigned long int ext_cap; /* Extended Capabilities */ unsigned long int ext_cap_0c; /* Ext Caps from 0x0c query */ + unsigned long int ext_cap_10; /* Ext Caps from 0x10 query */ unsigned long int identity; /* Identification */ unsigned int x_res, y_res; /* X/Y resolution in units/mm */ unsigned int x_max, y_max; /* Max coordinates (from FW) */ @@ -156,6 +183,7 @@ struct synaptics_data { bool disable_gesture; /* disable gestures */ struct serio *pt_port; /* Pass-through serio port */ + unsigned char pt_buttons; /* Pass-through buttons */ /* * Last received Advanced Gesture Mode (AGM) packet. An AGM packet diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index baa0d9786f50..1ae4e547b419 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -23,6 +23,7 @@ config IOMMU_IO_PGTABLE config IOMMU_IO_PGTABLE_LPAE bool "ARMv7/v8 Long Descriptor Format" select IOMMU_IO_PGTABLE + depends on ARM || ARM64 || COMPILE_TEST help Enable support for the ARM long descriptor pagetable format. This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page @@ -63,6 +64,7 @@ config MSM_IOMMU bool "MSM IOMMU Support" depends on ARM depends on ARCH_MSM8X60 || ARCH_MSM8960 || COMPILE_TEST + depends on BROKEN select IOMMU_API help Support for the IOMMUs found on certain Qualcomm SOCs. diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 7ce52737c7a1..dc14fec4ede1 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1186,8 +1186,15 @@ static const struct iommu_ops exynos_iommu_ops = { static int __init exynos_iommu_init(void) { + struct device_node *np; int ret; + np = of_find_matching_node(NULL, sysmmu_of_match); + if (!np) + return 0; + + of_node_put(np); + lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table", LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL); if (!lv2table_kmem_cache) { diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 5a500edf00cc..b610a8dee238 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -56,7 +56,8 @@ ((((d)->levels - ((l) - ARM_LPAE_START_LVL(d) + 1)) \ * (d)->bits_per_level) + (d)->pg_shift) -#define ARM_LPAE_PAGES_PER_PGD(d) ((d)->pgd_size >> (d)->pg_shift) +#define ARM_LPAE_PAGES_PER_PGD(d) \ + DIV_ROUND_UP((d)->pgd_size, 1UL << (d)->pg_shift) /* * Calculate the index at level l used to map virtual address a using the @@ -66,7 +67,7 @@ ((l) == ARM_LPAE_START_LVL(d) ? ilog2(ARM_LPAE_PAGES_PER_PGD(d)) : 0) #define ARM_LPAE_LVL_IDX(a,l,d) \ - (((a) >> ARM_LPAE_LVL_SHIFT(l,d)) & \ + (((u64)(a) >> ARM_LPAE_LVL_SHIFT(l,d)) & \ ((1 << ((d)->bits_per_level + ARM_LPAE_PGD_IDX(l,d))) - 1)) /* Calculate the block/page mapping size at level l for pagetable in d. */ diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index f59f857b702e..a4ba851825c2 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1376,6 +1376,13 @@ static int __init omap_iommu_init(void) struct kmem_cache *p; const unsigned long flags = SLAB_HWCACHE_ALIGN; size_t align = 1 << 10; /* L2 pagetable alignement */ + struct device_node *np; + + np = of_find_matching_node(NULL, omap_iommu_of_match); + if (!np) + return 0; + + of_node_put(np); p = kmem_cache_create("iopte_cache", IOPTE_TABLE_SIZE, align, flags, iopte_cachep_ctor); diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 6a8b1ec4a48a..9f74fddcd304 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1015,8 +1015,15 @@ static struct platform_driver rk_iommu_driver = { static int __init rk_iommu_init(void) { + struct device_node *np; int ret; + np = of_find_matching_node(NULL, rk_iommu_dt_ids); + if (!np) + return 0; + + of_node_put(np); + ret = bus_set_iommu(&platform_bus_type, &rk_iommu_ops); if (ret) return ret; diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 463c235acbdc..4387dae14e45 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -69,6 +69,7 @@ static void __iomem *per_cpu_int_base; static void __iomem *main_int_base; static struct irq_domain *armada_370_xp_mpic_domain; static u32 doorbell_mask_reg; +static int parent_irq; #ifdef CONFIG_PCI_MSI static struct irq_domain *armada_370_xp_msi_domain; static DECLARE_BITMAP(msi_used, PCI_MSI_DOORBELL_NR); @@ -356,6 +357,7 @@ static int armada_xp_mpic_secondary_init(struct notifier_block *nfb, { if (action == CPU_STARTING || action == CPU_STARTING_FROZEN) armada_xp_mpic_smp_cpu_init(); + return NOTIFY_OK; } @@ -364,6 +366,20 @@ static struct notifier_block armada_370_xp_mpic_cpu_notifier = { .priority = 100, }; +static int mpic_cascaded_secondary_init(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + if (action == CPU_STARTING || action == CPU_STARTING_FROZEN) + enable_percpu_irq(parent_irq, IRQ_TYPE_NONE); + + return NOTIFY_OK; +} + +static struct notifier_block mpic_cascaded_cpu_notifier = { + .notifier_call = mpic_cascaded_secondary_init, + .priority = 100, +}; + #endif /* CONFIG_SMP */ static struct irq_domain_ops armada_370_xp_mpic_irq_ops = { @@ -539,7 +555,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node, struct device_node *parent) { struct resource main_int_res, per_cpu_int_res; - int parent_irq, nr_irqs, i; + int nr_irqs, i; u32 control; BUG_ON(of_address_to_resource(node, 0, &main_int_res)); @@ -587,6 +603,9 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node, register_cpu_notifier(&armada_370_xp_mpic_cpu_notifier); #endif } else { +#ifdef CONFIG_SMP + register_cpu_notifier(&mpic_cascaded_cpu_notifier); +#endif irq_set_chained_handler(parent_irq, armada_370_xp_mpic_handle_cascade_irq); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index d8996bdf0f61..596b0a9eee99 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -416,13 +416,14 @@ static void its_send_single_command(struct its_node *its, { struct its_cmd_block *cmd, *sync_cmd, *next_cmd; struct its_collection *sync_col; + unsigned long flags; - raw_spin_lock(&its->lock); + raw_spin_lock_irqsave(&its->lock, flags); cmd = its_allocate_entry(its); if (!cmd) { /* We're soooooo screewed... */ pr_err_ratelimited("ITS can't allocate, dropping command\n"); - raw_spin_unlock(&its->lock); + raw_spin_unlock_irqrestore(&its->lock, flags); return; } sync_col = builder(cmd, desc); @@ -442,7 +443,7 @@ static void its_send_single_command(struct its_node *its, post: next_cmd = its_post_commands(its); - raw_spin_unlock(&its->lock); + raw_spin_unlock_irqrestore(&its->lock, flags); its_wait_for_range_completion(its, cmd, next_cmd); } @@ -799,21 +800,43 @@ static int its_alloc_tables(struct its_node *its) { int err; int i; - int psz = PAGE_SIZE; + int psz = SZ_64K; u64 shr = GITS_BASER_InnerShareable; for (i = 0; i < GITS_BASER_NR_REGS; i++) { u64 val = readq_relaxed(its->base + GITS_BASER + i * 8); u64 type = GITS_BASER_TYPE(val); u64 entry_size = GITS_BASER_ENTRY_SIZE(val); + int order = get_order(psz); + int alloc_size; u64 tmp; void *base; if (type == GITS_BASER_TYPE_NONE) continue; - /* We're lazy and only allocate a single page for now */ - base = (void *)get_zeroed_page(GFP_KERNEL); + /* + * Allocate as many entries as required to fit the + * range of device IDs that the ITS can grok... The ID + * space being incredibly sparse, this results in a + * massive waste of memory. + * + * For other tables, only allocate a single page. + */ + if (type == GITS_BASER_TYPE_DEVICE) { + u64 typer = readq_relaxed(its->base + GITS_TYPER); + u32 ids = GITS_TYPER_DEVBITS(typer); + + order = get_order((1UL << ids) * entry_size); + if (order >= MAX_ORDER) { + order = MAX_ORDER - 1; + pr_warn("%s: Device Table too large, reduce its page order to %u\n", + its->msi_chip.of_node->full_name, order); + } + } + + alloc_size = (1 << order) * PAGE_SIZE; + base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!base) { err = -ENOMEM; goto out_free; @@ -841,7 +864,7 @@ retry_baser: break; } - val |= (PAGE_SIZE / psz) - 1; + val |= (alloc_size / psz) - 1; writeq_relaxed(val, its->base + GITS_BASER + i * 8); tmp = readq_relaxed(its->base + GITS_BASER + i * 8); @@ -882,7 +905,7 @@ retry_baser: } pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n", - (int)(PAGE_SIZE / entry_size), + (int)(alloc_size / entry_size), its_base_type_string[type], (unsigned long)virt_to_phys(base), psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); @@ -1020,8 +1043,9 @@ static void its_cpu_init_collection(void) static struct its_device *its_find_device(struct its_node *its, u32 dev_id) { struct its_device *its_dev = NULL, *tmp; + unsigned long flags; - raw_spin_lock(&its->lock); + raw_spin_lock_irqsave(&its->lock, flags); list_for_each_entry(tmp, &its->its_device_list, entry) { if (tmp->device_id == dev_id) { @@ -1030,7 +1054,7 @@ static struct its_device *its_find_device(struct its_node *its, u32 dev_id) } } - raw_spin_unlock(&its->lock); + raw_spin_unlock_irqrestore(&its->lock, flags); return its_dev; } @@ -1040,6 +1064,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, { struct its_device *dev; unsigned long *lpi_map; + unsigned long flags; void *itt; int lpi_base; int nr_lpis; @@ -1056,7 +1081,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, nr_ites = max(2UL, roundup_pow_of_two(nvecs)); sz = nr_ites * its->ite_size; sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1; - itt = kmalloc(sz, GFP_KERNEL); + itt = kzalloc(sz, GFP_KERNEL); lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis); if (!dev || !itt || !lpi_map) { @@ -1075,9 +1100,9 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, dev->device_id = dev_id; INIT_LIST_HEAD(&dev->entry); - raw_spin_lock(&its->lock); + raw_spin_lock_irqsave(&its->lock, flags); list_add(&dev->entry, &its->its_device_list); - raw_spin_unlock(&its->lock); + raw_spin_unlock_irqrestore(&its->lock, flags); /* Bind the device to the first possible CPU */ cpu = cpumask_first(cpu_online_mask); @@ -1091,9 +1116,11 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, static void its_free_device(struct its_device *its_dev) { - raw_spin_lock(&its_dev->its->lock); + unsigned long flags; + + raw_spin_lock_irqsave(&its_dev->its->lock, flags); list_del(&its_dev->entry); - raw_spin_unlock(&its_dev->its->lock); + raw_spin_unlock_irqrestore(&its_dev->its->lock, flags); kfree(its_dev->itt); kfree(its_dev); } @@ -1112,31 +1139,69 @@ static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq) return 0; } +struct its_pci_alias { + struct pci_dev *pdev; + u32 dev_id; + u32 count; +}; + +static int its_pci_msi_vec_count(struct pci_dev *pdev) +{ + int msi, msix; + + msi = max(pci_msi_vec_count(pdev), 0); + msix = max(pci_msix_vec_count(pdev), 0); + + return max(msi, msix); +} + +static int its_get_pci_alias(struct pci_dev *pdev, u16 alias, void *data) +{ + struct its_pci_alias *dev_alias = data; + + dev_alias->dev_id = alias; + if (pdev != dev_alias->pdev) + dev_alias->count += its_pci_msi_vec_count(dev_alias->pdev); + + return 0; +} + static int its_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *info) { struct pci_dev *pdev; struct its_node *its; - u32 dev_id; struct its_device *its_dev; + struct its_pci_alias dev_alias; if (!dev_is_pci(dev)) return -EINVAL; pdev = to_pci_dev(dev); - dev_id = PCI_DEVID(pdev->bus->number, pdev->devfn); + dev_alias.pdev = pdev; + dev_alias.count = nvec; + + pci_for_each_dma_alias(pdev, its_get_pci_alias, &dev_alias); its = domain->parent->host_data; - its_dev = its_find_device(its, dev_id); - if (WARN_ON(its_dev)) - return -EINVAL; + its_dev = its_find_device(its, dev_alias.dev_id); + if (its_dev) { + /* + * We already have seen this ID, probably through + * another alias (PCI bridge of some sort). No need to + * create the device. + */ + dev_dbg(dev, "Reusing ITT for devID %x\n", dev_alias.dev_id); + goto out; + } - its_dev = its_create_device(its, dev_id, nvec); + its_dev = its_create_device(its, dev_alias.dev_id, dev_alias.count); if (!its_dev) return -ENOMEM; - dev_dbg(&pdev->dev, "ITT %d entries, %d bits\n", nvec, ilog2(nvec)); - + dev_dbg(&pdev->dev, "ITT %d entries, %d bits\n", + dev_alias.count, ilog2(dev_alias.count)); +out: info->scratchpad[0].ptr = its_dev; info->scratchpad[1].ptr = dev; return 0; @@ -1255,6 +1320,34 @@ static const struct irq_domain_ops its_domain_ops = { .deactivate = its_irq_domain_deactivate, }; +static int its_force_quiescent(void __iomem *base) +{ + u32 count = 1000000; /* 1s */ + u32 val; + + val = readl_relaxed(base + GITS_CTLR); + if (val & GITS_CTLR_QUIESCENT) + return 0; + + /* Disable the generation of all interrupts to this ITS */ + val &= ~GITS_CTLR_ENABLE; + writel_relaxed(val, base + GITS_CTLR); + + /* Poll GITS_CTLR and wait until ITS becomes quiescent */ + while (1) { + val = readl_relaxed(base + GITS_CTLR); + if (val & GITS_CTLR_QUIESCENT) + return 0; + + count--; + if (!count) + return -EBUSY; + + cpu_relax(); + udelay(1); + } +} + static int its_probe(struct device_node *node, struct irq_domain *parent) { struct resource res; @@ -1283,6 +1376,13 @@ static int its_probe(struct device_node *node, struct irq_domain *parent) goto out_unmap; } + err = its_force_quiescent(its_base); + if (err) { + pr_warn("%s: failed to quiesce, giving up\n", + node->full_name); + goto out_unmap; + } + pr_info("ITS: %s\n", node->full_name); its = kzalloc(sizeof(*its), GFP_KERNEL); @@ -1323,7 +1423,7 @@ static int its_probe(struct device_node *node, struct irq_domain *parent) writeq_relaxed(baser, its->base + GITS_CBASER); tmp = readq_relaxed(its->base + GITS_CBASER); writeq_relaxed(0, its->base + GITS_CWRITER); - writel_relaxed(1, its->base + GITS_CTLR); + writel_relaxed(GITS_CTLR_ENABLE, its->base + GITS_CTLR); if ((tmp ^ baser) & GITS_BASER_SHAREABILITY_MASK) { pr_info("ITS: using cache flushing for cmd queue\n"); @@ -1382,12 +1482,11 @@ static bool gic_rdists_supports_plpis(void) int its_cpu_init(void) { - if (!gic_rdists_supports_plpis()) { - pr_info("CPU%d: LPIs not supported\n", smp_processor_id()); - return -ENXIO; - } - if (!list_empty(&its_nodes)) { + if (!gic_rdists_supports_plpis()) { + pr_info("CPU%d: LPIs not supported\n", smp_processor_id()); + return -ENXIO; + } its_cpu_init_lpis(); its_cpu_init_collection(); } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 1c6dea2fbc34..fd8850def1b8 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -466,7 +466,7 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, tlist |= 1 << (mpidr & 0xf); cpu = cpumask_next(cpu, mask); - if (cpu == nr_cpu_ids) + if (cpu >= nr_cpu_ids) goto out; mpidr = cpu_logical_map(cpu); diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 4634cf7d0ec3..471e1cdc1933 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -154,23 +154,25 @@ static inline unsigned int gic_irq(struct irq_data *d) static void gic_mask_irq(struct irq_data *d) { u32 mask = 1 << (gic_irq(d) % 32); + unsigned long flags; - raw_spin_lock(&irq_controller_lock); + raw_spin_lock_irqsave(&irq_controller_lock, flags); writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4); if (gic_arch_extn.irq_mask) gic_arch_extn.irq_mask(d); - raw_spin_unlock(&irq_controller_lock); + raw_spin_unlock_irqrestore(&irq_controller_lock, flags); } static void gic_unmask_irq(struct irq_data *d) { u32 mask = 1 << (gic_irq(d) % 32); + unsigned long flags; - raw_spin_lock(&irq_controller_lock); + raw_spin_lock_irqsave(&irq_controller_lock, flags); if (gic_arch_extn.irq_unmask) gic_arch_extn.irq_unmask(d); writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_SET + (gic_irq(d) / 32) * 4); - raw_spin_unlock(&irq_controller_lock); + raw_spin_unlock_irqrestore(&irq_controller_lock, flags); } static void gic_eoi_irq(struct irq_data *d) @@ -188,6 +190,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) { void __iomem *base = gic_dist_base(d); unsigned int gicirq = gic_irq(d); + unsigned long flags; int ret; /* Interrupt configuration for SGIs can't be changed */ @@ -199,14 +202,14 @@ static int gic_set_type(struct irq_data *d, unsigned int type) type != IRQ_TYPE_EDGE_RISING) return -EINVAL; - raw_spin_lock(&irq_controller_lock); + raw_spin_lock_irqsave(&irq_controller_lock, flags); if (gic_arch_extn.irq_set_type) gic_arch_extn.irq_set_type(d, type); ret = gic_configure_irq(gicirq, type, base, NULL); - raw_spin_unlock(&irq_controller_lock); + raw_spin_unlock_irqrestore(&irq_controller_lock, flags); return ret; } @@ -227,6 +230,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3); unsigned int cpu, shift = (gic_irq(d) % 4) * 8; u32 val, mask, bit; + unsigned long flags; if (!force) cpu = cpumask_any_and(mask_val, cpu_online_mask); @@ -236,12 +240,12 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids) return -EINVAL; - raw_spin_lock(&irq_controller_lock); + raw_spin_lock_irqsave(&irq_controller_lock, flags); mask = 0xff << shift; bit = gic_cpu_map[cpu] << shift; val = readl_relaxed(reg) & ~mask; writel_relaxed(val | bit, reg); - raw_spin_unlock(&irq_controller_lock); + raw_spin_unlock_irqrestore(&irq_controller_lock, flags); return IRQ_SET_MASK_OK; } diff --git a/drivers/isdn/gigaset/ev-layer.c b/drivers/isdn/gigaset/ev-layer.c index c8ced12fa452..1cfcea62aed9 100644 --- a/drivers/isdn/gigaset/ev-layer.c +++ b/drivers/isdn/gigaset/ev-layer.c @@ -389,22 +389,49 @@ zsau_resp[] = {NULL, ZSAU_UNKNOWN} }; -/* retrieve CID from parsed response - * returns 0 if no CID, -1 if invalid CID, or CID value 1..65535 +/* check for and remove fixed string prefix + * If s starts with prefix terminated by a non-alphanumeric character, + * return pointer to the first character after that, otherwise return NULL. */ -static int cid_of_response(char *s) +static char *skip_prefix(char *s, const char *prefix) { - int cid; - int rc; - - if (s[-1] != ';') - return 0; /* no CID separator */ - rc = kstrtoint(s, 10, &cid); - if (rc) - return 0; /* CID not numeric */ - if (cid < 1 || cid > 65535) - return -1; /* CID out of range */ - return cid; + while (*prefix) + if (*s++ != *prefix++) + return NULL; + if (isalnum(*s)) + return NULL; + return s; +} + +/* queue event with CID */ +static void add_cid_event(struct cardstate *cs, int cid, int type, + void *ptr, int parameter) +{ + unsigned long flags; + unsigned next, tail; + struct event_t *event; + + gig_dbg(DEBUG_EVENT, "queueing event %d for cid %d", type, cid); + + spin_lock_irqsave(&cs->ev_lock, flags); + + tail = cs->ev_tail; + next = (tail + 1) % MAX_EVENTS; + if (unlikely(next == cs->ev_head)) { + dev_err(cs->dev, "event queue full\n"); + kfree(ptr); + } else { + event = cs->events + tail; + event->type = type; + event->cid = cid; + event->ptr = ptr; + event->arg = NULL; + event->parameter = parameter; + event->at_state = NULL; + cs->ev_tail = next; + } + + spin_unlock_irqrestore(&cs->ev_lock, flags); } /** @@ -417,190 +444,188 @@ static int cid_of_response(char *s) */ void gigaset_handle_modem_response(struct cardstate *cs) { - unsigned char *argv[MAX_REC_PARAMS + 1]; - int params; - int i, j; + char *eoc, *psep, *ptr; const struct resp_type_t *rt; const struct zsau_resp_t *zr; - int curarg; - unsigned long flags; - unsigned next, tail, head; - struct event_t *event; - int resp_code; - int param_type; - int abort; - size_t len; - int cid; - int rawstring; - - len = cs->cbytes; - if (!len) { + int cid, parameter; + u8 type, value; + + if (!cs->cbytes) { /* ignore additional LFs/CRs (M10x config mode or cx100) */ gig_dbg(DEBUG_MCMD, "skipped EOL [%02X]", cs->respdata[0]); return; } - cs->respdata[len] = 0; - argv[0] = cs->respdata; - params = 1; + cs->respdata[cs->cbytes] = 0; + if (cs->at_state.getstring) { - /* getstring only allowed without cid at the moment */ + /* state machine wants next line verbatim */ cs->at_state.getstring = 0; - rawstring = 1; - cid = 0; - } else { - /* parse line */ - for (i = 0; i < len; i++) - switch (cs->respdata[i]) { - case ';': - case ',': - case '=': - if (params > MAX_REC_PARAMS) { - dev_warn(cs->dev, - "too many parameters in response\n"); - /* need last parameter (might be CID) */ - params--; - } - argv[params++] = cs->respdata + i + 1; - } - - rawstring = 0; - cid = params > 1 ? cid_of_response(argv[params - 1]) : 0; - if (cid < 0) { - gigaset_add_event(cs, &cs->at_state, RSP_INVAL, - NULL, 0, NULL); - return; - } + ptr = kstrdup(cs->respdata, GFP_ATOMIC); + gig_dbg(DEBUG_EVENT, "string==%s", ptr ? ptr : "NULL"); + add_cid_event(cs, 0, RSP_STRING, ptr, 0); + return; + } - for (j = 1; j < params; ++j) - argv[j][-1] = 0; + /* look up response type */ + for (rt = resp_type; rt->response; ++rt) { + eoc = skip_prefix(cs->respdata, rt->response); + if (eoc) + break; + } + if (!rt->response) { + add_cid_event(cs, 0, RSP_NONE, NULL, 0); + gig_dbg(DEBUG_EVENT, "unknown modem response: '%s'\n", + cs->respdata); + return; + } - gig_dbg(DEBUG_EVENT, "CMD received: %s", argv[0]); - if (cid) { - --params; - gig_dbg(DEBUG_EVENT, "CID: %s", argv[params]); - } - gig_dbg(DEBUG_EVENT, "available params: %d", params - 1); - for (j = 1; j < params; j++) - gig_dbg(DEBUG_EVENT, "param %d: %s", j, argv[j]); + /* check for CID */ + psep = strrchr(cs->respdata, ';'); + if (psep && + !kstrtoint(psep + 1, 10, &cid) && + cid >= 1 && cid <= 65535) { + /* valid CID: chop it off */ + *psep = 0; + } else { + /* no valid CID: leave unchanged */ + cid = 0; } - spin_lock_irqsave(&cs->ev_lock, flags); - head = cs->ev_head; - tail = cs->ev_tail; + gig_dbg(DEBUG_EVENT, "CMD received: %s", cs->respdata); + if (cid) + gig_dbg(DEBUG_EVENT, "CID: %d", cid); - abort = 1; - curarg = 0; - while (curarg < params) { - next = (tail + 1) % MAX_EVENTS; - if (unlikely(next == head)) { - dev_err(cs->dev, "event queue full\n"); - break; - } + switch (rt->type) { + case RT_NOTHING: + /* check parameter separator */ + if (*eoc) + goto bad_param; /* extra parameter */ - event = cs->events + tail; - event->at_state = NULL; - event->cid = cid; - event->ptr = NULL; - event->arg = NULL; - tail = next; + add_cid_event(cs, cid, rt->resp_code, NULL, 0); + break; - if (rawstring) { - resp_code = RSP_STRING; - param_type = RT_STRING; - } else { - for (rt = resp_type; rt->response; ++rt) - if (!strcmp(argv[curarg], rt->response)) + case RT_RING: + /* check parameter separator */ + if (!*eoc) + eoc = NULL; /* no parameter */ + else if (*eoc++ != ',') + goto bad_param; + + add_cid_event(cs, 0, rt->resp_code, NULL, cid); + + /* process parameters as individual responses */ + while (eoc) { + /* look up parameter type */ + psep = NULL; + for (rt = resp_type; rt->response; ++rt) { + psep = skip_prefix(eoc, rt->response); + if (psep) break; + } - if (!rt->response) { - event->type = RSP_NONE; - gig_dbg(DEBUG_EVENT, - "unknown modem response: '%s'\n", - argv[curarg]); - break; + /* all legal parameters are of type RT_STRING */ + if (!psep || rt->type != RT_STRING) { + dev_warn(cs->dev, + "illegal RING parameter: '%s'\n", + eoc); + return; } - resp_code = rt->resp_code; - param_type = rt->type; - ++curarg; - } + /* skip parameter value separator */ + if (*psep++ != '=') + goto bad_param; - event->type = resp_code; + /* look up end of parameter */ + eoc = strchr(psep, ','); + if (eoc) + *eoc++ = 0; - switch (param_type) { - case RT_NOTHING: - break; - case RT_RING: - if (!cid) { - dev_err(cs->dev, - "received RING without CID!\n"); - event->type = RSP_INVAL; - abort = 1; - } else { - event->cid = 0; - event->parameter = cid; - abort = 0; - } + /* retrieve parameter value */ + ptr = kstrdup(psep, GFP_ATOMIC); + + /* queue event */ + add_cid_event(cs, cid, rt->resp_code, ptr, 0); + } + break; + + case RT_ZSAU: + /* check parameter separator */ + if (!*eoc) { + /* no parameter */ + add_cid_event(cs, cid, rt->resp_code, NULL, ZSAU_NONE); break; - case RT_ZSAU: - if (curarg >= params) { - event->parameter = ZSAU_NONE; + } + if (*eoc++ != '=') + goto bad_param; + + /* look up parameter value */ + for (zr = zsau_resp; zr->str; ++zr) + if (!strcmp(eoc, zr->str)) break; - } - for (zr = zsau_resp; zr->str; ++zr) - if (!strcmp(argv[curarg], zr->str)) - break; - event->parameter = zr->code; - if (!zr->str) - dev_warn(cs->dev, - "%s: unknown parameter %s after ZSAU\n", - __func__, argv[curarg]); - ++curarg; - break; - case RT_STRING: - if (curarg < params) { - event->ptr = kstrdup(argv[curarg], GFP_ATOMIC); - if (!event->ptr) - dev_err(cs->dev, "out of memory\n"); - ++curarg; - } - gig_dbg(DEBUG_EVENT, "string==%s", - event->ptr ? (char *) event->ptr : "NULL"); - break; - case RT_ZCAU: - event->parameter = -1; - if (curarg + 1 < params) { - u8 type, value; - - i = kstrtou8(argv[curarg++], 16, &type); - j = kstrtou8(argv[curarg++], 16, &value); - if (i == 0 && j == 0) - event->parameter = (type << 8) | value; - } else - curarg = params - 1; - break; - case RT_NUMBER: - if (curarg >= params || - kstrtoint(argv[curarg++], 10, &event->parameter)) - event->parameter = -1; - gig_dbg(DEBUG_EVENT, "parameter==%d", event->parameter); - break; + if (!zr->str) + goto bad_param; + + add_cid_event(cs, cid, rt->resp_code, NULL, zr->code); + break; + + case RT_STRING: + /* check parameter separator */ + if (*eoc++ != '=') + goto bad_param; + + /* retrieve parameter value */ + ptr = kstrdup(eoc, GFP_ATOMIC); + + /* queue event */ + add_cid_event(cs, cid, rt->resp_code, ptr, 0); + break; + + case RT_ZCAU: + /* check parameter separators */ + if (*eoc++ != '=') + goto bad_param; + psep = strchr(eoc, ','); + if (!psep) + goto bad_param; + *psep++ = 0; + + /* decode parameter values */ + if (kstrtou8(eoc, 16, &type) || kstrtou8(psep, 16, &value)) { + *--psep = ','; + goto bad_param; } + parameter = (type << 8) | value; - if (resp_code == RSP_ZDLE) - cs->dle = event->parameter; + add_cid_event(cs, cid, rt->resp_code, NULL, parameter); + break; - if (abort) - break; - } + case RT_NUMBER: + /* check parameter separator */ + if (*eoc++ != '=') + goto bad_param; - cs->ev_tail = tail; - spin_unlock_irqrestore(&cs->ev_lock, flags); + /* decode parameter value */ + if (kstrtoint(eoc, 10, ¶meter)) + goto bad_param; + + /* special case ZDLE: set flag before queueing event */ + if (rt->resp_code == RSP_ZDLE) + cs->dle = parameter; - if (curarg != params) - gig_dbg(DEBUG_EVENT, - "invalid number of processed parameters: %d/%d", - curarg, params); + add_cid_event(cs, cid, rt->resp_code, NULL, parameter); + break; + +bad_param: + /* parameter unexpected, incomplete or malformed */ + dev_warn(cs->dev, "bad parameter in response '%s'\n", + cs->respdata); + add_cid_event(cs, cid, rt->resp_code, NULL, -1); + break; + + default: + dev_err(cs->dev, "%s: internal error on '%s'\n", + __func__, cs->respdata); + } } EXPORT_SYMBOL_GPL(gigaset_handle_modem_response); diff --git a/drivers/isdn/icn/icn.c b/drivers/isdn/icn/icn.c index 6a7447c304ac..358a574d9e8b 100644 --- a/drivers/isdn/icn/icn.c +++ b/drivers/isdn/icn/icn.c @@ -1609,7 +1609,7 @@ icn_setup(char *line) if (ints[0] > 1) membase = (unsigned long)ints[2]; if (str && *str) { - strcpy(sid, str); + strlcpy(sid, str, sizeof(sid)); icn_id = sid; if ((p = strchr(sid, ','))) { *p++ = 0; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 37de0173b6d2..74adcd2c967e 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -289,9 +289,16 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, struct request_queue *q = bdev_get_queue(where->bdev); unsigned short logical_block_size = queue_logical_block_size(q); sector_t num_sectors; + unsigned int uninitialized_var(special_cmd_max_sectors); - /* Reject unsupported discard requests */ - if ((rw & REQ_DISCARD) && !blk_queue_discard(q)) { + /* + * Reject unsupported discard and write same requests. + */ + if (rw & REQ_DISCARD) + special_cmd_max_sectors = q->limits.max_discard_sectors; + else if (rw & REQ_WRITE_SAME) + special_cmd_max_sectors = q->limits.max_write_same_sectors; + if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) { dec_count(io, region, -EOPNOTSUPP); return; } @@ -317,7 +324,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, store_io_and_region_in_bio(bio, io, region); if (rw & REQ_DISCARD) { - num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; remaining -= num_sectors; } else if (rw & REQ_WRITE_SAME) { @@ -326,7 +333,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, */ dp->get_page(dp, &page, &len, &offset); bio_add_page(bio, page, logical_block_size, offset); - num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; offset = 0; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 8b204ae216ab..f83a0f3fc365 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -20,6 +20,8 @@ #include <linux/log2.h> #include <linux/dm-kcopyd.h> +#include "dm.h" + #include "dm-exception-store.h" #define DM_MSG_PREFIX "snapshots" @@ -291,12 +293,23 @@ struct origin { }; /* + * This structure is allocated for each origin target + */ +struct dm_origin { + struct dm_dev *dev; + struct dm_target *ti; + unsigned split_boundary; + struct list_head hash_list; +}; + +/* * Size of the hash table for origin volumes. If we make this * the size of the minors list then it should be nearly perfect */ #define ORIGIN_HASH_SIZE 256 #define ORIGIN_MASK 0xFF static struct list_head *_origins; +static struct list_head *_dm_origins; static struct rw_semaphore _origins_lock; static DECLARE_WAIT_QUEUE_HEAD(_pending_exceptions_done); @@ -310,12 +323,22 @@ static int init_origin_hash(void) _origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head), GFP_KERNEL); if (!_origins) { - DMERR("unable to allocate memory"); + DMERR("unable to allocate memory for _origins"); return -ENOMEM; } - for (i = 0; i < ORIGIN_HASH_SIZE; i++) INIT_LIST_HEAD(_origins + i); + + _dm_origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head), + GFP_KERNEL); + if (!_dm_origins) { + DMERR("unable to allocate memory for _dm_origins"); + kfree(_origins); + return -ENOMEM; + } + for (i = 0; i < ORIGIN_HASH_SIZE; i++) + INIT_LIST_HEAD(_dm_origins + i); + init_rwsem(&_origins_lock); return 0; @@ -324,6 +347,7 @@ static int init_origin_hash(void) static void exit_origin_hash(void) { kfree(_origins); + kfree(_dm_origins); } static unsigned origin_hash(struct block_device *bdev) @@ -350,6 +374,30 @@ static void __insert_origin(struct origin *o) list_add_tail(&o->hash_list, sl); } +static struct dm_origin *__lookup_dm_origin(struct block_device *origin) +{ + struct list_head *ol; + struct dm_origin *o; + + ol = &_dm_origins[origin_hash(origin)]; + list_for_each_entry (o, ol, hash_list) + if (bdev_equal(o->dev->bdev, origin)) + return o; + + return NULL; +} + +static void __insert_dm_origin(struct dm_origin *o) +{ + struct list_head *sl = &_dm_origins[origin_hash(o->dev->bdev)]; + list_add_tail(&o->hash_list, sl); +} + +static void __remove_dm_origin(struct dm_origin *o) +{ + list_del(&o->hash_list); +} + /* * _origins_lock must be held when calling this function. * Returns number of snapshots registered using the supplied cow device, plus: @@ -1840,9 +1888,40 @@ static int snapshot_preresume(struct dm_target *ti) static void snapshot_resume(struct dm_target *ti) { struct dm_snapshot *s = ti->private; - struct dm_snapshot *snap_src = NULL, *snap_dest = NULL; + struct dm_snapshot *snap_src = NULL, *snap_dest = NULL, *snap_merging = NULL; + struct dm_origin *o; + struct mapped_device *origin_md = NULL; + bool must_restart_merging = false; down_read(&_origins_lock); + + o = __lookup_dm_origin(s->origin->bdev); + if (o) + origin_md = dm_table_get_md(o->ti->table); + if (!origin_md) { + (void) __find_snapshots_sharing_cow(s, NULL, NULL, &snap_merging); + if (snap_merging) + origin_md = dm_table_get_md(snap_merging->ti->table); + } + if (origin_md == dm_table_get_md(ti->table)) + origin_md = NULL; + if (origin_md) { + if (dm_hold(origin_md)) + origin_md = NULL; + } + + up_read(&_origins_lock); + + if (origin_md) { + dm_internal_suspend_fast(origin_md); + if (snap_merging && test_bit(RUNNING_MERGE, &snap_merging->state_bits)) { + must_restart_merging = true; + stop_merge(snap_merging); + } + } + + down_read(&_origins_lock); + (void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL); if (snap_src && snap_dest) { down_write(&snap_src->lock); @@ -1851,8 +1930,16 @@ static void snapshot_resume(struct dm_target *ti) up_write(&snap_dest->lock); up_write(&snap_src->lock); } + up_read(&_origins_lock); + if (origin_md) { + if (must_restart_merging) + start_merge(snap_merging); + dm_internal_resume_fast(origin_md); + dm_put(origin_md); + } + /* Now we have correct chunk size, reregister */ reregister_snapshot(s); @@ -2133,11 +2220,6 @@ static int origin_write_extent(struct dm_snapshot *merging_snap, * Origin: maps a linear range of a device, with hooks for snapshotting. */ -struct dm_origin { - struct dm_dev *dev; - unsigned split_boundary; -}; - /* * Construct an origin mapping: <dev_path> * The context for an origin is merely a 'struct dm_dev *' @@ -2166,6 +2248,7 @@ static int origin_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_open; } + o->ti = ti; ti->private = o; ti->num_flush_bios = 1; @@ -2180,6 +2263,7 @@ bad_alloc: static void origin_dtr(struct dm_target *ti) { struct dm_origin *o = ti->private; + dm_put_device(ti, o->dev); kfree(o); } @@ -2216,6 +2300,19 @@ static void origin_resume(struct dm_target *ti) struct dm_origin *o = ti->private; o->split_boundary = get_origin_minimum_chunksize(o->dev->bdev); + + down_write(&_origins_lock); + __insert_dm_origin(o); + up_write(&_origins_lock); +} + +static void origin_postsuspend(struct dm_target *ti) +{ + struct dm_origin *o = ti->private; + + down_write(&_origins_lock); + __remove_dm_origin(o); + up_write(&_origins_lock); } static void origin_status(struct dm_target *ti, status_type_t type, @@ -2258,12 +2355,13 @@ static int origin_iterate_devices(struct dm_target *ti, static struct target_type origin_target = { .name = "snapshot-origin", - .version = {1, 8, 1}, + .version = {1, 9, 0}, .module = THIS_MODULE, .ctr = origin_ctr, .dtr = origin_dtr, .map = origin_map, .resume = origin_resume, + .postsuspend = origin_postsuspend, .status = origin_status, .merge = origin_merge, .iterate_devices = origin_iterate_devices, @@ -2271,7 +2369,7 @@ static struct target_type origin_target = { static struct target_type snapshot_target = { .name = "snapshot", - .version = {1, 12, 0}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, @@ -2285,7 +2383,7 @@ static struct target_type snapshot_target = { static struct target_type merge_target = { .name = dm_snapshot_merge_target_name, - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 654773cb1eee..921aafd12aee 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2358,17 +2358,6 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; case -ENODATA: - if (get_pool_mode(tc->pool) == PM_READ_ONLY) { - /* - * This block isn't provisioned, and we have no way - * of doing so. - */ - handle_unserviceable_bio(tc->pool, bio); - cell_defer_no_holder(tc, virt_cell); - return DM_MAPIO_SUBMITTED; - } - /* fall through */ - case -EWOULDBLOCK: thin_defer_cell(tc, virt_cell); return DM_MAPIO_SUBMITTED; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 73f28802dc7a..9b641b38b857 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2616,6 +2616,19 @@ void dm_get(struct mapped_device *md) BUG_ON(test_bit(DMF_FREEING, &md->flags)); } +int dm_hold(struct mapped_device *md) +{ + spin_lock(&_minor_lock); + if (test_bit(DMF_FREEING, &md->flags)) { + spin_unlock(&_minor_lock); + return -EBUSY; + } + dm_get(md); + spin_unlock(&_minor_lock); + return 0; +} +EXPORT_SYMBOL_GPL(dm_hold); + const char *dm_device_name(struct mapped_device *md) { return md->name; @@ -2638,10 +2651,16 @@ static void __dm_destroy(struct mapped_device *md, bool wait) if (dm_request_based(md)) flush_kthread_worker(&md->kworker); + /* + * Take suspend_lock so that presuspend and postsuspend methods + * do not race with internal suspend. + */ + mutex_lock(&md->suspend_lock); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); dm_table_postsuspend_targets(map); } + mutex_unlock(&md->suspend_lock); /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ dm_put_live_table(md, srcu_idx); @@ -3115,6 +3134,7 @@ void dm_internal_suspend_fast(struct mapped_device *md) flush_workqueue(md->wq); dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); } +EXPORT_SYMBOL_GPL(dm_internal_suspend_fast); void dm_internal_resume_fast(struct mapped_device *md) { @@ -3126,6 +3146,7 @@ void dm_internal_resume_fast(struct mapped_device *md) done: mutex_unlock(&md->suspend_lock); } +EXPORT_SYMBOL_GPL(dm_internal_resume_fast); /*----------------------------------------------------------------- * Event notification. diff --git a/drivers/md/md.c b/drivers/md/md.c index cadf9cc02b25..717daad71fb1 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5080,7 +5080,8 @@ int md_run(struct mddev *mddev) } if (err) { mddev_detach(mddev); - pers->free(mddev, mddev->private); + if (mddev->private) + pers->free(mddev, mddev->private); module_put(pers->owner); bitmap_destroy(mddev); return err; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index a13f738a7b39..3ed9f42ddca6 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -467,8 +467,6 @@ static int raid0_run(struct mddev *mddev) dump_zones(mddev); ret = md_integrity_register(mddev); - if (ret) - raid0_free(mddev, conf); return ret; } diff --git a/drivers/mmc/core/pwrseq_simple.c b/drivers/mmc/core/pwrseq_simple.c index e9f1d8d84613..c53f14a7ce54 100644 --- a/drivers/mmc/core/pwrseq_simple.c +++ b/drivers/mmc/core/pwrseq_simple.c @@ -124,7 +124,7 @@ int mmc_pwrseq_simple_alloc(struct mmc_host *host, struct device *dev) PTR_ERR(pwrseq->reset_gpios[i]) != -ENOSYS) { ret = PTR_ERR(pwrseq->reset_gpios[i]); - while (--i) + while (i--) gpiod_put(pwrseq->reset_gpios[i]); goto clk_put; diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 5b76a173cd95..5897d8d8fa5a 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -526,6 +526,7 @@ config MTD_NAND_SUNXI config MTD_NAND_HISI504 tristate "Support for NAND controller on Hisilicon SoC Hip04" + depends on HAS_DMA help Enables support for NAND controller on Hisilicon SoC Hip04. diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 96b0b1d27df1..10b1f7a4fe50 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -480,6 +480,42 @@ static void disable_int(struct pxa3xx_nand_info *info, uint32_t int_mask) nand_writel(info, NDCR, ndcr | int_mask); } +static void drain_fifo(struct pxa3xx_nand_info *info, void *data, int len) +{ + if (info->ecc_bch) { + int timeout; + + /* + * According to the datasheet, when reading from NDDB + * with BCH enabled, after each 32 bytes reads, we + * have to make sure that the NDSR.RDDREQ bit is set. + * + * Drain the FIFO 8 32 bits reads at a time, and skip + * the polling on the last read. + */ + while (len > 8) { + __raw_readsl(info->mmio_base + NDDB, data, 8); + + for (timeout = 0; + !(nand_readl(info, NDSR) & NDSR_RDDREQ); + timeout++) { + if (timeout >= 5) { + dev_err(&info->pdev->dev, + "Timeout on RDDREQ while draining the FIFO\n"); + return; + } + + mdelay(1); + } + + data += 32; + len -= 8; + } + } + + __raw_readsl(info->mmio_base + NDDB, data, len); +} + static void handle_data_pio(struct pxa3xx_nand_info *info) { unsigned int do_bytes = min(info->data_size, info->chunk_size); @@ -496,14 +532,14 @@ static void handle_data_pio(struct pxa3xx_nand_info *info) DIV_ROUND_UP(info->oob_size, 4)); break; case STATE_PIO_READING: - __raw_readsl(info->mmio_base + NDDB, - info->data_buff + info->data_buff_pos, - DIV_ROUND_UP(do_bytes, 4)); + drain_fifo(info, + info->data_buff + info->data_buff_pos, + DIV_ROUND_UP(do_bytes, 4)); if (info->oob_size > 0) - __raw_readsl(info->mmio_base + NDDB, - info->oob_buff + info->oob_buff_pos, - DIV_ROUND_UP(info->oob_size, 4)); + drain_fifo(info, + info->oob_buff + info->oob_buff_pos, + DIV_ROUND_UP(info->oob_size, 4)); break; default: dev_err(&info->pdev->dev, "%s: invalid state %d\n", __func__, @@ -1572,6 +1608,8 @@ static int alloc_nand_resource(struct platform_device *pdev) int ret, irq, cs; pdata = dev_get_platdata(&pdev->dev); + if (pdata->num_cs <= 0) + return -ENODEV; info = devm_kzalloc(&pdev->dev, sizeof(*info) + (sizeof(*mtd) + sizeof(*host)) * pdata->num_cs, GFP_KERNEL); if (!info) diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index da4c79259f67..16e34b37d134 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -425,9 +425,10 @@ retry: ubi_warn(ubi, "corrupted VID header at PEB %d, LEB %d:%d", pnum, vol_id, lnum); err = -EBADMSG; - } else + } else { err = -EINVAL; ubi_ro_mode(ubi); + } } goto out_free; } else if (err == UBI_IO_BITFLIPS) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c026ce9cd7b6..7b4684ccdb3f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4038,6 +4038,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_fix_features = bond_fix_features, .ndo_bridge_setlink = ndo_dflt_netdev_switch_port_bridge_setlink, .ndo_bridge_dellink = ndo_dflt_netdev_switch_port_bridge_dellink, + .ndo_features_check = passthru_features_check, }; static const struct device_type bond_type = { diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 98d73aab52fe..58808f651452 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -131,7 +131,7 @@ config CAN_RCAR config CAN_XILINXCAN tristate "Xilinx CAN" - depends on ARCH_ZYNQ || MICROBLAZE || COMPILE_TEST + depends on ARCH_ZYNQ || ARM64 || MICROBLAZE || COMPILE_TEST depends on COMMON_CLK && HAS_IOMEM ---help--- Xilinx CAN driver. This driver supports both soft AXI CAN IP and diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index eeb4b8b6b335..f4e40aa4d2a2 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -291,13 +291,13 @@ static inline unsigned int get_tx_echo_mb(const struct at91_priv *priv) static inline u32 at91_read(const struct at91_priv *priv, enum at91_reg reg) { - return __raw_readl(priv->reg_base + reg); + return readl_relaxed(priv->reg_base + reg); } static inline void at91_write(const struct at91_priv *priv, enum at91_reg reg, u32 value) { - __raw_writel(value, priv->reg_base + reg); + writel_relaxed(value, priv->reg_base + reg); } static inline void set_mb_mode_prio(const struct at91_priv *priv, diff --git a/drivers/net/can/cc770/cc770_platform.c b/drivers/net/can/cc770/cc770_platform.c index b1e8851d3cc4..866e5e12fdd2 100644 --- a/drivers/net/can/cc770/cc770_platform.c +++ b/drivers/net/can/cc770/cc770_platform.c @@ -254,7 +254,7 @@ static int cc770_platform_remove(struct platform_device *pdev) return 0; } -static struct of_device_id cc770_platform_table[] = { +static const struct of_device_id cc770_platform_table[] = { {.compatible = "bosch,cc770"}, /* CC770 from Bosch */ {.compatible = "intc,82527"}, /* AN82527 from Intel CP */ {}, diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index fed1bbd0b0d2..e3d7e22a4fa0 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1725,7 +1725,7 @@ static int grcan_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id grcan_match[] = { +static const struct of_device_id grcan_match[] = { {.name = "GAISLER_GRCAN"}, {.name = "01_03d"}, {.name = "GAISLER_GRHCAN"}, diff --git a/drivers/net/can/led.c b/drivers/net/can/led.c index ab7f1b01be49..c1b667675fa1 100644 --- a/drivers/net/can/led.c +++ b/drivers/net/can/led.c @@ -30,20 +30,28 @@ void can_led_event(struct net_device *netdev, enum can_led_event event) case CAN_LED_EVENT_OPEN: led_trigger_event(priv->tx_led_trig, LED_FULL); led_trigger_event(priv->rx_led_trig, LED_FULL); + led_trigger_event(priv->rxtx_led_trig, LED_FULL); break; case CAN_LED_EVENT_STOP: led_trigger_event(priv->tx_led_trig, LED_OFF); led_trigger_event(priv->rx_led_trig, LED_OFF); + led_trigger_event(priv->rxtx_led_trig, LED_OFF); break; case CAN_LED_EVENT_TX: - if (led_delay) + if (led_delay) { led_trigger_blink_oneshot(priv->tx_led_trig, &led_delay, &led_delay, 1); + led_trigger_blink_oneshot(priv->rxtx_led_trig, + &led_delay, &led_delay, 1); + } break; case CAN_LED_EVENT_RX: - if (led_delay) + if (led_delay) { led_trigger_blink_oneshot(priv->rx_led_trig, &led_delay, &led_delay, 1); + led_trigger_blink_oneshot(priv->rxtx_led_trig, + &led_delay, &led_delay, 1); + } break; } } @@ -55,6 +63,7 @@ static void can_led_release(struct device *gendev, void *res) led_trigger_unregister_simple(priv->tx_led_trig); led_trigger_unregister_simple(priv->rx_led_trig); + led_trigger_unregister_simple(priv->rxtx_led_trig); } /* Register CAN LED triggers for a CAN device @@ -76,11 +85,15 @@ void devm_can_led_init(struct net_device *netdev) "%s-tx", netdev->name); snprintf(priv->rx_led_trig_name, sizeof(priv->rx_led_trig_name), "%s-rx", netdev->name); + snprintf(priv->rxtx_led_trig_name, sizeof(priv->rxtx_led_trig_name), + "%s-rxtx", netdev->name); led_trigger_register_simple(priv->tx_led_trig_name, &priv->tx_led_trig); led_trigger_register_simple(priv->rx_led_trig_name, &priv->rx_led_trig); + led_trigger_register_simple(priv->rxtx_led_trig_name, + &priv->rxtx_led_trig); devres_add(&netdev->dev, res); } @@ -97,7 +110,7 @@ static int can_led_notifier(struct notifier_block *nb, unsigned long msg, if (!priv) return NOTIFY_DONE; - if (!priv->tx_led_trig || !priv->rx_led_trig) + if (!priv->tx_led_trig || !priv->rx_led_trig || !priv->rxtx_led_trig) return NOTIFY_DONE; if (msg == NETDEV_CHANGENAME) { @@ -106,6 +119,9 @@ static int can_led_notifier(struct notifier_block *nb, unsigned long msg, snprintf(name, sizeof(name), "%s-rx", netdev->name); led_trigger_rename_static(name, priv->rx_led_trig); + + snprintf(name, sizeof(name), "%s-rxtx", netdev->name); + led_trigger_rename_static(name, priv->rxtx_led_trig); } return NOTIFY_DONE; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 2e04b3aeeb37..ef655177bb5e 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -312,8 +312,8 @@ static inline u32 m_can_fifo_read(const struct m_can_priv *priv, static inline void m_can_fifo_write(const struct m_can_priv *priv, u32 fpi, unsigned int offset, u32 val) { - return writel(val, priv->mram_base + priv->mcfg[MRAM_TXB].off + - fpi * TXB_ELEMENT_SIZE + offset); + writel(val, priv->mram_base + priv->mcfg[MRAM_TXB].off + + fpi * TXB_ELEMENT_SIZE + offset); } static inline void m_can_config_endisable(const struct m_can_priv *priv, diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index ad024e60ba8c..c7427bdd3a4b 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -43,7 +43,7 @@ struct mpc5xxx_can_data { }; #ifdef CONFIG_PPC_MPC52xx -static struct of_device_id mpc52xx_cdm_ids[] = { +static const struct of_device_id mpc52xx_cdm_ids[] = { { .compatible = "fsl,mpc5200-cdm", }, {} }; diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c index 93115250eaf5..0552ed46a206 100644 --- a/drivers/net/can/sja1000/sja1000_platform.c +++ b/drivers/net/can/sja1000/sja1000_platform.c @@ -242,7 +242,7 @@ static int sp_remove(struct platform_device *pdev) return 0; } -static struct of_device_id sp_of_table[] = { +static const struct of_device_id sp_of_table[] = { {.compatible = "nxp,sja1000"}, {}, }; diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index bacca0bd89c1..411c1af92c62 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -139,7 +139,7 @@ struct tx_msg { u8 cmd; u8 net; u8 dlc; - __le32 hnd; + u32 hnd; /* opaque handle, not used by device */ __le32 id; /* upper 3 bits contain flags */ u8 data[8]; }; @@ -149,7 +149,7 @@ struct tx_done_msg { u8 cmd; u8 net; u8 status; - __le32 hnd; + u32 hnd; /* opaque handle, not used by device */ __le32 ts; }; diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index a316fa4b91ab..d269ae0b072a 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -14,6 +14,7 @@ * Copyright (C) 2015 Valeo S.A. */ +#include <linux/spinlock.h> #include <linux/kernel.h> #include <linux/completion.h> #include <linux/module.h> @@ -467,10 +468,11 @@ struct kvaser_usb { struct kvaser_usb_net_priv { struct can_priv can; - atomic_t active_tx_urbs; - struct usb_anchor tx_submitted; + spinlock_t tx_contexts_lock; + int active_tx_contexts; struct kvaser_usb_tx_urb_context tx_contexts[MAX_TX_URBS]; + struct usb_anchor tx_submitted; struct completion start_comp, stop_comp; struct kvaser_usb *dev; @@ -694,6 +696,7 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev, struct kvaser_usb_net_priv *priv; struct sk_buff *skb; struct can_frame *cf; + unsigned long flags; u8 channel, tid; channel = msg->u.tx_acknowledge_header.channel; @@ -737,12 +740,15 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev, stats->tx_packets++; stats->tx_bytes += context->dlc; - can_get_echo_skb(priv->netdev, context->echo_index); - context->echo_index = MAX_TX_URBS; - atomic_dec(&priv->active_tx_urbs); + spin_lock_irqsave(&priv->tx_contexts_lock, flags); + can_get_echo_skb(priv->netdev, context->echo_index); + context->echo_index = MAX_TX_URBS; + --priv->active_tx_contexts; netif_wake_queue(priv->netdev); + + spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); } static void kvaser_usb_simple_msg_callback(struct urb *urb) @@ -803,17 +809,6 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv, return 0; } -static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) -{ - int i; - - usb_kill_anchored_urbs(&priv->tx_submitted); - atomic_set(&priv->active_tx_urbs, 0); - - for (i = 0; i < MAX_TX_URBS; i++) - priv->tx_contexts[i].echo_index = MAX_TX_URBS; -} - static void kvaser_usb_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, const struct kvaser_usb_error_summary *es, struct can_frame *cf) @@ -1515,6 +1510,24 @@ error: return err; } +static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv) +{ + int i; + + priv->active_tx_contexts = 0; + for (i = 0; i < MAX_TX_URBS; i++) + priv->tx_contexts[i].echo_index = MAX_TX_URBS; +} + +/* This method might sleep. Do not call it in the atomic context + * of URB completions. + */ +static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) +{ + usb_kill_anchored_urbs(&priv->tx_submitted); + kvaser_usb_reset_tx_urb_contexts(priv); +} + static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev) { int i; @@ -1634,6 +1647,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, struct kvaser_msg *msg; int i, err, ret = NETDEV_TX_OK; u8 *msg_tx_can_flags = NULL; /* GCC */ + unsigned long flags; if (can_dropped_invalid_skb(netdev, skb)) return NETDEV_TX_OK; @@ -1687,12 +1701,21 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, if (cf->can_id & CAN_RTR_FLAG) *msg_tx_can_flags |= MSG_FLAG_REMOTE_FRAME; + spin_lock_irqsave(&priv->tx_contexts_lock, flags); for (i = 0; i < ARRAY_SIZE(priv->tx_contexts); i++) { if (priv->tx_contexts[i].echo_index == MAX_TX_URBS) { context = &priv->tx_contexts[i]; + + context->echo_index = i; + can_put_echo_skb(skb, netdev, context->echo_index); + ++priv->active_tx_contexts; + if (priv->active_tx_contexts >= MAX_TX_URBS) + netif_stop_queue(netdev); + break; } } + spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); /* This should never happen; it implies a flow control bug */ if (!context) { @@ -1704,7 +1727,6 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, } context->priv = priv; - context->echo_index = i; context->dlc = cf->can_dlc; msg->u.tx_can.tid = context->echo_index; @@ -1716,18 +1738,17 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, kvaser_usb_write_bulk_callback, context); usb_anchor_urb(urb, &priv->tx_submitted); - can_put_echo_skb(skb, netdev, context->echo_index); - - atomic_inc(&priv->active_tx_urbs); - - if (atomic_read(&priv->active_tx_urbs) >= MAX_TX_URBS) - netif_stop_queue(netdev); - err = usb_submit_urb(urb, GFP_ATOMIC); if (unlikely(err)) { + spin_lock_irqsave(&priv->tx_contexts_lock, flags); + can_free_echo_skb(netdev, context->echo_index); + context->echo_index = MAX_TX_URBS; + --priv->active_tx_contexts; + netif_wake_queue(netdev); + + spin_unlock_irqrestore(&priv->tx_contexts_lock, flags); - atomic_dec(&priv->active_tx_urbs); usb_unanchor_urb(urb); stats->tx_dropped++; @@ -1835,7 +1856,7 @@ static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev) if (!dev->nets[i]) continue; - unregister_netdev(dev->nets[i]->netdev); + unregister_candev(dev->nets[i]->netdev); } kvaser_usb_unlink_all_urbs(dev); @@ -1854,7 +1875,7 @@ static int kvaser_usb_init_one(struct usb_interface *intf, struct kvaser_usb *dev = usb_get_intfdata(intf); struct net_device *netdev; struct kvaser_usb_net_priv *priv; - int i, err; + int err; err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel); if (err) @@ -1868,19 +1889,17 @@ static int kvaser_usb_init_one(struct usb_interface *intf, priv = netdev_priv(netdev); + init_usb_anchor(&priv->tx_submitted); init_completion(&priv->start_comp); init_completion(&priv->stop_comp); - init_usb_anchor(&priv->tx_submitted); - atomic_set(&priv->active_tx_urbs, 0); - - for (i = 0; i < ARRAY_SIZE(priv->tx_contexts); i++) - priv->tx_contexts[i].echo_index = MAX_TX_URBS; - priv->dev = dev; priv->netdev = netdev; priv->channel = channel; + spin_lock_init(&priv->tx_contexts_lock); + kvaser_usb_reset_tx_urb_contexts(priv); + priv->can.state = CAN_STATE_STOPPED; priv->can.clock.freq = CAN_USB_CLOCK; priv->can.bittiming_const = &kvaser_usb_bittiming_const; diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 6c6764312285..6bddfe062b51 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -1185,7 +1185,7 @@ static int xcan_remove(struct platform_device *pdev) } /* Match table for OF platform binding */ -static struct of_device_id xcan_of_match[] = { +static const struct of_device_id xcan_of_match[] = { { .compatible = "xlnx,zynq-can-1.0", }, { .compatible = "xlnx,axi-can-1.00.a", }, { /* end of list */ }, diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 48e62a34f7f2..18550c7ebe6f 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -7,7 +7,7 @@ config NET_DSA_MV88E6XXX config NET_DSA_MV88E6060 tristate "Marvell 88E6060 ethernet switch chip support" - select NET_DSA + depends on NET_DSA select NET_DSA_TAG_TRAILER ---help--- This enables support for the Marvell 88E6060 ethernet switch @@ -19,7 +19,7 @@ config NET_DSA_MV88E6XXX_NEED_PPU config NET_DSA_MV88E6131 tristate "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support" - select NET_DSA + depends on NET_DSA select NET_DSA_MV88E6XXX select NET_DSA_MV88E6XXX_NEED_PPU select NET_DSA_TAG_DSA @@ -29,7 +29,7 @@ config NET_DSA_MV88E6131 config NET_DSA_MV88E6123_61_65 tristate "Marvell 88E6123/6161/6165 ethernet switch chip support" - select NET_DSA + depends on NET_DSA select NET_DSA_MV88E6XXX select NET_DSA_TAG_EDSA ---help--- @@ -38,7 +38,7 @@ config NET_DSA_MV88E6123_61_65 config NET_DSA_MV88E6171 tristate "Marvell 88E6171/6172 ethernet switch chip support" - select NET_DSA + depends on NET_DSA select NET_DSA_MV88E6XXX select NET_DSA_TAG_EDSA ---help--- @@ -47,7 +47,7 @@ config NET_DSA_MV88E6171 config NET_DSA_MV88E6352 tristate "Marvell 88E6176/88E6352 ethernet switch chip support" - select NET_DSA + depends on NET_DSA select NET_DSA_MV88E6XXX select NET_DSA_TAG_EDSA ---help--- @@ -56,8 +56,7 @@ config NET_DSA_MV88E6352 config NET_DSA_BCM_SF2 tristate "Broadcom Starfighter 2 Ethernet switch support" - depends on HAS_IOMEM - select NET_DSA + depends on HAS_IOMEM && NET_DSA select NET_DSA_TAG_BRCM select FIXED_PHY select BCM7XXX_PHY diff --git a/drivers/net/dsa/mv88e6123_61_65.c b/drivers/net/dsa/mv88e6123_61_65.c index e9c736e1cef3..2d7e1ffe9fdc 100644 --- a/drivers/net/dsa/mv88e6123_61_65.c +++ b/drivers/net/dsa/mv88e6123_61_65.c @@ -222,28 +222,6 @@ static int mv88e6123_61_65_setup_port(struct dsa_switch *ds, int p) val |= 0x000c; REG_WRITE(addr, 0x04, val); - /* Port Control 1: disable trunking. Also, if this is the - * CPU port, enable learn messages to be sent to this port. - */ - REG_WRITE(addr, 0x05, dsa_is_cpu_port(ds, p) ? 0x8000 : 0x0000); - - /* Port based VLAN map: give each port its own address - * database, allow the CPU port to talk to each of the 'real' - * ports, and allow each of the 'real' ports to only talk to - * the upstream port. - */ - val = (p & 0xf) << 12; - if (dsa_is_cpu_port(ds, p)) - val |= ds->phys_port_mask; - else - val |= 1 << dsa_upstream_port(ds); - REG_WRITE(addr, 0x06, val); - - /* Default VLAN ID and priority: don't set a default VLAN - * ID, and set the default packet priority to zero. - */ - REG_WRITE(addr, 0x07, 0x0000); - /* Port Control 2: don't force a good FCS, set the maximum * frame size to 10240 bytes, don't let the switch add or * strip 802.1q tags, don't discard tagged or untagged frames @@ -288,18 +266,17 @@ static int mv88e6123_61_65_setup_port(struct dsa_switch *ds, int p) */ REG_WRITE(addr, 0x19, 0x7654); - return 0; + return mv88e6xxx_setup_port_common(ds, p); } static int mv88e6123_61_65_setup(struct dsa_switch *ds) { - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); int i; int ret; - mutex_init(&ps->smi_mutex); - mutex_init(&ps->stats_mutex); - mutex_init(&ps->phy_mutex); + ret = mv88e6xxx_setup_common(ds); + if (ret < 0) + return ret; ret = mv88e6123_61_65_switch_reset(ds); if (ret < 0) diff --git a/drivers/net/dsa/mv88e6171.c b/drivers/net/dsa/mv88e6171.c index 9808c860a797..18cfead83dc9 100644 --- a/drivers/net/dsa/mv88e6171.c +++ b/drivers/net/dsa/mv88e6171.c @@ -17,6 +17,10 @@ #include <net/dsa.h> #include "mv88e6xxx.h" +/* Switch product IDs */ +#define ID_6171 0x1710 +#define ID_6172 0x1720 + static char *mv88e6171_probe(struct device *host_dev, int sw_addr) { struct mii_bus *bus = dsa_host_dev_to_mii_bus(host_dev); @@ -27,9 +31,9 @@ static char *mv88e6171_probe(struct device *host_dev, int sw_addr) ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03); if (ret >= 0) { - if ((ret & 0xfff0) == 0x1710) + if ((ret & 0xfff0) == ID_6171) return "Marvell 88E6171"; - if ((ret & 0xfff0) == 0x1720) + if ((ret & 0xfff0) == ID_6172) return "Marvell 88E6172"; } @@ -221,28 +225,6 @@ static int mv88e6171_setup_port(struct dsa_switch *ds, int p) val |= 0x000c; REG_WRITE(addr, 0x04, val); - /* Port Control 1: disable trunking. Also, if this is the - * CPU port, enable learn messages to be sent to this port. - */ - REG_WRITE(addr, 0x05, dsa_is_cpu_port(ds, p) ? 0x8000 : 0x0000); - - /* Port based VLAN map: give each port its own address - * database, allow the CPU port to talk to each of the 'real' - * ports, and allow each of the 'real' ports to only talk to - * the upstream port. - */ - val = (p & 0xf) << 12; - if (dsa_is_cpu_port(ds, p)) - val |= ds->phys_port_mask; - else - val |= 1 << dsa_upstream_port(ds); - REG_WRITE(addr, 0x06, val); - - /* Default VLAN ID and priority: don't set a default VLAN - * ID, and set the default packet priority to zero. - */ - REG_WRITE(addr, 0x07, 0x0000); - /* Port Control 2: don't force a good FCS, set the maximum * frame size to 10240 bytes, don't let the switch add or * strip 802.1q tags, don't discard tagged or untagged frames @@ -287,17 +269,17 @@ static int mv88e6171_setup_port(struct dsa_switch *ds, int p) */ REG_WRITE(addr, 0x19, 0x7654); - return 0; + return mv88e6xxx_setup_port_common(ds, p); } static int mv88e6171_setup(struct dsa_switch *ds) { - struct mv88e6xxx_priv_state *ps = (void *)(ds + 1); int i; int ret; - mutex_init(&ps->smi_mutex); - mutex_init(&ps->stats_mutex); + ret = mv88e6xxx_setup_common(ds); + if (ret < 0) + return ret; ret = mv88e6171_switch_reset(ds); if (ret < 0) @@ -318,8 +300,6 @@ static int mv88e6171_setup(struct dsa_switch *ds) return ret; } - mutex_init(&ps->phy_mutex); - return 0; } @@ -410,6 +390,28 @@ static int mv88e6171_get_sset_count(struct dsa_switch *ds) return ARRAY_SIZE(mv88e6171_hw_stats); } +static int mv88e6171_get_eee(struct dsa_switch *ds, int port, + struct ethtool_eee *e) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + + if (ps->id == ID_6172) + return mv88e6xxx_get_eee(ds, port, e); + + return -EOPNOTSUPP; +} + +static int mv88e6171_set_eee(struct dsa_switch *ds, int port, + struct phy_device *phydev, struct ethtool_eee *e) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + + if (ps->id == ID_6172) + return mv88e6xxx_set_eee(ds, port, phydev, e); + + return -EOPNOTSUPP; +} + struct dsa_switch_driver mv88e6171_switch_driver = { .tag_protocol = DSA_TAG_PROTO_EDSA, .priv_size = sizeof(struct mv88e6xxx_priv_state), @@ -422,11 +424,19 @@ struct dsa_switch_driver mv88e6171_switch_driver = { .get_strings = mv88e6171_get_strings, .get_ethtool_stats = mv88e6171_get_ethtool_stats, .get_sset_count = mv88e6171_get_sset_count, + .set_eee = mv88e6171_set_eee, + .get_eee = mv88e6171_get_eee, #ifdef CONFIG_NET_DSA_HWMON .get_temp = mv88e6xxx_get_temp, #endif .get_regs_len = mv88e6xxx_get_regs_len, .get_regs = mv88e6xxx_get_regs, + .port_join_bridge = mv88e6xxx_join_bridge, + .port_leave_bridge = mv88e6xxx_leave_bridge, + .port_stp_update = mv88e6xxx_port_stp_update, + .fdb_add = mv88e6xxx_port_fdb_add, + .fdb_del = mv88e6xxx_port_fdb_del, + .fdb_getnext = mv88e6xxx_port_fdb_getnext, }; MODULE_ALIAS("platform:mv88e6171"); diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c index 7bc5998384c6..41fe3a6a72d1 100644 --- a/drivers/net/dsa/mv88e6352.c +++ b/drivers/net/dsa/mv88e6352.c @@ -215,28 +215,6 @@ static int mv88e6352_setup_port(struct dsa_switch *ds, int p) val |= 0x000c; REG_WRITE(addr, 0x04, val); - /* Port Control 1: disable trunking. Also, if this is the - * CPU port, enable learn messages to be sent to this port. - */ - REG_WRITE(addr, 0x05, dsa_is_cpu_port(ds, p) ? 0x8000 : 0x0000); - - /* Port based VLAN map: give each port its own address - * database, allow the CPU port to talk to each of the 'real' - * ports, and allow each of the 'real' ports to only talk to - * the upstream port. - */ - val = (p & 0xf) << 12; - if (dsa_is_cpu_port(ds, p)) - val |= ds->phys_port_mask; - else - val |= 1 << dsa_upstream_port(ds); - REG_WRITE(addr, 0x06, val); - - /* Default VLAN ID and priority: don't set a default VLAN - * ID, and set the default packet priority to zero. - */ - REG_WRITE(addr, 0x07, 0x0000); - /* Port Control 2: don't force a good FCS, set the maximum * frame size to 10240 bytes, don't let the switch add or * strip 802.1q tags, don't discard tagged or untagged frames @@ -281,7 +259,7 @@ static int mv88e6352_setup_port(struct dsa_switch *ds, int p) */ REG_WRITE(addr, 0x19, 0x7654); - return 0; + return mv88e6xxx_setup_port_common(ds, p); } #ifdef CONFIG_NET_DSA_HWMON @@ -385,12 +363,11 @@ static int mv88e6352_setup(struct dsa_switch *ds) int ret; int i; - mutex_init(&ps->smi_mutex); - mutex_init(&ps->stats_mutex); - mutex_init(&ps->phy_mutex); - mutex_init(&ps->eeprom_mutex); + ret = mv88e6xxx_setup_common(ds); + if (ret < 0) + return ret; - ps->id = REG_READ(REG_PORT(0), 0x03) & 0xfff0; + mutex_init(&ps->eeprom_mutex); ret = mv88e6352_switch_reset(ds); if (ret < 0) @@ -729,6 +706,12 @@ struct dsa_switch_driver mv88e6352_switch_driver = { .set_eeprom = mv88e6352_set_eeprom, .get_regs_len = mv88e6xxx_get_regs_len, .get_regs = mv88e6xxx_get_regs, + .port_join_bridge = mv88e6xxx_join_bridge, + .port_leave_bridge = mv88e6xxx_leave_bridge, + .port_stp_update = mv88e6xxx_port_stp_update, + .fdb_add = mv88e6xxx_port_fdb_add, + .fdb_del = mv88e6xxx_port_fdb_del, + .fdb_getnext = mv88e6xxx_port_fdb_getnext, }; MODULE_ALIAS("platform:mv88e6352"); diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index c18ffc98aacc..13572cc24c6d 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -9,6 +9,8 @@ */ #include <linux/delay.h> +#include <linux/etherdevice.h> +#include <linux/if_bridge.h> #include <linux/jiffies.h> #include <linux/list.h> #include <linux/module.h> @@ -72,19 +74,16 @@ int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg) return ret & 0xffff; } -int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg) +/* Must be called with SMI mutex held */ +static int _mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg) { - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); struct mii_bus *bus = dsa_host_dev_to_mii_bus(ds->master_dev); int ret; if (bus == NULL) return -EINVAL; - mutex_lock(&ps->smi_mutex); ret = __mv88e6xxx_reg_read(bus, ds->pd->sw_addr, addr, reg); - mutex_unlock(&ps->smi_mutex); - if (ret < 0) return ret; @@ -94,6 +93,18 @@ int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg) return ret; } +int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int ret; + + mutex_lock(&ps->smi_mutex); + ret = _mv88e6xxx_reg_read(ds, addr, reg); + mutex_unlock(&ps->smi_mutex); + + return ret; +} + int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr, int reg, u16 val) { @@ -125,11 +136,11 @@ int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr, return 0; } -int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val) +/* Must be called with SMI mutex held */ +static int _mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, + u16 val) { - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); struct mii_bus *bus = dsa_host_dev_to_mii_bus(ds->master_dev); - int ret; if (bus == NULL) return -EINVAL; @@ -137,8 +148,16 @@ int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val) dev_dbg(ds->master_dev, "-> addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n", addr, reg, val); + return __mv88e6xxx_reg_write(bus, ds->pd->sw_addr, addr, reg, val); +} + +int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int ret; + mutex_lock(&ps->smi_mutex); - ret = __mv88e6xxx_reg_write(bus, ds->pd->sw_addr, addr, reg, val); + ret = _mv88e6xxx_reg_write(ds, addr, reg, val); mutex_unlock(&ps->smi_mutex); return ret; @@ -627,6 +646,31 @@ int mv88e6xxx_eeprom_busy_wait(struct dsa_switch *ds) return mv88e6xxx_wait(ds, REG_GLOBAL2, 0x14, 0x8000); } +/* Must be called with SMI lock held */ +static int _mv88e6xxx_wait(struct dsa_switch *ds, int reg, int offset, u16 mask) +{ + unsigned long timeout = jiffies + HZ / 10; + + while (time_before(jiffies, timeout)) { + int ret; + + ret = _mv88e6xxx_reg_read(ds, reg, offset); + if (ret < 0) + return ret; + if (!(ret & mask)) + return 0; + + usleep_range(1000, 2000); + } + return -ETIMEDOUT; +} + +/* Must be called with SMI lock held */ +static int _mv88e6xxx_atu_wait(struct dsa_switch *ds) +{ + return _mv88e6xxx_wait(ds, REG_GLOBAL, 0x0b, ATU_BUSY); +} + int mv88e6xxx_phy_read_indirect(struct dsa_switch *ds, int addr, int regnum) { int ret; @@ -700,6 +744,423 @@ int mv88e6xxx_set_eee(struct dsa_switch *ds, int port, return 0; } +static int _mv88e6xxx_atu_cmd(struct dsa_switch *ds, int fid, u16 cmd) +{ + int ret; + + ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, 0x01, fid); + if (ret < 0) + return ret; + + ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, 0x0b, cmd); + if (ret < 0) + return ret; + + return _mv88e6xxx_atu_wait(ds); +} + +static int _mv88e6xxx_flush_fid(struct dsa_switch *ds, int fid) +{ + int ret; + + ret = _mv88e6xxx_atu_wait(ds); + if (ret < 0) + return ret; + + return _mv88e6xxx_atu_cmd(ds, fid, ATU_CMD_FLUSH_NONSTATIC_FID); +} + +static int mv88e6xxx_set_port_state(struct dsa_switch *ds, int port, u8 state) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int reg, ret; + u8 oldstate; + + mutex_lock(&ps->smi_mutex); + + reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), 0x04); + if (reg < 0) + goto abort; + + oldstate = reg & PSTATE_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 >= PSTATE_LEARNING && state <= PSTATE_BLOCKING) { + ret = _mv88e6xxx_flush_fid(ds, ps->fid[port]); + if (ret) + goto abort; + } + reg = (reg & ~PSTATE_MASK) | state; + ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), 0x04, reg); + } + +abort: + mutex_unlock(&ps->smi_mutex); + return ret; +} + +/* Must be called with smi lock held */ +static int _mv88e6xxx_update_port_config(struct dsa_switch *ds, int port) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + u8 fid = ps->fid[port]; + u16 reg = fid << 12; + + if (dsa_is_cpu_port(ds, port)) + reg |= ds->phys_port_mask; + else + reg |= (ps->bridge_mask[fid] | + (1 << dsa_upstream_port(ds))) & ~(1 << port); + + return _mv88e6xxx_reg_write(ds, REG_PORT(port), 0x06, reg); +} + +/* Must be called with smi lock held */ +static int _mv88e6xxx_update_bridge_config(struct dsa_switch *ds, int fid) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int port; + u32 mask; + int ret; + + mask = ds->phys_port_mask; + while (mask) { + port = __ffs(mask); + mask &= ~(1 << port); + if (ps->fid[port] != fid) + continue; + + ret = _mv88e6xxx_update_port_config(ds, port); + if (ret) + return ret; + } + + return _mv88e6xxx_flush_fid(ds, fid); +} + +/* Bridge handling functions */ + +int mv88e6xxx_join_bridge(struct dsa_switch *ds, int port, u32 br_port_mask) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int ret = 0; + u32 nmask; + int fid; + + /* If the bridge group is not empty, join that group. + * Otherwise create a new group. + */ + fid = ps->fid[port]; + nmask = br_port_mask & ~(1 << port); + if (nmask) + fid = ps->fid[__ffs(nmask)]; + + nmask = ps->bridge_mask[fid] | (1 << port); + if (nmask != br_port_mask) { + netdev_err(ds->ports[port], + "join: Bridge port mask mismatch fid=%d mask=0x%x expected 0x%x\n", + fid, br_port_mask, nmask); + return -EINVAL; + } + + mutex_lock(&ps->smi_mutex); + + ps->bridge_mask[fid] = br_port_mask; + + if (fid != ps->fid[port]) { + ps->fid_mask |= 1 << ps->fid[port]; + ps->fid[port] = fid; + ret = _mv88e6xxx_update_bridge_config(ds, fid); + } + + mutex_unlock(&ps->smi_mutex); + + return ret; +} + +int mv88e6xxx_leave_bridge(struct dsa_switch *ds, int port, u32 br_port_mask) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + u8 fid, newfid; + int ret; + + fid = ps->fid[port]; + + if (ps->bridge_mask[fid] != br_port_mask) { + netdev_err(ds->ports[port], + "leave: Bridge port mask mismatch fid=%d mask=0x%x expected 0x%x\n", + fid, br_port_mask, ps->bridge_mask[fid]); + return -EINVAL; + } + + /* If the port was the last port of a bridge, we are done. + * Otherwise assign a new fid to the port, and fix up + * the bridge configuration. + */ + if (br_port_mask == (1 << port)) + return 0; + + mutex_lock(&ps->smi_mutex); + + newfid = __ffs(ps->fid_mask); + ps->fid[port] = newfid; + ps->fid_mask &= (1 << newfid); + ps->bridge_mask[fid] &= ~(1 << port); + ps->bridge_mask[newfid] = 1 << port; + + ret = _mv88e6xxx_update_bridge_config(ds, fid); + if (!ret) + ret = _mv88e6xxx_update_bridge_config(ds, newfid); + + mutex_unlock(&ps->smi_mutex); + + return ret; +} + +int mv88e6xxx_port_stp_update(struct dsa_switch *ds, int port, u8 state) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int stp_state; + + switch (state) { + case BR_STATE_DISABLED: + stp_state = PSTATE_DISABLED; + break; + case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: + stp_state = PSTATE_BLOCKING; + break; + case BR_STATE_LEARNING: + stp_state = PSTATE_LEARNING; + break; + case BR_STATE_FORWARDING: + default: + stp_state = PSTATE_FORWARDING; + 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->port_state[port] = stp_state; + set_bit(port, &ps->port_state_update_mask); + schedule_work(&ps->bridge_work); + + return 0; +} + +static int __mv88e6xxx_write_addr(struct dsa_switch *ds, + const unsigned char *addr) +{ + int i, ret; + + for (i = 0; i < 3; i++) { + ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, 0x0d + i, + (addr[i * 2] << 8) | addr[i * 2 + 1]); + if (ret < 0) + return ret; + } + + return 0; +} + +static int __mv88e6xxx_read_addr(struct dsa_switch *ds, unsigned char *addr) +{ + int i, ret; + + for (i = 0; i < 3; i++) { + ret = _mv88e6xxx_reg_read(ds, REG_GLOBAL, 0x0d + i); + if (ret < 0) + return ret; + addr[i * 2] = ret >> 8; + addr[i * 2 + 1] = ret & 0xff; + } + + return 0; +} + +static int __mv88e6xxx_port_fdb_cmd(struct dsa_switch *ds, int port, + const unsigned char *addr, int state) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + u8 fid = ps->fid[port]; + int ret; + + ret = _mv88e6xxx_atu_wait(ds); + if (ret < 0) + return ret; + + ret = __mv88e6xxx_write_addr(ds, addr); + if (ret < 0) + return ret; + + ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, 0x0c, + (0x10 << port) | state); + if (ret) + return ret; + + ret = _mv88e6xxx_atu_cmd(ds, fid, ATU_CMD_LOAD_FID); + + return ret; +} + +int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + int state = is_multicast_ether_addr(addr) ? + FDB_STATE_MC_STATIC : FDB_STATE_STATIC; + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int ret; + + mutex_lock(&ps->smi_mutex); + ret = __mv88e6xxx_port_fdb_cmd(ds, port, addr, state); + mutex_unlock(&ps->smi_mutex); + + return ret; +} + +int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int ret; + + mutex_lock(&ps->smi_mutex); + ret = __mv88e6xxx_port_fdb_cmd(ds, port, addr, FDB_STATE_UNUSED); + mutex_unlock(&ps->smi_mutex); + + return ret; +} + +static int __mv88e6xxx_port_getnext(struct dsa_switch *ds, int port, + unsigned char *addr, bool *is_static) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + u8 fid = ps->fid[port]; + int ret, state; + + ret = _mv88e6xxx_atu_wait(ds); + if (ret < 0) + return ret; + + ret = __mv88e6xxx_write_addr(ds, addr); + if (ret < 0) + return ret; + + do { + ret = _mv88e6xxx_atu_cmd(ds, fid, ATU_CMD_GETNEXT_FID); + if (ret < 0) + return ret; + + ret = _mv88e6xxx_reg_read(ds, REG_GLOBAL, 0x0c); + if (ret < 0) + return ret; + state = ret & FDB_STATE_MASK; + if (state == FDB_STATE_UNUSED) + return -ENOENT; + } while (!(((ret >> 4) & 0xff) & (1 << port))); + + ret = __mv88e6xxx_read_addr(ds, addr); + if (ret < 0) + return ret; + + *is_static = state == (is_multicast_ether_addr(addr) ? + FDB_STATE_MC_STATIC : FDB_STATE_STATIC); + + return 0; +} + +/* get next entry for port */ +int mv88e6xxx_port_fdb_getnext(struct dsa_switch *ds, int port, + unsigned char *addr, bool *is_static) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int ret; + + mutex_lock(&ps->smi_mutex); + ret = __mv88e6xxx_port_getnext(ds, port, addr, is_static); + mutex_unlock(&ps->smi_mutex); + + return ret; +} + +static void mv88e6xxx_bridge_work(struct work_struct *work) +{ + struct mv88e6xxx_priv_state *ps; + struct dsa_switch *ds; + int port; + + 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->port_state[port]); + } +} + +int mv88e6xxx_setup_port_common(struct dsa_switch *ds, int port) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + int ret, fid; + + mutex_lock(&ps->smi_mutex); + + /* Port Control 1: disable trunking, disable sending + * learning messages to this port. + */ + ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), 0x05, 0x0000); + if (ret) + goto abort; + + /* Port based VLAN map: give each port its own address + * database, allow the CPU port to talk to each of the 'real' + * ports, and allow each of the 'real' ports to only talk to + * the upstream port. + */ + fid = __ffs(ps->fid_mask); + ps->fid[port] = fid; + ps->fid_mask &= ~(1 << fid); + + if (!dsa_is_cpu_port(ds, port)) + ps->bridge_mask[fid] = 1 << port; + + ret = _mv88e6xxx_update_port_config(ds, port); + if (ret) + goto abort; + + /* Default VLAN ID and priority: don't set a default VLAN + * ID, and set the default packet priority to zero. + */ + ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), 0x07, 0x0000); +abort: + mutex_unlock(&ps->smi_mutex); + return ret; +} + +int mv88e6xxx_setup_common(struct dsa_switch *ds) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + + mutex_init(&ps->smi_mutex); + mutex_init(&ps->stats_mutex); + mutex_init(&ps->phy_mutex); + + ps->id = REG_READ(REG_PORT(0), 0x03) & 0xfff0; + + ps->fid_mask = (1 << DSA_MAX_PORTS) - 1; + + INIT_WORK(&ps->bridge_work, mv88e6xxx_bridge_work); + + return 0; +} + static int __init mv88e6xxx_init(void) { #if IS_ENABLED(CONFIG_NET_DSA_MV88E6131) diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 5fd42ced9011..aaf239aba726 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -15,6 +15,30 @@ #define REG_GLOBAL 0x1b #define REG_GLOBAL2 0x1c +/* ATU commands */ + +#define ATU_BUSY 0x8000 + +#define ATU_CMD_LOAD_FID (ATU_BUSY | 0x3000) +#define ATU_CMD_GETNEXT_FID (ATU_BUSY | 0x4000) +#define ATU_CMD_FLUSH_NONSTATIC_FID (ATU_BUSY | 0x6000) + +/* port states */ + +#define PSTATE_MASK 0x03 +#define PSTATE_DISABLED 0x00 +#define PSTATE_BLOCKING 0x01 +#define PSTATE_LEARNING 0x02 +#define PSTATE_FORWARDING 0x03 + +/* FDB states */ + +#define FDB_STATE_MASK 0x0f + +#define FDB_STATE_UNUSED 0x00 +#define FDB_STATE_MC_STATIC 0x07 /* static multicast */ +#define FDB_STATE_STATIC 0x0e /* static unicast */ + struct mv88e6xxx_priv_state { /* When using multi-chip addressing, this mutex protects * access to the indirect access registers. (In single-chip @@ -49,6 +73,17 @@ struct mv88e6xxx_priv_state { struct mutex eeprom_mutex; int id; /* switch product id */ + + /* hw bridging */ + + u32 fid_mask; + u8 fid[DSA_MAX_PORTS]; + u16 bridge_mask[DSA_MAX_PORTS]; + + unsigned long port_state_update_mask; + u8 port_state[DSA_MAX_PORTS]; + + struct work_struct bridge_work; }; struct mv88e6xxx_hw_stat { @@ -57,6 +92,8 @@ struct mv88e6xxx_hw_stat { int reg; }; +int mv88e6xxx_setup_port_common(struct dsa_switch *ds, int port); +int mv88e6xxx_setup_common(struct dsa_switch *ds); int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg); int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg); int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr, @@ -91,6 +128,15 @@ int mv88e6xxx_phy_write_indirect(struct dsa_switch *ds, int addr, int regnum, int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e); int mv88e6xxx_set_eee(struct dsa_switch *ds, int port, struct phy_device *phydev, struct ethtool_eee *e); +int mv88e6xxx_join_bridge(struct dsa_switch *ds, int port, u32 br_port_mask); +int mv88e6xxx_leave_bridge(struct dsa_switch *ds, int port, u32 br_port_mask); +int mv88e6xxx_port_stp_update(struct dsa_switch *ds, int port, u8 state); +int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); +int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); +int mv88e6xxx_port_fdb_getnext(struct dsa_switch *ds, int port, + unsigned char *addr, bool *is_static); extern struct dsa_switch_driver mv88e6131_switch_driver; extern struct dsa_switch_driver mv88e6123_61_65_switch_driver; diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c index ec20611e9de2..0c37aefaaea0 100644 --- a/drivers/net/ethernet/adi/bfin_mac.c +++ b/drivers/net/ethernet/adi/bfin_mac.c @@ -983,7 +983,7 @@ static int bfin_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int bfin_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int bfin_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; u32 remainder; @@ -1003,7 +1003,7 @@ static int bfin_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int bfin_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { u64 ns; unsigned long flags; @@ -1039,8 +1039,8 @@ static struct ptp_clock_info bfin_ptp_caps = { .pps = 0, .adjfreq = bfin_ptp_adjfreq, .adjtime = bfin_ptp_adjtime, - .gettime = bfin_ptp_gettime, - .settime = bfin_ptp_settime, + .gettime64 = bfin_ptp_gettime, + .settime64 = bfin_ptp_settime, .enable = bfin_ptp_enable, }; diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 2b8bfeeee9cf..ae89de7deb13 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1588,7 +1588,7 @@ static int greth_of_remove(struct platform_device *of_dev) return 0; } -static struct of_device_id greth_of_match[] = { +static const struct of_device_id greth_of_match[] = { { .name = "GAISLER_ETHMAC", }, diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index fd9296a5014d..79ea35869e1e 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -89,7 +89,7 @@ MODULE_PARM_DESC(dma_tx_num, "Number of descriptors in the TX list"); #define TXQUEUESTOP_THRESHHOLD 2 -static struct of_device_id altera_tse_ids[]; +static const struct of_device_id altera_tse_ids[]; static inline u32 tse_tx_avail(struct altera_tse_private *priv) { @@ -1576,7 +1576,7 @@ static const struct altera_dmaops altera_dtype_msgdma = { .start_rxdma = msgdma_start_rxdma, }; -static struct of_device_id altera_tse_ids[] = { +static const struct of_device_id altera_tse_ids[] = { { .compatible = "altr,tse-msgdma-1.0", .data = &altera_dtype_msgdma, }, { .compatible = "altr,tse-1.0", .data = &altera_dtype_sgdma, }, { .compatible = "ALTR,tse-1.0", .data = &altera_dtype_sgdma, }, diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 8eb37e0194b5..bc8b04f42882 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1543,7 +1543,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) { struct pcnet32_private *lp; int i, media; - int fdx, mii, fset, dxsuflo; + int fdx, mii, fset, dxsuflo, sram; int chip_version; char *chipname; struct net_device *dev; @@ -1580,7 +1580,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) } /* initialize variables */ - fdx = mii = fset = dxsuflo = 0; + fdx = mii = fset = dxsuflo = sram = 0; chip_version = (chip_version >> 12) & 0xffff; switch (chip_version) { @@ -1613,6 +1613,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) chipname = "PCnet/FAST III 79C973"; /* PCI */ fdx = 1; mii = 1; + sram = 1; break; case 0x2626: chipname = "PCnet/Home 79C978"; /* PCI */ @@ -1636,6 +1637,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) chipname = "PCnet/FAST III 79C975"; /* PCI */ fdx = 1; mii = 1; + sram = 1; break; case 0x2628: chipname = "PCnet/PRO 79C976"; @@ -1664,6 +1666,31 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) dxsuflo = 1; } + /* + * The Am79C973/Am79C975 controllers come with 12K of SRAM + * which we can use for the Tx/Rx buffers but most importantly, + * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid + * Tx fifo underflows. + */ + if (sram) { + /* + * The SRAM is being configured in two steps. First we + * set the SRAM size in the BCR25:SRAM_SIZE bits. According + * to the datasheet, each bit corresponds to a 512-byte + * page so we can have at most 24 pages. The SRAM_SIZE + * holds the value of the upper 8 bits of the 16-bit SRAM size. + * The low 8-bits start at 0x00 and end at 0xff. So the + * address range is from 0x0000 up to 0x17ff. Therefore, + * the SRAM_SIZE is set to 0x17. The next step is to set + * the BCR26:SRAM_BND midway through so the Tx and Rx + * buffers can share the SRAM equally. + */ + a->write_bcr(ioaddr, 25, 0x17); + a->write_bcr(ioaddr, 26, 0xc); + /* And finally enable the NOUFLO bit */ + a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11)); + } + dev = alloc_etherdev(sizeof(*lp)); if (!dev) { ret = -ENOMEM; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 29a09271b64a..34c28aac767f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -365,6 +365,8 @@ #define MAC_HWF0R_TXCOESEL_WIDTH 1 #define MAC_HWF0R_VLHASH_INDEX 4 #define MAC_HWF0R_VLHASH_WIDTH 1 +#define MAC_HWF1R_ADDR64_INDEX 14 +#define MAC_HWF1R_ADDR64_WIDTH 2 #define MAC_HWF1R_ADVTHWORD_INDEX 13 #define MAC_HWF1R_ADVTHWORD_WIDTH 1 #define MAC_HWF1R_DBGMEMA_INDEX 19 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 400757b49872..80dd7a92f357 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1068,7 +1068,7 @@ static void xgbe_tx_desc_reset(struct xgbe_ring_data *rdata) rdesc->desc3 = 0; /* Make sure ownership is written to the descriptor */ - wmb(); + dma_wmb(); } static void xgbe_tx_desc_init(struct xgbe_channel *channel) @@ -1124,12 +1124,12 @@ static void xgbe_rx_desc_reset(struct xgbe_ring_data *rdata) * is written to the descriptor(s) before setting the OWN bit * for the descriptor */ - wmb(); + dma_wmb(); XGMAC_SET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, OWN, 1); /* Make sure ownership is written to the descriptor */ - wmb(); + dma_wmb(); } static void xgbe_rx_desc_init(struct xgbe_channel *channel) @@ -1358,18 +1358,20 @@ static void xgbe_tx_start_xmit(struct xgbe_channel *channel, struct xgbe_prv_data *pdata = channel->pdata; struct xgbe_ring_data *rdata; + /* Make sure everything is written before the register write */ + wmb(); + /* Issue a poll command to Tx DMA by writing address * of next immediate free descriptor */ rdata = XGBE_GET_DESC_DATA(ring, ring->cur); XGMAC_DMA_IOWRITE(channel, DMA_CH_TDTR_LO, lower_32_bits(rdata->rdesc_dma)); - /* Start the Tx coalescing timer */ + /* Start the Tx timer */ if (pdata->tx_usecs && !channel->tx_timer_active) { channel->tx_timer_active = 1; - hrtimer_start(&channel->tx_timer, - ktime_set(0, pdata->tx_usecs * NSEC_PER_USEC), - HRTIMER_MODE_REL); + mod_timer(&channel->tx_timer, + jiffies + usecs_to_jiffies(pdata->tx_usecs)); } ring->tx.xmit_more = 0; @@ -1565,7 +1567,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) * is written to the descriptor(s) before setting the OWN bit * for the first descriptor */ - wmb(); + dma_wmb(); /* Set OWN bit for the first descriptor */ rdata = XGBE_GET_DESC_DATA(ring, start_index); @@ -1577,7 +1579,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) #endif /* Make sure ownership is written to the descriptor */ - wmb(); + dma_wmb(); ring->cur = cur_index + 1; if (!packet->skb->xmit_more || @@ -1613,7 +1615,7 @@ static int xgbe_dev_read(struct xgbe_channel *channel) return 1; /* Make sure descriptor fields are read after reading the OWN bit */ - rmb(); + dma_rmb(); #ifdef XGMAC_ENABLE_RX_DESC_DUMP xgbe_dump_rx_desc(ring, rdesc, ring->cur); @@ -2004,7 +2006,8 @@ static void xgbe_config_tx_fifo_size(struct xgbe_prv_data *pdata) for (i = 0; i < pdata->tx_q_count; i++) XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TQS, fifo_size); - netdev_notice(pdata->netdev, "%d Tx queues, %d byte fifo per queue\n", + netdev_notice(pdata->netdev, + "%d Tx hardware queues, %d byte fifo per queue\n", pdata->tx_q_count, ((fifo_size + 1) * 256)); } @@ -2019,7 +2022,8 @@ static void xgbe_config_rx_fifo_size(struct xgbe_prv_data *pdata) for (i = 0; i < pdata->rx_q_count; i++) XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RQS, fifo_size); - netdev_notice(pdata->netdev, "%d Rx queues, %d byte fifo per queue\n", + netdev_notice(pdata->netdev, + "%d Rx hardware queues, %d byte fifo per queue\n", pdata->rx_q_count, ((fifo_size + 1) * 256)); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 885b02b5be07..347fe2419a18 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -411,11 +411,9 @@ static irqreturn_t xgbe_dma_isr(int irq, void *data) return IRQ_HANDLED; } -static enum hrtimer_restart xgbe_tx_timer(struct hrtimer *timer) +static void xgbe_tx_timer(unsigned long data) { - struct xgbe_channel *channel = container_of(timer, - struct xgbe_channel, - tx_timer); + struct xgbe_channel *channel = (struct xgbe_channel *)data; struct xgbe_prv_data *pdata = channel->pdata; struct napi_struct *napi; @@ -437,8 +435,6 @@ static enum hrtimer_restart xgbe_tx_timer(struct hrtimer *timer) channel->tx_timer_active = 0; DBGPR("<--xgbe_tx_timer\n"); - - return HRTIMER_NORESTART; } static void xgbe_init_tx_timers(struct xgbe_prv_data *pdata) @@ -454,9 +450,8 @@ static void xgbe_init_tx_timers(struct xgbe_prv_data *pdata) break; DBGPR(" %s adding tx timer\n", channel->name); - hrtimer_init(&channel->tx_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL); - channel->tx_timer.function = xgbe_tx_timer; + setup_timer(&channel->tx_timer, xgbe_tx_timer, + (unsigned long)channel); } DBGPR("<--xgbe_init_tx_timers\n"); @@ -475,8 +470,7 @@ static void xgbe_stop_tx_timers(struct xgbe_prv_data *pdata) break; DBGPR(" %s deleting tx timer\n", channel->name); - channel->tx_timer_active = 0; - hrtimer_cancel(&channel->tx_timer); + del_timer_sync(&channel->tx_timer); } DBGPR("<--xgbe_stop_tx_timers\n"); @@ -519,6 +513,7 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) RXFIFOSIZE); hw_feat->tx_fifo_size = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, TXFIFOSIZE); + hw_feat->dma_width = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, ADDR64); hw_feat->dcb = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, DCBEN); hw_feat->sph = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, SPHEN); hw_feat->tso = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, TSOEN); @@ -553,6 +548,21 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) break; } + /* Translate the address width setting into actual number */ + switch (hw_feat->dma_width) { + case 0: + hw_feat->dma_width = 32; + break; + case 1: + hw_feat->dma_width = 40; + break; + case 2: + hw_feat->dma_width = 48; + break; + default: + hw_feat->dma_width = 32; + } + /* The Queue, Channel and TC counts are zero based so increment them * to get the actual number */ @@ -692,6 +702,7 @@ void xgbe_init_rx_coalesce(struct xgbe_prv_data *pdata) DBGPR("-->xgbe_init_rx_coalesce\n"); pdata->rx_riwt = hw_if->usec_to_riwt(pdata, XGMAC_INIT_DMA_RX_USECS); + pdata->rx_usecs = XGMAC_INIT_DMA_RX_USECS; pdata->rx_frames = XGMAC_INIT_DMA_RX_FRAMES; hw_if->config_rx_coalesce(pdata); @@ -1800,6 +1811,9 @@ static void xgbe_rx_refresh(struct xgbe_channel *channel) ring->dirty++; } + /* Make sure everything is written before the register write */ + wmb(); + /* Update the Rx Tail Pointer Register with address of * the last cleaned entry */ rdata = XGBE_GET_DESC_DATA(ring, ring->dirty - 1); @@ -1807,16 +1821,15 @@ static void xgbe_rx_refresh(struct xgbe_channel *channel) lower_32_bits(rdata->rdesc_dma)); } -static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata, +static struct sk_buff *xgbe_create_skb(struct napi_struct *napi, struct xgbe_ring_data *rdata, unsigned int *len) { - struct net_device *netdev = pdata->netdev; struct sk_buff *skb; u8 *packet; unsigned int copy_len; - skb = netdev_alloc_skb_ip_align(netdev, rdata->rx.hdr.dma_len); + skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len); if (!skb) return NULL; @@ -1863,7 +1876,7 @@ static int xgbe_tx_poll(struct xgbe_channel *channel) /* Make sure descriptor fields are read after reading the OWN * bit */ - rmb(); + dma_rmb(); #ifdef XGMAC_ENABLE_TX_DESC_DUMP xgbe_dump_tx_desc(ring, ring->dirty, 1, 0); @@ -1986,7 +1999,7 @@ read_again: rdata->rx.hdr.dma_len, DMA_FROM_DEVICE); - skb = xgbe_create_skb(pdata, rdata, &put_len); + skb = xgbe_create_skb(napi, rdata, &put_len); if (!skb) { error = 1; goto skip_data; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index ebf489351555..b4f6eaaa08f0 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -291,7 +291,6 @@ static int xgbe_get_settings(struct net_device *netdev, return -ENODEV; ret = phy_ethtool_gset(pdata->phydev, cmd); - cmd->transceiver = XCVR_EXTERNAL; DBGPR("<--xgbe_get_settings\n"); @@ -378,18 +377,14 @@ static int xgbe_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec) { struct xgbe_prv_data *pdata = netdev_priv(netdev); - struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned int riwt; DBGPR("-->xgbe_get_coalesce\n"); memset(ec, 0, sizeof(struct ethtool_coalesce)); - riwt = pdata->rx_riwt; - ec->rx_coalesce_usecs = hw_if->riwt_to_usec(pdata, riwt); + ec->rx_coalesce_usecs = pdata->rx_usecs; ec->rx_max_coalesced_frames = pdata->rx_frames; - ec->tx_coalesce_usecs = pdata->tx_usecs; ec->tx_max_coalesced_frames = pdata->tx_frames; DBGPR("<--xgbe_get_coalesce\n"); @@ -403,13 +398,14 @@ static int xgbe_set_coalesce(struct net_device *netdev, struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; unsigned int rx_frames, rx_riwt, rx_usecs; - unsigned int tx_frames, tx_usecs; + unsigned int tx_frames; DBGPR("-->xgbe_set_coalesce\n"); /* Check for not supported parameters */ if ((ec->rx_coalesce_usecs_irq) || (ec->rx_max_coalesced_frames_irq) || + (ec->tx_coalesce_usecs) || (ec->tx_coalesce_usecs_irq) || (ec->tx_max_coalesced_frames_irq) || (ec->stats_block_coalesce_usecs) || @@ -439,17 +435,17 @@ static int xgbe_set_coalesce(struct net_device *netdev, } rx_riwt = hw_if->usec_to_riwt(pdata, ec->rx_coalesce_usecs); + rx_usecs = ec->rx_coalesce_usecs; rx_frames = ec->rx_max_coalesced_frames; /* Use smallest possible value if conversion resulted in zero */ - if (ec->rx_coalesce_usecs && !rx_riwt) + if (rx_usecs && !rx_riwt) rx_riwt = 1; /* Check the bounds of values for Rx */ if (rx_riwt > XGMAC_MAX_DMA_RIWT) { - rx_usecs = hw_if->riwt_to_usec(pdata, XGMAC_MAX_DMA_RIWT); netdev_alert(netdev, "rx-usec is limited to %d usecs\n", - rx_usecs); + hw_if->riwt_to_usec(pdata, XGMAC_MAX_DMA_RIWT)); return -EINVAL; } if (rx_frames > pdata->rx_desc_count) { @@ -458,7 +454,6 @@ static int xgbe_set_coalesce(struct net_device *netdev, return -EINVAL; } - tx_usecs = ec->tx_coalesce_usecs; tx_frames = ec->tx_max_coalesced_frames; /* Check the bounds of values for Tx */ @@ -469,10 +464,10 @@ static int xgbe_set_coalesce(struct net_device *netdev, } pdata->rx_riwt = rx_riwt; + pdata->rx_usecs = rx_usecs; pdata->rx_frames = rx_frames; hw_if->config_rx_coalesce(pdata); - pdata->tx_usecs = tx_usecs; pdata->tx_frames = tx_frames; hw_if->config_tx_coalesce(pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 32dd65137051..2e4c22d94a6b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -374,15 +374,6 @@ static int xgbe_probe(struct platform_device *pdev) pdata->awcache = XGBE_DMA_SYS_AWCACHE; } - /* Set the DMA mask */ - if (!dev->dma_mask) - dev->dma_mask = &dev->coherent_dma_mask; - ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40)); - if (ret) { - dev_err(dev, "dma_set_mask_and_coherent failed\n"); - goto err_io; - } - /* Get the device interrupt */ ret = platform_get_irq(pdev, 0); if (ret < 0) { @@ -409,6 +400,16 @@ static int xgbe_probe(struct platform_device *pdev) /* Set default configuration data */ xgbe_default_config(pdata); + /* Set the DMA mask */ + if (!dev->dma_mask) + dev->dma_mask = &dev->coherent_dma_mask; + ret = dma_set_mask_and_coherent(dev, + DMA_BIT_MASK(pdata->hw_feat.dma_width)); + if (ret) { + dev_err(dev, "dma_set_mask_and_coherent failed\n"); + goto err_io; + } + /* Calculate the number of Tx and Rx rings to be created * -Tx (DMA) Channels map 1-to-1 to Tx Queues so set * the number of Tx queues to the number of Tx channels diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c index f326178ef376..b03e4f58d02e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c @@ -179,7 +179,7 @@ static int xgbe_adjtime(struct ptp_clock_info *info, s64 delta) return 0; } -static int xgbe_gettime(struct ptp_clock_info *info, struct timespec *ts) +static int xgbe_gettime(struct ptp_clock_info *info, struct timespec64 *ts) { struct xgbe_prv_data *pdata = container_of(info, struct xgbe_prv_data, @@ -193,12 +193,13 @@ static int xgbe_gettime(struct ptp_clock_info *info, struct timespec *ts) spin_unlock_irqrestore(&pdata->tstamp_lock, flags); - *ts = ns_to_timespec(nsec); + *ts = ns_to_timespec64(nsec); return 0; } -static int xgbe_settime(struct ptp_clock_info *info, const struct timespec *ts) +static int xgbe_settime(struct ptp_clock_info *info, + const struct timespec64 *ts) { struct xgbe_prv_data *pdata = container_of(info, struct xgbe_prv_data, @@ -206,7 +207,7 @@ static int xgbe_settime(struct ptp_clock_info *info, const struct timespec *ts) unsigned long flags; u64 nsec; - nsec = timespec_to_ns(ts); + nsec = timespec64_to_ns(ts); spin_lock_irqsave(&pdata->tstamp_lock, flags); @@ -236,8 +237,8 @@ void xgbe_ptp_register(struct xgbe_prv_data *pdata) info->max_adj = pdata->ptpclk_rate; info->adjfreq = xgbe_adjfreq; info->adjtime = xgbe_adjtime; - info->gettime = xgbe_gettime; - info->settime = xgbe_settime; + info->gettime64 = xgbe_gettime; + info->settime64 = xgbe_settime; info->enable = xgbe_enable; clock = ptp_clock_register(info, pdata->dev); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 1eea3e5a5d08..dd742426eb04 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -222,7 +222,7 @@ ((_idx) & ((_ring)->rdesc_count - 1))) /* Default coalescing parameters */ -#define XGMAC_INIT_DMA_TX_USECS 50 +#define XGMAC_INIT_DMA_TX_USECS 1000 #define XGMAC_INIT_DMA_TX_FRAMES 25 #define XGMAC_MAX_DMA_RIWT 0xff @@ -410,7 +410,7 @@ struct xgbe_channel { unsigned int saved_ier; unsigned int tx_timer_active; - struct hrtimer tx_timer; + struct timer_list tx_timer; struct xgbe_ring *tx_ring; struct xgbe_ring *rx_ring; @@ -632,6 +632,7 @@ struct xgbe_hw_features { unsigned int rx_fifo_size; /* MTL Receive FIFO Size */ unsigned int tx_fifo_size; /* MTL Transmit FIFO Size */ unsigned int adv_ts_hi; /* Advance Timestamping High Word */ + unsigned int dma_width; /* DMA width */ unsigned int dcb; /* DCB Feature */ unsigned int sph; /* Split Header Feature */ unsigned int tso; /* TCP Segmentation Offload */ @@ -715,6 +716,7 @@ struct xgbe_prv_data { /* Rx coalescing settings */ unsigned int rx_riwt; + unsigned int rx_usecs; unsigned int rx_frames; /* Current Rx buffer size */ diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h index ec45f3256f0e..d9bc89d69266 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h @@ -97,6 +97,8 @@ enum xgene_enet_rm { #define QCOHERENT BIT(4) #define RECOMBBUF BIT(27) +#define MAC_OFFSET 0x30 + #define BLOCK_ETH_CSR_OFFSET 0x2000 #define BLOCK_ETH_RING_IF_OFFSET 0x9000 #define BLOCK_ETH_DIAG_CSR_OFFSET 0xD000 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 635a83be7e5e..40d3530d7f30 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -428,13 +428,23 @@ static int xgene_enet_register_irq(struct net_device *ndev) { struct xgene_enet_pdata *pdata = netdev_priv(ndev); struct device *dev = ndev_to_dev(ndev); + struct xgene_enet_desc_ring *ring; int ret; - ret = devm_request_irq(dev, pdata->rx_ring->irq, xgene_enet_rx_irq, - IRQF_SHARED, ndev->name, pdata->rx_ring); - if (ret) { - netdev_err(ndev, "rx%d interrupt request failed\n", - pdata->rx_ring->irq); + ring = pdata->rx_ring; + ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, + IRQF_SHARED, ring->irq_name, ring); + if (ret) + netdev_err(ndev, "Failed to request irq %s\n", ring->irq_name); + + if (pdata->cq_cnt) { + ring = pdata->tx_ring->cp_ring; + ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, + IRQF_SHARED, ring->irq_name, ring); + if (ret) { + netdev_err(ndev, "Failed to request irq %s\n", + ring->irq_name); + } } return ret; @@ -448,6 +458,37 @@ static void xgene_enet_free_irq(struct net_device *ndev) pdata = netdev_priv(ndev); dev = ndev_to_dev(ndev); devm_free_irq(dev, pdata->rx_ring->irq, pdata->rx_ring); + + if (pdata->cq_cnt) { + devm_free_irq(dev, pdata->tx_ring->cp_ring->irq, + pdata->tx_ring->cp_ring); + } +} + +static void xgene_enet_napi_enable(struct xgene_enet_pdata *pdata) +{ + struct napi_struct *napi; + + napi = &pdata->rx_ring->napi; + napi_enable(napi); + + if (pdata->cq_cnt) { + napi = &pdata->tx_ring->cp_ring->napi; + napi_enable(napi); + } +} + +static void xgene_enet_napi_disable(struct xgene_enet_pdata *pdata) +{ + struct napi_struct *napi; + + napi = &pdata->rx_ring->napi; + napi_disable(napi); + + if (pdata->cq_cnt) { + napi = &pdata->tx_ring->cp_ring->napi; + napi_disable(napi); + } } static int xgene_enet_open(struct net_device *ndev) @@ -462,7 +503,7 @@ static int xgene_enet_open(struct net_device *ndev) ret = xgene_enet_register_irq(ndev); if (ret) return ret; - napi_enable(&pdata->rx_ring->napi); + xgene_enet_napi_enable(pdata); if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII) phy_start(pdata->phy_dev); @@ -486,7 +527,7 @@ static int xgene_enet_close(struct net_device *ndev) else cancel_delayed_work_sync(&pdata->link_work); - napi_disable(&pdata->rx_ring->napi); + xgene_enet_napi_disable(pdata); xgene_enet_free_irq(ndev); xgene_enet_process_ring(pdata->rx_ring, -1); @@ -580,6 +621,8 @@ static void xgene_enet_free_desc_rings(struct xgene_enet_pdata *pdata) if (ring) { if (ring->cp_ring && ring->cp_ring->cp_skb) devm_kfree(dev, ring->cp_ring->cp_skb); + if (ring->cp_ring && pdata->cq_cnt) + xgene_enet_free_desc_ring(ring->cp_ring); xgene_enet_free_desc_ring(ring); } @@ -645,9 +688,11 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev) struct device *dev = ndev_to_dev(ndev); struct xgene_enet_desc_ring *rx_ring, *tx_ring, *cp_ring; struct xgene_enet_desc_ring *buf_pool = NULL; - u8 cpu_bufnum = 0, eth_bufnum = START_ETH_BUFNUM; - u8 bp_bufnum = START_BP_BUFNUM; - u16 ring_id, ring_num = START_RING_NUM; + u8 cpu_bufnum = pdata->cpu_bufnum; + u8 eth_bufnum = pdata->eth_bufnum; + u8 bp_bufnum = pdata->bp_bufnum; + u16 ring_num = pdata->ring_num; + u16 ring_id; int ret; /* allocate rx descriptor ring */ @@ -671,6 +716,12 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev) rx_ring->nbufpool = NUM_BUFPOOL; rx_ring->buf_pool = buf_pool; rx_ring->irq = pdata->rx_irq; + if (!pdata->cq_cnt) { + snprintf(rx_ring->irq_name, IRQ_ID_SIZE, "%s-rx-txc", + ndev->name); + } else { + snprintf(rx_ring->irq_name, IRQ_ID_SIZE, "%s-rx", ndev->name); + } buf_pool->rx_skb = devm_kcalloc(dev, buf_pool->slots, sizeof(struct sk_buff *), GFP_KERNEL); if (!buf_pool->rx_skb) { @@ -692,7 +743,22 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev) } pdata->tx_ring = tx_ring; - cp_ring = pdata->rx_ring; + if (!pdata->cq_cnt) { + cp_ring = pdata->rx_ring; + } else { + /* allocate tx completion descriptor ring */ + ring_id = xgene_enet_get_ring_id(RING_OWNER_CPU, cpu_bufnum++); + cp_ring = xgene_enet_create_desc_ring(ndev, ring_num++, + RING_CFGSIZE_16KB, + ring_id); + if (!cp_ring) { + ret = -ENOMEM; + goto err; + } + cp_ring->irq = pdata->txc_irq; + snprintf(cp_ring->irq_name, IRQ_ID_SIZE, "%s-txc", ndev->name); + } + cp_ring->cp_skb = devm_kcalloc(dev, tx_ring->slots, sizeof(struct sk_buff *), GFP_KERNEL); if (!cp_ring->cp_skb) { @@ -752,6 +818,22 @@ static const struct net_device_ops xgene_ndev_ops = { .ndo_set_mac_address = xgene_enet_set_mac_address, }; +static int xgene_get_port_id(struct device *dev, struct xgene_enet_pdata *pdata) +{ + u32 id = 0; + int ret; + + ret = device_property_read_u32(dev, "port-id", &id); + if (!ret && id > 1) { + dev_err(dev, "Incorrect port-id specified\n"); + return -ENODEV; + } + + pdata->port_id = id; + + return 0; +} + static int xgene_get_mac_address(struct device *dev, unsigned char *addr) { @@ -835,13 +917,9 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) return -ENOMEM; } - ret = platform_get_irq(pdev, 0); - if (ret <= 0) { - dev_err(dev, "Unable to get ENET Rx IRQ\n"); - ret = ret ? : -ENXIO; + ret = xgene_get_port_id(dev, pdata); + if (ret) return ret; - } - pdata->rx_irq = ret; if (xgene_get_mac_address(dev, ndev->dev_addr) != ETH_ALEN) eth_hw_addr_random(ndev); @@ -860,19 +938,37 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) return -ENODEV; } + ret = platform_get_irq(pdev, 0); + if (ret <= 0) { + dev_err(dev, "Unable to get ENET Rx IRQ\n"); + ret = ret ? : -ENXIO; + return ret; + } + pdata->rx_irq = ret; + + if (pdata->phy_mode != PHY_INTERFACE_MODE_RGMII) { + ret = platform_get_irq(pdev, 1); + if (ret <= 0) { + dev_err(dev, "Unable to get ENET Tx completion IRQ\n"); + ret = ret ? : -ENXIO; + return ret; + } + pdata->txc_irq = ret; + } + pdata->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pdata->clk)) { /* Firmware may have set up the clock already. */ pdata->clk = NULL; } - base_addr = pdata->base_addr; + base_addr = pdata->base_addr - (pdata->port_id * MAC_OFFSET); pdata->eth_csr_addr = base_addr + BLOCK_ETH_CSR_OFFSET; pdata->eth_ring_if_addr = base_addr + BLOCK_ETH_RING_IF_OFFSET; pdata->eth_diag_csr_addr = base_addr + BLOCK_ETH_DIAG_CSR_OFFSET; if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII || pdata->phy_mode == PHY_INTERFACE_MODE_SGMII) { - pdata->mcx_mac_addr = base_addr + BLOCK_ETH_MAC_OFFSET; + pdata->mcx_mac_addr = pdata->base_addr + BLOCK_ETH_MAC_OFFSET; pdata->mcx_mac_csr_addr = base_addr + BLOCK_ETH_MAC_CSR_OFFSET; } else { pdata->mcx_mac_addr = base_addr + BLOCK_AXG_MAC_OFFSET; @@ -928,13 +1024,60 @@ static void xgene_enet_setup_ops(struct xgene_enet_pdata *pdata) pdata->mac_ops = &xgene_sgmac_ops; pdata->port_ops = &xgene_sgport_ops; pdata->rm = RM1; + pdata->cq_cnt = XGENE_MAX_TXC_RINGS; break; default: pdata->mac_ops = &xgene_xgmac_ops; pdata->port_ops = &xgene_xgport_ops; pdata->rm = RM0; + pdata->cq_cnt = XGENE_MAX_TXC_RINGS; break; } + + switch (pdata->port_id) { + case 0: + pdata->cpu_bufnum = START_CPU_BUFNUM_0; + pdata->eth_bufnum = START_ETH_BUFNUM_0; + pdata->bp_bufnum = START_BP_BUFNUM_0; + pdata->ring_num = START_RING_NUM_0; + break; + case 1: + pdata->cpu_bufnum = START_CPU_BUFNUM_1; + pdata->eth_bufnum = START_ETH_BUFNUM_1; + pdata->bp_bufnum = START_BP_BUFNUM_1; + pdata->ring_num = START_RING_NUM_1; + break; + default: + break; + } + +} + +static void xgene_enet_napi_add(struct xgene_enet_pdata *pdata) +{ + struct napi_struct *napi; + + napi = &pdata->rx_ring->napi; + netif_napi_add(pdata->ndev, napi, xgene_enet_napi, NAPI_POLL_WEIGHT); + + if (pdata->cq_cnt) { + napi = &pdata->tx_ring->cp_ring->napi; + netif_napi_add(pdata->ndev, napi, xgene_enet_napi, + NAPI_POLL_WEIGHT); + } +} + +static void xgene_enet_napi_del(struct xgene_enet_pdata *pdata) +{ + struct napi_struct *napi; + + napi = &pdata->rx_ring->napi; + netif_napi_del(napi); + + if (pdata->cq_cnt) { + napi = &pdata->tx_ring->cp_ring->napi; + netif_napi_del(napi); + } } static int xgene_enet_probe(struct platform_device *pdev) @@ -942,7 +1085,6 @@ static int xgene_enet_probe(struct platform_device *pdev) struct net_device *ndev; struct xgene_enet_pdata *pdata; struct device *dev = &pdev->dev; - struct napi_struct *napi; struct xgene_mac_ops *mac_ops; int ret; @@ -984,8 +1126,7 @@ static int xgene_enet_probe(struct platform_device *pdev) if (ret) goto err; - napi = &pdata->rx_ring->napi; - netif_napi_add(ndev, napi, xgene_enet_napi, NAPI_POLL_WEIGHT); + xgene_enet_napi_add(pdata); mac_ops = pdata->mac_ops; if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII) ret = xgene_enet_mdio_config(pdata); @@ -1012,7 +1153,7 @@ static int xgene_enet_remove(struct platform_device *pdev) mac_ops->rx_disable(pdata); mac_ops->tx_disable(pdata); - netif_napi_del(&pdata->rx_ring->napi); + xgene_enet_napi_del(pdata); xgene_enet_mdio_remove(pdata); xgene_enet_delete_desc_rings(pdata); unregister_netdev(ndev); @@ -1033,7 +1174,7 @@ MODULE_DEVICE_TABLE(acpi, xgene_enet_acpi_match); #endif #ifdef CONFIG_OF -static struct of_device_id xgene_enet_of_match[] = { +static const struct of_device_id xgene_enet_of_match[] = { {.compatible = "apm,xgene-enet",}, {.compatible = "apm,xgene1-sgenet",}, {.compatible = "apm,xgene1-xgenet",}, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index c2d465c3db66..8f3d232b09bc 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -41,9 +41,18 @@ #define SKB_BUFFER_SIZE (XGENE_ENET_MAX_MTU - NET_IP_ALIGN) #define NUM_PKT_BUF 64 #define NUM_BUFPOOL 32 -#define START_ETH_BUFNUM 2 -#define START_BP_BUFNUM 0x22 -#define START_RING_NUM 8 + +#define START_CPU_BUFNUM_0 0 +#define START_ETH_BUFNUM_0 2 +#define START_BP_BUFNUM_0 0x22 +#define START_RING_NUM_0 8 +#define START_CPU_BUFNUM_1 12 +#define START_ETH_BUFNUM_1 10 +#define START_BP_BUFNUM_1 0x2A +#define START_RING_NUM_1 264 + +#define IRQ_ID_SIZE 16 +#define XGENE_MAX_TXC_RINGS 1 #define PHY_POLL_LINK_ON (10 * HZ) #define PHY_POLL_LINK_OFF (PHY_POLL_LINK_ON / 5) @@ -57,6 +66,7 @@ struct xgene_enet_desc_ring { u16 tail; u16 slots; u16 irq; + char irq_name[IRQ_ID_SIZE]; u32 size; u32 state[NUM_RING_CONFIG]; void __iomem *cmd_base; @@ -111,6 +121,8 @@ struct xgene_enet_pdata { u32 cp_qcnt_hi; u32 cp_qcnt_low; u32 rx_irq; + u32 txc_irq; + u8 cq_cnt; void __iomem *eth_csr_addr; void __iomem *eth_ring_if_addr; void __iomem *eth_diag_csr_addr; @@ -125,6 +137,11 @@ struct xgene_enet_pdata { struct xgene_mac_ops *mac_ops; struct xgene_port_ops *port_ops; struct delayed_work link_work; + u32 port_id; + u8 cpu_bufnum; + u8 eth_bufnum; + u8 bp_bufnum; + u16 ring_num; }; struct xgene_indirect_ctl { diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c index f5d4f68c288c..f27fb6f2a93b 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c @@ -226,6 +226,7 @@ static u32 xgene_enet_link_status(struct xgene_enet_pdata *p) static void xgene_sgmac_init(struct xgene_enet_pdata *p) { u32 data, loop = 10; + u32 offset = p->port_id * 4; xgene_sgmac_reset(p); @@ -272,9 +273,9 @@ static void xgene_sgmac_init(struct xgene_enet_pdata *p) xgene_enet_wr_csr(p, RSIF_RAM_DBG_REG0_ADDR, 0); /* Bypass traffic gating */ - xgene_enet_wr_csr(p, CFG_LINK_AGGR_RESUME_0_ADDR, TX_PORT0); + xgene_enet_wr_csr(p, CFG_LINK_AGGR_RESUME_0_ADDR + offset, TX_PORT0); xgene_enet_wr_csr(p, CFG_BYPASS_ADDR, RESUME_TX); - xgene_enet_wr_csr(p, SG_RX_DV_GATE_REG_0_ADDR, RESUME_RX0); + xgene_enet_wr_csr(p, SG_RX_DV_GATE_REG_0_ADDR + offset, RESUME_RX0); } static void xgene_sgmac_rxtx(struct xgene_enet_pdata *p, u32 bits, bool set) @@ -330,13 +331,14 @@ static void xgene_enet_cle_bypass(struct xgene_enet_pdata *p, u32 dst_ring_num, u16 bufpool_id) { u32 data, fpsel; + u32 offset = p->port_id * MAC_OFFSET; data = CFG_CLE_BYPASS_EN0; - xgene_enet_wr_csr(p, CLE_BYPASS_REG0_0_ADDR, data); + xgene_enet_wr_csr(p, CLE_BYPASS_REG0_0_ADDR + offset, data); fpsel = xgene_enet_ring_bufnum(bufpool_id) - 0x20; data = CFG_CLE_DSTQID0(dst_ring_num) | CFG_CLE_FPSEL0(fpsel); - xgene_enet_wr_csr(p, CLE_BYPASS_REG1_0_ADDR, data); + xgene_enet_wr_csr(p, CLE_BYPASS_REG1_0_ADDR + offset, data); } static void xgene_enet_shutdown(struct xgene_enet_pdata *p) diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index daae0e016253..2f98846e2d89 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -1621,7 +1621,7 @@ static int bmac_remove(struct macio_dev *mdev) return 0; } -static struct of_device_id bmac_match[] = +static const struct of_device_id bmac_match[] = { { .name = "bmac", diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index 7fcaf0da42a8..a18948286682 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -984,7 +984,7 @@ static irqreturn_t mace_rxdma_intr(int irq, void *dev_id) return IRQ_HANDLED; } -static struct of_device_id mace_match[] = +static const struct of_device_id mace_match[] = { { .name = "mace", diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index ee4fdfe65e9e..a6f9142b9048 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -142,7 +142,7 @@ config BNX2X_SRIOV config BGMAC tristate "BCMA bus GBit core support" - depends on BCMA_HOST_SOC && HAS_DMA && BCM47XX + depends on BCMA_HOST_SOC && HAS_DMA && (BCM47XX || ARCH_BCM_5301X) select PHYLIB ---help--- This driver supports GBit MAC and BCM4706 GBit MAC cores on BCMA bus. diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 0469f72c6e7e..fa8f9e147c34 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -14,6 +14,7 @@ #include <linux/etherdevice.h> #include <linux/mii.h> #include <linux/phy.h> +#include <linux/phy_fixed.h> #include <linux/interrupt.h> #include <linux/dma-mapping.h> #include <bcm47xx_nvram.h> @@ -114,53 +115,91 @@ static void bgmac_dma_tx_enable(struct bgmac *bgmac, bgmac_write(bgmac, ring->mmio_base + BGMAC_DMA_TX_CTL, ctl); } +static void +bgmac_dma_tx_add_buf(struct bgmac *bgmac, struct bgmac_dma_ring *ring, + int i, int len, u32 ctl0) +{ + struct bgmac_slot_info *slot; + struct bgmac_dma_desc *dma_desc; + u32 ctl1; + + if (i == ring->num_slots - 1) + ctl0 |= BGMAC_DESC_CTL0_EOT; + + ctl1 = len & BGMAC_DESC_CTL1_LEN; + + slot = &ring->slots[i]; + dma_desc = &ring->cpu_base[i]; + dma_desc->addr_low = cpu_to_le32(lower_32_bits(slot->dma_addr)); + dma_desc->addr_high = cpu_to_le32(upper_32_bits(slot->dma_addr)); + dma_desc->ctl0 = cpu_to_le32(ctl0); + dma_desc->ctl1 = cpu_to_le32(ctl1); +} + static netdev_tx_t bgmac_dma_tx_add(struct bgmac *bgmac, struct bgmac_dma_ring *ring, struct sk_buff *skb) { struct device *dma_dev = bgmac->core->dma_dev; struct net_device *net_dev = bgmac->net_dev; - struct bgmac_dma_desc *dma_desc; - struct bgmac_slot_info *slot; - u32 ctl0, ctl1; + struct bgmac_slot_info *slot = &ring->slots[ring->end]; int free_slots; + int nr_frags; + u32 flags; + int index = ring->end; + int i; if (skb->len > BGMAC_DESC_CTL1_LEN) { bgmac_err(bgmac, "Too long skb (%d)\n", skb->len); - goto err_stop_drop; + goto err_drop; } + if (skb->ip_summed == CHECKSUM_PARTIAL) + skb_checksum_help(skb); + + nr_frags = skb_shinfo(skb)->nr_frags; + if (ring->start <= ring->end) free_slots = ring->start - ring->end + BGMAC_TX_RING_SLOTS; else free_slots = ring->start - ring->end; - if (free_slots == 1) { + + if (free_slots <= nr_frags + 1) { bgmac_err(bgmac, "TX ring is full, queue should be stopped!\n"); netif_stop_queue(net_dev); return NETDEV_TX_BUSY; } - slot = &ring->slots[ring->end]; - slot->skb = skb; - slot->dma_addr = dma_map_single(dma_dev, skb->data, skb->len, + slot->dma_addr = dma_map_single(dma_dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); - if (dma_mapping_error(dma_dev, slot->dma_addr)) { - bgmac_err(bgmac, "Mapping error of skb on ring 0x%X\n", - ring->mmio_base); - goto err_stop_drop; - } + if (unlikely(dma_mapping_error(dma_dev, slot->dma_addr))) + goto err_dma_head; - ctl0 = BGMAC_DESC_CTL0_IOC | BGMAC_DESC_CTL0_SOF | BGMAC_DESC_CTL0_EOF; - if (ring->end == ring->num_slots - 1) - ctl0 |= BGMAC_DESC_CTL0_EOT; - ctl1 = skb->len & BGMAC_DESC_CTL1_LEN; + flags = BGMAC_DESC_CTL0_SOF; + if (!nr_frags) + flags |= BGMAC_DESC_CTL0_EOF | BGMAC_DESC_CTL0_IOC; - dma_desc = ring->cpu_base; - dma_desc += ring->end; - dma_desc->addr_low = cpu_to_le32(lower_32_bits(slot->dma_addr)); - dma_desc->addr_high = cpu_to_le32(upper_32_bits(slot->dma_addr)); - dma_desc->ctl0 = cpu_to_le32(ctl0); - dma_desc->ctl1 = cpu_to_le32(ctl1); + bgmac_dma_tx_add_buf(bgmac, ring, index, skb_headlen(skb), flags); + flags = 0; + + for (i = 0; i < nr_frags; i++) { + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + int len = skb_frag_size(frag); + + index = (index + 1) % BGMAC_TX_RING_SLOTS; + slot = &ring->slots[index]; + slot->dma_addr = skb_frag_dma_map(dma_dev, frag, 0, + len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dma_dev, slot->dma_addr))) + goto err_dma; + + if (i == nr_frags - 1) + flags |= BGMAC_DESC_CTL0_EOF | BGMAC_DESC_CTL0_IOC; + + bgmac_dma_tx_add_buf(bgmac, ring, index, len, flags); + } + + slot->skb = skb; netdev_sent_queue(net_dev, skb->len); @@ -169,20 +208,35 @@ static netdev_tx_t bgmac_dma_tx_add(struct bgmac *bgmac, /* Increase ring->end to point empty slot. We tell hardware the first * slot it should *not* read. */ - if (++ring->end >= BGMAC_TX_RING_SLOTS) - ring->end = 0; + ring->end = (index + 1) % BGMAC_TX_RING_SLOTS; bgmac_write(bgmac, ring->mmio_base + BGMAC_DMA_TX_INDEX, ring->index_base + ring->end * sizeof(struct bgmac_dma_desc)); - /* Always keep one slot free to allow detecting bugged calls. */ - if (--free_slots == 1) + free_slots -= nr_frags + 1; + if (free_slots < 8) netif_stop_queue(net_dev); return NETDEV_TX_OK; -err_stop_drop: - netif_stop_queue(net_dev); +err_dma: + dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb), + DMA_TO_DEVICE); + + while (i > 0) { + int index = (ring->end + i) % BGMAC_TX_RING_SLOTS; + struct bgmac_slot_info *slot = &ring->slots[index]; + u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1); + int len = ctl1 & BGMAC_DESC_CTL1_LEN; + + dma_unmap_page(dma_dev, slot->dma_addr, len, DMA_TO_DEVICE); + } + +err_dma_head: + bgmac_err(bgmac, "Mapping error of skb on ring 0x%X\n", + ring->mmio_base); + +err_drop: dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -204,32 +258,45 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring) while (ring->start != empty_slot) { struct bgmac_slot_info *slot = &ring->slots[ring->start]; + u32 ctl1 = le32_to_cpu(ring->cpu_base[ring->start].ctl1); + int len = ctl1 & BGMAC_DESC_CTL1_LEN; - if (slot->skb) { + if (!slot->dma_addr) { + bgmac_err(bgmac, "Hardware reported transmission for empty TX ring slot %d! End of ring: %d\n", + ring->start, ring->end); + goto next; + } + + if (ctl1 & BGMAC_DESC_CTL0_SOF) /* Unmap no longer used buffer */ - dma_unmap_single(dma_dev, slot->dma_addr, - slot->skb->len, DMA_TO_DEVICE); - slot->dma_addr = 0; + dma_unmap_single(dma_dev, slot->dma_addr, len, + DMA_TO_DEVICE); + else + dma_unmap_page(dma_dev, slot->dma_addr, len, + DMA_TO_DEVICE); + if (slot->skb) { bytes_compl += slot->skb->len; pkts_compl++; /* Free memory! :) */ dev_kfree_skb(slot->skb); slot->skb = NULL; - } else { - bgmac_err(bgmac, "Hardware reported transmission for empty TX ring slot %d! End of ring: %d\n", - ring->start, ring->end); } +next: + slot->dma_addr = 0; if (++ring->start >= BGMAC_TX_RING_SLOTS) ring->start = 0; freed = true; } + if (!pkts_compl) + return; + netdev_completed_queue(bgmac->net_dev, pkts_compl, bytes_compl); - if (freed && netif_queue_stopped(bgmac->net_dev)) + if (netif_queue_stopped(bgmac->net_dev)) netif_wake_queue(bgmac->net_dev); } @@ -275,31 +342,31 @@ static int bgmac_dma_rx_skb_for_slot(struct bgmac *bgmac, struct bgmac_slot_info *slot) { struct device *dma_dev = bgmac->core->dma_dev; - struct sk_buff *skb; dma_addr_t dma_addr; struct bgmac_rx_header *rx; + void *buf; /* Alloc skb */ - skb = netdev_alloc_skb(bgmac->net_dev, BGMAC_RX_BUF_SIZE); - if (!skb) + buf = netdev_alloc_frag(BGMAC_RX_ALLOC_SIZE); + if (!buf) return -ENOMEM; /* Poison - if everything goes fine, hardware will overwrite it */ - rx = (struct bgmac_rx_header *)skb->data; + rx = buf; rx->len = cpu_to_le16(0xdead); rx->flags = cpu_to_le16(0xbeef); /* Map skb for the DMA */ - dma_addr = dma_map_single(dma_dev, skb->data, - BGMAC_RX_BUF_SIZE, DMA_FROM_DEVICE); + dma_addr = dma_map_single(dma_dev, buf, BGMAC_RX_BUF_SIZE, + DMA_FROM_DEVICE); if (dma_mapping_error(dma_dev, dma_addr)) { bgmac_err(bgmac, "DMA mapping error\n"); - dev_kfree_skb(skb); + put_page(virt_to_head_page(buf)); return -ENOMEM; } /* Update the slot */ - slot->skb = skb; + slot->buf = buf; slot->dma_addr = dma_addr; return 0; @@ -342,8 +409,9 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring, while (ring->start != ring->end) { struct device *dma_dev = bgmac->core->dma_dev; struct bgmac_slot_info *slot = &ring->slots[ring->start]; - struct sk_buff *skb = slot->skb; - struct bgmac_rx_header *rx; + struct bgmac_rx_header *rx = slot->buf; + struct sk_buff *skb; + void *buf = slot->buf; u16 len, flags; /* Unmap buffer to make it accessible to the CPU */ @@ -351,7 +419,6 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring, BGMAC_RX_BUF_SIZE, DMA_FROM_DEVICE); /* Get info from the header */ - rx = (struct bgmac_rx_header *)skb->data; len = le16_to_cpu(rx->len); flags = le16_to_cpu(rx->flags); @@ -392,12 +459,13 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring, dma_unmap_single(dma_dev, old_dma_addr, BGMAC_RX_BUF_SIZE, DMA_FROM_DEVICE); + skb = build_skb(buf, BGMAC_RX_ALLOC_SIZE); skb_put(skb, BGMAC_RX_FRAME_OFFSET + len); skb_pull(skb, BGMAC_RX_FRAME_OFFSET); skb_checksum_none_assert(skb); skb->protocol = eth_type_trans(skb, bgmac->net_dev); - netif_receive_skb(skb); + napi_gro_receive(&bgmac->napi, skb); handled++; } while (0); @@ -433,40 +501,79 @@ static bool bgmac_dma_unaligned(struct bgmac *bgmac, return false; } -static void bgmac_dma_ring_free(struct bgmac *bgmac, - struct bgmac_dma_ring *ring) +static void bgmac_dma_tx_ring_free(struct bgmac *bgmac, + struct bgmac_dma_ring *ring) { struct device *dma_dev = bgmac->core->dma_dev; + struct bgmac_dma_desc *dma_desc = ring->cpu_base; struct bgmac_slot_info *slot; - int size; int i; for (i = 0; i < ring->num_slots; i++) { + int len = dma_desc[i].ctl1 & BGMAC_DESC_CTL1_LEN; + slot = &ring->slots[i]; - if (slot->skb) { - if (slot->dma_addr) - dma_unmap_single(dma_dev, slot->dma_addr, - slot->skb->len, DMA_TO_DEVICE); - dev_kfree_skb(slot->skb); - } + dev_kfree_skb(slot->skb); + + if (!slot->dma_addr) + continue; + + if (slot->skb) + dma_unmap_single(dma_dev, slot->dma_addr, + len, DMA_TO_DEVICE); + else + dma_unmap_page(dma_dev, slot->dma_addr, + len, DMA_TO_DEVICE); } +} - if (ring->cpu_base) { - /* Free ring of descriptors */ - size = ring->num_slots * sizeof(struct bgmac_dma_desc); - dma_free_coherent(dma_dev, size, ring->cpu_base, - ring->dma_base); +static void bgmac_dma_rx_ring_free(struct bgmac *bgmac, + struct bgmac_dma_ring *ring) +{ + struct device *dma_dev = bgmac->core->dma_dev; + struct bgmac_slot_info *slot; + int i; + + for (i = 0; i < ring->num_slots; i++) { + slot = &ring->slots[i]; + if (!slot->buf) + continue; + + if (slot->dma_addr) + dma_unmap_single(dma_dev, slot->dma_addr, + BGMAC_RX_BUF_SIZE, + DMA_FROM_DEVICE); + put_page(virt_to_head_page(slot->buf)); } } +static void bgmac_dma_ring_desc_free(struct bgmac *bgmac, + struct bgmac_dma_ring *ring) +{ + struct device *dma_dev = bgmac->core->dma_dev; + int size; + + if (!ring->cpu_base) + return; + + /* Free ring of descriptors */ + size = ring->num_slots * sizeof(struct bgmac_dma_desc); + dma_free_coherent(dma_dev, size, ring->cpu_base, + ring->dma_base); +} + static void bgmac_dma_free(struct bgmac *bgmac) { int i; - for (i = 0; i < BGMAC_MAX_TX_RINGS; i++) - bgmac_dma_ring_free(bgmac, &bgmac->tx_ring[i]); - for (i = 0; i < BGMAC_MAX_RX_RINGS; i++) - bgmac_dma_ring_free(bgmac, &bgmac->rx_ring[i]); + for (i = 0; i < BGMAC_MAX_TX_RINGS; i++) { + bgmac_dma_tx_ring_free(bgmac, &bgmac->tx_ring[i]); + bgmac_dma_ring_desc_free(bgmac, &bgmac->tx_ring[i]); + } + for (i = 0; i < BGMAC_MAX_RX_RINGS; i++) { + bgmac_dma_rx_ring_free(bgmac, &bgmac->rx_ring[i]); + bgmac_dma_ring_desc_free(bgmac, &bgmac->rx_ring[i]); + } } static int bgmac_dma_alloc(struct bgmac *bgmac) @@ -1330,13 +1437,46 @@ static void bgmac_adjust_link(struct net_device *net_dev) } } +static int bgmac_fixed_phy_register(struct bgmac *bgmac) +{ + struct fixed_phy_status fphy_status = { + .link = 1, + .speed = SPEED_1000, + .duplex = DUPLEX_FULL, + }; + struct phy_device *phy_dev; + int err; + + phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); + if (!phy_dev || IS_ERR(phy_dev)) { + bgmac_err(bgmac, "Failed to register fixed PHY device\n"); + return -ENODEV; + } + + err = phy_connect_direct(bgmac->net_dev, phy_dev, bgmac_adjust_link, + PHY_INTERFACE_MODE_MII); + if (err) { + bgmac_err(bgmac, "Connecting PHY failed\n"); + return err; + } + + bgmac->phy_dev = phy_dev; + + return err; +} + static int bgmac_mii_register(struct bgmac *bgmac) { + struct bcma_chipinfo *ci = &bgmac->core->bus->chipinfo; struct mii_bus *mii_bus; struct phy_device *phy_dev; char bus_id[MII_BUS_ID_SIZE + 3]; int i, err = 0; + if (ci->id == BCMA_CHIP_ID_BCM4707 || + ci->id == BCMA_CHIP_ID_BCM53018) + return bgmac_fixed_phy_register(bgmac); + mii_bus = mdiobus_alloc(); if (!mii_bus) return -ENOMEM; @@ -1517,6 +1657,10 @@ static int bgmac_probe(struct bcma_device *core) goto err_dma_free; } + net_dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + net_dev->hw_features = net_dev->features; + net_dev->vlan_features = net_dev->features; + err = register_netdev(bgmac->net_dev); if (err) { bgmac_err(bgmac, "Cannot register net device\n"); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index 89fa5bc69c51..3ad965fe7fcc 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -345,8 +345,8 @@ #define BGMAC_DESC_CTL0_EOT 0x10000000 /* End of ring */ #define BGMAC_DESC_CTL0_IOC 0x20000000 /* IRQ on complete */ -#define BGMAC_DESC_CTL0_SOF 0x40000000 /* Start of frame */ -#define BGMAC_DESC_CTL0_EOF 0x80000000 /* End of frame */ +#define BGMAC_DESC_CTL0_EOF 0x40000000 /* End of frame */ +#define BGMAC_DESC_CTL0_SOF 0x80000000 /* Start of frame */ #define BGMAC_DESC_CTL1_LEN 0x00001FFF #define BGMAC_PHY_NOREGS 0x1E @@ -362,6 +362,8 @@ #define BGMAC_RX_FRAME_OFFSET 30 /* There are 2 unused bytes between header and real data */ #define BGMAC_RX_MAX_FRAME_SIZE 1536 /* Copied from b44/tg3 */ #define BGMAC_RX_BUF_SIZE (BGMAC_RX_FRAME_OFFSET + BGMAC_RX_MAX_FRAME_SIZE) +#define BGMAC_RX_ALLOC_SIZE (SKB_DATA_ALIGN(BGMAC_RX_BUF_SIZE) + \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define BGMAC_BFL_ENETROBO 0x0010 /* has ephy roboswitch spi */ #define BGMAC_BFL_ENETADM 0x0080 /* has ADMtek switch */ @@ -383,7 +385,10 @@ #define ETHER_MAX_LEN 1518 struct bgmac_slot_info { - struct sk_buff *skb; + union { + struct sk_buff *skb; + void *buf; + }; dma_addr_t dma_addr; }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 2ee12b54239b..8120d266e068 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12557,6 +12557,7 @@ static netdev_features_t bnx2x_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { + features = vlan_features_check(skb, features); return vxlan_features_check(skb, features); } @@ -12769,7 +12770,7 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO | NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX; - if (!CHIP_IS_E1x(bp)) { + if (!chip_is_e1x) { dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT; dev->hw_enc_features = @@ -13278,7 +13279,7 @@ static int bnx2x_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int bnx2x_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int bnx2x_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info); u64 ns; @@ -13295,7 +13296,7 @@ static int bnx2x_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int bnx2x_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info); u64 ns; @@ -13333,8 +13334,8 @@ static void bnx2x_register_phc(struct bnx2x *bp) bp->ptp_clock_info.pps = 0; bp->ptp_clock_info.adjfreq = bnx2x_ptp_adjfreq; bp->ptp_clock_info.adjtime = bnx2x_ptp_adjtime; - bp->ptp_clock_info.gettime = bnx2x_ptp_gettime; - bp->ptp_clock_info.settime = bnx2x_ptp_settime; + bp->ptp_clock_info.gettime64 = bnx2x_ptp_gettime; + bp->ptp_clock_info.settime64 = bnx2x_ptp_settime; bp->ptp_clock_info.enable = bnx2x_ptp_enable; bp->ptp_clock = ptp_clock_register(&bp->ptp_clock_info, &bp->pdev->dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index e74ae628bbb9..31e14079e1d7 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -197,6 +197,14 @@ enum dma_reg { DMA_PRIORITY_0, DMA_PRIORITY_1, DMA_PRIORITY_2, + DMA_INDEX2RING_0, + DMA_INDEX2RING_1, + DMA_INDEX2RING_2, + DMA_INDEX2RING_3, + DMA_INDEX2RING_4, + DMA_INDEX2RING_5, + DMA_INDEX2RING_6, + DMA_INDEX2RING_7, }; static const u8 bcmgenet_dma_regs_v3plus[] = { @@ -208,6 +216,14 @@ static const u8 bcmgenet_dma_regs_v3plus[] = { [DMA_PRIORITY_0] = 0x30, [DMA_PRIORITY_1] = 0x34, [DMA_PRIORITY_2] = 0x38, + [DMA_INDEX2RING_0] = 0x70, + [DMA_INDEX2RING_1] = 0x74, + [DMA_INDEX2RING_2] = 0x78, + [DMA_INDEX2RING_3] = 0x7C, + [DMA_INDEX2RING_4] = 0x80, + [DMA_INDEX2RING_5] = 0x84, + [DMA_INDEX2RING_6] = 0x88, + [DMA_INDEX2RING_7] = 0x8C, }; static const u8 bcmgenet_dma_regs_v2[] = { @@ -831,9 +847,10 @@ static struct ethtool_ops bcmgenet_ethtool_ops = { }; /* Power down the unimac, based on mode. */ -static void bcmgenet_power_down(struct bcmgenet_priv *priv, +static int bcmgenet_power_down(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode) { + int ret = 0; u32 reg; switch (mode) { @@ -842,7 +859,7 @@ static void bcmgenet_power_down(struct bcmgenet_priv *priv, break; case GENET_POWER_WOL_MAGIC: - bcmgenet_wol_power_down_cfg(priv, mode); + ret = bcmgenet_wol_power_down_cfg(priv, mode); break; case GENET_POWER_PASSIVE: @@ -852,11 +869,15 @@ static void bcmgenet_power_down(struct bcmgenet_priv *priv, reg |= (EXT_PWR_DOWN_PHY | EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + + bcmgenet_phy_power_set(priv->dev, false); } break; default: break; } + + return 0; } static void bcmgenet_power_up(struct bcmgenet_priv *priv, @@ -943,36 +964,58 @@ static void bcmgenet_free_cb(struct enet_cb *cb) dma_unmap_addr_set(cb, dma_addr, 0); } -static inline void bcmgenet_tx_ring16_int_disable(struct bcmgenet_priv *priv, - struct bcmgenet_tx_ring *ring) +static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring) +{ + bcmgenet_intrl2_0_writel(ring->priv, + UMAC_IRQ_RXDMA_BDONE | UMAC_IRQ_RXDMA_PDONE, + INTRL2_CPU_MASK_SET); +} + +static inline void bcmgenet_rx_ring16_int_enable(struct bcmgenet_rx_ring *ring) +{ + bcmgenet_intrl2_0_writel(ring->priv, + UMAC_IRQ_RXDMA_BDONE | UMAC_IRQ_RXDMA_PDONE, + INTRL2_CPU_MASK_CLEAR); +} + +static inline void bcmgenet_rx_ring_int_disable(struct bcmgenet_rx_ring *ring) +{ + bcmgenet_intrl2_1_writel(ring->priv, + 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index), + INTRL2_CPU_MASK_SET); +} + +static inline void bcmgenet_rx_ring_int_enable(struct bcmgenet_rx_ring *ring) { - bcmgenet_intrl2_0_writel(priv, + bcmgenet_intrl2_1_writel(ring->priv, + 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index), + INTRL2_CPU_MASK_CLEAR); +} + +static inline void bcmgenet_tx_ring16_int_disable(struct bcmgenet_tx_ring *ring) +{ + bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE, INTRL2_CPU_MASK_SET); } -static inline void bcmgenet_tx_ring16_int_enable(struct bcmgenet_priv *priv, - struct bcmgenet_tx_ring *ring) +static inline void bcmgenet_tx_ring16_int_enable(struct bcmgenet_tx_ring *ring) { - bcmgenet_intrl2_0_writel(priv, + bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE, INTRL2_CPU_MASK_CLEAR); } -static inline void bcmgenet_tx_ring_int_enable(struct bcmgenet_priv *priv, - struct bcmgenet_tx_ring *ring) +static inline void bcmgenet_tx_ring_int_enable(struct bcmgenet_tx_ring *ring) { - bcmgenet_intrl2_1_writel(priv, (1 << ring->index), + bcmgenet_intrl2_1_writel(ring->priv, 1 << ring->index, INTRL2_CPU_MASK_CLEAR); - priv->int1_mask &= ~(1 << ring->index); } -static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_priv *priv, - struct bcmgenet_tx_ring *ring) +static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_tx_ring *ring) { - bcmgenet_intrl2_1_writel(priv, (1 << ring->index), + bcmgenet_intrl2_1_writel(ring->priv, 1 << ring->index, INTRL2_CPU_MASK_SET); - priv->int1_mask |= (1 << ring->index); } /* Unlocked version of the reclaim routine */ @@ -1064,7 +1107,7 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget) if (work_done == 0) { napi_complete(napi); - ring->int_enable(ring->priv, ring); + ring->int_enable(ring); return 0; } @@ -1375,11 +1418,10 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, /* bcmgenet_desc_rx - descriptor based rx process. * this could be called from bottom half, or from NAPI polling method. */ -static unsigned int bcmgenet_desc_rx(struct bcmgenet_priv *priv, - unsigned int index, +static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, unsigned int budget) { - struct bcmgenet_rx_ring *ring = &priv->rx_rings[index]; + struct bcmgenet_priv *priv = ring->priv; struct net_device *dev = priv->dev; struct enet_cb *cb; struct sk_buff *skb; @@ -1391,7 +1433,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_priv *priv, unsigned int discards; unsigned int chksum_ok = 0; - p_index = bcmgenet_rdma_ring_readl(priv, index, RDMA_PROD_INDEX); + p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX); discards = (p_index >> DMA_P_INDEX_DISCARD_CNT_SHIFT) & DMA_P_INDEX_DISCARD_CNT_MASK; @@ -1404,7 +1446,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_priv *priv, /* Clear HW register when we reach 75% of maximum 0xFFFF */ if (ring->old_discards >= 0xC000) { ring->old_discards = 0; - bcmgenet_rdma_ring_writel(priv, index, 0, + bcmgenet_rdma_ring_writel(priv, ring->index, 0, RDMA_PROD_INDEX); } } @@ -1512,7 +1554,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_priv *priv, dev->stats.multicast++; /* Notify kernel */ - napi_gro_receive(&priv->napi, skb); + napi_gro_receive(&ring->napi, skb); netif_dbg(priv, rx_status, dev, "pushed up to kernel\n"); next: @@ -1523,12 +1565,29 @@ next: ring->read_ptr = ring->cb_ptr; ring->c_index = (ring->c_index + 1) & DMA_C_INDEX_MASK; - bcmgenet_rdma_ring_writel(priv, index, ring->c_index, RDMA_CONS_INDEX); + bcmgenet_rdma_ring_writel(priv, ring->index, ring->c_index, RDMA_CONS_INDEX); } return rxpktprocessed; } +/* Rx NAPI polling method */ +static int bcmgenet_rx_poll(struct napi_struct *napi, int budget) +{ + struct bcmgenet_rx_ring *ring = container_of(napi, + struct bcmgenet_rx_ring, napi); + unsigned int work_done; + + work_done = bcmgenet_desc_rx(ring, budget); + + if (work_done < budget) { + napi_complete(napi); + ring->int_enable(ring); + } + + return work_done; +} + /* Assign skb to RX DMA descriptor. */ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, struct bcmgenet_rx_ring *ring) @@ -1637,8 +1696,10 @@ static int init_umac(struct bcmgenet_priv *priv) { struct device *kdev = &priv->pdev->dev; int ret; - u32 reg, cpu_mask_clear; - int index; + u32 reg; + u32 int0_enable = 0; + u32 int1_enable = 0; + int i; dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n"); @@ -1665,15 +1726,17 @@ static int init_umac(struct bcmgenet_priv *priv) bcmgenet_intr_disable(priv); - cpu_mask_clear = UMAC_IRQ_RXDMA_BDONE | UMAC_IRQ_TXDMA_BDONE; + /* Enable Rx default queue 16 interrupts */ + int0_enable |= (UMAC_IRQ_RXDMA_BDONE | UMAC_IRQ_RXDMA_PDONE); - dev_dbg(kdev, "%s:Enabling RXDMA_BDONE interrupt\n", __func__); + /* Enable Tx default queue 16 interrupts */ + int0_enable |= (UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE); /* Monitor cable plug/unplugged event for internal PHY */ if (phy_is_internal(priv->phydev)) { - cpu_mask_clear |= (UMAC_IRQ_LINK_DOWN | UMAC_IRQ_LINK_UP); + int0_enable |= (UMAC_IRQ_LINK_DOWN | UMAC_IRQ_LINK_UP); } else if (priv->ext_phy) { - cpu_mask_clear |= (UMAC_IRQ_LINK_DOWN | UMAC_IRQ_LINK_UP); + int0_enable |= (UMAC_IRQ_LINK_DOWN | UMAC_IRQ_LINK_UP); } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { reg = bcmgenet_bp_mc_get(priv); reg |= BIT(priv->hw_params->bp_in_en_shift); @@ -1688,13 +1751,18 @@ static int init_umac(struct bcmgenet_priv *priv) /* Enable MDIO interrupts on GENET v3+ */ if (priv->hw_params->flags & GENET_HAS_MDIO_INTR) - cpu_mask_clear |= UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR; + int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR); - bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, INTRL2_CPU_MASK_CLEAR); + /* Enable Rx priority queue interrupts */ + for (i = 0; i < priv->hw_params->rx_queues; ++i) + int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i)); - for (index = 0; index < priv->hw_params->tx_queues; index++) - bcmgenet_intrl2_1_writel(priv, (1 << index), - INTRL2_CPU_MASK_CLEAR); + /* Enable Tx priority queue interrupts */ + for (i = 0; i < priv->hw_params->tx_queues; ++i) + int1_enable |= (1 << i); + + bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR); + bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR); /* Enable rx/tx engine.*/ dev_dbg(kdev, "done init umac\n"); @@ -1713,7 +1781,6 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv, spin_lock_init(&ring->lock); ring->priv = priv; - netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64); ring->index = index; if (index == DESC_INDEX) { ring->queue = 0; @@ -1757,17 +1824,6 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv, TDMA_WRITE_PTR); bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1, DMA_END_ADDR); - - napi_enable(&ring->napi); -} - -static void bcmgenet_fini_tx_ring(struct bcmgenet_priv *priv, - unsigned int index) -{ - struct bcmgenet_tx_ring *ring = &priv->tx_rings[index]; - - napi_disable(&ring->napi); - netif_napi_del(&ring->napi); } /* Initialize a RDMA ring */ @@ -1779,7 +1835,15 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv, u32 words_per_bd = WORDS_PER_BD(priv); int ret; + ring->priv = priv; ring->index = index; + if (index == DESC_INDEX) { + ring->int_enable = bcmgenet_rx_ring16_int_enable; + ring->int_disable = bcmgenet_rx_ring16_int_disable; + } else { + ring->int_enable = bcmgenet_rx_ring_int_enable; + ring->int_disable = bcmgenet_rx_ring_int_disable; + } ring->cbs = priv->rx_cbs + start_ptr; ring->size = size; ring->c_index = 0; @@ -1815,6 +1879,62 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv, return ret; } +static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_tx_ring *ring; + + for (i = 0; i < priv->hw_params->tx_queues; ++i) { + ring = &priv->tx_rings[i]; + netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64); + } + + ring = &priv->tx_rings[DESC_INDEX]; + netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, 64); +} + +static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_tx_ring *ring; + + for (i = 0; i < priv->hw_params->tx_queues; ++i) { + ring = &priv->tx_rings[i]; + napi_enable(&ring->napi); + } + + ring = &priv->tx_rings[DESC_INDEX]; + napi_enable(&ring->napi); +} + +static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_tx_ring *ring; + + for (i = 0; i < priv->hw_params->tx_queues; ++i) { + ring = &priv->tx_rings[i]; + napi_disable(&ring->napi); + } + + ring = &priv->tx_rings[DESC_INDEX]; + napi_disable(&ring->napi); +} + +static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_tx_ring *ring; + + for (i = 0; i < priv->hw_params->tx_queues; ++i) { + ring = &priv->tx_rings[i]; + netif_napi_del(&ring->napi); + } + + ring = &priv->tx_rings[DESC_INDEX]; + netif_napi_del(&ring->napi); +} + /* Initialize Tx queues * * Queues 0-3 are priority-based, each one has 32 descriptors, @@ -1875,6 +1995,9 @@ static void bcmgenet_init_tx_queues(struct net_device *dev) bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1); bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2); + /* Initialize Tx NAPI */ + bcmgenet_init_tx_napi(priv); + /* Enable Tx queues */ bcmgenet_tdma_writel(priv, ring_cfg, DMA_RING_CFG); @@ -1884,6 +2007,62 @@ static void bcmgenet_init_tx_queues(struct net_device *dev) bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL); } +static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_rx_ring *ring; + + for (i = 0; i < priv->hw_params->rx_queues; ++i) { + ring = &priv->rx_rings[i]; + netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll, 64); + } + + ring = &priv->rx_rings[DESC_INDEX]; + netif_napi_add(priv->dev, &ring->napi, bcmgenet_rx_poll, 64); +} + +static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_rx_ring *ring; + + for (i = 0; i < priv->hw_params->rx_queues; ++i) { + ring = &priv->rx_rings[i]; + napi_enable(&ring->napi); + } + + ring = &priv->rx_rings[DESC_INDEX]; + napi_enable(&ring->napi); +} + +static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_rx_ring *ring; + + for (i = 0; i < priv->hw_params->rx_queues; ++i) { + ring = &priv->rx_rings[i]; + napi_disable(&ring->napi); + } + + ring = &priv->rx_rings[DESC_INDEX]; + napi_disable(&ring->napi); +} + +static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv) +{ + unsigned int i; + struct bcmgenet_rx_ring *ring; + + for (i = 0; i < priv->hw_params->rx_queues; ++i) { + ring = &priv->rx_rings[i]; + netif_napi_del(&ring->napi); + } + + ring = &priv->rx_rings[DESC_INDEX]; + netif_napi_del(&ring->napi); +} + /* Initialize Rx queues * * Queues 0-15 are priority queues. Hardware Filtering Block (HFB) can be @@ -1933,6 +2112,9 @@ static int bcmgenet_init_rx_queues(struct net_device *dev) ring_cfg |= (1 << DESC_INDEX); dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT)); + /* Initialize Rx NAPI */ + bcmgenet_init_rx_napi(priv); + /* Enable rings */ bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG); @@ -2016,12 +2198,8 @@ static void __bcmgenet_fini_dma(struct bcmgenet_priv *priv) static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) { - int i; - - bcmgenet_fini_tx_ring(priv, DESC_INDEX); - - for (i = 0; i < priv->hw_params->tx_queues; i++) - bcmgenet_fini_tx_ring(priv, i); + bcmgenet_fini_rx_napi(priv); + bcmgenet_fini_tx_napi(priv); __bcmgenet_fini_dma(priv); } @@ -2035,9 +2213,6 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv) netif_dbg(priv, hw, priv->dev, "%s\n", __func__); - /* Init rDma */ - bcmgenet_rdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE); - /* Initialize common Rx ring structures */ priv->rx_bds = priv->base + priv->hw_params->rdma_offset; priv->num_rx_bds = TOTAL_DESC; @@ -2051,25 +2226,13 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv) cb->bd_addr = priv->rx_bds + i * DMA_DESC_SIZE; } - /* Initialize Rx queues */ - ret = bcmgenet_init_rx_queues(priv->dev); - if (ret) { - netdev_err(priv->dev, "failed to initialize Rx queues\n"); - bcmgenet_free_rx_buffers(priv); - kfree(priv->rx_cbs); - return ret; - } - - /* Init tDma */ - bcmgenet_tdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE); - /* Initialize common TX ring structures */ priv->tx_bds = priv->base + priv->hw_params->tdma_offset; priv->num_tx_bds = TOTAL_DESC; priv->tx_cbs = kcalloc(priv->num_tx_bds, sizeof(struct enet_cb), GFP_KERNEL); if (!priv->tx_cbs) { - __bcmgenet_fini_dma(priv); + kfree(priv->rx_cbs); return -ENOMEM; } @@ -2078,28 +2241,26 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv) cb->bd_addr = priv->tx_bds + i * DMA_DESC_SIZE; } - /* Initialize Tx queues */ - bcmgenet_init_tx_queues(priv->dev); - - return 0; -} + /* Init rDma */ + bcmgenet_rdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE); -/* NAPI polling method*/ -static int bcmgenet_poll(struct napi_struct *napi, int budget) -{ - struct bcmgenet_priv *priv = container_of(napi, - struct bcmgenet_priv, napi); - unsigned int work_done; + /* Initialize Rx queues */ + ret = bcmgenet_init_rx_queues(priv->dev); + if (ret) { + netdev_err(priv->dev, "failed to initialize Rx queues\n"); + bcmgenet_free_rx_buffers(priv); + kfree(priv->rx_cbs); + kfree(priv->tx_cbs); + return ret; + } - work_done = bcmgenet_desc_rx(priv, DESC_INDEX, budget); + /* Init tDma */ + bcmgenet_tdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE); - if (work_done < budget) { - napi_complete(napi); - bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_BDONE, - INTRL2_CPU_MASK_CLEAR); - } + /* Initialize Tx queues */ + bcmgenet_init_tx_queues(priv->dev); - return work_done; + return 0; } /* Interrupt bottom half */ @@ -2126,50 +2287,66 @@ static void bcmgenet_irq_task(struct work_struct *work) } } -/* bcmgenet_isr1: interrupt handler for ring buffer. */ +/* bcmgenet_isr1: handle Rx and Tx priority queues */ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id) { struct bcmgenet_priv *priv = dev_id; - struct bcmgenet_tx_ring *ring; + struct bcmgenet_rx_ring *rx_ring; + struct bcmgenet_tx_ring *tx_ring; unsigned int index; /* Save irq status for bottom-half processing. */ priv->irq1_stat = bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) & ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS); + /* clear interrupts */ bcmgenet_intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR); netif_dbg(priv, intr, priv->dev, "%s: IRQ=0x%x\n", __func__, priv->irq1_stat); - /* Check the MBDONE interrupts. - * packet is done, reclaim descriptors - */ + /* Check Rx priority queue interrupts */ + for (index = 0; index < priv->hw_params->rx_queues; index++) { + if (!(priv->irq1_stat & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index))) + continue; + + rx_ring = &priv->rx_rings[index]; + + if (likely(napi_schedule_prep(&rx_ring->napi))) { + rx_ring->int_disable(rx_ring); + __napi_schedule(&rx_ring->napi); + } + } + + /* Check Tx priority queue interrupts */ for (index = 0; index < priv->hw_params->tx_queues; index++) { if (!(priv->irq1_stat & BIT(index))) continue; - ring = &priv->tx_rings[index]; + tx_ring = &priv->tx_rings[index]; - if (likely(napi_schedule_prep(&ring->napi))) { - ring->int_disable(priv, ring); - __napi_schedule(&ring->napi); + if (likely(napi_schedule_prep(&tx_ring->napi))) { + tx_ring->int_disable(tx_ring); + __napi_schedule(&tx_ring->napi); } } return IRQ_HANDLED; } -/* bcmgenet_isr0: Handle various interrupts. */ +/* bcmgenet_isr0: handle Rx and Tx default queues + other stuff */ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) { struct bcmgenet_priv *priv = dev_id; + struct bcmgenet_rx_ring *rx_ring; + struct bcmgenet_tx_ring *tx_ring; /* Save irq status for bottom-half processing. */ priv->irq0_stat = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) & ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS); + /* clear interrupts */ bcmgenet_intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR); @@ -2177,25 +2354,23 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) "IRQ=0x%x\n", priv->irq0_stat); if (priv->irq0_stat & (UMAC_IRQ_RXDMA_BDONE | UMAC_IRQ_RXDMA_PDONE)) { - /* We use NAPI(software interrupt throttling, if - * Rx Descriptor throttling is not used. - * Disable interrupt, will be enabled in the poll method. - */ - if (likely(napi_schedule_prep(&priv->napi))) { - bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_BDONE, - INTRL2_CPU_MASK_SET); - __napi_schedule(&priv->napi); + rx_ring = &priv->rx_rings[DESC_INDEX]; + + if (likely(napi_schedule_prep(&rx_ring->napi))) { + rx_ring->int_disable(rx_ring); + __napi_schedule(&rx_ring->napi); } } - if (priv->irq0_stat & - (UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE)) { - struct bcmgenet_tx_ring *ring = &priv->tx_rings[DESC_INDEX]; - if (likely(napi_schedule_prep(&ring->napi))) { - ring->int_disable(priv, ring); - __napi_schedule(&ring->napi); + if (priv->irq0_stat & (UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE)) { + tx_ring = &priv->tx_rings[DESC_INDEX]; + + if (likely(napi_schedule_prep(&tx_ring->napi))) { + tx_ring->int_disable(tx_ring); + __napi_schedule(&tx_ring->napi); } } + if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R | UMAC_IRQ_PHY_DET_F | UMAC_IRQ_LINK_UP | @@ -2283,18 +2458,170 @@ static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl) bcmgenet_tdma_writel(priv, reg, DMA_CTRL); } +static bool bcmgenet_hfb_is_filter_enabled(struct bcmgenet_priv *priv, + u32 f_index) +{ + u32 offset; + u32 reg; + + offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32); + reg = bcmgenet_hfb_reg_readl(priv, offset); + return !!(reg & (1 << (f_index % 32))); +} + +static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index) +{ + u32 offset; + u32 reg; + + offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32); + reg = bcmgenet_hfb_reg_readl(priv, offset); + reg |= (1 << (f_index % 32)); + bcmgenet_hfb_reg_writel(priv, reg, offset); +} + +static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv, + u32 f_index, u32 rx_queue) +{ + u32 offset; + u32 reg; + + offset = f_index / 8; + reg = bcmgenet_rdma_readl(priv, DMA_INDEX2RING_0 + offset); + reg &= ~(0xF << (4 * (f_index % 8))); + reg |= ((rx_queue & 0xF) << (4 * (f_index % 8))); + bcmgenet_rdma_writel(priv, reg, DMA_INDEX2RING_0 + offset); +} + +static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv, + u32 f_index, u32 f_length) +{ + u32 offset; + u32 reg; + + offset = HFB_FLT_LEN_V3PLUS + + ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4) * + sizeof(u32); + reg = bcmgenet_hfb_reg_readl(priv, offset); + reg &= ~(0xFF << (8 * (f_index % 4))); + reg |= ((f_length & 0xFF) << (8 * (f_index % 4))); + bcmgenet_hfb_reg_writel(priv, reg, offset); +} + +static int bcmgenet_hfb_find_unused_filter(struct bcmgenet_priv *priv) +{ + u32 f_index; + + for (f_index = 0; f_index < priv->hw_params->hfb_filter_cnt; f_index++) + if (!bcmgenet_hfb_is_filter_enabled(priv, f_index)) + return f_index; + + return -ENOMEM; +} + +/* bcmgenet_hfb_add_filter + * + * Add new filter to Hardware Filter Block to match and direct Rx traffic to + * desired Rx queue. + * + * f_data is an array of unsigned 32-bit integers where each 32-bit integer + * provides filter data for 2 bytes (4 nibbles) of Rx frame: + * + * bits 31:20 - unused + * bit 19 - nibble 0 match enable + * bit 18 - nibble 1 match enable + * bit 17 - nibble 2 match enable + * bit 16 - nibble 3 match enable + * bits 15:12 - nibble 0 data + * bits 11:8 - nibble 1 data + * bits 7:4 - nibble 2 data + * bits 3:0 - nibble 3 data + * + * Example: + * In order to match: + * - Ethernet frame type = 0x0800 (IP) + * - IP version field = 4 + * - IP protocol field = 0x11 (UDP) + * + * The following filter is needed: + * u32 hfb_filter_ipv4_udp[] = { + * Rx frame offset 0x00: 0x00000000, 0x00000000, 0x00000000, 0x00000000, + * Rx frame offset 0x08: 0x00000000, 0x00000000, 0x000F0800, 0x00084000, + * Rx frame offset 0x10: 0x00000000, 0x00000000, 0x00000000, 0x00030011, + * }; + * + * To add the filter to HFB and direct the traffic to Rx queue 0, call: + * bcmgenet_hfb_add_filter(priv, hfb_filter_ipv4_udp, + * ARRAY_SIZE(hfb_filter_ipv4_udp), 0); + */ +int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data, + u32 f_length, u32 rx_queue) +{ + int f_index; + u32 i; + + f_index = bcmgenet_hfb_find_unused_filter(priv); + if (f_index < 0) + return -ENOMEM; + + if (f_length > priv->hw_params->hfb_filter_size) + return -EINVAL; + + for (i = 0; i < f_length; i++) + bcmgenet_hfb_writel(priv, f_data[i], + (f_index * priv->hw_params->hfb_filter_size + i) * + sizeof(u32)); + + bcmgenet_hfb_set_filter_length(priv, f_index, 2 * f_length); + bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f_index, rx_queue); + bcmgenet_hfb_enable_filter(priv, f_index); + bcmgenet_hfb_reg_writel(priv, 0x1, HFB_CTRL); + + return 0; +} + +/* bcmgenet_hfb_clear + * + * Clear Hardware Filter Block and disable all filtering. + */ +static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv) +{ + u32 i; + + bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL); + bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS); + bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4); + + for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++) + bcmgenet_rdma_writel(priv, 0x0, i); + + for (i = 0; i < (priv->hw_params->hfb_filter_cnt / 4); i++) + bcmgenet_hfb_reg_writel(priv, 0x0, + HFB_FLT_LEN_V3PLUS + i * sizeof(u32)); + + for (i = 0; i < priv->hw_params->hfb_filter_cnt * + priv->hw_params->hfb_filter_size; i++) + bcmgenet_hfb_writel(priv, 0x0, i * sizeof(u32)); +} + +static void bcmgenet_hfb_init(struct bcmgenet_priv *priv) +{ + if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) + return; + + bcmgenet_hfb_clear(priv); +} + static void bcmgenet_netif_start(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); /* Start the network engine */ - napi_enable(&priv->napi); + bcmgenet_enable_rx_napi(priv); + bcmgenet_enable_tx_napi(priv); umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true); - if (phy_is_internal(priv->phydev)) - bcmgenet_power_up(priv, GENET_POWER_PASSIVE); - netif_tx_start_all_queues(dev); phy_start(priv->phydev); @@ -2313,6 +2640,12 @@ static int bcmgenet_open(struct net_device *dev) if (!IS_ERR(priv->clk)) clk_prepare_enable(priv->clk); + /* If this is an internal GPHY, power it back on now, before UniMAC is + * brought out of reset as absolutely no UniMAC activity is allowed + */ + if (phy_is_internal(priv->phydev)) + bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + /* take MAC out of reset */ bcmgenet_umac_reset(priv); @@ -2348,6 +2681,9 @@ static int bcmgenet_open(struct net_device *dev) /* Always enable ring 16 - descriptor ring */ bcmgenet_enable_dma(priv, dma_ctrl); + /* HFB init */ + bcmgenet_hfb_init(priv); + ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED, dev->name, priv); if (ret < 0) { @@ -2387,10 +2723,10 @@ static void bcmgenet_netif_stop(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); netif_tx_stop_all_queues(dev); - napi_disable(&priv->napi); phy_stop(priv->phydev); - bcmgenet_intr_disable(priv); + bcmgenet_disable_rx_napi(priv); + bcmgenet_disable_tx_napi(priv); /* Wait for pending work items to complete. Since interrupts are * disabled no new work will be scheduled. @@ -2433,12 +2769,12 @@ static int bcmgenet_close(struct net_device *dev) free_irq(priv->irq1, priv); if (phy_is_internal(priv->phydev)) - bcmgenet_power_down(priv, GENET_POWER_PASSIVE); + ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE); if (!IS_ERR(priv->clk)) clk_disable_unprepare(priv->clk); - return 0; + return ret; } static void bcmgenet_timeout(struct net_device *dev) @@ -2592,6 +2928,7 @@ static struct bcmgenet_hw_params bcmgenet_hw_params[] = { .bp_in_en_shift = 17, .bp_in_mask = 0x1ffff, .hfb_filter_cnt = 48, + .hfb_filter_size = 128, .qtag_mask = 0x3F, .tbuf_offset = 0x0600, .hfb_offset = 0x8000, @@ -2609,6 +2946,7 @@ static struct bcmgenet_hw_params bcmgenet_hw_params[] = { .bp_in_en_shift = 17, .bp_in_mask = 0x1ffff, .hfb_filter_cnt = 48, + .hfb_filter_size = 128, .qtag_mask = 0x3F, .tbuf_offset = 0x0600, .hfb_offset = 0x8000, @@ -2789,7 +3127,6 @@ static int bcmgenet_probe(struct platform_device *pdev) dev->watchdog_timeo = 2 * HZ; dev->ethtool_ops = &bcmgenet_ethtool_ops; dev->netdev_ops = &bcmgenet_netdev_ops; - netif_napi_add(dev, &priv->napi, bcmgenet_poll, 64); priv->msg_enable = netif_msg_init(-1, GENET_MSG_DEFAULT); @@ -2922,14 +3259,16 @@ static int bcmgenet_suspend(struct device *d) /* Prepare the device for Wake-on-LAN and switch to the slow clock */ if (device_may_wakeup(d) && priv->wolopts) { - bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC); + ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC); clk_prepare_enable(priv->clk_wol); + } else if (phy_is_internal(priv->phydev)) { + ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE); } /* Turn off the clocks */ clk_disable_unprepare(priv->clk); - return 0; + return ret; } static int bcmgenet_resume(struct device *d) @@ -2948,6 +3287,12 @@ static int bcmgenet_resume(struct device *d) if (ret) return ret; + /* If this is an internal GPHY, power it back on now, before UniMAC is + * brought out of reset as absolutely no UniMAC activity is allowed + */ + if (phy_is_internal(priv->phydev)) + bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + bcmgenet_umac_reset(priv); ret = init_umac(priv); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 2a8113898aed..a834da1dfe4c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -310,6 +310,11 @@ struct bcmgenet_mib_counters { #define UMAC_IRQ_MDIO_DONE (1 << 23) #define UMAC_IRQ_MDIO_ERROR (1 << 24) +/* INTRL2 instance 1 definitions */ +#define UMAC_IRQ1_TX_INTR_MASK 0xFFFF +#define UMAC_IRQ1_RX_INTR_MASK 0xFFFF +#define UMAC_IRQ1_RX_INTR_SHIFT 16 + /* Register block offsets */ #define GENET_SYS_OFF 0x0000 #define GENET_GR_BRIDGE_OFF 0x0040 @@ -354,6 +359,7 @@ struct bcmgenet_mib_counters { #define EXT_GPHY_CTRL 0x1C #define EXT_CFG_IDDQ_BIAS (1 << 0) #define EXT_CFG_PWR_DOWN (1 << 1) +#define EXT_CK25_DIS (1 << 4) #define EXT_GPHY_RESET (1 << 5) /* DMA rings size */ @@ -509,6 +515,7 @@ struct bcmgenet_hw_params { u8 bp_in_en_shift; u32 bp_in_mask; u8 hfb_filter_cnt; + u8 hfb_filter_size; u8 qtag_mask; u16 tbuf_offset; u32 hfb_offset; @@ -533,14 +540,13 @@ struct bcmgenet_tx_ring { unsigned int prod_index; /* Tx ring producer index SW copy */ unsigned int cb_ptr; /* Tx ring initial CB ptr */ unsigned int end_ptr; /* Tx ring end CB ptr */ - void (*int_enable)(struct bcmgenet_priv *priv, - struct bcmgenet_tx_ring *); - void (*int_disable)(struct bcmgenet_priv *priv, - struct bcmgenet_tx_ring *); + void (*int_enable)(struct bcmgenet_tx_ring *); + void (*int_disable)(struct bcmgenet_tx_ring *); struct bcmgenet_priv *priv; }; struct bcmgenet_rx_ring { + struct napi_struct napi; /* Rx NAPI struct */ unsigned int index; /* Rx ring index */ struct enet_cb *cbs; /* Rx ring buffer control block */ unsigned int size; /* Rx ring size */ @@ -549,6 +555,9 @@ struct bcmgenet_rx_ring { unsigned int cb_ptr; /* Rx ring initial CB ptr */ unsigned int end_ptr; /* Rx ring end CB ptr */ unsigned int old_discards; + void (*int_enable)(struct bcmgenet_rx_ring *); + void (*int_disable)(struct bcmgenet_rx_ring *); + struct bcmgenet_priv *priv; }; /* device context */ @@ -556,11 +565,6 @@ struct bcmgenet_priv { void __iomem *base; enum bcmgenet_version version; struct net_device *dev; - u32 int0_mask; - u32 int1_mask; - - /* NAPI for descriptor based rx */ - struct napi_struct napi ____cacheline_aligned; /* transmit variables */ void __iomem *tx_bds; @@ -662,6 +666,7 @@ int bcmgenet_mii_init(struct net_device *dev); int bcmgenet_mii_config(struct net_device *dev, bool init); void bcmgenet_mii_exit(struct net_device *dev); void bcmgenet_mii_reset(struct net_device *dev); +void bcmgenet_phy_power_set(struct net_device *dev, bool enable); void bcmgenet_mii_setup(struct net_device *dev); /* Wake-on-LAN routines */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 446889cc3c6a..6d3b66a103cc 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -168,7 +168,7 @@ void bcmgenet_mii_reset(struct net_device *dev) } } -static void bcmgenet_ephy_power_up(struct net_device *dev) +void bcmgenet_phy_power_set(struct net_device *dev, bool enable) { struct bcmgenet_priv *priv = netdev_priv(dev); u32 reg = 0; @@ -178,14 +178,25 @@ static void bcmgenet_ephy_power_up(struct net_device *dev) return; reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL); - reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN); - reg |= EXT_GPHY_RESET; - bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - mdelay(2); + if (enable) { + reg &= ~EXT_CK25_DIS; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + + reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN); + reg |= EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); - reg &= ~EXT_GPHY_RESET; + reg &= ~EXT_GPHY_RESET; + } else { + reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + reg |= EXT_CK25_DIS; + } bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); - udelay(20); + udelay(60); } static void bcmgenet_internal_phy_setup(struct net_device *dev) @@ -193,8 +204,8 @@ static void bcmgenet_internal_phy_setup(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); u32 reg; - /* Power up EPHY */ - bcmgenet_ephy_power_up(dev); + /* Power up PHY */ + bcmgenet_phy_power_set(dev, true); /* enable APD */ reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); reg |= EXT_PWR_DN_EN_LD; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 22b33da32ba4..d02d19bd34e0 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6217,7 +6217,7 @@ static int tg3_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int tg3_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int tg3_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; u32 remainder; @@ -6235,12 +6235,12 @@ static int tg3_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int tg3_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { u64 ns; struct tg3 *tp = container_of(ptp, struct tg3, ptp_info); - ns = timespec_to_ns(ts); + ns = timespec64_to_ns(ts); tg3_full_lock(tp, 0); tg3_refclk_write(tp, ns); @@ -6320,8 +6320,8 @@ static const struct ptp_clock_info tg3_ptp_caps = { .pps = 0, .adjfreq = tg3_ptp_adjfreq, .adjtime = tg3_ptp_adjtime, - .gettime = tg3_ptp_gettime, - .settime = tg3_ptp_settime, + .gettime64 = tg3_ptp_gettime, + .settime64 = tg3_ptp_settime, .enable = tg3_ptp_enable, }; diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index ac6473f75eb9..7daa088a9bb7 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -97,6 +97,17 @@ config CHELSIO_T4_DCB If unsure, say N. +config CHELSIO_T4_FCOE + bool "Fibre Channel over Ethernet (FCoE) Support for Chelsio T5 cards" + default n + depends on CHELSIO_T4 && CHELSIO_T4_DCB && FCOE + ---help--- + Enable FCoE offload features. + Say Y here if you want to enable Fibre Channel over Ethernet (FCoE) support + in the driver. + + If unsure, say N. + config CHELSIO_T4VF tristate "Chelsio Communications T4/T5 Virtual Function Ethernet support" depends on PCI diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile index ae50cd72358c..07d9b68a4da2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/Makefile +++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile @@ -6,4 +6,5 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o +cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 4555634b985d..bf46ca935e2a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -387,6 +387,10 @@ struct sge_rspq; #include "cxgb4_dcb.h" +#ifdef CONFIG_CHELSIO_T4_FCOE +#include "cxgb4_fcoe.h" +#endif /* CONFIG_CHELSIO_T4_FCOE */ + struct port_info { struct adapter *adapter; u16 viid; @@ -406,6 +410,9 @@ struct port_info { #ifdef CONFIG_CHELSIO_T4_DCB struct port_dcb_info dcb; /* Data Center Bridging support */ #endif +#ifdef CONFIG_CHELSIO_T4_FCOE + struct cxgb_fcoe fcoe; +#endif /* CONFIG_CHELSIO_T4_FCOE */ }; struct dentry; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c new file mode 100644 index 000000000000..6c8a62eefe51 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c @@ -0,0 +1,122 @@ +/* + * This file is part of the Chelsio T4 Ethernet driver for Linux. + * + * Copyright (c) 2015 Chelsio Communications, Inc. 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. + */ + +#ifdef CONFIG_CHELSIO_T4_FCOE + +#include <scsi/fc/fc_fs.h> +#include <scsi/libfcoe.h> +#include "cxgb4.h" + +bool cxgb_fcoe_sof_eof_supported(struct adapter *adap, struct sk_buff *skb) +{ + struct fcoe_hdr *fcoeh = (struct fcoe_hdr *)skb_network_header(skb); + u8 sof = fcoeh->fcoe_sof; + u8 eof = 0; + + if ((sof != FC_SOF_I3) && (sof != FC_SOF_N3)) { + dev_err(adap->pdev_dev, "Unsupported SOF 0x%x\n", sof); + return false; + } + + skb_copy_bits(skb, skb->len - 4, &eof, 1); + + if ((eof != FC_EOF_N) && (eof != FC_EOF_T)) { + dev_err(adap->pdev_dev, "Unsupported EOF 0x%x\n", eof); + return false; + } + + return true; +} + +/** + * cxgb_fcoe_enable - enable FCoE offload features + * @netdev: net device + * + * Returns 0 on success or -EINVAL on failure. + */ +int cxgb_fcoe_enable(struct net_device *netdev) +{ + struct port_info *pi = netdev_priv(netdev); + struct adapter *adap = pi->adapter; + struct cxgb_fcoe *fcoe = &pi->fcoe; + + if (is_t4(adap->params.chip)) + return -EINVAL; + + if (!(adap->flags & FULL_INIT_DONE)) + return -EINVAL; + + dev_info(adap->pdev_dev, "Enabling FCoE offload features\n"); + + netdev->features |= NETIF_F_FCOE_CRC; + netdev->vlan_features |= NETIF_F_FCOE_CRC; + netdev->features |= NETIF_F_FCOE_MTU; + netdev->vlan_features |= NETIF_F_FCOE_MTU; + + netdev_features_change(netdev); + + fcoe->flags |= CXGB_FCOE_ENABLED; + + return 0; +} + +/** + * cxgb_fcoe_disable - disable FCoE offload + * @netdev: net device + * + * Returns 0 on success or -EINVAL on failure. + */ +int cxgb_fcoe_disable(struct net_device *netdev) +{ + struct port_info *pi = netdev_priv(netdev); + struct adapter *adap = pi->adapter; + struct cxgb_fcoe *fcoe = &pi->fcoe; + + if (!(fcoe->flags & CXGB_FCOE_ENABLED)) + return -EINVAL; + + dev_info(adap->pdev_dev, "Disabling FCoE offload features\n"); + + fcoe->flags &= ~CXGB_FCOE_ENABLED; + + netdev->features &= ~NETIF_F_FCOE_CRC; + netdev->vlan_features &= ~NETIF_F_FCOE_CRC; + netdev->features &= ~NETIF_F_FCOE_MTU; + netdev->vlan_features &= ~NETIF_F_FCOE_MTU; + + netdev_features_change(netdev); + + return 0; +} +#endif /* CONFIG_CHELSIO_T4_FCOE */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.h new file mode 100644 index 000000000000..bf9258a56ac9 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.h @@ -0,0 +1,57 @@ +/* + * This file is part of the Chelsio T4 Ethernet driver for Linux. + * + * Copyright (c) 2015 Chelsio Communications, Inc. 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 __CXGB4_FCOE_H__ +#define __CXGB4_FCOE_H__ + +#ifdef CONFIG_CHELSIO_T4_FCOE + +#define CXGB_FCOE_TXPKT_CSUM_START 28 +#define CXGB_FCOE_TXPKT_CSUM_END 8 + +/* fcoe flags */ +enum { + CXGB_FCOE_ENABLED = (1 << 0), +}; + +struct cxgb_fcoe { + u8 flags; +}; + +int cxgb_fcoe_enable(struct net_device *); +int cxgb_fcoe_disable(struct net_device *); +bool cxgb_fcoe_sof_eof_supported(struct adapter *, struct sk_buff *); + +#endif /* CONFIG_CHELSIO_T4_FCOE */ +#endif /* __CXGB4_FCOE_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 4af8a9fd75ae..e40e283ff36c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -124,7 +124,7 @@ struct filter_entry { /* Macros needed to support the PCI Device ID Table ... */ #define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \ - static struct pci_device_id cxgb4_pci_tbl[] = { + static const struct pci_device_id cxgb4_pci_tbl[] = { #define CH_PCI_DEVICE_ID_FUNCTION 0x4 /* Include PCI Device IDs for both PF4 and PF0-3 so our PCI probe() routine is @@ -1271,6 +1271,10 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, txq = 0; } else { txq = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; +#ifdef CONFIG_CHELSIO_T4_FCOE + if (skb->protocol == htons(ETH_P_FCOE)) + txq = skb->priority & 0x7; +#endif /* CONFIG_CHELSIO_T4_FCOE */ } return txq; } @@ -4578,6 +4582,10 @@ static const struct net_device_ops cxgb4_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = cxgb_netpoll, #endif +#ifdef CONFIG_CHELSIO_T4_FCOE + .ndo_fcoe_enable = cxgb_fcoe_enable, + .ndo_fcoe_disable = cxgb_fcoe_disable, +#endif /* CONFIG_CHELSIO_T4_FCOE */ #ifdef CONFIG_NET_RX_BUSY_POLL .ndo_busy_poll = cxgb_busy_poll, #endif diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index b4b9f6048fe7..c46e7a938317 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -46,6 +46,9 @@ #ifdef CONFIG_NET_RX_BUSY_POLL #include <net/busy_poll.h> #endif /* CONFIG_NET_RX_BUSY_POLL */ +#ifdef CONFIG_CHELSIO_T4_FCOE +#include <scsi/fc/fc_fcoe.h> +#endif /* CONFIG_CHELSIO_T4_FCOE */ #include "cxgb4.h" #include "t4_regs.h" #include "t4_values.h" @@ -1044,6 +1047,38 @@ static inline void txq_advance(struct sge_txq *q, unsigned int n) q->pidx -= q->size; } +#ifdef CONFIG_CHELSIO_T4_FCOE +static inline int +cxgb_fcoe_offload(struct sk_buff *skb, struct adapter *adap, + const struct port_info *pi, u64 *cntrl) +{ + const struct cxgb_fcoe *fcoe = &pi->fcoe; + + if (!(fcoe->flags & CXGB_FCOE_ENABLED)) + return 0; + + if (skb->protocol != htons(ETH_P_FCOE)) + return 0; + + skb_reset_mac_header(skb); + skb->mac_len = sizeof(struct ethhdr); + + skb_set_network_header(skb, skb->mac_len); + skb_set_transport_header(skb, skb->mac_len + sizeof(struct fcoe_hdr)); + + if (!cxgb_fcoe_sof_eof_supported(adap, skb)) + return -ENOTSUPP; + + /* FC CRC offload */ + *cntrl = TXPKT_CSUM_TYPE(TX_CSUM_FCOE) | + TXPKT_L4CSUM_DIS | TXPKT_IPCSUM_DIS | + TXPKT_CSUM_START(CXGB_FCOE_TXPKT_CSUM_START) | + TXPKT_CSUM_END(CXGB_FCOE_TXPKT_CSUM_END) | + TXPKT_CSUM_LOC(CXGB_FCOE_TXPKT_CSUM_END); + return 0; +} +#endif /* CONFIG_CHELSIO_T4_FCOE */ + /** * t4_eth_xmit - add a packet to an Ethernet Tx queue * @skb: the packet @@ -1066,6 +1101,9 @@ netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev) const struct skb_shared_info *ssi; dma_addr_t addr[MAX_SKB_FRAGS + 1]; bool immediate = false; +#ifdef CONFIG_CHELSIO_T4_FCOE + int err; +#endif /* CONFIG_CHELSIO_T4_FCOE */ /* * The chip min packet length is 10 octets but play safe and reject @@ -1082,6 +1120,13 @@ out_free: dev_kfree_skb_any(skb); q = &adap->sge.ethtxq[qidx + pi->first_qset]; reclaim_completed_tx(adap, &q->q, true); + cntrl = TXPKT_L4CSUM_DIS | TXPKT_IPCSUM_DIS; + +#ifdef CONFIG_CHELSIO_T4_FCOE + err = cxgb_fcoe_offload(skb, adap, pi, &cntrl); + if (unlikely(err == -ENOTSUPP)) + goto out_free; +#endif /* CONFIG_CHELSIO_T4_FCOE */ flits = calc_tx_flits(skb); ndesc = flits_to_desc(flits); @@ -1153,13 +1198,17 @@ out_free: dev_kfree_skb_any(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { cntrl = hwcsum(skb) | TXPKT_IPCSUM_DIS; q->tx_cso++; - } else - cntrl = TXPKT_L4CSUM_DIS | TXPKT_IPCSUM_DIS; + } } if (skb_vlan_tag_present(skb)) { q->vlan_ins++; cntrl |= TXPKT_VLAN_VLD | TXPKT_VLAN(skb_vlan_tag_get(skb)); +#ifdef CONFIG_CHELSIO_T4_FCOE + if (skb->protocol == htons(ETH_P_FCOE)) + cntrl |= TXPKT_VLAN( + ((skb->priority & 0x7) << VLAN_PRIO_SHIFT)); +#endif /* CONFIG_CHELSIO_T4_FCOE */ } cpl->ctrl0 = htonl(TXPKT_OPCODE(CPL_TX_PKT_XT) | @@ -1759,6 +1808,9 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, struct sge *s = &q->adap->sge; int cpl_trace_pkt = is_t4(q->adap->params.chip) ? CPL_TRACE_PKT : CPL_TRACE_PKT_T5; +#ifdef CONFIG_CHELSIO_T4_FCOE + struct port_info *pi; +#endif if (unlikely(*(u8 *)rsp == cpl_trace_pkt)) return handle_trace_pkt(q->adap, si); @@ -1799,8 +1851,24 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, skb->ip_summed = CHECKSUM_COMPLETE; rxq->stats.rx_cso++; } - } else + } else { skb_checksum_none_assert(skb); +#ifdef CONFIG_CHELSIO_T4_FCOE +#define CPL_RX_PKT_FLAGS (RXF_PSH_F | RXF_SYN_F | RXF_UDP_F | \ + RXF_TCP_F | RXF_IP_F | RXF_IP6_F | RXF_LRO_F) + + pi = netdev_priv(skb->dev); + if (!(pkt->l2info & cpu_to_be32(CPL_RX_PKT_FLAGS))) { + if ((pkt->l2info & cpu_to_be32(RXF_FCOE_F)) && + (pi->fcoe.flags & CXGB_FCOE_ENABLED)) { + if (!(pkt->err_vec & cpu_to_be16(RXERR_CSUM_F))) + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + } + +#undef CPL_RX_PKT_FLAGS +#endif /* CONFIG_CHELSIO_T4_FCOE */ + } if (unlikely(pkt->vlan_ex)) { __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(pkt->vlan)); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 1498d078c319..afbe1682ff48 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -1120,7 +1120,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, } /* Installed successfully, update the cached header too. */ - memcpy(card_fw, fs_fw, sizeof(*card_fw)); + *card_fw = *fs_fw; card_fw_usable = 1; *reset = 0; /* already reset as part of load_fw */ } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index 0fb975e258b3..30a2f56e99c2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -794,6 +794,14 @@ struct cpl_rx_pkt { __be16 err_vec; }; +#define RXF_PSH_S 20 +#define RXF_PSH_V(x) ((x) << RXF_PSH_S) +#define RXF_PSH_F RXF_PSH_V(1U) + +#define RXF_SYN_S 21 +#define RXF_SYN_V(x) ((x) << RXF_SYN_S) +#define RXF_SYN_F RXF_SYN_V(1U) + #define RXF_UDP_S 22 #define RXF_UDP_V(x) ((x) << RXF_UDP_S) #define RXF_UDP_F RXF_UDP_V(1U) @@ -810,6 +818,18 @@ struct cpl_rx_pkt { #define RXF_IP6_V(x) ((x) << RXF_IP6_S) #define RXF_IP6_F RXF_IP6_V(1U) +#define RXF_SYN_COOKIE_S 26 +#define RXF_SYN_COOKIE_V(x) ((x) << RXF_SYN_COOKIE_S) +#define RXF_SYN_COOKIE_F RXF_SYN_COOKIE_V(1U) + +#define RXF_FCOE_S 26 +#define RXF_FCOE_V(x) ((x) << RXF_FCOE_S) +#define RXF_FCOE_F RXF_FCOE_V(1U) + +#define RXF_LRO_S 27 +#define RXF_LRO_V(x) ((x) << RXF_LRO_S) +#define RXF_LRO_F RXF_LRO_V(1U) + /* rx_pkt.l2info fields */ #define RX_ETHHDR_LEN_S 0 #define RX_ETHHDR_LEN_M 0x1F @@ -846,6 +866,11 @@ struct cpl_rx_pkt { #define RX_IPHDR_LEN_V(x) ((x) << RX_IPHDR_LEN_S) #define RX_IPHDR_LEN_G(x) (((x) >> RX_IPHDR_LEN_S) & RX_IPHDR_LEN_M) +/* rx_pkt.err_vec fields */ +#define RXERR_CSUM_S 13 +#define RXERR_CSUM_V(x) ((x) << RXERR_CSUM_S) +#define RXERR_CSUM_F RXERR_CSUM_V(1U) + struct cpl_trace_pkt { u8 opcode; u8 intf; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index ddfb5b846045..1a9a6f334d2d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -60,8 +60,6 @@ * -- Used to finish the definition of the PCI ID Table. Note that we * -- will be adding a trailing semi-colon (";") here. */ -#ifdef CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN - #ifndef CH_PCI_DEVICE_ID_FUNCTION #error CH_PCI_DEVICE_ID_FUNCTION not defined! #endif @@ -154,8 +152,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x5087), /* Custom T580-CR */ CH_PCI_ID_TABLE_FENTRY(0x5088), /* Custom T570-CR */ CH_PCI_ID_TABLE_FENTRY(0x5089), /* Custom T520-CR */ + CH_PCI_ID_TABLE_FENTRY(0x5090), /* Custom T540-CR */ CH_PCI_DEVICE_ID_TABLE_DEFINE_END; -#endif /* CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN */ - #endif /* __T4_PCI_ID_TBL_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 122e2964e63b..1d893b0b7ddf 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -3034,7 +3034,7 @@ static void cxgb4vf_pci_shutdown(struct pci_dev *pdev) /* Macros needed to support the PCI Device ID Table ... */ #define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \ - static struct pci_device_id cxgb4vf_pci_tbl[] = { + static const struct pci_device_id cxgb4vf_pci_tbl[] = { #define CH_PCI_DEVICE_ID_FUNCTION 0x8 #define CH_PCI_ID_TABLE_ENTRY(devid) \ diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 3b42556f7f8d..ed41559bae77 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -589,7 +589,7 @@ static void tulip_tx_timeout(struct net_device *dev) (unsigned int)tp->rx_ring[i].buffer1, (unsigned int)tp->rx_ring[i].buffer2, buf[0], buf[1], buf[2]); - for (j = 0; buf[j] != 0xee && j < 1600; j++) + for (j = 0; ((j < 1600) && buf[j] != 0xee); j++) if (j < 100) pr_cont(" %02x", buf[j]); pr_cont(" j=%d\n", j); diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 996bbc6a244f..4b0494b9cc7c 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -30,11 +30,12 @@ #include <linux/firmware.h> #include <linux/slab.h> #include <linux/u64_stats_sync.h> +#include <linux/cpumask.h> #include "be_hw.h" #include "be_roce.h" -#define DRV_VER "10.4u" +#define DRV_VER "10.6.0.1" #define DRV_NAME "be2net" #define BE_NAME "Emulex BladeEngine2" #define BE3_NAME "Emulex BladeEngine3" @@ -183,6 +184,7 @@ struct be_eq_obj { u16 spurious_intr; struct napi_struct napi; struct be_adapter *adapter; + cpumask_var_t affinity_mask; #ifdef CONFIG_NET_RX_BUSY_POLL #define BE_EQ_IDLE 0 @@ -362,6 +364,7 @@ struct be_vf_cfg { u16 vlan_tag; u32 tx_rate; u32 plink_tracking; + u32 privileges; }; enum vf_state { @@ -468,6 +471,7 @@ struct be_adapter { u8 __iomem *csr; /* CSR BAR used only for BE2/3 */ u8 __iomem *db; /* Door Bell */ + u8 __iomem *pcicfg; /* On SH,BEx only. Shadow of PCI config space */ struct mutex mbox_lock; /* For serializing mbox cmds to BE card */ struct be_dma_mem mbox_mem; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index dc278391a391..fb140faeafb1 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1849,15 +1849,11 @@ int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *set_eqd, { int num_eqs, i = 0; - if (lancer_chip(adapter) && num > 8) { - while (num) { - num_eqs = min(num, 8); - __be_cmd_modify_eqd(adapter, &set_eqd[i], num_eqs); - i += num_eqs; - num -= num_eqs; - } - } else { - __be_cmd_modify_eqd(adapter, set_eqd, num); + while (num) { + num_eqs = min(num, 8); + __be_cmd_modify_eqd(adapter, &set_eqd[i], num_eqs); + i += num_eqs; + num -= num_eqs; } return 0; @@ -1865,7 +1861,7 @@ int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *set_eqd, /* Uses sycnhronous mcc */ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array, - u32 num) + u32 num, u32 domain) { struct be_mcc_wrb *wrb; struct be_cmd_req_vlan_config *req; @@ -1883,6 +1879,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array, be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_VLAN_CONFIG, sizeof(*req), wrb, NULL); + req->hdr.domain = domain; req->interface_id = if_id; req->untagged = BE_IF_FLAGS_UNTAGGED & be_if_cap_flags(adapter) ? 1 : 0; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 53e903f37247..1ec22300e254 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -2266,7 +2266,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter, int be_cmd_get_fw_ver(struct be_adapter *adapter); int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *, int num); int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array, - u32 num); + u32 num, u32 domain); int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 status); int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc); int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 5652b005947f..5ff7fba9b67c 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1261,7 +1261,7 @@ static int be_vid_config(struct be_adapter *adapter) for_each_set_bit(i, adapter->vids, VLAN_N_VID) vids[num++] = cpu_to_le16(i); - status = be_cmd_vlan_config(adapter, adapter->if_handle, vids, num); + status = be_cmd_vlan_config(adapter, adapter->if_handle, vids, num, 0); if (status) { dev_err(dev, "Setting HW VLAN filtering failed\n"); /* Set to VLAN promisc mode as setting VLAN filter failed */ @@ -1470,11 +1470,67 @@ static int be_get_vf_config(struct net_device *netdev, int vf, return 0; } +static int be_set_vf_tvt(struct be_adapter *adapter, int vf, u16 vlan) +{ + struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf]; + u16 vids[BE_NUM_VLANS_SUPPORTED]; + int vf_if_id = vf_cfg->if_handle; + int status; + + /* Enable Transparent VLAN Tagging */ + status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, vf_if_id, 0); + if (status) + return status; + + /* Clear pre-programmed VLAN filters on VF if any, if TVT is enabled */ + vids[0] = 0; + status = be_cmd_vlan_config(adapter, vf_if_id, vids, 1, vf + 1); + if (!status) + dev_info(&adapter->pdev->dev, + "Cleared guest VLANs on VF%d", vf); + + /* After TVT is enabled, disallow VFs to program VLAN filters */ + if (vf_cfg->privileges & BE_PRIV_FILTMGMT) { + status = be_cmd_set_fn_privileges(adapter, vf_cfg->privileges & + ~BE_PRIV_FILTMGMT, vf + 1); + if (!status) + vf_cfg->privileges &= ~BE_PRIV_FILTMGMT; + } + return 0; +} + +static int be_clear_vf_tvt(struct be_adapter *adapter, int vf) +{ + struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf]; + struct device *dev = &adapter->pdev->dev; + int status; + + /* Reset Transparent VLAN Tagging. */ + status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID, vf + 1, + vf_cfg->if_handle, 0); + if (status) + return status; + + /* Allow VFs to program VLAN filtering */ + if (!(vf_cfg->privileges & BE_PRIV_FILTMGMT)) { + status = be_cmd_set_fn_privileges(adapter, vf_cfg->privileges | + BE_PRIV_FILTMGMT, vf + 1); + if (!status) { + vf_cfg->privileges |= BE_PRIV_FILTMGMT; + dev_info(dev, "VF%d: FILTMGMT priv enabled", vf); + } + } + + dev_info(dev, + "Disable/re-enable i/f in VM to clear Transparent VLAN tag"); + return 0; +} + static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) { struct be_adapter *adapter = netdev_priv(netdev); struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf]; - int status = 0; + int status; if (!sriov_enabled(adapter)) return -EPERM; @@ -1484,24 +1540,19 @@ static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) if (vlan || qos) { vlan |= qos << VLAN_PRIO_SHIFT; - if (vf_cfg->vlan_tag != vlan) - status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, - vf_cfg->if_handle, 0); + status = be_set_vf_tvt(adapter, vf, vlan); } else { - /* Reset Transparent Vlan Tagging. */ - status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID, - vf + 1, vf_cfg->if_handle, 0); + status = be_clear_vf_tvt(adapter, vf); } if (status) { dev_err(&adapter->pdev->dev, - "VLAN %d config on VF %d failed : %#x\n", vlan, - vf, status); + "VLAN %d config on VF %d failed : %#x\n", vlan, vf, + status); return be_cmd_status(status); } vf_cfg->vlan_tag = vlan; - return 0; } @@ -2291,6 +2342,7 @@ static void be_evt_queues_destroy(struct be_adapter *adapter) napi_hash_del(&eqo->napi); netif_napi_del(&eqo->napi); } + free_cpumask_var(eqo->affinity_mask); be_queue_free(adapter, &eqo->q); } } @@ -2306,6 +2358,11 @@ static int be_evt_queues_create(struct be_adapter *adapter) adapter->cfg_num_qs); for_all_evt_queues(adapter, eqo, i) { + if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL)) + return -ENOMEM; + cpumask_set_cpu_local_first(i, dev_to_node(&adapter->pdev->dev), + eqo->affinity_mask); + netif_napi_add(adapter->netdev, &eqo->napi, be_poll, BE_NAPI_WEIGHT); napi_hash_add(&eqo->napi); @@ -2397,8 +2454,9 @@ static void be_tx_queues_destroy(struct be_adapter *adapter) static int be_tx_qs_create(struct be_adapter *adapter) { - struct be_queue_info *cq, *eq; + struct be_queue_info *cq; struct be_tx_obj *txo; + struct be_eq_obj *eqo; int status, i; adapter->num_tx_qs = min(adapter->num_evt_qs, be_max_txqs(adapter)); @@ -2416,8 +2474,8 @@ static int be_tx_qs_create(struct be_adapter *adapter) /* If num_evt_qs is less than num_tx_qs, then more than * one txq share an eq */ - eq = &adapter->eq_obj[i % adapter->num_evt_qs].q; - status = be_cmd_cq_create(adapter, cq, eq, false, 3); + eqo = &adapter->eq_obj[i % adapter->num_evt_qs]; + status = be_cmd_cq_create(adapter, cq, &eqo->q, false, 3); if (status) return status; @@ -2429,6 +2487,9 @@ static int be_tx_qs_create(struct be_adapter *adapter) status = be_cmd_txq_create(adapter, txo); if (status) return status; + + netif_set_xps_queue(adapter->netdev, eqo->affinity_mask, + eqo->idx); } dev_info(&adapter->pdev->dev, "created %d TX queue(s)\n", @@ -2868,14 +2929,12 @@ void be_detect_error(struct be_adapter *adapter) } } } else { - pci_read_config_dword(adapter->pdev, - PCICFG_UE_STATUS_LOW, &ue_lo); - pci_read_config_dword(adapter->pdev, - PCICFG_UE_STATUS_HIGH, &ue_hi); - pci_read_config_dword(adapter->pdev, - PCICFG_UE_STATUS_LOW_MASK, &ue_lo_mask); - pci_read_config_dword(adapter->pdev, - PCICFG_UE_STATUS_HI_MASK, &ue_hi_mask); + ue_lo = ioread32(adapter->pcicfg + PCICFG_UE_STATUS_LOW); + ue_hi = ioread32(adapter->pcicfg + PCICFG_UE_STATUS_HIGH); + ue_lo_mask = ioread32(adapter->pcicfg + + PCICFG_UE_STATUS_LOW_MASK); + ue_hi_mask = ioread32(adapter->pcicfg + + PCICFG_UE_STATUS_HI_MASK); ue_lo = (ue_lo & ~ue_lo_mask); ue_hi = (ue_hi & ~ue_hi_mask); @@ -2979,6 +3038,8 @@ static int be_msix_register(struct be_adapter *adapter) status = request_irq(vec, be_msix, 0, eqo->desc, eqo); if (status) goto err_msix; + + irq_set_affinity_hint(vec, eqo->affinity_mask); } return 0; @@ -3023,7 +3084,7 @@ static void be_irq_unregister(struct be_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct be_eq_obj *eqo; - int i; + int i, vec; if (!adapter->isr_registered) return; @@ -3035,8 +3096,11 @@ static void be_irq_unregister(struct be_adapter *adapter) } /* MSIx */ - for_all_evt_queues(adapter, eqo, i) - free_irq(be_msix_vec_get(adapter, eqo), eqo); + for_all_evt_queues(adapter, eqo, i) { + vec = be_msix_vec_get(adapter, eqo); + irq_set_affinity_hint(vec, NULL); + free_irq(vec, eqo); + } done: adapter->isr_registered = false; @@ -3480,7 +3544,6 @@ static int be_if_create(struct be_adapter *adapter, u32 *if_handle, u32 cap_flags, u32 vf) { u32 en_flags; - int status; en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS | @@ -3488,10 +3551,7 @@ static int be_if_create(struct be_adapter *adapter, u32 *if_handle, en_flags &= cap_flags; - status = be_cmd_if_create(adapter, cap_flags, en_flags, - if_handle, vf); - - return status; + return be_cmd_if_create(adapter, cap_flags, en_flags, if_handle, vf); } static int be_vfs_if_create(struct be_adapter *adapter) @@ -3510,8 +3570,13 @@ static int be_vfs_if_create(struct be_adapter *adapter) status = be_cmd_get_profile_config(adapter, &res, RESOURCE_LIMITS, vf + 1); - if (!status) + if (!status) { cap_flags = res.if_cap_flags; + /* Prevent VFs from enabling VLAN promiscuous + * mode + */ + cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS; + } } status = be_if_create(adapter, &vf_cfg->if_handle, @@ -3545,7 +3610,6 @@ static int be_vf_setup(struct be_adapter *adapter) struct device *dev = &adapter->pdev->dev; struct be_vf_cfg *vf_cfg; int status, old_vfs, vf; - u32 privileges; old_vfs = pci_num_vf(adapter->pdev); @@ -3575,15 +3639,18 @@ static int be_vf_setup(struct be_adapter *adapter) for_all_vfs(adapter, vf_cfg, vf) { /* Allow VFs to programs MAC/VLAN filters */ - status = be_cmd_get_fn_privileges(adapter, &privileges, vf + 1); - if (!status && !(privileges & BE_PRIV_FILTMGMT)) { + status = be_cmd_get_fn_privileges(adapter, &vf_cfg->privileges, + vf + 1); + if (!status && !(vf_cfg->privileges & BE_PRIV_FILTMGMT)) { status = be_cmd_set_fn_privileges(adapter, - privileges | + vf_cfg->privileges | BE_PRIV_FILTMGMT, vf + 1); - if (!status) + if (!status) { + vf_cfg->privileges |= BE_PRIV_FILTMGMT; dev_info(dev, "VF%d has FILTMGMT privilege\n", vf); + } } /* Allow full available bandwidth */ @@ -5154,6 +5221,7 @@ static int be_roce_map_pci_bars(struct be_adapter *adapter) static int be_map_pci_bars(struct be_adapter *adapter) { + struct pci_dev *pdev = adapter->pdev; u8 __iomem *addr; u32 sli_intf; @@ -5163,21 +5231,33 @@ static int be_map_pci_bars(struct be_adapter *adapter) adapter->virtfn = (sli_intf & SLI_INTF_FT_MASK) ? 1 : 0; if (BEx_chip(adapter) && be_physfn(adapter)) { - adapter->csr = pci_iomap(adapter->pdev, 2, 0); + adapter->csr = pci_iomap(pdev, 2, 0); if (!adapter->csr) return -ENOMEM; } - addr = pci_iomap(adapter->pdev, db_bar(adapter), 0); + addr = pci_iomap(pdev, db_bar(adapter), 0); if (!addr) goto pci_map_err; adapter->db = addr; + if (skyhawk_chip(adapter) || BEx_chip(adapter)) { + if (be_physfn(adapter)) { + /* PCICFG is the 2nd BAR in BE2 */ + addr = pci_iomap(pdev, BE2_chip(adapter) ? 1 : 0, 0); + if (!addr) + goto pci_map_err; + adapter->pcicfg = addr; + } else { + adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET; + } + } + be_roce_map_pci_bars(adapter); return 0; pci_map_err: - dev_err(&adapter->pdev->dev, "Error in mapping PCI BARs\n"); + dev_err(&pdev->dev, "Error in mapping PCI BARs\n"); be_unmap_pci_bars(adapter); return -ENOMEM; } diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index f88cfaa359e7..442410cd2ca4 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1299,7 +1299,7 @@ static int ethoc_resume(struct platform_device *pdev) # define ethoc_resume NULL #endif -static struct of_device_id ethoc_match[] = { +static const struct of_device_id ethoc_match[] = { { .compatible = "opencores,ethoc", }, {}, }; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 99492b7e3713..78e1ce09b1ab 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1189,13 +1189,12 @@ static void fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) { struct fec_enet_private *fep; - struct bufdesc *bdp, *bdp_t; + struct bufdesc *bdp; unsigned short status; struct sk_buff *skb; struct fec_enet_priv_tx_q *txq; struct netdev_queue *nq; int index = 0; - int i, bdnum; int entries_free; fep = netdev_priv(ndev); @@ -1216,29 +1215,18 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) if (bdp == txq->cur_tx) break; - bdp_t = bdp; - bdnum = 1; - index = fec_enet_get_bd_index(txq->tx_bd_base, bdp_t, fep); - skb = txq->tx_skbuff[index]; - while (!skb) { - bdp_t = fec_enet_get_nextdesc(bdp_t, fep, queue_id); - index = fec_enet_get_bd_index(txq->tx_bd_base, bdp_t, fep); - skb = txq->tx_skbuff[index]; - bdnum++; - } - if (skb_shinfo(skb)->nr_frags && - (status = bdp_t->cbd_sc) & BD_ENET_TX_READY) - break; + index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep); - for (i = 0; i < bdnum; i++) { - if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr)) - dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, - bdp->cbd_datlen, DMA_TO_DEVICE); - bdp->cbd_bufaddr = 0; - if (i < bdnum - 1) - bdp = fec_enet_get_nextdesc(bdp, fep, queue_id); - } + skb = txq->tx_skbuff[index]; txq->tx_skbuff[index] = NULL; + if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr)) + dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, + bdp->cbd_datlen, DMA_TO_DEVICE); + bdp->cbd_bufaddr = 0; + if (!skb) { + bdp = fec_enet_get_nextdesc(bdp, fep, queue_id); + continue; + } /* Check for errors. */ if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC | @@ -1479,8 +1467,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) vlan_packet_rcvd = true; - skb_copy_to_linear_data_offset(skb, VLAN_HLEN, - data, (2 * ETH_ALEN)); + memmove(skb->data + VLAN_HLEN, data, ETH_ALEN * 2); skb_pull(skb, VLAN_HLEN); } diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index f495796248db..afe7f39cdd7c 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -1057,7 +1057,7 @@ static int mpc52xx_fec_of_resume(struct platform_device *op) } #endif -static struct of_device_id mpc52xx_fec_match[] = { +static const struct of_device_id mpc52xx_fec_match[] = { { .compatible = "fsl,mpc5200b-fec", }, { .compatible = "fsl,mpc5200-fec", }, { .compatible = "mpc5200-fec", }, diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c index e0528900db02..1e647beaf989 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c @@ -134,7 +134,7 @@ static int mpc52xx_fec_mdio_remove(struct platform_device *of) return 0; } -static struct of_device_id mpc52xx_fec_mdio_match[] = { +static const struct of_device_id mpc52xx_fec_mdio_match[] = { { .compatible = "fsl,mpc5200b-mdio", }, { .compatible = "fsl,mpc5200-mdio", }, { .compatible = "mpc5200b-fec-phy", }, diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 4585895ddc9a..b833993d2e19 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -390,7 +390,7 @@ static int fec_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) * read the timecounter and return the correct value on ns, * after converting it into a struct timespec. */ -static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct fec_enet_private *adapter = container_of(ptp, struct fec_enet_private, ptp_caps); @@ -417,7 +417,7 @@ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) * wall timer value. */ static int fec_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct fec_enet_private *fep = container_of(ptp, struct fec_enet_private, ptp_caps); @@ -584,8 +584,8 @@ void fec_ptp_init(struct platform_device *pdev) fep->ptp_caps.pps = 1; fep->ptp_caps.adjfreq = fec_ptp_adjfreq; fep->ptp_caps.adjtime = fec_ptp_adjtime; - fep->ptp_caps.gettime = fec_ptp_gettime; - fep->ptp_caps.settime = fec_ptp_settime; + fep->ptp_caps.gettime64 = fec_ptp_gettime; + fep->ptp_caps.settime64 = fec_ptp_settime; fep->ptp_caps.enable = fec_ptp_enable; fep->cycle_speed = clk_get_rate(fep->clk_ptp); diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index a17628769a1f..9b3639eae676 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -916,7 +916,7 @@ static const struct net_device_ops fs_enet_netdev_ops = { #endif }; -static struct of_device_id fs_enet_match[]; +static const struct of_device_id fs_enet_match[]; static int fs_enet_probe(struct platform_device *ofdev) { const struct of_device_id *match; @@ -1082,7 +1082,7 @@ static int fs_enet_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id fs_enet_match[] = { +static const struct of_device_id fs_enet_match[] = { #ifdef CONFIG_FS_ENET_HAS_SCC { .compatible = "fsl,cpm1-scc-enet", diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c index 1d5617d2d8bd..68a428de0bc0 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c +++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c @@ -213,7 +213,7 @@ static int fs_enet_mdio_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id fs_enet_mdio_bb_match[] = { +static const struct of_device_id fs_enet_mdio_bb_match[] = { { .compatible = "fsl,cpm2-mdio-bitbang", }, diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c index 1648e3582500..2be383e6d258 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c @@ -95,7 +95,7 @@ static int fs_enet_fec_mii_write(struct mii_bus *bus, int phy_id, int location, } -static struct of_device_id fs_enet_mdio_fec_match[]; +static const struct of_device_id fs_enet_mdio_fec_match[]; static int fs_enet_mdio_probe(struct platform_device *ofdev) { const struct of_device_id *match; @@ -208,7 +208,7 @@ static int fs_enet_mdio_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id fs_enet_mdio_fec_match[] = { +static const struct of_device_id fs_enet_mdio_fec_match[] = { { .compatible = "fsl,pq1-fec-mdio", }, diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index d1a91e344e6b..3c40f6b99224 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -294,7 +294,7 @@ static void ucc_configure(phys_addr_t start, phys_addr_t end) #endif -static struct of_device_id fsl_pq_mdio_match[] = { +static const struct of_device_id fsl_pq_mdio_match[] = { #if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE) { .compatible = "fsl,gianfar-tbi", diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 7bf3682cdf47..4ee080d49bc0 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -158,7 +158,7 @@ static void gfar_init_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp, { u32 lstatus; - bdp->bufPtr = buf; + bdp->bufPtr = cpu_to_be32(buf); lstatus = BD_LFLAG(RXBD_EMPTY | RXBD_INTERRUPT); if (bdp == rx_queue->rx_bd_base + rx_queue->rx_ring_size - 1) @@ -166,7 +166,7 @@ static void gfar_init_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp, gfar_wmb(); - bdp->lstatus = lstatus; + bdp->lstatus = cpu_to_be32(lstatus); } static int gfar_init_bds(struct net_device *ndev) @@ -200,7 +200,8 @@ static int gfar_init_bds(struct net_device *ndev) /* Set the last descriptor in the ring to indicate wrap */ txbdp--; - txbdp->status |= TXBD_WRAP; + txbdp->status = cpu_to_be16(be16_to_cpu(txbdp->status) | + TXBD_WRAP); } rfbptr = ®s->rfbptr0; @@ -214,7 +215,7 @@ static int gfar_init_bds(struct net_device *ndev) struct sk_buff *skb = rx_queue->rx_skbuff[j]; if (skb) { - bufaddr = rxbdp->bufPtr; + bufaddr = be32_to_cpu(rxbdp->bufPtr); } else { skb = gfar_new_skb(ndev, &bufaddr); if (!skb) { @@ -696,19 +697,28 @@ static int gfar_parse_group(struct device_node *np, grp->priv = priv; spin_lock_init(&grp->grplock); if (priv->mode == MQ_MG_MODE) { - u32 *rxq_mask, *txq_mask; - rxq_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL); - txq_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL); + u32 rxq_mask, txq_mask; + int ret; + + grp->rx_bit_map = (DEFAULT_MAPPING >> priv->num_grps); + grp->tx_bit_map = (DEFAULT_MAPPING >> priv->num_grps); + + ret = of_property_read_u32(np, "fsl,rx-bit-map", &rxq_mask); + if (!ret) { + grp->rx_bit_map = rxq_mask ? + rxq_mask : (DEFAULT_MAPPING >> priv->num_grps); + } + + ret = of_property_read_u32(np, "fsl,tx-bit-map", &txq_mask); + if (!ret) { + grp->tx_bit_map = txq_mask ? + txq_mask : (DEFAULT_MAPPING >> priv->num_grps); + } if (priv->poll_mode == GFAR_SQ_POLLING) { /* One Q per interrupt group: Q0 to G0, Q1 to G1 */ grp->rx_bit_map = (DEFAULT_MAPPING >> priv->num_grps); grp->tx_bit_map = (DEFAULT_MAPPING >> priv->num_grps); - } else { /* GFAR_MQ_POLLING */ - grp->rx_bit_map = rxq_mask ? - *rxq_mask : (DEFAULT_MAPPING >> priv->num_grps); - grp->tx_bit_map = txq_mask ? - *txq_mask : (DEFAULT_MAPPING >> priv->num_grps); } } else { grp->rx_bit_map = 0xFF; @@ -769,11 +779,10 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) struct gfar_private *priv = NULL; struct device_node *np = ofdev->dev.of_node; struct device_node *child = NULL; - const u32 *stash; - const u32 *stash_len; - const u32 *stash_idx; + struct property *stash; + u32 stash_len = 0; + u32 stash_idx = 0; unsigned int num_tx_qs, num_rx_qs; - u32 *tx_queues, *rx_queues; unsigned short mode, poll_mode; if (!np) @@ -787,10 +796,6 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) poll_mode = GFAR_SQ_POLLING; } - /* parse the num of HW tx and rx queues */ - tx_queues = (u32 *)of_get_property(np, "fsl,num_tx_queues", NULL); - rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL); - if (mode == SQ_SG_MODE) { num_tx_qs = 1; num_rx_qs = 1; @@ -809,8 +814,17 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) num_tx_qs = num_grps; /* one txq per int group */ num_rx_qs = num_grps; /* one rxq per int group */ } else { /* GFAR_MQ_POLLING */ - num_tx_qs = tx_queues ? *tx_queues : 1; - num_rx_qs = rx_queues ? *rx_queues : 1; + u32 tx_queues, rx_queues; + int ret; + + /* parse the num of HW tx and rx queues */ + ret = of_property_read_u32(np, "fsl,num_tx_queues", + &tx_queues); + num_tx_qs = ret ? 1 : tx_queues; + + ret = of_property_read_u32(np, "fsl,num_rx_queues", + &rx_queues); + num_rx_qs = ret ? 1 : rx_queues; } } @@ -851,13 +865,17 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) if (err) goto rx_alloc_failed; + err = of_property_read_string(np, "model", &model); + if (err) { + pr_err("Device model property missing, aborting\n"); + goto rx_alloc_failed; + } + /* Init Rx queue filer rule set linked list */ INIT_LIST_HEAD(&priv->rx_list.list); priv->rx_list.count = 0; mutex_init(&priv->rx_queue_access); - model = of_get_property(np, "model", NULL); - for (i = 0; i < MAXGROUPS; i++) priv->gfargrp[i].regs = NULL; @@ -877,22 +895,22 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) goto err_grp_init; } - stash = of_get_property(np, "bd-stash", NULL); + stash = of_find_property(np, "bd-stash", NULL); if (stash) { priv->device_flags |= FSL_GIANFAR_DEV_HAS_BD_STASHING; priv->bd_stash_en = 1; } - stash_len = of_get_property(np, "rx-stash-len", NULL); + err = of_property_read_u32(np, "rx-stash-len", &stash_len); - if (stash_len) - priv->rx_stash_size = *stash_len; + if (err == 0) + priv->rx_stash_size = stash_len; - stash_idx = of_get_property(np, "rx-stash-idx", NULL); + err = of_property_read_u32(np, "rx-stash-idx", &stash_idx); - if (stash_idx) - priv->rx_stash_index = *stash_idx; + if (err == 0) + priv->rx_stash_index = stash_idx; if (stash_len || stash_idx) priv->device_flags |= FSL_GIANFAR_DEV_HAS_BUF_STASHING; @@ -919,15 +937,15 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) FSL_GIANFAR_DEV_HAS_EXTENDED_HASH | FSL_GIANFAR_DEV_HAS_TIMER; - ctype = of_get_property(np, "phy-connection-type", NULL); + err = of_property_read_string(np, "phy-connection-type", &ctype); /* We only care about rgmii-id. The rest are autodetected */ - if (ctype && !strcmp(ctype, "rgmii-id")) + if (err == 0 && !strcmp(ctype, "rgmii-id")) priv->interface = PHY_INTERFACE_MODE_RGMII_ID; else priv->interface = PHY_INTERFACE_MODE_MII; - if (of_get_property(np, "fsl,magic-packet", NULL)) + if (of_find_property(np, "fsl,magic-packet", NULL)) priv->device_flags |= FSL_GIANFAR_DEV_HAS_MAGIC_PACKET; priv->phy_node = of_parse_phandle(np, "phy-handle", 0); @@ -1884,14 +1902,15 @@ static void free_skb_tx_queue(struct gfar_priv_tx_q *tx_queue) if (!tx_queue->tx_skbuff[i]) continue; - dma_unmap_single(priv->dev, txbdp->bufPtr, - txbdp->length, DMA_TO_DEVICE); + dma_unmap_single(priv->dev, be32_to_cpu(txbdp->bufPtr), + be16_to_cpu(txbdp->length), DMA_TO_DEVICE); txbdp->lstatus = 0; for (j = 0; j < skb_shinfo(tx_queue->tx_skbuff[i])->nr_frags; j++) { txbdp++; - dma_unmap_page(priv->dev, txbdp->bufPtr, - txbdp->length, DMA_TO_DEVICE); + dma_unmap_page(priv->dev, be32_to_cpu(txbdp->bufPtr), + be16_to_cpu(txbdp->length), + DMA_TO_DEVICE); } txbdp++; dev_kfree_skb_any(tx_queue->tx_skbuff[i]); @@ -1911,7 +1930,7 @@ static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue) for (i = 0; i < rx_queue->rx_ring_size; i++) { if (rx_queue->rx_skbuff[i]) { - dma_unmap_single(priv->dev, rxbdp->bufPtr, + dma_unmap_single(priv->dev, be32_to_cpu(rxbdp->bufPtr), priv->rx_buffer_size, DMA_FROM_DEVICE); dev_kfree_skb_any(rx_queue->rx_skbuff[i]); @@ -2167,16 +2186,16 @@ static inline void gfar_tx_checksum(struct sk_buff *skb, struct txfcb *fcb, */ if (ip_hdr(skb)->protocol == IPPROTO_UDP) { flags |= TXFCB_UDP; - fcb->phcs = udp_hdr(skb)->check; + fcb->phcs = (__force __be16)(udp_hdr(skb)->check); } else - fcb->phcs = tcp_hdr(skb)->check; + fcb->phcs = (__force __be16)(tcp_hdr(skb)->check); /* l3os is the distance between the start of the * frame (skb->data) and the start of the IP hdr. * l4os is the distance between the start of the * l3 hdr and the l4 hdr */ - fcb->l3os = (u16)(skb_network_offset(skb) - fcb_length); + fcb->l3os = (u8)(skb_network_offset(skb) - fcb_length); fcb->l4os = skb_network_header_len(skb); fcb->flags = flags; @@ -2185,7 +2204,7 @@ static inline void gfar_tx_checksum(struct sk_buff *skb, struct txfcb *fcb, void inline gfar_tx_vlan(struct sk_buff *skb, struct txfcb *fcb) { fcb->flags |= TXFCB_VLN; - fcb->vlctl = skb_vlan_tag_get(skb); + fcb->vlctl = cpu_to_be16(skb_vlan_tag_get(skb)); } static inline struct txbd8 *skip_txbd(struct txbd8 *bdp, int stride, @@ -2298,7 +2317,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_queue->stats.tx_packets++; txbdp = txbdp_start = tx_queue->cur_tx; - lstatus = txbdp->lstatus; + lstatus = be32_to_cpu(txbdp->lstatus); /* Time stamp insertion requires one additional TxBD */ if (unlikely(do_tstamp)) @@ -2306,11 +2325,14 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_queue->tx_ring_size); if (nr_frags == 0) { - if (unlikely(do_tstamp)) - txbdp_tstamp->lstatus |= BD_LFLAG(TXBD_LAST | - TXBD_INTERRUPT); - else + if (unlikely(do_tstamp)) { + u32 lstatus_ts = be32_to_cpu(txbdp_tstamp->lstatus); + + lstatus_ts |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT); + txbdp_tstamp->lstatus = cpu_to_be32(lstatus_ts); + } else { lstatus |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT); + } } else { /* Place the fragment addresses and lengths into the TxBDs */ for (i = 0; i < nr_frags; i++) { @@ -2320,7 +2342,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) frag_len = skb_shinfo(skb)->frags[i].size; - lstatus = txbdp->lstatus | frag_len | + lstatus = be32_to_cpu(txbdp->lstatus) | frag_len | BD_LFLAG(TXBD_READY); /* Handle the last BD specially */ @@ -2336,11 +2358,11 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) goto dma_map_err; /* set the TxBD length and buffer pointer */ - txbdp->bufPtr = bufaddr; - txbdp->lstatus = lstatus; + txbdp->bufPtr = cpu_to_be32(bufaddr); + txbdp->lstatus = cpu_to_be32(lstatus); } - lstatus = txbdp_start->lstatus; + lstatus = be32_to_cpu(txbdp_start->lstatus); } /* Add TxPAL between FCB and frame if required */ @@ -2388,7 +2410,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(dma_mapping_error(priv->dev, bufaddr))) goto dma_map_err; - txbdp_start->bufPtr = bufaddr; + txbdp_start->bufPtr = cpu_to_be32(bufaddr); /* If time stamping is requested one additional TxBD must be set up. The * first TxBD points to the FCB and must have a data length of @@ -2396,9 +2418,15 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) * the full frame length. */ if (unlikely(do_tstamp)) { - txbdp_tstamp->bufPtr = txbdp_start->bufPtr + fcb_len; - txbdp_tstamp->lstatus |= BD_LFLAG(TXBD_READY) | - (skb_headlen(skb) - fcb_len); + u32 lstatus_ts = be32_to_cpu(txbdp_tstamp->lstatus); + + bufaddr = be32_to_cpu(txbdp_start->bufPtr); + bufaddr += fcb_len; + lstatus_ts |= BD_LFLAG(TXBD_READY) | + (skb_headlen(skb) - fcb_len); + + txbdp_tstamp->bufPtr = cpu_to_be32(bufaddr); + txbdp_tstamp->lstatus = cpu_to_be32(lstatus_ts); lstatus |= BD_LFLAG(TXBD_CRC | TXBD_READY) | GMAC_FCB_LEN; } else { lstatus |= BD_LFLAG(TXBD_CRC | TXBD_READY) | skb_headlen(skb); @@ -2421,7 +2449,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) gfar_wmb(); - txbdp_start->lstatus = lstatus; + txbdp_start->lstatus = cpu_to_be32(lstatus); gfar_wmb(); /* force lstatus write before tx_skbuff */ @@ -2460,13 +2488,14 @@ dma_map_err: if (do_tstamp) txbdp = next_txbd(txbdp, base, tx_queue->tx_ring_size); for (i = 0; i < nr_frags; i++) { - lstatus = txbdp->lstatus; + lstatus = be32_to_cpu(txbdp->lstatus); if (!(lstatus & BD_LFLAG(TXBD_READY))) break; - txbdp->lstatus = lstatus & ~BD_LFLAG(TXBD_READY); - bufaddr = txbdp->bufPtr; - dma_unmap_page(priv->dev, bufaddr, txbdp->length, + lstatus &= ~BD_LFLAG(TXBD_READY); + txbdp->lstatus = cpu_to_be32(lstatus); + bufaddr = be32_to_cpu(txbdp->bufPtr); + dma_unmap_page(priv->dev, bufaddr, be16_to_cpu(txbdp->length), DMA_TO_DEVICE); txbdp = next_txbd(txbdp, base, tx_queue->tx_ring_size); } @@ -2607,7 +2636,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) lbdp = skip_txbd(bdp, nr_txbds - 1, base, tx_ring_size); - lstatus = lbdp->lstatus; + lstatus = be32_to_cpu(lbdp->lstatus); /* Only clean completed frames */ if ((lstatus & BD_LFLAG(TXBD_READY)) && @@ -2616,11 +2645,12 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { next = next_txbd(bdp, base, tx_ring_size); - buflen = next->length + GMAC_FCB_LEN + GMAC_TXPAL_LEN; + buflen = be16_to_cpu(next->length) + + GMAC_FCB_LEN + GMAC_TXPAL_LEN; } else - buflen = bdp->length; + buflen = be16_to_cpu(bdp->length); - dma_unmap_single(priv->dev, bdp->bufPtr, + dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr), buflen, DMA_TO_DEVICE); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { @@ -2631,17 +2661,18 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) shhwtstamps.hwtstamp = ns_to_ktime(*ns); skb_pull(skb, GMAC_FCB_LEN + GMAC_TXPAL_LEN); skb_tstamp_tx(skb, &shhwtstamps); - bdp->lstatus &= BD_LFLAG(TXBD_WRAP); + gfar_clear_txbd_status(bdp); bdp = next; } - bdp->lstatus &= BD_LFLAG(TXBD_WRAP); + gfar_clear_txbd_status(bdp); bdp = next_txbd(bdp, base, tx_ring_size); for (i = 0; i < frags; i++) { - dma_unmap_page(priv->dev, bdp->bufPtr, - bdp->length, DMA_TO_DEVICE); - bdp->lstatus &= BD_LFLAG(TXBD_WRAP); + dma_unmap_page(priv->dev, be32_to_cpu(bdp->bufPtr), + be16_to_cpu(bdp->length), + DMA_TO_DEVICE); + gfar_clear_txbd_status(bdp); bdp = next_txbd(bdp, base, tx_ring_size); } @@ -2798,13 +2829,13 @@ static inline void gfar_rx_checksum(struct sk_buff *skb, struct rxfcb *fcb) * were verified, then we tell the kernel that no * checksumming is necessary. Otherwise, it is [FIXME] */ - if ((fcb->flags & RXFCB_CSUM_MASK) == (RXFCB_CIP | RXFCB_CTU)) + if ((be16_to_cpu(fcb->flags) & RXFCB_CSUM_MASK) == + (RXFCB_CIP | RXFCB_CTU)) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb_checksum_none_assert(skb); } - /* gfar_process_frame() -- handle one incoming packet if skb isn't NULL. */ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, int amount_pull, struct napi_struct *napi) @@ -2846,8 +2877,9 @@ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, * RXFCB_VLN is pseudo randomly set. */ if (dev->features & NETIF_F_HW_VLAN_CTAG_RX && - fcb->flags & RXFCB_VLN) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), fcb->vlctl); + be16_to_cpu(fcb->flags) & RXFCB_VLN) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + be16_to_cpu(fcb->vlctl)); /* Send the packet up the stack */ napi_gro_receive(napi, skb); @@ -2874,7 +2906,7 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) amount_pull = priv->uses_rxfcb ? GMAC_FCB_LEN : 0; - while (!((bdp->status & RXBD_EMPTY) || (--rx_work_limit < 0))) { + while (!(be16_to_cpu(bdp->status) & RXBD_EMPTY) && rx_work_limit--) { struct sk_buff *newskb; dma_addr_t bufaddr; @@ -2885,21 +2917,22 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) skb = rx_queue->rx_skbuff[rx_queue->skb_currx]; - dma_unmap_single(priv->dev, bdp->bufPtr, + dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr), priv->rx_buffer_size, DMA_FROM_DEVICE); - if (unlikely(!(bdp->status & RXBD_ERR) && - bdp->length > priv->rx_buffer_size)) - bdp->status = RXBD_LARGE; + if (unlikely(!(be16_to_cpu(bdp->status) & RXBD_ERR) && + be16_to_cpu(bdp->length) > priv->rx_buffer_size)) + bdp->status = cpu_to_be16(RXBD_LARGE); /* We drop the frame if we failed to allocate a new buffer */ - if (unlikely(!newskb || !(bdp->status & RXBD_LAST) || - bdp->status & RXBD_ERR)) { - count_errors(bdp->status, dev); + if (unlikely(!newskb || + !(be16_to_cpu(bdp->status) & RXBD_LAST) || + be16_to_cpu(bdp->status) & RXBD_ERR)) { + count_errors(be16_to_cpu(bdp->status), dev); if (unlikely(!newskb)) { newskb = skb; - bufaddr = bdp->bufPtr; + bufaddr = be32_to_cpu(bdp->bufPtr); } else if (skb) dev_kfree_skb(skb); } else { @@ -2908,7 +2941,8 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) howmany++; if (likely(skb)) { - pkt_len = bdp->length - ETH_FCS_LEN; + pkt_len = be16_to_cpu(bdp->length) - + ETH_FCS_LEN; /* Remove the FCS from the packet length */ skb_put(skb, pkt_len); rx_queue->stats.rx_bytes += pkt_len; @@ -3560,7 +3594,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv) phy_print_status(phydev); } -static struct of_device_id gfar_match[] = +static const struct of_device_id gfar_match[] = { { .type = "network", diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 9e1802400c23..daa1d37de642 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -544,12 +544,12 @@ struct txbd8 { union { struct { - u16 status; /* Status Fields */ - u16 length; /* Buffer length */ + __be16 status; /* Status Fields */ + __be16 length; /* Buffer length */ }; - u32 lstatus; + __be32 lstatus; }; - u32 bufPtr; /* Buffer Pointer */ + __be32 bufPtr; /* Buffer Pointer */ }; struct txfcb { @@ -557,28 +557,28 @@ struct txfcb { u8 ptp; /* Flag to enable tx timestamping */ u8 l4os; /* Level 4 Header Offset */ u8 l3os; /* Level 3 Header Offset */ - u16 phcs; /* Pseudo-header Checksum */ - u16 vlctl; /* VLAN control word */ + __be16 phcs; /* Pseudo-header Checksum */ + __be16 vlctl; /* VLAN control word */ }; struct rxbd8 { union { struct { - u16 status; /* Status Fields */ - u16 length; /* Buffer Length */ + __be16 status; /* Status Fields */ + __be16 length; /* Buffer Length */ }; - u32 lstatus; + __be32 lstatus; }; - u32 bufPtr; /* Buffer Pointer */ + __be32 bufPtr; /* Buffer Pointer */ }; struct rxfcb { - u16 flags; + __be16 flags; u8 rq; /* Receive Queue index */ u8 pro; /* Layer 4 Protocol */ u16 reserved; - u16 vlctl; /* VLAN control word */ + __be16 vlctl; /* VLAN control word */ }; struct gianfar_skb_cb { @@ -1287,6 +1287,14 @@ static inline void gfar_wmb(void) #endif } +static inline void gfar_clear_txbd_status(struct txbd8 *bdp) +{ + u32 lstatus = be32_to_cpu(bdp->lstatus); + + lstatus &= BD_LFLAG(TXBD_WRAP); + bdp->lstatus = cpu_to_be32(lstatus); +} + irqreturn_t gfar_receive(int irq, void *dev_id); int startup_gfar(struct net_device *dev); void stop_gfar(struct net_device *dev); diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c index 16826341a4c9..04265a7275e5 100644 --- a/drivers/net/ethernet/freescale/gianfar_ptp.c +++ b/drivers/net/ethernet/freescale/gianfar_ptp.c @@ -322,7 +322,8 @@ static int ptp_gianfar_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int ptp_gianfar_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int ptp_gianfar_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) { u64 ns; u32 remainder; @@ -341,7 +342,7 @@ static int ptp_gianfar_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int ptp_gianfar_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { u64 ns; unsigned long flags; @@ -418,8 +419,8 @@ static struct ptp_clock_info ptp_gianfar_caps = { .pps = 1, .adjfreq = ptp_gianfar_adjfreq, .adjtime = ptp_gianfar_adjtime, - .gettime = ptp_gianfar_gettime, - .settime = ptp_gianfar_settime, + .gettime64 = ptp_gianfar_gettime, + .settime64 = ptp_gianfar_settime, .enable = ptp_gianfar_enable, }; @@ -440,7 +441,7 @@ static int gianfar_ptp_probe(struct platform_device *dev) { struct device_node *node = dev->dev.of_node; struct etsects *etsects; - struct timespec now; + struct timespec64 now; int err = -ENOMEM; u32 tmr_ctrl; unsigned long flags; @@ -495,7 +496,7 @@ static int gianfar_ptp_probe(struct platform_device *dev) pr_err("ioremap ptp registers failed\n"); goto no_ioremap; } - getnstimeofday(&now); + getnstimeofday64(&now); ptp_gianfar_settime(&etsects->caps, &now); tmr_ctrl = @@ -554,7 +555,7 @@ static int gianfar_ptp_remove(struct platform_device *dev) return 0; } -static struct of_device_id match_table[] = { +static const struct of_device_id match_table[] = { { .compatible = "fsl,etsec-ptp" }, {}, }; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 357e8b576905..bfdccbd58be0 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3930,7 +3930,7 @@ static int ucc_geth_remove(struct platform_device* ofdev) return 0; } -static struct of_device_id ucc_geth_match[] = { +static const struct of_device_id ucc_geth_match[] = { { .type = "network", .compatible = "ucc_geth", diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index 3a83bc2c613c..7b8fe866f603 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -46,17 +46,43 @@ struct tgec_mdio_controller { #define MDIO_DATA(x) (x & 0xffff) #define MDIO_DATA_BSY BIT(31) +struct mdio_fsl_priv { + struct tgec_mdio_controller __iomem *mdio_base; + bool is_little_endian; +}; + +static u32 xgmac_read32(void __iomem *regs, + bool is_little_endian) +{ + if (is_little_endian) + return ioread32(regs); + else + return ioread32be(regs); +} + +static void xgmac_write32(u32 value, + void __iomem *regs, + bool is_little_endian) +{ + if (is_little_endian) + iowrite32(value, regs); + else + iowrite32be(value, regs); +} + /* * Wait until the MDIO bus is free */ static int xgmac_wait_until_free(struct device *dev, - struct tgec_mdio_controller __iomem *regs) + struct tgec_mdio_controller __iomem *regs, + bool is_little_endian) { unsigned int timeout; /* Wait till the bus is free */ timeout = TIMEOUT; - while ((ioread32be(®s->mdio_stat) & MDIO_STAT_BSY) && timeout) { + while ((xgmac_read32(®s->mdio_stat, is_little_endian) & + MDIO_STAT_BSY) && timeout) { cpu_relax(); timeout--; } @@ -73,13 +99,15 @@ static int xgmac_wait_until_free(struct device *dev, * Wait till the MDIO read or write operation is complete */ static int xgmac_wait_until_done(struct device *dev, - struct tgec_mdio_controller __iomem *regs) + struct tgec_mdio_controller __iomem *regs, + bool is_little_endian) { unsigned int timeout; /* Wait till the MDIO write is complete */ timeout = TIMEOUT; - while ((ioread32be(®s->mdio_data) & MDIO_DATA_BSY) && timeout) { + while ((xgmac_read32(®s->mdio_stat, is_little_endian) & + MDIO_STAT_BSY) && timeout) { cpu_relax(); timeout--; } @@ -99,12 +127,14 @@ static int xgmac_wait_until_done(struct device *dev, */ static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) { - struct tgec_mdio_controller __iomem *regs = bus->priv; + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; uint16_t dev_addr; u32 mdio_ctl, mdio_stat; int ret; + bool endian = priv->is_little_endian; - mdio_stat = ioread32be(®s->mdio_stat); + mdio_stat = xgmac_read32(®s->mdio_stat, endian); if (regnum & MII_ADDR_C45) { /* Clause 45 (ie 10G) */ dev_addr = (regnum >> 16) & 0x1f; @@ -115,29 +145,29 @@ static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 val mdio_stat &= ~MDIO_STAT_ENC; } - iowrite32be(mdio_stat, ®s->mdio_stat); + xgmac_write32(mdio_stat, ®s->mdio_stat, endian); - ret = xgmac_wait_until_free(&bus->dev, regs); + ret = xgmac_wait_until_free(&bus->dev, regs, endian); if (ret) return ret; /* Set the port and dev addr */ mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); - iowrite32be(mdio_ctl, ®s->mdio_ctl); + xgmac_write32(mdio_ctl, ®s->mdio_ctl, endian); /* Set the register address */ if (regnum & MII_ADDR_C45) { - iowrite32be(regnum & 0xffff, ®s->mdio_addr); + xgmac_write32(regnum & 0xffff, ®s->mdio_addr, endian); - ret = xgmac_wait_until_free(&bus->dev, regs); + ret = xgmac_wait_until_free(&bus->dev, regs, endian); if (ret) return ret; } /* Write the value to the register */ - iowrite32be(MDIO_DATA(value), ®s->mdio_data); + xgmac_write32(MDIO_DATA(value), ®s->mdio_data, endian); - ret = xgmac_wait_until_done(&bus->dev, regs); + ret = xgmac_wait_until_done(&bus->dev, regs, endian); if (ret) return ret; @@ -151,14 +181,16 @@ static int xgmac_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 val */ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) { - struct tgec_mdio_controller __iomem *regs = bus->priv; + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; uint16_t dev_addr; uint32_t mdio_stat; uint32_t mdio_ctl; uint16_t value; int ret; + bool endian = priv->is_little_endian; - mdio_stat = ioread32be(®s->mdio_stat); + mdio_stat = xgmac_read32(®s->mdio_stat, endian); if (regnum & MII_ADDR_C45) { dev_addr = (regnum >> 16) & 0x1f; mdio_stat |= MDIO_STAT_ENC; @@ -167,41 +199,41 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) mdio_stat &= ~MDIO_STAT_ENC; } - iowrite32be(mdio_stat, ®s->mdio_stat); + xgmac_write32(mdio_stat, ®s->mdio_stat, endian); - ret = xgmac_wait_until_free(&bus->dev, regs); + ret = xgmac_wait_until_free(&bus->dev, regs, endian); if (ret) return ret; /* Set the Port and Device Addrs */ mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); - iowrite32be(mdio_ctl, ®s->mdio_ctl); + xgmac_write32(mdio_ctl, ®s->mdio_ctl, endian); /* Set the register address */ if (regnum & MII_ADDR_C45) { - iowrite32be(regnum & 0xffff, ®s->mdio_addr); + xgmac_write32(regnum & 0xffff, ®s->mdio_addr, endian); - ret = xgmac_wait_until_free(&bus->dev, regs); + ret = xgmac_wait_until_free(&bus->dev, regs, endian); if (ret) return ret; } /* Initiate the read */ - iowrite32be(mdio_ctl | MDIO_CTL_READ, ®s->mdio_ctl); + xgmac_write32(mdio_ctl | MDIO_CTL_READ, ®s->mdio_ctl, endian); - ret = xgmac_wait_until_done(&bus->dev, regs); + ret = xgmac_wait_until_done(&bus->dev, regs, endian); if (ret) return ret; /* Return all Fs if nothing was there */ - if (ioread32be(®s->mdio_stat) & MDIO_STAT_RD_ER) { + if (xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) { dev_err(&bus->dev, "Error while reading PHY%d reg at %d.%hhu\n", phy_id, dev_addr, regnum); return 0xffff; } - value = ioread32be(®s->mdio_data) & 0xffff; + value = xgmac_read32(®s->mdio_data, endian) & 0xffff; dev_dbg(&bus->dev, "read %04x\n", value); return value; @@ -212,6 +244,7 @@ static int xgmac_mdio_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct mii_bus *bus; struct resource res; + struct mdio_fsl_priv *priv; int ret; ret = of_address_to_resource(np, 0, &res); @@ -220,7 +253,7 @@ static int xgmac_mdio_probe(struct platform_device *pdev) return ret; } - bus = mdiobus_alloc(); + bus = mdiobus_alloc_size(sizeof(struct mdio_fsl_priv)); if (!bus) return -ENOMEM; @@ -231,12 +264,19 @@ static int xgmac_mdio_probe(struct platform_device *pdev) snprintf(bus->id, MII_BUS_ID_SIZE, "%llx", (unsigned long long)res.start); /* Set the PHY base address */ - bus->priv = of_iomap(np, 0); - if (!bus->priv) { + priv = bus->priv; + priv->mdio_base = of_iomap(np, 0); + if (!priv->mdio_base) { ret = -ENOMEM; goto err_ioremap; } + if (of_get_property(pdev->dev.of_node, + "little-endian", NULL)) + priv->is_little_endian = true; + else + priv->is_little_endian = false; + ret = of_mdiobus_register(bus, np); if (ret) { dev_err(&pdev->dev, "cannot register MDIO bus\n"); @@ -248,7 +288,7 @@ static int xgmac_mdio_probe(struct platform_device *pdev) return 0; err_registration: - iounmap(bus->priv); + iounmap(priv->mdio_base); err_ioremap: mdiobus_free(bus); @@ -267,7 +307,7 @@ static int xgmac_mdio_remove(struct platform_device *pdev) return 0; } -static struct of_device_id xgmac_mdio_match[] = { +static const struct of_device_id xgmac_mdio_match[] = { { .compatible = "fsl,fman-xmdio", }, diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index c05e50759621..291c87036e17 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -103,7 +103,7 @@ static int ehea_probe_adapter(struct platform_device *dev); static int ehea_remove(struct platform_device *dev); -static struct of_device_id ehea_module_device_table[] = { +static const struct of_device_id ehea_module_device_table[] = { { .name = "lhea", .compatible = "IBM,lhea", @@ -116,7 +116,7 @@ static struct of_device_id ehea_module_device_table[] = { }; MODULE_DEVICE_TABLE(of, ehea_module_device_table); -static struct of_device_id ehea_device_table[] = { +static const struct of_device_id ehea_device_table[] = { { .name = "lhea", .compatible = "IBM,lhea", diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 162762d1a12c..8a17b97baa20 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2981,7 +2981,7 @@ static int emac_remove(struct platform_device *ofdev) } /* XXX Features in here should be replaced by properties... */ -static struct of_device_id emac_match[] = +static const struct of_device_id emac_match[] = { { .type = "network", diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c index dddaab11a4c7..fdb5cdb3cd15 100644 --- a/drivers/net/ethernet/ibm/emac/mal.c +++ b/drivers/net/ethernet/ibm/emac/mal.c @@ -753,7 +753,7 @@ static int mal_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id mal_platform_match[] = +static const struct of_device_id mal_platform_match[] = { { .compatible = "ibm,mcmal", diff --git a/drivers/net/ethernet/ibm/emac/rgmii.c b/drivers/net/ethernet/ibm/emac/rgmii.c index 457088fc5b06..206ccbbae7bb 100644 --- a/drivers/net/ethernet/ibm/emac/rgmii.c +++ b/drivers/net/ethernet/ibm/emac/rgmii.c @@ -305,7 +305,7 @@ static int rgmii_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id rgmii_match[] = +static const struct of_device_id rgmii_match[] = { { .compatible = "ibm,rgmii", diff --git a/drivers/net/ethernet/ibm/emac/tah.c b/drivers/net/ethernet/ibm/emac/tah.c index cb18e7f917c6..32cb6c9007c5 100644 --- a/drivers/net/ethernet/ibm/emac/tah.c +++ b/drivers/net/ethernet/ibm/emac/tah.c @@ -148,7 +148,7 @@ static int tah_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id tah_match[] = +static const struct of_device_id tah_match[] = { { .compatible = "ibm,tah", diff --git a/drivers/net/ethernet/ibm/emac/zmii.c b/drivers/net/ethernet/ibm/emac/zmii.c index 36409ccb75ea..8727b865ea02 100644 --- a/drivers/net/ethernet/ibm/emac/zmii.c +++ b/drivers/net/ethernet/ibm/emac/zmii.c @@ -295,7 +295,7 @@ static int zmii_remove(struct platform_device *ofdev) return 0; } -static struct of_device_id zmii_match[] = +static const struct of_device_id zmii_match[] = { { .compatible = "ibm,zmii", diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 072426a72745..cd7675ac5bf9 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1136,6 +1136,8 @@ restart_poll: ibmveth_replenish_task(adapter); if (frames_processed < budget) { + napi_complete(napi); + /* We think we are done - reenable interrupts, * then check once more to make sure we are done. */ @@ -1144,8 +1146,6 @@ restart_poll: BUG_ON(lpar_rc != H_SUCCESS); - napi_complete(napi); - if (ibmveth_rxq_pending_buffer(adapter) && napi_reschedule(napi)) { lpar_rc = h_vio_signal(adapter->vdev->unit_address, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 4be4576d71aa..4e56c3195989 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4084,6 +4084,8 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset) */ set_bit(__E1000_DOWN, &adapter->state); + netif_carrier_off(netdev); + /* disable receives in the hardware */ rctl = er32(RCTL); if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX)) @@ -4108,8 +4110,6 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset) del_timer_sync(&adapter->watchdog_timer); del_timer_sync(&adapter->phy_info_timer); - netif_carrier_off(netdev); - spin_lock(&adapter->stats64_lock); e1000e_update_stats(adapter); spin_unlock(&adapter->stats64_lock); @@ -6874,7 +6874,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_hw_init; if ((adapter->flags & FLAG_IS_ICH) && - (adapter->flags & FLAG_READ_ONLY_NVM)) + (adapter->flags & FLAG_READ_ONLY_NVM) && + (hw->mac.type < e1000_pch_spt)) e1000e_write_protect_nvm_ich8lan(&adapter->hw); hw->mac.ops.get_bus_info(&adapter->hw); diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 1490f1e8d6aa..6fedc2c327dd 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -106,7 +106,7 @@ static int e1000e_phc_adjtime(struct ptp_clock_info *ptp, s64 delta) * Read the timecounter and return the correct value in ns after converting * it into a struct timespec. **/ -static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, ptp_clock_info); @@ -133,14 +133,14 @@ static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) * wall timer value. **/ static int e1000e_phc_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, ptp_clock_info); unsigned long flags; u64 ns; - ns = timespec_to_ns(ts); + ns = timespec64_to_ns(ts); /* reset the timecounter */ spin_lock_irqsave(&adapter->systim_lock, flags); @@ -171,11 +171,12 @@ static void e1000e_systim_overflow_work(struct work_struct *work) struct e1000_adapter *adapter = container_of(work, struct e1000_adapter, systim_overflow_work.work); struct e1000_hw *hw = &adapter->hw; - struct timespec ts; + struct timespec64 ts; - adapter->ptp_clock_info.gettime(&adapter->ptp_clock_info, &ts); + adapter->ptp_clock_info.gettime64(&adapter->ptp_clock_info, &ts); - e_dbg("SYSTIM overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); + e_dbg("SYSTIM overflow check at %lld.%09lu\n", + (long long) ts.tv_sec, ts.tv_nsec); schedule_delayed_work(&adapter->systim_overflow_work, E1000_SYSTIM_OVERFLOW_PERIOD); @@ -190,8 +191,8 @@ static const struct ptp_clock_info e1000e_ptp_clock_info = { .pps = 0, .adjfreq = e1000e_phc_adjfreq, .adjtime = e1000e_phc_adjtime, - .gettime = e1000e_phc_gettime, - .settime = e1000e_phc_settime, + .gettime64 = e1000e_phc_gettime, + .settime64 = e1000e_phc_settime, .enable = e1000e_phc_enable, }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c b/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c index d966044e017a..02008e976d18 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c @@ -285,7 +285,7 @@ static int fm10k_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int fm10k_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int fm10k_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct fm10k_intfc *interface; unsigned long flags; @@ -297,17 +297,17 @@ static int fm10k_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) now = fm10k_systime_read(interface) + interface->ptp_adjust; read_unlock_irqrestore(&interface->systime_lock, flags); - *ts = ns_to_timespec(now); + *ts = ns_to_timespec64(now); return 0; } static int fm10k_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct fm10k_intfc *interface; unsigned long flags; - u64 ns = timespec_to_ns(ts); + u64 ns = timespec64_to_ns(ts); interface = container_of(ptp, struct fm10k_intfc, ptp_caps); @@ -419,8 +419,8 @@ void fm10k_ptp_register(struct fm10k_intfc *interface) ptp_caps->max_adj = 976562; ptp_caps->adjfreq = fm10k_ptp_adjfreq; ptp_caps->adjtime = fm10k_ptp_adjtime; - ptp_caps->gettime = fm10k_ptp_gettime; - ptp_caps->settime = fm10k_ptp_settime; + ptp_caps->gettime64 = fm10k_ptp_gettime; + ptp_caps->settime64 = fm10k_ptp_settime; /* provide pins if BAR4 is accessible */ if (interface->sw_addr) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index d9f1fcb9c2be..d596f6624025 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -51,6 +51,7 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw) case I40E_DEV_ID_QSFP_B: case I40E_DEV_ID_QSFP_C: case I40E_DEV_ID_10G_BASE_T: + case I40E_DEV_ID_20G_KR2: hw->mac.type = I40E_MAC_XL710; break; case I40E_DEV_ID_VF: @@ -841,6 +842,7 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) case I40E_PHY_TYPE_10GBASE_KX4: case I40E_PHY_TYPE_10GBASE_KR: case I40E_PHY_TYPE_40GBASE_KR4: + case I40E_PHY_TYPE_20GBASE_KR2: media = I40E_MEDIA_TYPE_BACKPLANE; break; case I40E_PHY_TYPE_SGMII: @@ -857,7 +859,7 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) } #define I40E_PF_RESET_WAIT_COUNT_A0 200 -#define I40E_PF_RESET_WAIT_COUNT 110 +#define I40E_PF_RESET_WAIT_COUNT 200 /** * i40e_pf_reset - Reset the PF * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index b7d0aaac5480..c848b1862512 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -274,6 +274,12 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, case I40E_PHY_TYPE_40GBASE_LR4: ecmd->supported = SUPPORTED_40000baseLR4_Full; break; + case I40E_PHY_TYPE_20GBASE_KR2: + ecmd->supported = SUPPORTED_Autoneg | + SUPPORTED_20000baseKR2_Full; + ecmd->advertising = ADVERTISED_Autoneg | + ADVERTISED_20000baseKR2_Full; + break; case I40E_PHY_TYPE_10GBASE_KX4: ecmd->supported = SUPPORTED_Autoneg | SUPPORTED_10000baseKX4_Full; @@ -353,6 +359,9 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, /* need a SPEED_40000 in ethtool.h */ ethtool_cmd_speed_set(ecmd, 40000); break; + case I40E_LINK_SPEED_20GB: + ethtool_cmd_speed_set(ecmd, SPEED_20000); + break; case I40E_LINK_SPEED_10GB: ethtool_cmd_speed_set(ecmd, SPEED_10000); break; @@ -418,6 +427,11 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw, if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) ecmd->advertising |= ADVERTISED_100baseT_Full; break; + case I40E_DEV_ID_20G_KR2: + /* backplane 20G */ + ecmd->supported = SUPPORTED_20000baseKR2_Full; + ecmd->advertising = ADVERTISED_20000baseKR2_Full; + break; default: /* all the rest are 10G/1G */ ecmd->supported = SUPPORTED_10000baseT_Full | @@ -633,6 +647,8 @@ static int i40e_set_settings(struct net_device *netdev, advertise & ADVERTISED_10000baseKX4_Full || advertise & ADVERTISED_10000baseKR_Full) config.link_speed |= I40E_LINK_SPEED_10GB; + if (advertise & ADVERTISED_20000baseKR2_Full) + config.link_speed |= I40E_LINK_SPEED_20GB; if (advertise & ADVERTISED_40000baseKR4_Full || advertise & ADVERTISED_40000baseCR4_Full || advertise & ADVERTISED_40000baseSR4_Full || diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c1eaab532c15..845bceeda645 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,7 +39,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 2 -#define DRV_VERSION_BUILD 37 +#define DRV_VERSION_BUILD 43 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -75,6 +75,7 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_B), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0}, /* required last entry */ {0, } }; @@ -4639,6 +4640,9 @@ static void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) case I40E_LINK_SPEED_40GB: strlcpy(speed, "40 Gbps", SPEED_SIZE); break; + case I40E_LINK_SPEED_20GB: + strncpy(speed, "20 Gbps", SPEED_SIZE); + break; case I40E_LINK_SPEED_10GB: strlcpy(speed, "10 Gbps", SPEED_SIZE); break; @@ -5896,6 +5900,10 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) case i40e_aqc_opc_send_msg_to_peer: dev_info(&pf->pdev->dev, "ARQ: Msg from other pf\n"); break; + case i40e_aqc_opc_nvm_erase: + case i40e_aqc_opc_nvm_update: + i40e_debug(&pf->hw, I40E_DEBUG_NVM, "ARQ NVM operation completed\n"); + break; default: dev_info(&pf->pdev->dev, "ARQ Error: Unknown event 0x%04x received\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index fabcfa1b45b2..a92b7725dec3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -57,7 +57,7 @@ * timespec. However, since the registers are 64 bits of nanoseconds, we must * convert the result to a timespec before we can return. **/ -static void i40e_ptp_read(struct i40e_pf *pf, struct timespec *ts) +static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts) { struct i40e_hw *hw = &pf->hw; u32 hi, lo; @@ -69,7 +69,7 @@ static void i40e_ptp_read(struct i40e_pf *pf, struct timespec *ts) ns = (((u64)hi) << 32) | lo; - *ts = ns_to_timespec(ns); + *ts = ns_to_timespec64(ns); } /** @@ -81,10 +81,10 @@ static void i40e_ptp_read(struct i40e_pf *pf, struct timespec *ts) * we receive a timespec from the stack, we must convert that timespec into * nanoseconds before programming the registers. **/ -static void i40e_ptp_write(struct i40e_pf *pf, const struct timespec *ts) +static void i40e_ptp_write(struct i40e_pf *pf, const struct timespec64 *ts) { struct i40e_hw *hw = &pf->hw; - u64 ns = timespec_to_ns(ts); + u64 ns = timespec64_to_ns(ts); /* The timer will not update until the high register is written, so * write the low register first. @@ -159,14 +159,14 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); - struct timespec now, then = ns_to_timespec(delta); + struct timespec64 now, then = ns_to_timespec64(delta); unsigned long flags; spin_lock_irqsave(&pf->tmreg_lock, flags); i40e_ptp_read(pf, &now); - now = timespec_add(now, then); - i40e_ptp_write(pf, (const struct timespec *)&now); + now = timespec64_add(now, then); + i40e_ptp_write(pf, (const struct timespec64 *)&now); spin_unlock_irqrestore(&pf->tmreg_lock, flags); @@ -181,7 +181,7 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) * Read the device clock and return the correct value on ns, after converting it * into a timespec struct. **/ -static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); unsigned long flags; @@ -202,7 +202,7 @@ static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) * to ns happens in the write function. **/ static int i40e_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); unsigned long flags; @@ -613,8 +613,8 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf) pf->ptp_caps.pps = 0; pf->ptp_caps.adjfreq = i40e_ptp_adjfreq; pf->ptp_caps.adjtime = i40e_ptp_adjtime; - pf->ptp_caps.gettime = i40e_ptp_gettime; - pf->ptp_caps.settime = i40e_ptp_settime; + pf->ptp_caps.gettime64 = i40e_ptp_gettime; + pf->ptp_caps.settime64 = i40e_ptp_settime; pf->ptp_caps.enable = i40e_ptp_feature_enable; /* Attempt to register the clock before enabling the hardware. */ @@ -673,7 +673,7 @@ void i40e_ptp_init(struct i40e_pf *pf) dev_err(&pf->pdev->dev, "%s: ptp_clock_register failed\n", __func__); } else { - struct timespec ts; + struct timespec64 ts; u32 regval; dev_info(&pf->pdev->dev, "%s: added PHC on %s\n", __func__, @@ -695,7 +695,7 @@ void i40e_ptp_init(struct i40e_pf *pf) i40e_ptp_set_timestamp_mode(pf, &pf->tstamp_config); /* Set the clock value. */ - ts = ktime_to_timespec(ktime_get_real()); + ts = ktime_to_timespec64(ktime_get_real()); i40e_ptp_settime(&pf->ptp_caps, &ts); } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 83032d2c2275..67c7bc9e9c21 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -44,6 +44,7 @@ #define I40E_DEV_ID_QSFP_B 0x1584 #define I40E_DEV_ID_QSFP_C 0x1585 #define I40E_DEV_ID_10G_BASE_T 0x1586 +#define I40E_DEV_ID_20G_KR2 0x1587 #define I40E_DEV_ID_VF 0x154C #define I40E_DEV_ID_VF_HV 0x1571 diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index f07b9ff2b823..39fcb1dc4ea6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -51,6 +51,7 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw) case I40E_DEV_ID_QSFP_B: case I40E_DEV_ID_QSFP_C: case I40E_DEV_ID_10G_BASE_T: + case I40E_DEV_ID_20G_KR2: hw->mac.type = I40E_MAC_XL710; break; case I40E_DEV_ID_VF: diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index eba6e4b34f70..9c79cb6abb2b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -44,7 +44,8 @@ #define I40E_DEV_ID_QSFP_B 0x1584 #define I40E_DEV_ID_QSFP_C 0x1585 #define I40E_DEV_ID_10G_BASE_T 0x1586 -#define I40E_DEV_ID_VF 0x154C +#define I40E_DEV_ID_20G_KR2 0x1587 +#define I40E_DEV_ID_VF 0x154C #define I40E_DEV_ID_VF_HV 0x1571 #define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 981224743c73..34c8565031f6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -272,6 +272,8 @@ void i40evf_update_stats(struct i40evf_adapter *adapter); void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter); int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter); void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask); +void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter); +void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter); void i40e_napi_add_all(struct i40evf_adapter *adapter); void i40e_napi_del_all(struct i40evf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index b68b73163311..f4e77665bc54 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -209,7 +209,7 @@ static void i40evf_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->driver, i40evf_driver_name, 32); strlcpy(drvinfo->version, i40evf_driver_version, 32); - + strlcpy(drvinfo->fw_version, "N/A", 4); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); } diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 812b1200f35c..b08efafee1ae 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -28,8 +28,6 @@ #include "i40e_prototype.h" static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter); static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter); -static void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter); -static void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter); static int i40evf_close(struct net_device *netdev); char i40evf_driver_name[] = "i40evf"; @@ -973,8 +971,10 @@ void i40evf_down(struct i40evf_adapter *adapter) &adapter->crit_section)) usleep_range(500, 1000); - i40evf_irq_disable(adapter); + netif_carrier_off(netdev); + netif_tx_disable(netdev); i40evf_napi_disable_all(adapter); + i40evf_irq_disable(adapter); /* remove all MAC filters */ list_for_each_entry(f, &adapter->mac_filter_list, list) { @@ -997,13 +997,7 @@ void i40evf_down(struct i40evf_adapter *adapter) adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; } - netif_tx_disable(netdev); - - netif_tx_stop_all_queues(netdev); - msleep(20); - - netif_carrier_off(netdev); clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); } @@ -1358,6 +1352,11 @@ static void i40evf_watchdog_task(struct work_struct *work) goto watchdog_done; } + if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_QUEUES) { + i40evf_disable_queues(adapter); + goto watchdog_done; + } + if (adapter->aq_required & I40EVF_FLAG_AQ_MAP_VECTORS) { i40evf_map_queues(adapter); goto watchdog_done; @@ -1383,11 +1382,6 @@ static void i40evf_watchdog_task(struct work_struct *work) goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_QUEUES) { - i40evf_disable_queues(adapter); - goto watchdog_done; - } - if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_QUEUES) { i40evf_configure_queues(adapter); goto watchdog_done; @@ -1724,7 +1718,7 @@ out: * * Free all transmit software resources **/ -static void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) +void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) { int i; @@ -1794,7 +1788,7 @@ static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter) * * Free all receive software resources **/ -static void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) +void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) { int i; @@ -1824,7 +1818,7 @@ static int i40evf_open(struct net_device *netdev) dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); return -EIO; } - if (adapter->state != __I40EVF_DOWN) + if (adapter->state != __I40EVF_DOWN || adapter->aq_required) return -EBUSY; /* allocate transmit descriptors */ @@ -1888,9 +1882,6 @@ static int i40evf_close(struct net_device *netdev) adapter->state = __I40EVF_DOWN; i40evf_free_traffic_irqs(adapter); - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - return 0; } @@ -2504,6 +2495,8 @@ static void i40evf_remove(struct pci_dev *pdev) iounmap(hw->hw_addr); pci_release_regions(pdev); + i40evf_free_all_tx_resources(adapter); + i40evf_free_all_rx_resources(adapter); i40evf_free_queues(adapter); kfree(adapter->vf_res); /* If we got removed before an up/down sequence, we've got a filter diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 3f0c85ecbca6..4240a496dc50 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -761,6 +761,8 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, break; case I40E_VIRTCHNL_OP_DISABLE_QUEUES: adapter->aq_pending &= ~(I40EVF_FLAG_AQ_DISABLE_QUEUES); + i40evf_free_all_tx_resources(adapter); + i40evf_free_all_rx_resources(adapter); break; case I40E_VIRTCHNL_OP_CONFIG_VSI_QUEUES: adapter->aq_pending &= ~(I40EVF_FLAG_AQ_CONFIGURE_QUEUES); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index f366b3b96d03..8457d0306e3a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1776,6 +1776,7 @@ void igb_down(struct igb_adapter *adapter) wr32(E1000_RCTL, rctl & ~E1000_RCTL_EN); /* flush and sleep below */ + netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); /* disable transmits in the hardware */ @@ -1797,12 +1798,9 @@ void igb_down(struct igb_adapter *adapter) } } - del_timer_sync(&adapter->watchdog_timer); del_timer_sync(&adapter->phy_info_timer); - netif_carrier_off(netdev); - /* record the stats before reset*/ spin_lock(&adapter->stats64_lock); igb_update_stats(adapter, &adapter->stats64); @@ -2095,6 +2093,7 @@ static const struct net_device_ops igb_netdev_ops = { #endif .ndo_fix_features = igb_fix_features, .ndo_set_features = igb_set_features, + .ndo_features_check = passthru_features_check, }; /** diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 52d01b8b01ed..c4894fb5c1d2 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -116,7 +116,8 @@ static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc) } /* SYSTIM read access for I210/I211 */ -static void igb_ptp_read_i210(struct igb_adapter *adapter, struct timespec *ts) +static void igb_ptp_read_i210(struct igb_adapter *adapter, + struct timespec64 *ts) { struct e1000_hw *hw = &adapter->hw; u32 sec, nsec; @@ -134,7 +135,7 @@ static void igb_ptp_read_i210(struct igb_adapter *adapter, struct timespec *ts) } static void igb_ptp_write_i210(struct igb_adapter *adapter, - const struct timespec *ts) + const struct timespec64 *ts) { struct e1000_hw *hw = &adapter->hw; @@ -269,13 +270,13 @@ static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta) struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); unsigned long flags; - struct timespec now, then = ns_to_timespec(delta); + struct timespec64 now, then = ns_to_timespec64(delta); spin_lock_irqsave(&igb->tmreg_lock, flags); igb_ptp_read_i210(igb, &now); - now = timespec_add(now, then); - igb_ptp_write_i210(igb, (const struct timespec *)&now); + now = timespec64_add(now, then); + igb_ptp_write_i210(igb, (const struct timespec64 *)&now); spin_unlock_irqrestore(&igb->tmreg_lock, flags); @@ -283,7 +284,7 @@ static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta) } static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp, - struct timespec *ts) + struct timespec64 *ts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -304,7 +305,7 @@ static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp, } static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp, - struct timespec *ts) + struct timespec64 *ts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -320,7 +321,7 @@ static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp, } static int igb_ptp_settime_82576(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -340,7 +341,7 @@ static int igb_ptp_settime_82576(struct ptp_clock_info *ptp, } static int igb_ptp_settime_i210(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); @@ -627,11 +628,12 @@ static void igb_ptp_overflow_check(struct work_struct *work) { struct igb_adapter *igb = container_of(work, struct igb_adapter, ptp_overflow_work.work); - struct timespec ts; + struct timespec64 ts; - igb->ptp_caps.gettime(&igb->ptp_caps, &ts); + igb->ptp_caps.gettime64(&igb->ptp_caps, &ts); - pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); + pr_debug("igb overflow check at %lld.%09lu\n", + (long long) ts.tv_sec, ts.tv_nsec); schedule_delayed_work(&igb->ptp_overflow_work, IGB_SYSTIM_OVERFLOW_PERIOD); @@ -989,8 +991,8 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576; adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; - adapter->ptp_caps.gettime = igb_ptp_gettime_82576; - adapter->ptp_caps.settime = igb_ptp_settime_82576; + adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576; + adapter->ptp_caps.settime64 = igb_ptp_settime_82576; adapter->ptp_caps.enable = igb_ptp_feature_enable; adapter->cc.read = igb_ptp_read_82576; adapter->cc.mask = CYCLECOUNTER_MASK(64); @@ -1009,8 +1011,8 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; - adapter->ptp_caps.gettime = igb_ptp_gettime_82576; - adapter->ptp_caps.settime = igb_ptp_settime_82576; + adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576; + adapter->ptp_caps.settime64 = igb_ptp_settime_82576; adapter->ptp_caps.enable = igb_ptp_feature_enable; adapter->cc.read = igb_ptp_read_82580; adapter->cc.mask = CYCLECOUNTER_MASK(IGB_NBITS_82580); @@ -1038,8 +1040,8 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.pin_config = adapter->sdp_config; adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210; - adapter->ptp_caps.gettime = igb_ptp_gettime_i210; - adapter->ptp_caps.settime = igb_ptp_settime_i210; + adapter->ptp_caps.gettime64 = igb_ptp_gettime_i210; + adapter->ptp_caps.settime64 = igb_ptp_settime_i210; adapter->ptp_caps.enable = igb_ptp_feature_enable_i210; adapter->ptp_caps.verify = igb_ptp_verify_pin; /* Enable the timer functions by clearing bit 31. */ @@ -1057,7 +1059,7 @@ void igb_ptp_init(struct igb_adapter *adapter) /* Initialize the clock and overflow work for devices that need it. */ if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) { - struct timespec ts = ktime_to_timespec(ktime_get_real()); + struct timespec64 ts = ktime_to_timespec64(ktime_get_real()); igb_ptp_settime_i210(&adapter->ptp_caps, &ts); } else { @@ -1171,7 +1173,7 @@ void igb_ptp_reset(struct igb_adapter *adapter) /* Re-initialize the timer. */ if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) { - struct timespec ts = ktime_to_timespec(ktime_get_real()); + struct timespec64 ts = ktime_to_timespec64(ktime_get_real()); igb_ptp_write_i210(adapter, &ts); } else { diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index c17ea4b8f84d..95af14e139d7 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1519,6 +1519,7 @@ void igbvf_down(struct igbvf_adapter *adapter) rxdctl = er32(RXDCTL(0)); ew32(RXDCTL(0), rxdctl & ~E1000_RXDCTL_QUEUE_ENABLE); + netif_carrier_off(netdev); netif_stop_queue(netdev); /* disable transmits in the hardware */ @@ -1535,8 +1536,6 @@ void igbvf_down(struct igbvf_adapter *adapter) del_timer_sync(&adapter->watchdog_timer); - netif_carrier_off(netdev); - /* record the stats before reset*/ igbvf_update_stats(adapter); diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 11a1bdbe3fd9..31f91459312f 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -285,6 +285,8 @@ ixgb_down(struct ixgb_adapter *adapter, bool kill_watchdog) /* prevent the interrupt handler from restarting watchdog */ set_bit(__IXGB_DOWN, &adapter->flags); + netif_carrier_off(netdev); + napi_disable(&adapter->napi); /* waiting for NAPI to complete can re-enable interrupts */ ixgb_irq_disable(adapter); @@ -298,7 +300,6 @@ ixgb_down(struct ixgb_adapter *adapter, bool kill_watchdog) adapter->link_speed = 0; adapter->link_duplex = 0; - netif_carrier_off(netdev); netif_stop_queue(netdev); ixgb_reset(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index bd46f5d1c943..75b9e938728d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -279,7 +279,7 @@ static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) * read the timecounter and return the correct value on ns, * after converting it into a struct timespec. */ -static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); @@ -306,7 +306,7 @@ static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) * wall timer value. */ static int ixgbe_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); @@ -407,7 +407,7 @@ void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter) { bool timeout = time_is_before_jiffies(adapter->last_overflow_check + IXGBE_OVERFLOW_PERIOD); - struct timespec ts; + struct timespec64 ts; if (timeout) { ixgbe_ptp_gettime(&adapter->ptp_caps, &ts); @@ -874,8 +874,8 @@ static int ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) adapter->ptp_caps.pps = 1; adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq; adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; - adapter->ptp_caps.gettime = ixgbe_ptp_gettime; - adapter->ptp_caps.settime = ixgbe_ptp_settime; + adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime; + adapter->ptp_caps.settime64 = ixgbe_ptp_settime; adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; break; case ixgbe_mac_82599EB: @@ -890,8 +890,8 @@ static int ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq; adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; - adapter->ptp_caps.gettime = ixgbe_ptp_gettime; - adapter->ptp_caps.settime = ixgbe_ptp_settime; + adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime; + adapter->ptp_caps.settime64 = ixgbe_ptp_settime; adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; break; default: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 90b5309cdb5c..666e7bdeb4f1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -164,7 +164,8 @@ static int mlx4_en_phc_adjtime(struct ptp_clock_info *ptp, s64 delta) * Read the timecounter and return the correct value in ns after converting * it into a struct timespec. **/ -static int mlx4_en_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int mlx4_en_phc_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) { struct mlx4_en_dev *mdev = container_of(ptp, struct mlx4_en_dev, ptp_clock_info); @@ -191,11 +192,11 @@ static int mlx4_en_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) * wall timer value. **/ static int mlx4_en_phc_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct mlx4_en_dev *mdev = container_of(ptp, struct mlx4_en_dev, ptp_clock_info); - u64 ns = timespec_to_ns(ts); + u64 ns = timespec64_to_ns(ts); unsigned long flags; /* reset the timecounter */ @@ -232,8 +233,8 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = { .pps = 0, .adjfreq = mlx4_en_phc_adjfreq, .adjtime = mlx4_en_phc_adjtime, - .gettime = mlx4_en_phc_gettime, - .settime = mlx4_en_phc_settime, + .gettime64 = mlx4_en_phc_gettime, + .settime64 = mlx4_en_phc_settime, .enable = mlx4_en_phc_enable, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index c59ed925adaf..ebc93a101c93 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1698,8 +1698,6 @@ int mlx4_en_start_port(struct net_device *dev) /* Schedule multicast task to populate multicast list */ queue_work(mdev->workqueue, &priv->rx_mode_task); - mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap); - #ifdef CONFIG_MLX4_EN_VXLAN if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) vxlan_get_rx_port(dev); @@ -2375,10 +2373,38 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { + features = vlan_features_check(skb, features); return vxlan_features_check(skb, features); } #endif +static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[queue_index]; + struct mlx4_update_qp_params params; + int err; + + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT)) + return -EOPNOTSUPP; + + /* rate provided to us in Mbs, check if it fits into 12 bits, if not use Gbs */ + if (maxrate >> 12) { + params.rate_unit = MLX4_QP_RATE_LIMIT_GBS; + params.rate_val = maxrate / 1000; + } else if (maxrate) { + params.rate_unit = MLX4_QP_RATE_LIMIT_MBS; + params.rate_val = maxrate; + } else { /* zero serves to revoke the QP rate-limitation */ + params.rate_unit = 0; + params.rate_val = 0; + } + + err = mlx4_update_qp(priv->mdev->dev, tx_ring->qpn, MLX4_UPDATE_QP_RATE_LIMIT, + ¶ms); + return err; +} + static const struct net_device_ops mlx4_netdev_ops = { .ndo_open = mlx4_en_open, .ndo_stop = mlx4_en_close, @@ -2410,6 +2436,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_del_vxlan_port = mlx4_en_del_vxlan_port, .ndo_features_check = mlx4_en_features_check, #endif + .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, }; static const struct net_device_ops mlx4_netdev_ops_master = { @@ -2444,6 +2471,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_del_vxlan_port = mlx4_en_del_vxlan_port, .ndo_features_check = mlx4_en_features_check, #endif + .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, }; struct mlx4_en_bond { @@ -2853,6 +2881,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, queue_delayed_work(mdev->workqueue, &priv->service_task, SERVICE_TASK_DELAY); + mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap); + return 0; out: diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 242bcee5d774..4a471f5d1b56 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -144,7 +144,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [19] = "Performance optimized for limited rule configuration flow steering support", [20] = "Recoverable error events support", [21] = "Port Remap support", - [22] = "QCN support" + [22] = "QCN support", + [23] = "QP rate limiting support" }; int i; @@ -697,6 +698,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET 0xb0 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET 0xa8 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET 0xac +#define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc +#define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0 +#define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2 + dev_cap->flags2 = 0; mailbox = mlx4_alloc_cmd_mailbox(dev); @@ -904,6 +909,18 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET); dev_cap->dmfs_high_rate_qpn_range &= MGM_QPN_MASK; + MLX4_GET(size, outbox, QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET); + dev_cap->rl_caps.num_rates = size; + if (dev_cap->rl_caps.num_rates) { + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT; + MLX4_GET(size, outbox, QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET); + dev_cap->rl_caps.max_val = size & 0xfff; + dev_cap->rl_caps.max_unit = size >> 14; + MLX4_GET(size, outbox, QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET); + dev_cap->rl_caps.min_val = size & 0xfff; + dev_cap->rl_caps.min_unit = size >> 14; + } + MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET); if (field32 & (1 << 16)) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP; @@ -979,6 +996,15 @@ void mlx4_dev_cap_dump(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->dmfs_high_rate_qpn_base); mlx4_dbg(dev, "DMFS high rate steer QPn range: %d\n", dev_cap->dmfs_high_rate_qpn_range); + + if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT) { + struct mlx4_rate_limit_caps *rl_caps = &dev_cap->rl_caps; + + mlx4_dbg(dev, "QP Rate-Limit: #rates %d, unit/val max %d/%d, min %d/%d\n", + rl_caps->num_rates, rl_caps->max_unit, rl_caps->max_val, + rl_caps->min_unit, rl_caps->min_val); + } + dump_dev_cap_flags(dev, dev_cap->flags); dump_dev_cap_flags2(dev, dev_cap->flags2); } @@ -1075,6 +1101,7 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, u64 flags; int err = 0; u8 field; + u16 field16; u32 bmme_flags, field32; int real_port; int slave_port; @@ -1158,6 +1185,10 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, field &= 0xfe; MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_ECN_QCN_VER_OFFSET); + /* turn off QP max-rate limiting for guests */ + field16 = 0; + MLX4_PUT(outbox->buf, field16, QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index f44f7f6017ed..863655bd3947 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -127,6 +127,7 @@ struct mlx4_dev_cap { u32 max_counters; u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; + struct mlx4_rate_limit_caps rl_caps; struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; }; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 7e487223489a..43aa76775b5f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -489,6 +489,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.dmfs_high_rate_qpn_range = MLX4_A0_STEERING_TABLE_SIZE; } + dev->caps.rl_caps = dev_cap->rl_caps; + dev->caps.reserved_qps_cnt[MLX4_QP_REGION_RSS_RAW_ETH] = dev->caps.dmfs_high_rate_qpn_range; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 94553b501c76..8ad241bbcf25 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -453,7 +453,7 @@ struct mlx4_en_port_stats { unsigned long rx_chksum_none; unsigned long rx_chksum_complete; unsigned long tx_chksum_offload; -#define NUM_PORT_STATS 9 +#define NUM_PORT_STATS 10 }; struct mlx4_en_perf_stats { diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index eda29dbbfcd2..69e4462e4ee4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -442,6 +442,11 @@ int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn, cmd->qp_context.param3 |= cpu_to_be32(MLX4_STRIP_VLAN); } + if (attr & MLX4_UPDATE_QP_RATE_LIMIT) { + qp_mask |= 1ULL << MLX4_UPD_QP_MASK_RATE_LIMIT; + cmd->qp_context.rate_limit_params = cpu_to_be16((params->rate_unit << 14) | params->rate_val); + } + cmd->primary_addr_path_mask = cpu_to_be64(pri_addr_path_mask); cmd->qp_mask = cpu_to_be64(qp_mask); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index d43e25914d19..c258f8625aac 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2947,8 +2947,12 @@ static int verify_qp_parameters(struct mlx4_dev *dev, qp_type = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff; optpar = be32_to_cpu(*(__be32 *) inbox->buf); - if (slave != mlx4_master_func_num(dev)) + if (slave != mlx4_master_func_num(dev)) { qp_ctx->params2 &= ~MLX4_QP_BIT_FPP; + /* setting QP rate-limit is disallowed for VFs */ + if (qp_ctx->rate_limit_params) + return -EPERM; + } switch (qp_type) { case MLX4_QP_ST_RC: diff --git a/drivers/net/ethernet/octeon/octeon_mgmt.c b/drivers/net/ethernet/octeon/octeon_mgmt.c index d36599f47af5..7bf9c028d8d7 100644 --- a/drivers/net/ethernet/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/octeon/octeon_mgmt.c @@ -1557,7 +1557,7 @@ static int octeon_mgmt_remove(struct platform_device *pdev) return 0; } -static struct of_device_id octeon_mgmt_match[] = { +static const struct of_device_id octeon_mgmt_match[] = { { .compatible = "cavium,octeon-5750-mix", }, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index a430a34a4434..367f3976df56 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -507,6 +507,7 @@ static netdev_features_t qlcnic_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { + features = vlan_features_check(skb, features); return vxlan_features_check(skb, features); } #endif diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 223348d8cc07..c9558e6d57ad 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -30,6 +30,7 @@ #include <linux/if_vlan.h> #include <linux/if_bridge.h> #include <linux/bitops.h> +#include <linux/ctype.h> #include <net/switchdev.h> #include <net/rtnetlink.h> #include <net/ip_fib.h> @@ -1630,6 +1631,53 @@ rocker_cmd_get_port_settings_macaddr_proc(struct rocker *rocker, return 0; } +struct port_name { + char *buf; + size_t len; +}; + +static int +rocker_cmd_get_port_settings_phys_name_proc(struct rocker *rocker, + struct rocker_port *rocker_port, + struct rocker_desc_info *desc_info, + void *priv) +{ + struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1]; + struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1]; + struct port_name *name = priv; + struct rocker_tlv *attr; + size_t i, j, len; + char *str; + + rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info); + if (!attrs[ROCKER_TLV_CMD_INFO]) + return -EIO; + + rocker_tlv_parse_nested(info_attrs, ROCKER_TLV_CMD_PORT_SETTINGS_MAX, + attrs[ROCKER_TLV_CMD_INFO]); + attr = info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_PHYS_NAME]; + if (!attr) + return -EIO; + + len = min_t(size_t, rocker_tlv_len(attr), name->len); + str = rocker_tlv_data(attr); + + /* make sure name only contains alphanumeric characters */ + for (i = j = 0; i < len; ++i) { + if (isalnum(str[i])) { + name->buf[j] = str[i]; + j++; + } + } + + if (j == 0) + return -EIO; + + name->buf[j] = '\0'; + + return 0; +} + static int rocker_cmd_set_port_settings_ethtool_prep(struct rocker *rocker, struct rocker_port *rocker_port, @@ -2955,11 +3003,16 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, struct rocker_port *p; struct rocker *rocker = rocker_port->rocker; u32 group_id = ROCKER_GROUP_L2_FLOOD(vlan_id, 0); - u32 group_ids[ROCKER_FP_PORTS_MAX]; + u32 *group_ids; u8 group_count = 0; - int err; + int err = 0; int i; + group_ids = kcalloc(rocker->port_count, sizeof(u32), + rocker_op_flags_gfp(flags)); + if (!group_ids) + return -ENOMEM; + /* Adjust the flood group for this VLAN. The flood group * references an L2 interface group for each port in this * VLAN. @@ -2977,7 +3030,7 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, /* If there are no bridged ports in this VLAN, we're done */ if (group_count == 0) - return 0; + goto no_ports_in_vlan; err = rocker_group_l2_flood(rocker_port, flags, vlan_id, group_count, group_ids, @@ -2986,6 +3039,8 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 flood group\n", err); +no_ports_in_vlan: + kfree(group_ids); return err; } @@ -4131,8 +4186,42 @@ static int rocker_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, rocker_port->brport_flags, mask); } -static int rocker_port_switch_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +static int rocker_port_get_phys_port_name(struct net_device *dev, + char *buf, size_t len) +{ + struct rocker_port *rocker_port = netdev_priv(dev); + struct port_name name = { .buf = buf, .len = len }; + int err; + + err = rocker_cmd_exec(rocker_port->rocker, rocker_port, + rocker_cmd_get_port_settings_prep, NULL, + rocker_cmd_get_port_settings_phys_name_proc, + &name, false); + + return err ? -EOPNOTSUPP : 0; +} + +static const struct net_device_ops rocker_port_netdev_ops = { + .ndo_open = rocker_port_open, + .ndo_stop = rocker_port_stop, + .ndo_start_xmit = rocker_port_xmit, + .ndo_set_mac_address = rocker_port_set_mac_address, + .ndo_vlan_rx_add_vid = rocker_port_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = rocker_port_vlan_rx_kill_vid, + .ndo_fdb_add = rocker_port_fdb_add, + .ndo_fdb_del = rocker_port_fdb_del, + .ndo_fdb_dump = rocker_port_fdb_dump, + .ndo_bridge_setlink = rocker_port_bridge_setlink, + .ndo_bridge_getlink = rocker_port_bridge_getlink, + .ndo_get_phys_port_name = rocker_port_get_phys_port_name, +}; + +/******************** + * swdev interface + ********************/ + +static int rocker_port_swdev_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid) { struct rocker_port *rocker_port = netdev_priv(dev); struct rocker *rocker = rocker_port->rocker; @@ -4142,18 +4231,18 @@ static int rocker_port_switch_parent_id_get(struct net_device *dev, return 0; } -static int rocker_port_switch_port_stp_update(struct net_device *dev, u8 state) +static int rocker_port_swdev_port_stp_update(struct net_device *dev, u8 state) { struct rocker_port *rocker_port = netdev_priv(dev); return rocker_port_stp_update(rocker_port, state); } -static int rocker_port_switch_fib_ipv4_add(struct net_device *dev, - __be32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 nlflags, u32 tb_id) +static int rocker_port_swdev_fib_ipv4_add(struct net_device *dev, + __be32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 nlflags, u32 tb_id) { struct rocker_port *rocker_port = netdev_priv(dev); int flags = 0; @@ -4162,10 +4251,10 @@ static int rocker_port_switch_fib_ipv4_add(struct net_device *dev, fi, tb_id, flags); } -static int rocker_port_switch_fib_ipv4_del(struct net_device *dev, - __be32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) +static int rocker_port_swdev_fib_ipv4_del(struct net_device *dev, + __be32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) { struct rocker_port *rocker_port = netdev_priv(dev); int flags = ROCKER_OP_FLAG_REMOVE; @@ -4174,22 +4263,11 @@ static int rocker_port_switch_fib_ipv4_del(struct net_device *dev, fi, tb_id, flags); } -static const struct net_device_ops rocker_port_netdev_ops = { - .ndo_open = rocker_port_open, - .ndo_stop = rocker_port_stop, - .ndo_start_xmit = rocker_port_xmit, - .ndo_set_mac_address = rocker_port_set_mac_address, - .ndo_vlan_rx_add_vid = rocker_port_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = rocker_port_vlan_rx_kill_vid, - .ndo_fdb_add = rocker_port_fdb_add, - .ndo_fdb_del = rocker_port_fdb_del, - .ndo_fdb_dump = rocker_port_fdb_dump, - .ndo_bridge_setlink = rocker_port_bridge_setlink, - .ndo_bridge_getlink = rocker_port_bridge_getlink, - .ndo_switch_parent_id_get = rocker_port_switch_parent_id_get, - .ndo_switch_port_stp_update = rocker_port_switch_port_stp_update, - .ndo_switch_fib_ipv4_add = rocker_port_switch_fib_ipv4_add, - .ndo_switch_fib_ipv4_del = rocker_port_switch_fib_ipv4_del, +static const struct swdev_ops rocker_port_swdev_ops = { + .swdev_parent_id_get = rocker_port_swdev_parent_id_get, + .swdev_port_stp_update = rocker_port_swdev_port_stp_update, + .swdev_fib_ipv4_add = rocker_port_swdev_fib_ipv4_add, + .swdev_fib_ipv4_del = rocker_port_swdev_fib_ipv4_del, }; /******************** @@ -4544,6 +4622,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_port_dev_addr_init(rocker, rocker_port); dev->netdev_ops = &rocker_port_netdev_ops; dev->ethtool_ops = &rocker_port_ethtool_ops; + dev->swdev_ops = &rocker_port_swdev_ops; netif_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx, NAPI_POLL_WEIGHT); netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx, diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h index 51e430d25138..a4e9591d7457 100644 --- a/drivers/net/ethernet/rocker/rocker.h +++ b/drivers/net/ethernet/rocker/rocker.h @@ -158,6 +158,7 @@ enum { ROCKER_TLV_CMD_PORT_SETTINGS_MACADDR, /* binary */ ROCKER_TLV_CMD_PORT_SETTINGS_MODE, /* u8 */ ROCKER_TLV_CMD_PORT_SETTINGS_LEARNING, /* u8 */ + ROCKER_TLV_CMD_PORT_SETTINGS_PHYS_NAME, /* binary */ __ROCKER_TLV_CMD_PORT_SETTINGS_MAX, ROCKER_TLV_CMD_PORT_SETTINGS_MAX = diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 6b861e3de4b0..a2e9aee05cdd 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -323,9 +323,9 @@ struct efx_ptp_data { static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta); static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta); -static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts); +static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts); static int efx_phc_settime(struct ptp_clock_info *ptp, - const struct timespec *e_ts); + const struct timespec64 *e_ts); static int efx_phc_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); @@ -1198,8 +1198,8 @@ static const struct ptp_clock_info efx_phc_clock_info = { .pps = 1, .adjfreq = efx_phc_adjfreq, .adjtime = efx_phc_adjtime, - .gettime = efx_phc_gettime, - .settime = efx_phc_settime, + .gettime64 = efx_phc_gettime, + .settime64 = efx_phc_settime, .enable = efx_phc_enable, }; @@ -1837,7 +1837,7 @@ static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta) NULL, 0, NULL); } -static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, @@ -1859,28 +1859,28 @@ static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) kt = ptp_data->nic_to_kernel_time( MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_MAJOR), MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_MINOR), 0); - *ts = ktime_to_timespec(kt); + *ts = ktime_to_timespec64(kt); return 0; } static int efx_phc_settime(struct ptp_clock_info *ptp, - const struct timespec *e_ts) + const struct timespec64 *e_ts) { /* Get the current NIC time, efx_phc_gettime. * Subtract from the desired time to get the offset * call efx_phc_adjtime with the offset */ int rc; - struct timespec time_now; - struct timespec delta; + struct timespec64 time_now; + struct timespec64 delta; rc = efx_phc_gettime(ptp, &time_now); if (rc != 0) return rc; - delta = timespec_sub(*e_ts, time_now); + delta = timespec64_sub(*e_ts, time_now); - rc = efx_phc_adjtime(ptp, timespec_to_ns(&delta)); + rc = efx_phc_adjtime(ptp, timespec64_to_ns(&delta)); if (rc != 0) return rc; diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 5d093dc0f5f5..5a1a3e7c93e7 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2204,27 +2204,18 @@ static int try_toggle_control_gpio(struct device *dev, int value, unsigned int nsdelay) { struct gpio_desc *gpio = *desc; + enum gpiod_flags flags = value ? GPIOD_OUT_LOW : GPIOD_OUT_HIGH; int res; - gpio = devm_gpiod_get_index(dev, name, index); - if (IS_ERR(gpio)) { - if (PTR_ERR(gpio) == -ENOENT) { - *desc = NULL; - return 0; - } - + gpio = devm_gpiod_get_index_optional(dev, name, index, flags); + if (IS_ERR(gpio)) return PTR_ERR(gpio); + + if (gpio) { + if (nsdelay) + usleep_range(nsdelay, 2 * nsdelay); + gpiod_set_value_cansleep(gpio, value); } - res = gpiod_direction_output(gpio, !value); - if (res) { - dev_err(dev, "unable to toggle gpio %s: %i\n", name, res); - devm_gpiod_put(dev, gpio); - gpio = NULL; - return res; - } - if (nsdelay) - usleep_range(nsdelay, 2 * nsdelay); - gpiod_set_value_cansleep(gpio, value); *desc = gpio; return 0; @@ -2248,10 +2239,9 @@ static int smc_drv_probe(struct platform_device *pdev) const struct of_device_id *match = NULL; struct smc_local *lp; struct net_device *ndev; - struct resource *res; + struct resource *res, *ires; unsigned int __iomem *addr; unsigned long irq_flags = SMC_IRQ_FLAGS; - unsigned long irq_resflags; int ret; ndev = alloc_etherdev(sizeof(struct smc_local)); @@ -2343,19 +2333,16 @@ static int smc_drv_probe(struct platform_device *pdev) goto out_free_netdev; } - ndev->irq = platform_get_irq(pdev, 0); - if (ndev->irq <= 0) { + ires = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!ires) { ret = -ENODEV; goto out_release_io; } - /* - * If this platform does not specify any special irqflags, or if - * the resource supplies a trigger, override the irqflags with - * the trigger flags from the resource. - */ - irq_resflags = irqd_get_trigger_type(irq_get_irq_data(ndev->irq)); - if (irq_flags == -1 || irq_resflags & IRQF_TRIGGER_MASK) - irq_flags = irq_resflags & IRQF_TRIGGER_MASK; + + ndev->irq = ires->start; + + if (irq_flags == -1 || ires->flags & IRQF_TRIGGER_MASK) + irq_flags = ires->flags & IRQF_TRIGGER_MASK; ret = smc_request_attrib(pdev, ndev); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index c5ee79d8a8c5..172f3188361e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -105,7 +105,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) * Description: this function will read the current time from the * hardware clock and store it in @ts. */ -static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec *ts) +static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct stmmac_priv *priv = container_of(ptp, struct stmmac_priv, ptp_clock_ops); @@ -135,7 +135,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec *ts) * hardware clock. */ static int stmmac_set_time(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct stmmac_priv *priv = container_of(ptp, struct stmmac_priv, ptp_clock_ops); @@ -168,8 +168,8 @@ static struct ptp_clock_info stmmac_ptp_clock_ops = { .pps = 0, .adjfreq = stmmac_adjust_freq, .adjtime = stmmac_adjust_time, - .gettime = stmmac_get_time, - .settime = stmmac_set_time, + .gettime64 = stmmac_get_time, + .settime64 = stmmac_set_time, .enable = stmmac_enable, }; diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index f6a71092e135..631e0afd07d2 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -88,6 +88,7 @@ config TI_CPTS config TI_KEYSTONE_NETCP tristate "TI Keystone NETCP Core Support" select TI_CPSW_ALE + select TI_DAVINCI_MDIO depends on OF depends on KEYSTONE_NAVIGATOR_DMA && KEYSTONE_NAVIGATOR_QMSS ---help--- diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index fbe42cb107ec..074b6369da66 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -167,7 +167,7 @@ static int cpts_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; u32 remainder; @@ -185,7 +185,7 @@ static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int cpts_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { u64 ns; unsigned long flags; @@ -216,20 +216,20 @@ static struct ptp_clock_info cpts_info = { .pps = 0, .adjfreq = cpts_ptp_adjfreq, .adjtime = cpts_ptp_adjtime, - .gettime = cpts_ptp_gettime, - .settime = cpts_ptp_settime, + .gettime64 = cpts_ptp_gettime, + .settime64 = cpts_ptp_settime, .enable = cpts_ptp_enable, }; static void cpts_overflow_check(struct work_struct *work) { - struct timespec ts; + struct timespec64 ts; struct cpts *cpts = container_of(work, struct cpts, overflow_work.work); cpts_write32(cpts, CPTS_EN, control); cpts_write32(cpts, TS_PEND_EN, int_enable); cpts_ptp_gettime(&cpts->info, &ts); - pr_debug("cpts overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); + pr_debug("cpts overflow check at %lld.%09lu\n", ts.tv_sec, ts.tv_nsec); schedule_delayed_work(&cpts->overflow_work, CPTS_OVERFLOW_PERIOD); } diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index 906e9bc412f5..bbacf5cccec2 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -41,7 +41,10 @@ struct netcp_tx_pipe { struct netcp_device *netcp_device; void *dma_queue; unsigned int dma_queue_id; - u8 dma_psflags; + /* To port for packet forwarded to switch. Used only by ethss */ + u8 switch_to_port; +#define SWITCH_TO_PORT_IN_TAGINFO BIT(0) + u8 flags; void *dma_channel; const char *dma_chan_name; }; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 9f14d8b515c7..43efc3a0cda5 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1098,9 +1098,9 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, struct netcp_tx_pipe *tx_pipe = NULL; struct netcp_hook_list *tx_hook; struct netcp_packet p_info; - u32 packet_info = 0; unsigned int dma_sz; dma_addr_t dma; + u32 tmp = 0; int ret = 0; p_info.netcp = netcp; @@ -1140,20 +1140,27 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, memmove(p_info.psdata, p_info.psdata + p_info.psdata_len, p_info.psdata_len); set_words(psdata, p_info.psdata_len, psdata); - packet_info |= - (p_info.psdata_len & KNAV_DMA_DESC_PSLEN_MASK) << + tmp |= (p_info.psdata_len & KNAV_DMA_DESC_PSLEN_MASK) << KNAV_DMA_DESC_PSLEN_SHIFT; } - packet_info |= KNAV_DMA_DESC_HAS_EPIB | + tmp |= KNAV_DMA_DESC_HAS_EPIB | ((netcp->tx_compl_qid & KNAV_DMA_DESC_RETQ_MASK) << - KNAV_DMA_DESC_RETQ_SHIFT) | - ((tx_pipe->dma_psflags & KNAV_DMA_DESC_PSFLAG_MASK) << - KNAV_DMA_DESC_PSFLAG_SHIFT); + KNAV_DMA_DESC_RETQ_SHIFT); - set_words(&packet_info, 1, &desc->packet_info); + if (!(tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO)) { + tmp |= ((tx_pipe->switch_to_port & KNAV_DMA_DESC_PSFLAG_MASK) << + KNAV_DMA_DESC_PSFLAG_SHIFT); + } + + set_words(&tmp, 1, &desc->packet_info); set_words((u32 *)&skb, 1, &desc->pad[0]); + if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) { + tmp = tx_pipe->switch_to_port; + set_words((u32 *)&tmp, 1, &desc->tag_info); + } + /* submit packet descriptor */ ret = knav_pool_desc_map(netcp->tx_pool, desc, sizeof(*desc), &dma, &dma_sz); @@ -2127,7 +2134,7 @@ static int netcp_remove(struct platform_device *pdev) return 0; } -static struct of_device_id of_match[] = { +static const struct of_device_id of_match[] = { { .compatible = "ti,netcp-1.0", }, {}, }; diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 84f5ce525750..2bef655279f3 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -40,35 +40,61 @@ #define GBE_MODULE_NAME "netcp-gbe" #define GBE_SS_VERSION_14 0x4ed21104 +#define GBE_SS_REG_INDEX 0 +#define GBE_SGMII34_REG_INDEX 1 +#define GBE_SM_REG_INDEX 2 +/* offset relative to base of GBE_SS_REG_INDEX */ #define GBE13_SGMII_MODULE_OFFSET 0x100 -#define GBE13_SGMII34_MODULE_OFFSET 0x400 -#define GBE13_SWITCH_MODULE_OFFSET 0x800 -#define GBE13_HOST_PORT_OFFSET 0x834 -#define GBE13_SLAVE_PORT_OFFSET 0x860 -#define GBE13_EMAC_OFFSET 0x900 -#define GBE13_SLAVE_PORT2_OFFSET 0xa00 -#define GBE13_HW_STATS_OFFSET 0xb00 -#define GBE13_ALE_OFFSET 0xe00 +/* offset relative to base of GBE_SM_REG_INDEX */ +#define GBE13_HOST_PORT_OFFSET 0x34 +#define GBE13_SLAVE_PORT_OFFSET 0x60 +#define GBE13_EMAC_OFFSET 0x100 +#define GBE13_SLAVE_PORT2_OFFSET 0x200 +#define GBE13_HW_STATS_OFFSET 0x300 +#define GBE13_ALE_OFFSET 0x600 #define GBE13_HOST_PORT_NUM 0 -#define GBE13_NUM_SLAVES 4 -#define GBE13_NUM_ALE_PORTS (GBE13_NUM_SLAVES + 1) #define GBE13_NUM_ALE_ENTRIES 1024 +/* 1G Ethernet NU SS defines */ +#define GBENU_MODULE_NAME "netcp-gbenu" +#define GBE_SS_ID_NU 0x4ee6 +#define GBE_SS_ID_2U 0x4ee8 + +#define IS_SS_ID_MU(d) \ + ((GBE_IDENT((d)->ss_version) == GBE_SS_ID_NU) || \ + (GBE_IDENT((d)->ss_version) == GBE_SS_ID_2U)) + +#define IS_SS_ID_NU(d) \ + (GBE_IDENT((d)->ss_version) == GBE_SS_ID_NU) + +#define GBENU_SS_REG_INDEX 0 +#define GBENU_SM_REG_INDEX 1 +#define GBENU_SGMII_MODULE_OFFSET 0x100 +#define GBENU_HOST_PORT_OFFSET 0x1000 +#define GBENU_SLAVE_PORT_OFFSET 0x2000 +#define GBENU_EMAC_OFFSET 0x2330 +#define GBENU_HW_STATS_OFFSET 0x1a000 +#define GBENU_ALE_OFFSET 0x1e000 +#define GBENU_HOST_PORT_NUM 0 +#define GBENU_NUM_ALE_ENTRIES 1024 + /* 10G Ethernet SS defines */ #define XGBE_MODULE_NAME "netcp-xgbe" #define XGBE_SS_VERSION_10 0x4ee42100 -#define XGBE_SERDES_REG_INDEX 1 +#define XGBE_SS_REG_INDEX 0 +#define XGBE_SM_REG_INDEX 1 +#define XGBE_SERDES_REG_INDEX 2 + +/* offset relative to base of XGBE_SS_REG_INDEX */ #define XGBE10_SGMII_MODULE_OFFSET 0x100 -#define XGBE10_SWITCH_MODULE_OFFSET 0x1000 -#define XGBE10_HOST_PORT_OFFSET 0x1034 -#define XGBE10_SLAVE_PORT_OFFSET 0x1064 -#define XGBE10_EMAC_OFFSET 0x1400 -#define XGBE10_ALE_OFFSET 0x1700 -#define XGBE10_HW_STATS_OFFSET 0x1800 +/* offset relative to base of XGBE_SM_REG_INDEX */ +#define XGBE10_HOST_PORT_OFFSET 0x34 +#define XGBE10_SLAVE_PORT_OFFSET 0x64 +#define XGBE10_EMAC_OFFSET 0x400 +#define XGBE10_ALE_OFFSET 0x700 +#define XGBE10_HW_STATS_OFFSET 0x800 #define XGBE10_HOST_PORT_NUM 0 -#define XGBE10_NUM_SLAVES 2 -#define XGBE10_NUM_ALE_PORTS (XGBE10_NUM_SLAVES + 1) #define XGBE10_NUM_ALE_ENTRIES 1024 #define GBE_TIMER_INTERVAL (HZ / 2) @@ -88,7 +114,7 @@ #define MACSL_FULLDUPLEX BIT(0) #define GBE_CTL_P0_ENABLE BIT(2) -#define GBE_REG_VAL_STAT_ENABLE_ALL 0xff +#define GBE13_REG_VAL_STAT_ENABLE_ALL 0xff #define XGBE_REG_VAL_STAT_ENABLE_ALL 0xf #define GBE_STATS_CD_SEL BIT(28) @@ -108,11 +134,20 @@ #define GBE_STATSC_MODULE 2 #define GBE_STATSD_MODULE 3 +#define GBENU_STATS0_MODULE 0 +#define GBENU_STATS1_MODULE 1 +#define GBENU_STATS2_MODULE 2 +#define GBENU_STATS3_MODULE 3 +#define GBENU_STATS4_MODULE 4 +#define GBENU_STATS5_MODULE 5 +#define GBENU_STATS6_MODULE 6 +#define GBENU_STATS7_MODULE 7 +#define GBENU_STATS8_MODULE 8 + #define XGBE_STATS0_MODULE 0 #define XGBE_STATS1_MODULE 1 #define XGBE_STATS2_MODULE 2 -#define MAX_SLAVES GBE13_NUM_SLAVES /* s: 0-based slave_port */ #define SGMII_BASE(s) \ (((s) < 2) ? gbe_dev->sgmii_port_regs : gbe_dev->sgmii_port34_regs) @@ -125,10 +160,14 @@ #define GBE_SET_REG_OFS(p, rb, rn) p->rb##_ofs.rn = \ offsetof(struct gbe##_##rb, rn) +#define GBENU_SET_REG_OFS(p, rb, rn) p->rb##_ofs.rn = \ + offsetof(struct gbenu##_##rb, rn) #define XGBE_SET_REG_OFS(p, rb, rn) p->rb##_ofs.rn = \ offsetof(struct xgbe##_##rb, rn) #define GBE_REG_ADDR(p, rb, rn) (p->rb + p->rb##_ofs.rn) +#define HOST_TX_PRI_MAP_DEFAULT 0x00000000 + struct xgbe_ss_regs { u32 id_ver; u32 synce_count; @@ -258,6 +297,192 @@ struct xgbe_hw_stats { #define XGBE10_NUM_STAT_ENTRIES (sizeof(struct xgbe_hw_stats)/sizeof(u32)) +struct gbenu_ss_regs { + u32 id_ver; + u32 synce_count; /* NU */ + u32 synce_mux; /* NU */ + u32 control; /* 2U */ + u32 __rsvd_0[2]; /* 2U */ + u32 rgmii_status; /* 2U */ + u32 ss_status; /* 2U */ +}; + +struct gbenu_switch_regs { + u32 id_ver; + u32 control; + u32 __rsvd_0[2]; + u32 emcontrol; + u32 stat_port_en; + u32 ptype; /* NU */ + u32 soft_idle; + u32 thru_rate; /* NU */ + u32 gap_thresh; /* NU */ + u32 tx_start_wds; /* NU */ + u32 eee_prescale; /* 2U */ + u32 tx_g_oflow_thresh_set; /* NU */ + u32 tx_g_oflow_thresh_clr; /* NU */ + u32 tx_g_buf_thresh_set_l; /* NU */ + u32 tx_g_buf_thresh_set_h; /* NU */ + u32 tx_g_buf_thresh_clr_l; /* NU */ + u32 tx_g_buf_thresh_clr_h; /* NU */ +}; + +struct gbenu_port_regs { + u32 __rsvd_0; + u32 control; + u32 max_blks; /* 2U */ + u32 mem_align1; + u32 blk_cnt; + u32 port_vlan; + u32 tx_pri_map; /* NU */ + u32 pri_ctl; /* 2U */ + u32 rx_pri_map; + u32 rx_maxlen; + u32 tx_blks_pri; /* NU */ + u32 __rsvd_1; + u32 idle2lpi; /* 2U */ + u32 lpi2idle; /* 2U */ + u32 eee_status; /* 2U */ + u32 __rsvd_2; + u32 __rsvd_3[176]; /* NU: more to add */ + u32 __rsvd_4[2]; + u32 sa_lo; + u32 sa_hi; + u32 ts_ctl; + u32 ts_seq_ltype; + u32 ts_vlan; + u32 ts_ctl_ltype2; + u32 ts_ctl2; +}; + +struct gbenu_host_port_regs { + u32 __rsvd_0; + u32 control; + u32 flow_id_offset; /* 2U */ + u32 __rsvd_1; + u32 blk_cnt; + u32 port_vlan; + u32 tx_pri_map; /* NU */ + u32 pri_ctl; + u32 rx_pri_map; + u32 rx_maxlen; + u32 tx_blks_pri; /* NU */ + u32 __rsvd_2; + u32 idle2lpi; /* 2U */ + u32 lpi2wake; /* 2U */ + u32 eee_status; /* 2U */ + u32 __rsvd_3; + u32 __rsvd_4[184]; /* NU */ + u32 host_blks_pri; /* NU */ +}; + +struct gbenu_emac_regs { + u32 mac_control; + u32 mac_status; + u32 soft_reset; + u32 boff_test; + u32 rx_pause; + u32 __rsvd_0[11]; /* NU */ + u32 tx_pause; + u32 __rsvd_1[11]; /* NU */ + u32 em_control; + u32 tx_gap; +}; + +/* Some hw stat regs are applicable to slave port only. + * This is handled by gbenu_et_stats struct. Also some + * are for SS version NU and some are for 2U. + */ +struct gbenu_hw_stats { + u32 rx_good_frames; + u32 rx_broadcast_frames; + u32 rx_multicast_frames; + u32 rx_pause_frames; /* slave */ + u32 rx_crc_errors; + u32 rx_align_code_errors; /* slave */ + u32 rx_oversized_frames; + u32 rx_jabber_frames; /* slave */ + u32 rx_undersized_frames; + u32 rx_fragments; /* slave */ + u32 ale_drop; + u32 ale_overrun_drop; + u32 rx_bytes; + u32 tx_good_frames; + u32 tx_broadcast_frames; + u32 tx_multicast_frames; + u32 tx_pause_frames; /* slave */ + u32 tx_deferred_frames; /* slave */ + u32 tx_collision_frames; /* slave */ + u32 tx_single_coll_frames; /* slave */ + u32 tx_mult_coll_frames; /* slave */ + u32 tx_excessive_collisions; /* slave */ + u32 tx_late_collisions; /* slave */ + u32 rx_ipg_error; /* slave 10G only */ + u32 tx_carrier_sense_errors; /* slave */ + u32 tx_bytes; + u32 tx_64B_frames; + u32 tx_65_to_127B_frames; + u32 tx_128_to_255B_frames; + u32 tx_256_to_511B_frames; + u32 tx_512_to_1023B_frames; + u32 tx_1024B_frames; + u32 net_bytes; + u32 rx_bottom_fifo_drop; + u32 rx_port_mask_drop; + u32 rx_top_fifo_drop; + u32 ale_rate_limit_drop; + u32 ale_vid_ingress_drop; + u32 ale_da_eq_sa_drop; + u32 __rsvd_0[3]; + u32 ale_unknown_ucast; + u32 ale_unknown_ucast_bytes; + u32 ale_unknown_mcast; + u32 ale_unknown_mcast_bytes; + u32 ale_unknown_bcast; + u32 ale_unknown_bcast_bytes; + u32 ale_pol_match; + u32 ale_pol_match_red; /* NU */ + u32 ale_pol_match_yellow; /* NU */ + u32 __rsvd_1[44]; + u32 tx_mem_protect_err; + /* following NU only */ + u32 tx_pri0; + u32 tx_pri1; + u32 tx_pri2; + u32 tx_pri3; + u32 tx_pri4; + u32 tx_pri5; + u32 tx_pri6; + u32 tx_pri7; + u32 tx_pri0_bcnt; + u32 tx_pri1_bcnt; + u32 tx_pri2_bcnt; + u32 tx_pri3_bcnt; + u32 tx_pri4_bcnt; + u32 tx_pri5_bcnt; + u32 tx_pri6_bcnt; + u32 tx_pri7_bcnt; + u32 tx_pri0_drop; + u32 tx_pri1_drop; + u32 tx_pri2_drop; + u32 tx_pri3_drop; + u32 tx_pri4_drop; + u32 tx_pri5_drop; + u32 tx_pri6_drop; + u32 tx_pri7_drop; + u32 tx_pri0_drop_bcnt; + u32 tx_pri1_drop_bcnt; + u32 tx_pri2_drop_bcnt; + u32 tx_pri3_drop_bcnt; + u32 tx_pri4_drop_bcnt; + u32 tx_pri5_drop_bcnt; + u32 tx_pri6_drop_bcnt; + u32 tx_pri7_drop_bcnt; +}; + +#define GBENU_NUM_HW_STAT_ENTRIES (sizeof(struct gbenu_hw_stats) / sizeof(u32)) +#define GBENU_HW_STATS_REG_MAP_SZ 0x200 + struct gbe_ss_regs { u32 id_ver; u32 synce_count; @@ -316,6 +541,7 @@ struct gbe_port_regs_ofs { u16 ts_vlan; u16 ts_ctl_ltype2; u16 ts_ctl2; + u16 rx_maxlen; /* 2U, NU */ }; struct gbe_host_port_regs { @@ -390,9 +616,7 @@ struct gbe_hw_stats { }; #define GBE13_NUM_HW_STAT_ENTRIES (sizeof(struct gbe_hw_stats)/sizeof(u32)) -#define GBE13_NUM_HW_STATS_MOD 2 -#define XGBE10_NUM_HW_STATS_MOD 3 -#define GBE_MAX_HW_STAT_MODS 3 +#define GBE_MAX_HW_STAT_MODS 9 #define GBE_HW_STATS_REG_MAP_SZ 0x100 struct gbe_slave { @@ -420,11 +644,14 @@ struct gbe_priv { u32 ale_entries; u32 ale_ports; bool enable_ale; + u8 max_num_slaves; + u8 max_num_ports; /* max_num_slaves + 1 */ struct netcp_tx_pipe tx_pipe; int host_port; u32 rx_packet_max; u32 ss_version; + u32 stats_en_mask; void __iomem *ss_regs; void __iomem *switch_regs; @@ -475,275 +702,778 @@ struct netcp_ethtool_stat { int offset; }; -#define GBE_STATSA_INFO(field) "GBE_A:"#field, GBE_STATSA_MODULE,\ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ - offsetof(struct gbe_hw_stats, field) +#define GBE_STATSA_INFO(field) \ +{ \ + "GBE_A:"#field, GBE_STATSA_MODULE, \ + FIELD_SIZEOF(struct gbe_hw_stats, field), \ + offsetof(struct gbe_hw_stats, field) \ +} -#define GBE_STATSB_INFO(field) "GBE_B:"#field, GBE_STATSB_MODULE,\ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ - offsetof(struct gbe_hw_stats, field) +#define GBE_STATSB_INFO(field) \ +{ \ + "GBE_B:"#field, GBE_STATSB_MODULE, \ + FIELD_SIZEOF(struct gbe_hw_stats, field), \ + offsetof(struct gbe_hw_stats, field) \ +} -#define GBE_STATSC_INFO(field) "GBE_C:"#field, GBE_STATSC_MODULE,\ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ - offsetof(struct gbe_hw_stats, field) +#define GBE_STATSC_INFO(field) \ +{ \ + "GBE_C:"#field, GBE_STATSC_MODULE, \ + FIELD_SIZEOF(struct gbe_hw_stats, field), \ + offsetof(struct gbe_hw_stats, field) \ +} -#define GBE_STATSD_INFO(field) "GBE_D:"#field, GBE_STATSD_MODULE,\ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ - offsetof(struct gbe_hw_stats, field) +#define GBE_STATSD_INFO(field) \ +{ \ + "GBE_D:"#field, GBE_STATSD_MODULE, \ + FIELD_SIZEOF(struct gbe_hw_stats, field), \ + offsetof(struct gbe_hw_stats, field) \ +} static const struct netcp_ethtool_stat gbe13_et_stats[] = { /* GBE module A */ - {GBE_STATSA_INFO(rx_good_frames)}, - {GBE_STATSA_INFO(rx_broadcast_frames)}, - {GBE_STATSA_INFO(rx_multicast_frames)}, - {GBE_STATSA_INFO(rx_pause_frames)}, - {GBE_STATSA_INFO(rx_crc_errors)}, - {GBE_STATSA_INFO(rx_align_code_errors)}, - {GBE_STATSA_INFO(rx_oversized_frames)}, - {GBE_STATSA_INFO(rx_jabber_frames)}, - {GBE_STATSA_INFO(rx_undersized_frames)}, - {GBE_STATSA_INFO(rx_fragments)}, - {GBE_STATSA_INFO(rx_bytes)}, - {GBE_STATSA_INFO(tx_good_frames)}, - {GBE_STATSA_INFO(tx_broadcast_frames)}, - {GBE_STATSA_INFO(tx_multicast_frames)}, - {GBE_STATSA_INFO(tx_pause_frames)}, - {GBE_STATSA_INFO(tx_deferred_frames)}, - {GBE_STATSA_INFO(tx_collision_frames)}, - {GBE_STATSA_INFO(tx_single_coll_frames)}, - {GBE_STATSA_INFO(tx_mult_coll_frames)}, - {GBE_STATSA_INFO(tx_excessive_collisions)}, - {GBE_STATSA_INFO(tx_late_collisions)}, - {GBE_STATSA_INFO(tx_underrun)}, - {GBE_STATSA_INFO(tx_carrier_sense_errors)}, - {GBE_STATSA_INFO(tx_bytes)}, - {GBE_STATSA_INFO(tx_64byte_frames)}, - {GBE_STATSA_INFO(tx_65_to_127byte_frames)}, - {GBE_STATSA_INFO(tx_128_to_255byte_frames)}, - {GBE_STATSA_INFO(tx_256_to_511byte_frames)}, - {GBE_STATSA_INFO(tx_512_to_1023byte_frames)}, - {GBE_STATSA_INFO(tx_1024byte_frames)}, - {GBE_STATSA_INFO(net_bytes)}, - {GBE_STATSA_INFO(rx_sof_overruns)}, - {GBE_STATSA_INFO(rx_mof_overruns)}, - {GBE_STATSA_INFO(rx_dma_overruns)}, + GBE_STATSA_INFO(rx_good_frames), + GBE_STATSA_INFO(rx_broadcast_frames), + GBE_STATSA_INFO(rx_multicast_frames), + GBE_STATSA_INFO(rx_pause_frames), + GBE_STATSA_INFO(rx_crc_errors), + GBE_STATSA_INFO(rx_align_code_errors), + GBE_STATSA_INFO(rx_oversized_frames), + GBE_STATSA_INFO(rx_jabber_frames), + GBE_STATSA_INFO(rx_undersized_frames), + GBE_STATSA_INFO(rx_fragments), + GBE_STATSA_INFO(rx_bytes), + GBE_STATSA_INFO(tx_good_frames), + GBE_STATSA_INFO(tx_broadcast_frames), + GBE_STATSA_INFO(tx_multicast_frames), + GBE_STATSA_INFO(tx_pause_frames), + GBE_STATSA_INFO(tx_deferred_frames), + GBE_STATSA_INFO(tx_collision_frames), + GBE_STATSA_INFO(tx_single_coll_frames), + GBE_STATSA_INFO(tx_mult_coll_frames), + GBE_STATSA_INFO(tx_excessive_collisions), + GBE_STATSA_INFO(tx_late_collisions), + GBE_STATSA_INFO(tx_underrun), + GBE_STATSA_INFO(tx_carrier_sense_errors), + GBE_STATSA_INFO(tx_bytes), + GBE_STATSA_INFO(tx_64byte_frames), + GBE_STATSA_INFO(tx_65_to_127byte_frames), + GBE_STATSA_INFO(tx_128_to_255byte_frames), + GBE_STATSA_INFO(tx_256_to_511byte_frames), + GBE_STATSA_INFO(tx_512_to_1023byte_frames), + GBE_STATSA_INFO(tx_1024byte_frames), + GBE_STATSA_INFO(net_bytes), + GBE_STATSA_INFO(rx_sof_overruns), + GBE_STATSA_INFO(rx_mof_overruns), + GBE_STATSA_INFO(rx_dma_overruns), /* GBE module B */ - {GBE_STATSB_INFO(rx_good_frames)}, - {GBE_STATSB_INFO(rx_broadcast_frames)}, - {GBE_STATSB_INFO(rx_multicast_frames)}, - {GBE_STATSB_INFO(rx_pause_frames)}, - {GBE_STATSB_INFO(rx_crc_errors)}, - {GBE_STATSB_INFO(rx_align_code_errors)}, - {GBE_STATSB_INFO(rx_oversized_frames)}, - {GBE_STATSB_INFO(rx_jabber_frames)}, - {GBE_STATSB_INFO(rx_undersized_frames)}, - {GBE_STATSB_INFO(rx_fragments)}, - {GBE_STATSB_INFO(rx_bytes)}, - {GBE_STATSB_INFO(tx_good_frames)}, - {GBE_STATSB_INFO(tx_broadcast_frames)}, - {GBE_STATSB_INFO(tx_multicast_frames)}, - {GBE_STATSB_INFO(tx_pause_frames)}, - {GBE_STATSB_INFO(tx_deferred_frames)}, - {GBE_STATSB_INFO(tx_collision_frames)}, - {GBE_STATSB_INFO(tx_single_coll_frames)}, - {GBE_STATSB_INFO(tx_mult_coll_frames)}, - {GBE_STATSB_INFO(tx_excessive_collisions)}, - {GBE_STATSB_INFO(tx_late_collisions)}, - {GBE_STATSB_INFO(tx_underrun)}, - {GBE_STATSB_INFO(tx_carrier_sense_errors)}, - {GBE_STATSB_INFO(tx_bytes)}, - {GBE_STATSB_INFO(tx_64byte_frames)}, - {GBE_STATSB_INFO(tx_65_to_127byte_frames)}, - {GBE_STATSB_INFO(tx_128_to_255byte_frames)}, - {GBE_STATSB_INFO(tx_256_to_511byte_frames)}, - {GBE_STATSB_INFO(tx_512_to_1023byte_frames)}, - {GBE_STATSB_INFO(tx_1024byte_frames)}, - {GBE_STATSB_INFO(net_bytes)}, - {GBE_STATSB_INFO(rx_sof_overruns)}, - {GBE_STATSB_INFO(rx_mof_overruns)}, - {GBE_STATSB_INFO(rx_dma_overruns)}, + GBE_STATSB_INFO(rx_good_frames), + GBE_STATSB_INFO(rx_broadcast_frames), + GBE_STATSB_INFO(rx_multicast_frames), + GBE_STATSB_INFO(rx_pause_frames), + GBE_STATSB_INFO(rx_crc_errors), + GBE_STATSB_INFO(rx_align_code_errors), + GBE_STATSB_INFO(rx_oversized_frames), + GBE_STATSB_INFO(rx_jabber_frames), + GBE_STATSB_INFO(rx_undersized_frames), + GBE_STATSB_INFO(rx_fragments), + GBE_STATSB_INFO(rx_bytes), + GBE_STATSB_INFO(tx_good_frames), + GBE_STATSB_INFO(tx_broadcast_frames), + GBE_STATSB_INFO(tx_multicast_frames), + GBE_STATSB_INFO(tx_pause_frames), + GBE_STATSB_INFO(tx_deferred_frames), + GBE_STATSB_INFO(tx_collision_frames), + GBE_STATSB_INFO(tx_single_coll_frames), + GBE_STATSB_INFO(tx_mult_coll_frames), + GBE_STATSB_INFO(tx_excessive_collisions), + GBE_STATSB_INFO(tx_late_collisions), + GBE_STATSB_INFO(tx_underrun), + GBE_STATSB_INFO(tx_carrier_sense_errors), + GBE_STATSB_INFO(tx_bytes), + GBE_STATSB_INFO(tx_64byte_frames), + GBE_STATSB_INFO(tx_65_to_127byte_frames), + GBE_STATSB_INFO(tx_128_to_255byte_frames), + GBE_STATSB_INFO(tx_256_to_511byte_frames), + GBE_STATSB_INFO(tx_512_to_1023byte_frames), + GBE_STATSB_INFO(tx_1024byte_frames), + GBE_STATSB_INFO(net_bytes), + GBE_STATSB_INFO(rx_sof_overruns), + GBE_STATSB_INFO(rx_mof_overruns), + GBE_STATSB_INFO(rx_dma_overruns), /* GBE module C */ - {GBE_STATSC_INFO(rx_good_frames)}, - {GBE_STATSC_INFO(rx_broadcast_frames)}, - {GBE_STATSC_INFO(rx_multicast_frames)}, - {GBE_STATSC_INFO(rx_pause_frames)}, - {GBE_STATSC_INFO(rx_crc_errors)}, - {GBE_STATSC_INFO(rx_align_code_errors)}, - {GBE_STATSC_INFO(rx_oversized_frames)}, - {GBE_STATSC_INFO(rx_jabber_frames)}, - {GBE_STATSC_INFO(rx_undersized_frames)}, - {GBE_STATSC_INFO(rx_fragments)}, - {GBE_STATSC_INFO(rx_bytes)}, - {GBE_STATSC_INFO(tx_good_frames)}, - {GBE_STATSC_INFO(tx_broadcast_frames)}, - {GBE_STATSC_INFO(tx_multicast_frames)}, - {GBE_STATSC_INFO(tx_pause_frames)}, - {GBE_STATSC_INFO(tx_deferred_frames)}, - {GBE_STATSC_INFO(tx_collision_frames)}, - {GBE_STATSC_INFO(tx_single_coll_frames)}, - {GBE_STATSC_INFO(tx_mult_coll_frames)}, - {GBE_STATSC_INFO(tx_excessive_collisions)}, - {GBE_STATSC_INFO(tx_late_collisions)}, - {GBE_STATSC_INFO(tx_underrun)}, - {GBE_STATSC_INFO(tx_carrier_sense_errors)}, - {GBE_STATSC_INFO(tx_bytes)}, - {GBE_STATSC_INFO(tx_64byte_frames)}, - {GBE_STATSC_INFO(tx_65_to_127byte_frames)}, - {GBE_STATSC_INFO(tx_128_to_255byte_frames)}, - {GBE_STATSC_INFO(tx_256_to_511byte_frames)}, - {GBE_STATSC_INFO(tx_512_to_1023byte_frames)}, - {GBE_STATSC_INFO(tx_1024byte_frames)}, - {GBE_STATSC_INFO(net_bytes)}, - {GBE_STATSC_INFO(rx_sof_overruns)}, - {GBE_STATSC_INFO(rx_mof_overruns)}, - {GBE_STATSC_INFO(rx_dma_overruns)}, + GBE_STATSC_INFO(rx_good_frames), + GBE_STATSC_INFO(rx_broadcast_frames), + GBE_STATSC_INFO(rx_multicast_frames), + GBE_STATSC_INFO(rx_pause_frames), + GBE_STATSC_INFO(rx_crc_errors), + GBE_STATSC_INFO(rx_align_code_errors), + GBE_STATSC_INFO(rx_oversized_frames), + GBE_STATSC_INFO(rx_jabber_frames), + GBE_STATSC_INFO(rx_undersized_frames), + GBE_STATSC_INFO(rx_fragments), + GBE_STATSC_INFO(rx_bytes), + GBE_STATSC_INFO(tx_good_frames), + GBE_STATSC_INFO(tx_broadcast_frames), + GBE_STATSC_INFO(tx_multicast_frames), + GBE_STATSC_INFO(tx_pause_frames), + GBE_STATSC_INFO(tx_deferred_frames), + GBE_STATSC_INFO(tx_collision_frames), + GBE_STATSC_INFO(tx_single_coll_frames), + GBE_STATSC_INFO(tx_mult_coll_frames), + GBE_STATSC_INFO(tx_excessive_collisions), + GBE_STATSC_INFO(tx_late_collisions), + GBE_STATSC_INFO(tx_underrun), + GBE_STATSC_INFO(tx_carrier_sense_errors), + GBE_STATSC_INFO(tx_bytes), + GBE_STATSC_INFO(tx_64byte_frames), + GBE_STATSC_INFO(tx_65_to_127byte_frames), + GBE_STATSC_INFO(tx_128_to_255byte_frames), + GBE_STATSC_INFO(tx_256_to_511byte_frames), + GBE_STATSC_INFO(tx_512_to_1023byte_frames), + GBE_STATSC_INFO(tx_1024byte_frames), + GBE_STATSC_INFO(net_bytes), + GBE_STATSC_INFO(rx_sof_overruns), + GBE_STATSC_INFO(rx_mof_overruns), + GBE_STATSC_INFO(rx_dma_overruns), /* GBE module D */ - {GBE_STATSD_INFO(rx_good_frames)}, - {GBE_STATSD_INFO(rx_broadcast_frames)}, - {GBE_STATSD_INFO(rx_multicast_frames)}, - {GBE_STATSD_INFO(rx_pause_frames)}, - {GBE_STATSD_INFO(rx_crc_errors)}, - {GBE_STATSD_INFO(rx_align_code_errors)}, - {GBE_STATSD_INFO(rx_oversized_frames)}, - {GBE_STATSD_INFO(rx_jabber_frames)}, - {GBE_STATSD_INFO(rx_undersized_frames)}, - {GBE_STATSD_INFO(rx_fragments)}, - {GBE_STATSD_INFO(rx_bytes)}, - {GBE_STATSD_INFO(tx_good_frames)}, - {GBE_STATSD_INFO(tx_broadcast_frames)}, - {GBE_STATSD_INFO(tx_multicast_frames)}, - {GBE_STATSD_INFO(tx_pause_frames)}, - {GBE_STATSD_INFO(tx_deferred_frames)}, - {GBE_STATSD_INFO(tx_collision_frames)}, - {GBE_STATSD_INFO(tx_single_coll_frames)}, - {GBE_STATSD_INFO(tx_mult_coll_frames)}, - {GBE_STATSD_INFO(tx_excessive_collisions)}, - {GBE_STATSD_INFO(tx_late_collisions)}, - {GBE_STATSD_INFO(tx_underrun)}, - {GBE_STATSD_INFO(tx_carrier_sense_errors)}, - {GBE_STATSD_INFO(tx_bytes)}, - {GBE_STATSD_INFO(tx_64byte_frames)}, - {GBE_STATSD_INFO(tx_65_to_127byte_frames)}, - {GBE_STATSD_INFO(tx_128_to_255byte_frames)}, - {GBE_STATSD_INFO(tx_256_to_511byte_frames)}, - {GBE_STATSD_INFO(tx_512_to_1023byte_frames)}, - {GBE_STATSD_INFO(tx_1024byte_frames)}, - {GBE_STATSD_INFO(net_bytes)}, - {GBE_STATSD_INFO(rx_sof_overruns)}, - {GBE_STATSD_INFO(rx_mof_overruns)}, - {GBE_STATSD_INFO(rx_dma_overruns)}, + GBE_STATSD_INFO(rx_good_frames), + GBE_STATSD_INFO(rx_broadcast_frames), + GBE_STATSD_INFO(rx_multicast_frames), + GBE_STATSD_INFO(rx_pause_frames), + GBE_STATSD_INFO(rx_crc_errors), + GBE_STATSD_INFO(rx_align_code_errors), + GBE_STATSD_INFO(rx_oversized_frames), + GBE_STATSD_INFO(rx_jabber_frames), + GBE_STATSD_INFO(rx_undersized_frames), + GBE_STATSD_INFO(rx_fragments), + GBE_STATSD_INFO(rx_bytes), + GBE_STATSD_INFO(tx_good_frames), + GBE_STATSD_INFO(tx_broadcast_frames), + GBE_STATSD_INFO(tx_multicast_frames), + GBE_STATSD_INFO(tx_pause_frames), + GBE_STATSD_INFO(tx_deferred_frames), + GBE_STATSD_INFO(tx_collision_frames), + GBE_STATSD_INFO(tx_single_coll_frames), + GBE_STATSD_INFO(tx_mult_coll_frames), + GBE_STATSD_INFO(tx_excessive_collisions), + GBE_STATSD_INFO(tx_late_collisions), + GBE_STATSD_INFO(tx_underrun), + GBE_STATSD_INFO(tx_carrier_sense_errors), + GBE_STATSD_INFO(tx_bytes), + GBE_STATSD_INFO(tx_64byte_frames), + GBE_STATSD_INFO(tx_65_to_127byte_frames), + GBE_STATSD_INFO(tx_128_to_255byte_frames), + GBE_STATSD_INFO(tx_256_to_511byte_frames), + GBE_STATSD_INFO(tx_512_to_1023byte_frames), + GBE_STATSD_INFO(tx_1024byte_frames), + GBE_STATSD_INFO(net_bytes), + GBE_STATSD_INFO(rx_sof_overruns), + GBE_STATSD_INFO(rx_mof_overruns), + GBE_STATSD_INFO(rx_dma_overruns), }; -#define XGBE_STATS0_INFO(field) "GBE_0:"#field, XGBE_STATS0_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ - offsetof(struct xgbe_hw_stats, field) +/* This is the size of entries in GBENU_STATS_HOST */ +#define GBENU_ET_STATS_HOST_SIZE 33 + +#define GBENU_STATS_HOST(field) \ +{ \ + "GBE_HOST:"#field, GBENU_STATS0_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} -#define XGBE_STATS1_INFO(field) "GBE_1:"#field, XGBE_STATS1_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ - offsetof(struct xgbe_hw_stats, field) +/* This is the size of entries in GBENU_STATS_HOST */ +#define GBENU_ET_STATS_PORT_SIZE 46 -#define XGBE_STATS2_INFO(field) "GBE_2:"#field, XGBE_STATS2_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ - offsetof(struct xgbe_hw_stats, field) +#define GBENU_STATS_P1(field) \ +{ \ + "GBE_P1:"#field, GBENU_STATS1_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +#define GBENU_STATS_P2(field) \ +{ \ + "GBE_P2:"#field, GBENU_STATS2_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +#define GBENU_STATS_P3(field) \ +{ \ + "GBE_P3:"#field, GBENU_STATS3_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +#define GBENU_STATS_P4(field) \ +{ \ + "GBE_P4:"#field, GBENU_STATS4_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +#define GBENU_STATS_P5(field) \ +{ \ + "GBE_P5:"#field, GBENU_STATS5_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +#define GBENU_STATS_P6(field) \ +{ \ + "GBE_P6:"#field, GBENU_STATS6_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +#define GBENU_STATS_P7(field) \ +{ \ + "GBE_P7:"#field, GBENU_STATS7_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +#define GBENU_STATS_P8(field) \ +{ \ + "GBE_P8:"#field, GBENU_STATS8_MODULE, \ + FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + offsetof(struct gbenu_hw_stats, field) \ +} + +static const struct netcp_ethtool_stat gbenu_et_stats[] = { + /* GBENU Host Module */ + GBENU_STATS_HOST(rx_good_frames), + GBENU_STATS_HOST(rx_broadcast_frames), + GBENU_STATS_HOST(rx_multicast_frames), + GBENU_STATS_HOST(rx_crc_errors), + GBENU_STATS_HOST(rx_oversized_frames), + GBENU_STATS_HOST(rx_undersized_frames), + GBENU_STATS_HOST(ale_drop), + GBENU_STATS_HOST(ale_overrun_drop), + GBENU_STATS_HOST(rx_bytes), + GBENU_STATS_HOST(tx_good_frames), + GBENU_STATS_HOST(tx_broadcast_frames), + GBENU_STATS_HOST(tx_multicast_frames), + GBENU_STATS_HOST(tx_bytes), + GBENU_STATS_HOST(tx_64B_frames), + GBENU_STATS_HOST(tx_65_to_127B_frames), + GBENU_STATS_HOST(tx_128_to_255B_frames), + GBENU_STATS_HOST(tx_256_to_511B_frames), + GBENU_STATS_HOST(tx_512_to_1023B_frames), + GBENU_STATS_HOST(tx_1024B_frames), + GBENU_STATS_HOST(net_bytes), + GBENU_STATS_HOST(rx_bottom_fifo_drop), + GBENU_STATS_HOST(rx_port_mask_drop), + GBENU_STATS_HOST(rx_top_fifo_drop), + GBENU_STATS_HOST(ale_rate_limit_drop), + GBENU_STATS_HOST(ale_vid_ingress_drop), + GBENU_STATS_HOST(ale_da_eq_sa_drop), + GBENU_STATS_HOST(ale_unknown_ucast), + GBENU_STATS_HOST(ale_unknown_ucast_bytes), + GBENU_STATS_HOST(ale_unknown_mcast), + GBENU_STATS_HOST(ale_unknown_mcast_bytes), + GBENU_STATS_HOST(ale_unknown_bcast), + GBENU_STATS_HOST(ale_unknown_bcast_bytes), + GBENU_STATS_HOST(tx_mem_protect_err), + /* GBENU Module 1 */ + GBENU_STATS_P1(rx_good_frames), + GBENU_STATS_P1(rx_broadcast_frames), + GBENU_STATS_P1(rx_multicast_frames), + GBENU_STATS_P1(rx_pause_frames), + GBENU_STATS_P1(rx_crc_errors), + GBENU_STATS_P1(rx_align_code_errors), + GBENU_STATS_P1(rx_oversized_frames), + GBENU_STATS_P1(rx_jabber_frames), + GBENU_STATS_P1(rx_undersized_frames), + GBENU_STATS_P1(rx_fragments), + GBENU_STATS_P1(ale_drop), + GBENU_STATS_P1(ale_overrun_drop), + GBENU_STATS_P1(rx_bytes), + GBENU_STATS_P1(tx_good_frames), + GBENU_STATS_P1(tx_broadcast_frames), + GBENU_STATS_P1(tx_multicast_frames), + GBENU_STATS_P1(tx_pause_frames), + GBENU_STATS_P1(tx_deferred_frames), + GBENU_STATS_P1(tx_collision_frames), + GBENU_STATS_P1(tx_single_coll_frames), + GBENU_STATS_P1(tx_mult_coll_frames), + GBENU_STATS_P1(tx_excessive_collisions), + GBENU_STATS_P1(tx_late_collisions), + GBENU_STATS_P1(rx_ipg_error), + GBENU_STATS_P1(tx_carrier_sense_errors), + GBENU_STATS_P1(tx_bytes), + GBENU_STATS_P1(tx_64B_frames), + GBENU_STATS_P1(tx_65_to_127B_frames), + GBENU_STATS_P1(tx_128_to_255B_frames), + GBENU_STATS_P1(tx_256_to_511B_frames), + GBENU_STATS_P1(tx_512_to_1023B_frames), + GBENU_STATS_P1(tx_1024B_frames), + GBENU_STATS_P1(net_bytes), + GBENU_STATS_P1(rx_bottom_fifo_drop), + GBENU_STATS_P1(rx_port_mask_drop), + GBENU_STATS_P1(rx_top_fifo_drop), + GBENU_STATS_P1(ale_rate_limit_drop), + GBENU_STATS_P1(ale_vid_ingress_drop), + GBENU_STATS_P1(ale_da_eq_sa_drop), + GBENU_STATS_P1(ale_unknown_ucast), + GBENU_STATS_P1(ale_unknown_ucast_bytes), + GBENU_STATS_P1(ale_unknown_mcast), + GBENU_STATS_P1(ale_unknown_mcast_bytes), + GBENU_STATS_P1(ale_unknown_bcast), + GBENU_STATS_P1(ale_unknown_bcast_bytes), + GBENU_STATS_P1(tx_mem_protect_err), + /* GBENU Module 2 */ + GBENU_STATS_P2(rx_good_frames), + GBENU_STATS_P2(rx_broadcast_frames), + GBENU_STATS_P2(rx_multicast_frames), + GBENU_STATS_P2(rx_pause_frames), + GBENU_STATS_P2(rx_crc_errors), + GBENU_STATS_P2(rx_align_code_errors), + GBENU_STATS_P2(rx_oversized_frames), + GBENU_STATS_P2(rx_jabber_frames), + GBENU_STATS_P2(rx_undersized_frames), + GBENU_STATS_P2(rx_fragments), + GBENU_STATS_P2(ale_drop), + GBENU_STATS_P2(ale_overrun_drop), + GBENU_STATS_P2(rx_bytes), + GBENU_STATS_P2(tx_good_frames), + GBENU_STATS_P2(tx_broadcast_frames), + GBENU_STATS_P2(tx_multicast_frames), + GBENU_STATS_P2(tx_pause_frames), + GBENU_STATS_P2(tx_deferred_frames), + GBENU_STATS_P2(tx_collision_frames), + GBENU_STATS_P2(tx_single_coll_frames), + GBENU_STATS_P2(tx_mult_coll_frames), + GBENU_STATS_P2(tx_excessive_collisions), + GBENU_STATS_P2(tx_late_collisions), + GBENU_STATS_P2(rx_ipg_error), + GBENU_STATS_P2(tx_carrier_sense_errors), + GBENU_STATS_P2(tx_bytes), + GBENU_STATS_P2(tx_64B_frames), + GBENU_STATS_P2(tx_65_to_127B_frames), + GBENU_STATS_P2(tx_128_to_255B_frames), + GBENU_STATS_P2(tx_256_to_511B_frames), + GBENU_STATS_P2(tx_512_to_1023B_frames), + GBENU_STATS_P2(tx_1024B_frames), + GBENU_STATS_P2(net_bytes), + GBENU_STATS_P2(rx_bottom_fifo_drop), + GBENU_STATS_P2(rx_port_mask_drop), + GBENU_STATS_P2(rx_top_fifo_drop), + GBENU_STATS_P2(ale_rate_limit_drop), + GBENU_STATS_P2(ale_vid_ingress_drop), + GBENU_STATS_P2(ale_da_eq_sa_drop), + GBENU_STATS_P2(ale_unknown_ucast), + GBENU_STATS_P2(ale_unknown_ucast_bytes), + GBENU_STATS_P2(ale_unknown_mcast), + GBENU_STATS_P2(ale_unknown_mcast_bytes), + GBENU_STATS_P2(ale_unknown_bcast), + GBENU_STATS_P2(ale_unknown_bcast_bytes), + GBENU_STATS_P2(tx_mem_protect_err), + /* GBENU Module 3 */ + GBENU_STATS_P3(rx_good_frames), + GBENU_STATS_P3(rx_broadcast_frames), + GBENU_STATS_P3(rx_multicast_frames), + GBENU_STATS_P3(rx_pause_frames), + GBENU_STATS_P3(rx_crc_errors), + GBENU_STATS_P3(rx_align_code_errors), + GBENU_STATS_P3(rx_oversized_frames), + GBENU_STATS_P3(rx_jabber_frames), + GBENU_STATS_P3(rx_undersized_frames), + GBENU_STATS_P3(rx_fragments), + GBENU_STATS_P3(ale_drop), + GBENU_STATS_P3(ale_overrun_drop), + GBENU_STATS_P3(rx_bytes), + GBENU_STATS_P3(tx_good_frames), + GBENU_STATS_P3(tx_broadcast_frames), + GBENU_STATS_P3(tx_multicast_frames), + GBENU_STATS_P3(tx_pause_frames), + GBENU_STATS_P3(tx_deferred_frames), + GBENU_STATS_P3(tx_collision_frames), + GBENU_STATS_P3(tx_single_coll_frames), + GBENU_STATS_P3(tx_mult_coll_frames), + GBENU_STATS_P3(tx_excessive_collisions), + GBENU_STATS_P3(tx_late_collisions), + GBENU_STATS_P3(rx_ipg_error), + GBENU_STATS_P3(tx_carrier_sense_errors), + GBENU_STATS_P3(tx_bytes), + GBENU_STATS_P3(tx_64B_frames), + GBENU_STATS_P3(tx_65_to_127B_frames), + GBENU_STATS_P3(tx_128_to_255B_frames), + GBENU_STATS_P3(tx_256_to_511B_frames), + GBENU_STATS_P3(tx_512_to_1023B_frames), + GBENU_STATS_P3(tx_1024B_frames), + GBENU_STATS_P3(net_bytes), + GBENU_STATS_P3(rx_bottom_fifo_drop), + GBENU_STATS_P3(rx_port_mask_drop), + GBENU_STATS_P3(rx_top_fifo_drop), + GBENU_STATS_P3(ale_rate_limit_drop), + GBENU_STATS_P3(ale_vid_ingress_drop), + GBENU_STATS_P3(ale_da_eq_sa_drop), + GBENU_STATS_P3(ale_unknown_ucast), + GBENU_STATS_P3(ale_unknown_ucast_bytes), + GBENU_STATS_P3(ale_unknown_mcast), + GBENU_STATS_P3(ale_unknown_mcast_bytes), + GBENU_STATS_P3(ale_unknown_bcast), + GBENU_STATS_P3(ale_unknown_bcast_bytes), + GBENU_STATS_P3(tx_mem_protect_err), + /* GBENU Module 4 */ + GBENU_STATS_P4(rx_good_frames), + GBENU_STATS_P4(rx_broadcast_frames), + GBENU_STATS_P4(rx_multicast_frames), + GBENU_STATS_P4(rx_pause_frames), + GBENU_STATS_P4(rx_crc_errors), + GBENU_STATS_P4(rx_align_code_errors), + GBENU_STATS_P4(rx_oversized_frames), + GBENU_STATS_P4(rx_jabber_frames), + GBENU_STATS_P4(rx_undersized_frames), + GBENU_STATS_P4(rx_fragments), + GBENU_STATS_P4(ale_drop), + GBENU_STATS_P4(ale_overrun_drop), + GBENU_STATS_P4(rx_bytes), + GBENU_STATS_P4(tx_good_frames), + GBENU_STATS_P4(tx_broadcast_frames), + GBENU_STATS_P4(tx_multicast_frames), + GBENU_STATS_P4(tx_pause_frames), + GBENU_STATS_P4(tx_deferred_frames), + GBENU_STATS_P4(tx_collision_frames), + GBENU_STATS_P4(tx_single_coll_frames), + GBENU_STATS_P4(tx_mult_coll_frames), + GBENU_STATS_P4(tx_excessive_collisions), + GBENU_STATS_P4(tx_late_collisions), + GBENU_STATS_P4(rx_ipg_error), + GBENU_STATS_P4(tx_carrier_sense_errors), + GBENU_STATS_P4(tx_bytes), + GBENU_STATS_P4(tx_64B_frames), + GBENU_STATS_P4(tx_65_to_127B_frames), + GBENU_STATS_P4(tx_128_to_255B_frames), + GBENU_STATS_P4(tx_256_to_511B_frames), + GBENU_STATS_P4(tx_512_to_1023B_frames), + GBENU_STATS_P4(tx_1024B_frames), + GBENU_STATS_P4(net_bytes), + GBENU_STATS_P4(rx_bottom_fifo_drop), + GBENU_STATS_P4(rx_port_mask_drop), + GBENU_STATS_P4(rx_top_fifo_drop), + GBENU_STATS_P4(ale_rate_limit_drop), + GBENU_STATS_P4(ale_vid_ingress_drop), + GBENU_STATS_P4(ale_da_eq_sa_drop), + GBENU_STATS_P4(ale_unknown_ucast), + GBENU_STATS_P4(ale_unknown_ucast_bytes), + GBENU_STATS_P4(ale_unknown_mcast), + GBENU_STATS_P4(ale_unknown_mcast_bytes), + GBENU_STATS_P4(ale_unknown_bcast), + GBENU_STATS_P4(ale_unknown_bcast_bytes), + GBENU_STATS_P4(tx_mem_protect_err), + /* GBENU Module 5 */ + GBENU_STATS_P5(rx_good_frames), + GBENU_STATS_P5(rx_broadcast_frames), + GBENU_STATS_P5(rx_multicast_frames), + GBENU_STATS_P5(rx_pause_frames), + GBENU_STATS_P5(rx_crc_errors), + GBENU_STATS_P5(rx_align_code_errors), + GBENU_STATS_P5(rx_oversized_frames), + GBENU_STATS_P5(rx_jabber_frames), + GBENU_STATS_P5(rx_undersized_frames), + GBENU_STATS_P5(rx_fragments), + GBENU_STATS_P5(ale_drop), + GBENU_STATS_P5(ale_overrun_drop), + GBENU_STATS_P5(rx_bytes), + GBENU_STATS_P5(tx_good_frames), + GBENU_STATS_P5(tx_broadcast_frames), + GBENU_STATS_P5(tx_multicast_frames), + GBENU_STATS_P5(tx_pause_frames), + GBENU_STATS_P5(tx_deferred_frames), + GBENU_STATS_P5(tx_collision_frames), + GBENU_STATS_P5(tx_single_coll_frames), + GBENU_STATS_P5(tx_mult_coll_frames), + GBENU_STATS_P5(tx_excessive_collisions), + GBENU_STATS_P5(tx_late_collisions), + GBENU_STATS_P5(rx_ipg_error), + GBENU_STATS_P5(tx_carrier_sense_errors), + GBENU_STATS_P5(tx_bytes), + GBENU_STATS_P5(tx_64B_frames), + GBENU_STATS_P5(tx_65_to_127B_frames), + GBENU_STATS_P5(tx_128_to_255B_frames), + GBENU_STATS_P5(tx_256_to_511B_frames), + GBENU_STATS_P5(tx_512_to_1023B_frames), + GBENU_STATS_P5(tx_1024B_frames), + GBENU_STATS_P5(net_bytes), + GBENU_STATS_P5(rx_bottom_fifo_drop), + GBENU_STATS_P5(rx_port_mask_drop), + GBENU_STATS_P5(rx_top_fifo_drop), + GBENU_STATS_P5(ale_rate_limit_drop), + GBENU_STATS_P5(ale_vid_ingress_drop), + GBENU_STATS_P5(ale_da_eq_sa_drop), + GBENU_STATS_P5(ale_unknown_ucast), + GBENU_STATS_P5(ale_unknown_ucast_bytes), + GBENU_STATS_P5(ale_unknown_mcast), + GBENU_STATS_P5(ale_unknown_mcast_bytes), + GBENU_STATS_P5(ale_unknown_bcast), + GBENU_STATS_P5(ale_unknown_bcast_bytes), + GBENU_STATS_P5(tx_mem_protect_err), + /* GBENU Module 6 */ + GBENU_STATS_P6(rx_good_frames), + GBENU_STATS_P6(rx_broadcast_frames), + GBENU_STATS_P6(rx_multicast_frames), + GBENU_STATS_P6(rx_pause_frames), + GBENU_STATS_P6(rx_crc_errors), + GBENU_STATS_P6(rx_align_code_errors), + GBENU_STATS_P6(rx_oversized_frames), + GBENU_STATS_P6(rx_jabber_frames), + GBENU_STATS_P6(rx_undersized_frames), + GBENU_STATS_P6(rx_fragments), + GBENU_STATS_P6(ale_drop), + GBENU_STATS_P6(ale_overrun_drop), + GBENU_STATS_P6(rx_bytes), + GBENU_STATS_P6(tx_good_frames), + GBENU_STATS_P6(tx_broadcast_frames), + GBENU_STATS_P6(tx_multicast_frames), + GBENU_STATS_P6(tx_pause_frames), + GBENU_STATS_P6(tx_deferred_frames), + GBENU_STATS_P6(tx_collision_frames), + GBENU_STATS_P6(tx_single_coll_frames), + GBENU_STATS_P6(tx_mult_coll_frames), + GBENU_STATS_P6(tx_excessive_collisions), + GBENU_STATS_P6(tx_late_collisions), + GBENU_STATS_P6(rx_ipg_error), + GBENU_STATS_P6(tx_carrier_sense_errors), + GBENU_STATS_P6(tx_bytes), + GBENU_STATS_P6(tx_64B_frames), + GBENU_STATS_P6(tx_65_to_127B_frames), + GBENU_STATS_P6(tx_128_to_255B_frames), + GBENU_STATS_P6(tx_256_to_511B_frames), + GBENU_STATS_P6(tx_512_to_1023B_frames), + GBENU_STATS_P6(tx_1024B_frames), + GBENU_STATS_P6(net_bytes), + GBENU_STATS_P6(rx_bottom_fifo_drop), + GBENU_STATS_P6(rx_port_mask_drop), + GBENU_STATS_P6(rx_top_fifo_drop), + GBENU_STATS_P6(ale_rate_limit_drop), + GBENU_STATS_P6(ale_vid_ingress_drop), + GBENU_STATS_P6(ale_da_eq_sa_drop), + GBENU_STATS_P6(ale_unknown_ucast), + GBENU_STATS_P6(ale_unknown_ucast_bytes), + GBENU_STATS_P6(ale_unknown_mcast), + GBENU_STATS_P6(ale_unknown_mcast_bytes), + GBENU_STATS_P6(ale_unknown_bcast), + GBENU_STATS_P6(ale_unknown_bcast_bytes), + GBENU_STATS_P6(tx_mem_protect_err), + /* GBENU Module 7 */ + GBENU_STATS_P7(rx_good_frames), + GBENU_STATS_P7(rx_broadcast_frames), + GBENU_STATS_P7(rx_multicast_frames), + GBENU_STATS_P7(rx_pause_frames), + GBENU_STATS_P7(rx_crc_errors), + GBENU_STATS_P7(rx_align_code_errors), + GBENU_STATS_P7(rx_oversized_frames), + GBENU_STATS_P7(rx_jabber_frames), + GBENU_STATS_P7(rx_undersized_frames), + GBENU_STATS_P7(rx_fragments), + GBENU_STATS_P7(ale_drop), + GBENU_STATS_P7(ale_overrun_drop), + GBENU_STATS_P7(rx_bytes), + GBENU_STATS_P7(tx_good_frames), + GBENU_STATS_P7(tx_broadcast_frames), + GBENU_STATS_P7(tx_multicast_frames), + GBENU_STATS_P7(tx_pause_frames), + GBENU_STATS_P7(tx_deferred_frames), + GBENU_STATS_P7(tx_collision_frames), + GBENU_STATS_P7(tx_single_coll_frames), + GBENU_STATS_P7(tx_mult_coll_frames), + GBENU_STATS_P7(tx_excessive_collisions), + GBENU_STATS_P7(tx_late_collisions), + GBENU_STATS_P7(rx_ipg_error), + GBENU_STATS_P7(tx_carrier_sense_errors), + GBENU_STATS_P7(tx_bytes), + GBENU_STATS_P7(tx_64B_frames), + GBENU_STATS_P7(tx_65_to_127B_frames), + GBENU_STATS_P7(tx_128_to_255B_frames), + GBENU_STATS_P7(tx_256_to_511B_frames), + GBENU_STATS_P7(tx_512_to_1023B_frames), + GBENU_STATS_P7(tx_1024B_frames), + GBENU_STATS_P7(net_bytes), + GBENU_STATS_P7(rx_bottom_fifo_drop), + GBENU_STATS_P7(rx_port_mask_drop), + GBENU_STATS_P7(rx_top_fifo_drop), + GBENU_STATS_P7(ale_rate_limit_drop), + GBENU_STATS_P7(ale_vid_ingress_drop), + GBENU_STATS_P7(ale_da_eq_sa_drop), + GBENU_STATS_P7(ale_unknown_ucast), + GBENU_STATS_P7(ale_unknown_ucast_bytes), + GBENU_STATS_P7(ale_unknown_mcast), + GBENU_STATS_P7(ale_unknown_mcast_bytes), + GBENU_STATS_P7(ale_unknown_bcast), + GBENU_STATS_P7(ale_unknown_bcast_bytes), + GBENU_STATS_P7(tx_mem_protect_err), + /* GBENU Module 8 */ + GBENU_STATS_P8(rx_good_frames), + GBENU_STATS_P8(rx_broadcast_frames), + GBENU_STATS_P8(rx_multicast_frames), + GBENU_STATS_P8(rx_pause_frames), + GBENU_STATS_P8(rx_crc_errors), + GBENU_STATS_P8(rx_align_code_errors), + GBENU_STATS_P8(rx_oversized_frames), + GBENU_STATS_P8(rx_jabber_frames), + GBENU_STATS_P8(rx_undersized_frames), + GBENU_STATS_P8(rx_fragments), + GBENU_STATS_P8(ale_drop), + GBENU_STATS_P8(ale_overrun_drop), + GBENU_STATS_P8(rx_bytes), + GBENU_STATS_P8(tx_good_frames), + GBENU_STATS_P8(tx_broadcast_frames), + GBENU_STATS_P8(tx_multicast_frames), + GBENU_STATS_P8(tx_pause_frames), + GBENU_STATS_P8(tx_deferred_frames), + GBENU_STATS_P8(tx_collision_frames), + GBENU_STATS_P8(tx_single_coll_frames), + GBENU_STATS_P8(tx_mult_coll_frames), + GBENU_STATS_P8(tx_excessive_collisions), + GBENU_STATS_P8(tx_late_collisions), + GBENU_STATS_P8(rx_ipg_error), + GBENU_STATS_P8(tx_carrier_sense_errors), + GBENU_STATS_P8(tx_bytes), + GBENU_STATS_P8(tx_64B_frames), + GBENU_STATS_P8(tx_65_to_127B_frames), + GBENU_STATS_P8(tx_128_to_255B_frames), + GBENU_STATS_P8(tx_256_to_511B_frames), + GBENU_STATS_P8(tx_512_to_1023B_frames), + GBENU_STATS_P8(tx_1024B_frames), + GBENU_STATS_P8(net_bytes), + GBENU_STATS_P8(rx_bottom_fifo_drop), + GBENU_STATS_P8(rx_port_mask_drop), + GBENU_STATS_P8(rx_top_fifo_drop), + GBENU_STATS_P8(ale_rate_limit_drop), + GBENU_STATS_P8(ale_vid_ingress_drop), + GBENU_STATS_P8(ale_da_eq_sa_drop), + GBENU_STATS_P8(ale_unknown_ucast), + GBENU_STATS_P8(ale_unknown_ucast_bytes), + GBENU_STATS_P8(ale_unknown_mcast), + GBENU_STATS_P8(ale_unknown_mcast_bytes), + GBENU_STATS_P8(ale_unknown_bcast), + GBENU_STATS_P8(ale_unknown_bcast_bytes), + GBENU_STATS_P8(tx_mem_protect_err), +}; + +#define XGBE_STATS0_INFO(field) \ +{ \ + "GBE_0:"#field, XGBE_STATS0_MODULE, \ + FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + offsetof(struct xgbe_hw_stats, field) \ +} + +#define XGBE_STATS1_INFO(field) \ +{ \ + "GBE_1:"#field, XGBE_STATS1_MODULE, \ + FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + offsetof(struct xgbe_hw_stats, field) \ +} + +#define XGBE_STATS2_INFO(field) \ +{ \ + "GBE_2:"#field, XGBE_STATS2_MODULE, \ + FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + offsetof(struct xgbe_hw_stats, field) \ +} static const struct netcp_ethtool_stat xgbe10_et_stats[] = { /* GBE module 0 */ - {XGBE_STATS0_INFO(rx_good_frames)}, - {XGBE_STATS0_INFO(rx_broadcast_frames)}, - {XGBE_STATS0_INFO(rx_multicast_frames)}, - {XGBE_STATS0_INFO(rx_oversized_frames)}, - {XGBE_STATS0_INFO(rx_undersized_frames)}, - {XGBE_STATS0_INFO(overrun_type4)}, - {XGBE_STATS0_INFO(overrun_type5)}, - {XGBE_STATS0_INFO(rx_bytes)}, - {XGBE_STATS0_INFO(tx_good_frames)}, - {XGBE_STATS0_INFO(tx_broadcast_frames)}, - {XGBE_STATS0_INFO(tx_multicast_frames)}, - {XGBE_STATS0_INFO(tx_bytes)}, - {XGBE_STATS0_INFO(tx_64byte_frames)}, - {XGBE_STATS0_INFO(tx_65_to_127byte_frames)}, - {XGBE_STATS0_INFO(tx_128_to_255byte_frames)}, - {XGBE_STATS0_INFO(tx_256_to_511byte_frames)}, - {XGBE_STATS0_INFO(tx_512_to_1023byte_frames)}, - {XGBE_STATS0_INFO(tx_1024byte_frames)}, - {XGBE_STATS0_INFO(net_bytes)}, - {XGBE_STATS0_INFO(rx_sof_overruns)}, - {XGBE_STATS0_INFO(rx_mof_overruns)}, - {XGBE_STATS0_INFO(rx_dma_overruns)}, + XGBE_STATS0_INFO(rx_good_frames), + XGBE_STATS0_INFO(rx_broadcast_frames), + XGBE_STATS0_INFO(rx_multicast_frames), + XGBE_STATS0_INFO(rx_oversized_frames), + XGBE_STATS0_INFO(rx_undersized_frames), + XGBE_STATS0_INFO(overrun_type4), + XGBE_STATS0_INFO(overrun_type5), + XGBE_STATS0_INFO(rx_bytes), + XGBE_STATS0_INFO(tx_good_frames), + XGBE_STATS0_INFO(tx_broadcast_frames), + XGBE_STATS0_INFO(tx_multicast_frames), + XGBE_STATS0_INFO(tx_bytes), + XGBE_STATS0_INFO(tx_64byte_frames), + XGBE_STATS0_INFO(tx_65_to_127byte_frames), + XGBE_STATS0_INFO(tx_128_to_255byte_frames), + XGBE_STATS0_INFO(tx_256_to_511byte_frames), + XGBE_STATS0_INFO(tx_512_to_1023byte_frames), + XGBE_STATS0_INFO(tx_1024byte_frames), + XGBE_STATS0_INFO(net_bytes), + XGBE_STATS0_INFO(rx_sof_overruns), + XGBE_STATS0_INFO(rx_mof_overruns), + XGBE_STATS0_INFO(rx_dma_overruns), /* XGBE module 1 */ - {XGBE_STATS1_INFO(rx_good_frames)}, - {XGBE_STATS1_INFO(rx_broadcast_frames)}, - {XGBE_STATS1_INFO(rx_multicast_frames)}, - {XGBE_STATS1_INFO(rx_pause_frames)}, - {XGBE_STATS1_INFO(rx_crc_errors)}, - {XGBE_STATS1_INFO(rx_align_code_errors)}, - {XGBE_STATS1_INFO(rx_oversized_frames)}, - {XGBE_STATS1_INFO(rx_jabber_frames)}, - {XGBE_STATS1_INFO(rx_undersized_frames)}, - {XGBE_STATS1_INFO(rx_fragments)}, - {XGBE_STATS1_INFO(overrun_type4)}, - {XGBE_STATS1_INFO(overrun_type5)}, - {XGBE_STATS1_INFO(rx_bytes)}, - {XGBE_STATS1_INFO(tx_good_frames)}, - {XGBE_STATS1_INFO(tx_broadcast_frames)}, - {XGBE_STATS1_INFO(tx_multicast_frames)}, - {XGBE_STATS1_INFO(tx_pause_frames)}, - {XGBE_STATS1_INFO(tx_deferred_frames)}, - {XGBE_STATS1_INFO(tx_collision_frames)}, - {XGBE_STATS1_INFO(tx_single_coll_frames)}, - {XGBE_STATS1_INFO(tx_mult_coll_frames)}, - {XGBE_STATS1_INFO(tx_excessive_collisions)}, - {XGBE_STATS1_INFO(tx_late_collisions)}, - {XGBE_STATS1_INFO(tx_underrun)}, - {XGBE_STATS1_INFO(tx_carrier_sense_errors)}, - {XGBE_STATS1_INFO(tx_bytes)}, - {XGBE_STATS1_INFO(tx_64byte_frames)}, - {XGBE_STATS1_INFO(tx_65_to_127byte_frames)}, - {XGBE_STATS1_INFO(tx_128_to_255byte_frames)}, - {XGBE_STATS1_INFO(tx_256_to_511byte_frames)}, - {XGBE_STATS1_INFO(tx_512_to_1023byte_frames)}, - {XGBE_STATS1_INFO(tx_1024byte_frames)}, - {XGBE_STATS1_INFO(net_bytes)}, - {XGBE_STATS1_INFO(rx_sof_overruns)}, - {XGBE_STATS1_INFO(rx_mof_overruns)}, - {XGBE_STATS1_INFO(rx_dma_overruns)}, + XGBE_STATS1_INFO(rx_good_frames), + XGBE_STATS1_INFO(rx_broadcast_frames), + XGBE_STATS1_INFO(rx_multicast_frames), + XGBE_STATS1_INFO(rx_pause_frames), + XGBE_STATS1_INFO(rx_crc_errors), + XGBE_STATS1_INFO(rx_align_code_errors), + XGBE_STATS1_INFO(rx_oversized_frames), + XGBE_STATS1_INFO(rx_jabber_frames), + XGBE_STATS1_INFO(rx_undersized_frames), + XGBE_STATS1_INFO(rx_fragments), + XGBE_STATS1_INFO(overrun_type4), + XGBE_STATS1_INFO(overrun_type5), + XGBE_STATS1_INFO(rx_bytes), + XGBE_STATS1_INFO(tx_good_frames), + XGBE_STATS1_INFO(tx_broadcast_frames), + XGBE_STATS1_INFO(tx_multicast_frames), + XGBE_STATS1_INFO(tx_pause_frames), + XGBE_STATS1_INFO(tx_deferred_frames), + XGBE_STATS1_INFO(tx_collision_frames), + XGBE_STATS1_INFO(tx_single_coll_frames), + XGBE_STATS1_INFO(tx_mult_coll_frames), + XGBE_STATS1_INFO(tx_excessive_collisions), + XGBE_STATS1_INFO(tx_late_collisions), + XGBE_STATS1_INFO(tx_underrun), + XGBE_STATS1_INFO(tx_carrier_sense_errors), + XGBE_STATS1_INFO(tx_bytes), + XGBE_STATS1_INFO(tx_64byte_frames), + XGBE_STATS1_INFO(tx_65_to_127byte_frames), + XGBE_STATS1_INFO(tx_128_to_255byte_frames), + XGBE_STATS1_INFO(tx_256_to_511byte_frames), + XGBE_STATS1_INFO(tx_512_to_1023byte_frames), + XGBE_STATS1_INFO(tx_1024byte_frames), + XGBE_STATS1_INFO(net_bytes), + XGBE_STATS1_INFO(rx_sof_overruns), + XGBE_STATS1_INFO(rx_mof_overruns), + XGBE_STATS1_INFO(rx_dma_overruns), /* XGBE module 2 */ - {XGBE_STATS2_INFO(rx_good_frames)}, - {XGBE_STATS2_INFO(rx_broadcast_frames)}, - {XGBE_STATS2_INFO(rx_multicast_frames)}, - {XGBE_STATS2_INFO(rx_pause_frames)}, - {XGBE_STATS2_INFO(rx_crc_errors)}, - {XGBE_STATS2_INFO(rx_align_code_errors)}, - {XGBE_STATS2_INFO(rx_oversized_frames)}, - {XGBE_STATS2_INFO(rx_jabber_frames)}, - {XGBE_STATS2_INFO(rx_undersized_frames)}, - {XGBE_STATS2_INFO(rx_fragments)}, - {XGBE_STATS2_INFO(overrun_type4)}, - {XGBE_STATS2_INFO(overrun_type5)}, - {XGBE_STATS2_INFO(rx_bytes)}, - {XGBE_STATS2_INFO(tx_good_frames)}, - {XGBE_STATS2_INFO(tx_broadcast_frames)}, - {XGBE_STATS2_INFO(tx_multicast_frames)}, - {XGBE_STATS2_INFO(tx_pause_frames)}, - {XGBE_STATS2_INFO(tx_deferred_frames)}, - {XGBE_STATS2_INFO(tx_collision_frames)}, - {XGBE_STATS2_INFO(tx_single_coll_frames)}, - {XGBE_STATS2_INFO(tx_mult_coll_frames)}, - {XGBE_STATS2_INFO(tx_excessive_collisions)}, - {XGBE_STATS2_INFO(tx_late_collisions)}, - {XGBE_STATS2_INFO(tx_underrun)}, - {XGBE_STATS2_INFO(tx_carrier_sense_errors)}, - {XGBE_STATS2_INFO(tx_bytes)}, - {XGBE_STATS2_INFO(tx_64byte_frames)}, - {XGBE_STATS2_INFO(tx_65_to_127byte_frames)}, - {XGBE_STATS2_INFO(tx_128_to_255byte_frames)}, - {XGBE_STATS2_INFO(tx_256_to_511byte_frames)}, - {XGBE_STATS2_INFO(tx_512_to_1023byte_frames)}, - {XGBE_STATS2_INFO(tx_1024byte_frames)}, - {XGBE_STATS2_INFO(net_bytes)}, - {XGBE_STATS2_INFO(rx_sof_overruns)}, - {XGBE_STATS2_INFO(rx_mof_overruns)}, - {XGBE_STATS2_INFO(rx_dma_overruns)}, + XGBE_STATS2_INFO(rx_good_frames), + XGBE_STATS2_INFO(rx_broadcast_frames), + XGBE_STATS2_INFO(rx_multicast_frames), + XGBE_STATS2_INFO(rx_pause_frames), + XGBE_STATS2_INFO(rx_crc_errors), + XGBE_STATS2_INFO(rx_align_code_errors), + XGBE_STATS2_INFO(rx_oversized_frames), + XGBE_STATS2_INFO(rx_jabber_frames), + XGBE_STATS2_INFO(rx_undersized_frames), + XGBE_STATS2_INFO(rx_fragments), + XGBE_STATS2_INFO(overrun_type4), + XGBE_STATS2_INFO(overrun_type5), + XGBE_STATS2_INFO(rx_bytes), + XGBE_STATS2_INFO(tx_good_frames), + XGBE_STATS2_INFO(tx_broadcast_frames), + XGBE_STATS2_INFO(tx_multicast_frames), + XGBE_STATS2_INFO(tx_pause_frames), + XGBE_STATS2_INFO(tx_deferred_frames), + XGBE_STATS2_INFO(tx_collision_frames), + XGBE_STATS2_INFO(tx_single_coll_frames), + XGBE_STATS2_INFO(tx_mult_coll_frames), + XGBE_STATS2_INFO(tx_excessive_collisions), + XGBE_STATS2_INFO(tx_late_collisions), + XGBE_STATS2_INFO(tx_underrun), + XGBE_STATS2_INFO(tx_carrier_sense_errors), + XGBE_STATS2_INFO(tx_bytes), + XGBE_STATS2_INFO(tx_64byte_frames), + XGBE_STATS2_INFO(tx_65_to_127byte_frames), + XGBE_STATS2_INFO(tx_128_to_255byte_frames), + XGBE_STATS2_INFO(tx_256_to_511byte_frames), + XGBE_STATS2_INFO(tx_512_to_1023byte_frames), + XGBE_STATS2_INFO(tx_1024byte_frames), + XGBE_STATS2_INFO(net_bytes), + XGBE_STATS2_INFO(rx_sof_overruns), + XGBE_STATS2_INFO(rx_mof_overruns), + XGBE_STATS2_INFO(rx_dma_overruns), }; #define for_each_intf(i, priv) \ @@ -1066,9 +1796,16 @@ static void netcp_ethss_update_link_state(struct gbe_priv *gbe_dev, if (!slave->open) return; - if (!SLAVE_LINK_IS_XGMII(slave)) - sgmii_link_state = netcp_sgmii_get_port_link(SGMII_BASE(sp), - sp); + if (!SLAVE_LINK_IS_XGMII(slave)) { + if (gbe_dev->ss_version == GBE_SS_VERSION_14) + sgmii_link_state = + netcp_sgmii_get_port_link(SGMII_BASE(sp), sp); + else + sgmii_link_state = + netcp_sgmii_get_port_link( + gbe_dev->sgmii_port_regs, sp); + } + phy_link_state = gbe_phy_link_status(slave); link_state = phy_link_state & sgmii_link_state; @@ -1137,6 +1874,7 @@ static int gbe_port_reset(struct gbe_slave *slave) static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave, int max_rx_len) { + void __iomem *rx_maxlen_reg; u32 xgmii_mode; if (max_rx_len > NETCP_MAX_FRAME_SIZE) @@ -1150,7 +1888,12 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave, writel(xgmii_mode, GBE_REG_ADDR(gbe_dev, ss_regs, control)); } - writel(max_rx_len, GBE_REG_ADDR(slave, emac_regs, rx_maxlen)); + if (IS_SS_ID_MU(gbe_dev)) + rx_maxlen_reg = GBE_REG_ADDR(slave, port_regs, rx_maxlen); + else + rx_maxlen_reg = GBE_REG_ADDR(slave, emac_regs, rx_maxlen); + + writel(max_rx_len, rx_maxlen_reg); writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control)); } @@ -1242,6 +1985,12 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) static void gbe_init_host_port(struct gbe_priv *priv) { int bypass_en = 1; + + /* Host Tx Pri */ + if (IS_SS_ID_NU(priv)) + writel(HOST_TX_PRI_MAP_DEFAULT, + GBE_REG_ADDR(priv, host_port_regs, tx_pri_map)); + /* Max length register */ writel(NETCP_MAX_FRAME_SIZE, GBE_REG_ADDR(priv, host_port_regs, rx_maxlen)); @@ -1472,15 +2221,21 @@ static int gbe_open(void *intf_priv, struct net_device *ndev) GBE_MAJOR_VERSION(reg), GBE_MINOR_VERSION(reg), GBE_RTL_VERSION(reg), GBE_IDENT(reg)); + /* For 10G and on NetCP 1.5, use directed to port */ + if ((gbe_dev->ss_version == XGBE_SS_VERSION_10) || IS_SS_ID_MU(gbe_dev)) + gbe_intf->tx_pipe.flags = SWITCH_TO_PORT_IN_TAGINFO; + if (gbe_dev->enable_ale) - gbe_intf->tx_pipe.dma_psflags = 0; + gbe_intf->tx_pipe.switch_to_port = 0; else - gbe_intf->tx_pipe.dma_psflags = port_num; + gbe_intf->tx_pipe.switch_to_port = port_num; - dev_dbg(gbe_dev->dev, "opened TX channel %s: %p with psflags %d\n", + dev_dbg(gbe_dev->dev, + "opened TX channel %s: %p with to port %d, flags %d\n", gbe_intf->tx_pipe.dma_chan_name, gbe_intf->tx_pipe.dma_channel, - gbe_intf->tx_pipe.dma_psflags); + gbe_intf->tx_pipe.switch_to_port, + gbe_intf->tx_pipe.flags); gbe_slave_stop(gbe_intf); @@ -1491,8 +2246,8 @@ static int gbe_open(void *intf_priv, struct net_device *ndev) writel(GBE_CTL_P0_ENABLE, GBE_REG_ADDR(gbe_dev, switch_regs, control)); /* All statistics enabled and STAT AB visible by default */ - writel(GBE_REG_VAL_STAT_ENABLE_ALL, GBE_REG_ADDR(gbe_dev, switch_regs, - stat_port_en)); + writel(gbe_dev->stats_en_mask, GBE_REG_ADDR(gbe_dev, switch_regs, + stat_port_en)); ret = gbe_slave_open(gbe_intf); if (ret) @@ -1529,6 +2284,7 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, { int port_reg_num; u32 port_reg_ofs, emac_reg_ofs; + u32 port_reg_blk_sz, emac_reg_blk_sz; if (of_property_read_u32(node, "slave-port", &slave->slave_num)) { dev_err(gbe_dev->dev, "missing slave-port parameter\n"); @@ -1560,23 +2316,29 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, } else { port_reg_ofs = GBE13_SLAVE_PORT_OFFSET; } + emac_reg_ofs = GBE13_EMAC_OFFSET; + port_reg_blk_sz = 0x30; + emac_reg_blk_sz = 0x40; + } else if (IS_SS_ID_MU(gbe_dev)) { + port_reg_ofs = GBENU_SLAVE_PORT_OFFSET; + emac_reg_ofs = GBENU_EMAC_OFFSET; + port_reg_blk_sz = 0x1000; + emac_reg_blk_sz = 0x1000; } else if (gbe_dev->ss_version == XGBE_SS_VERSION_10) { port_reg_ofs = XGBE10_SLAVE_PORT_OFFSET; + emac_reg_ofs = XGBE10_EMAC_OFFSET; + port_reg_blk_sz = 0x30; + emac_reg_blk_sz = 0x40; } else { dev_err(gbe_dev->dev, "unknown ethss(0x%x)\n", gbe_dev->ss_version); return -EINVAL; } - if (gbe_dev->ss_version == GBE_SS_VERSION_14) - emac_reg_ofs = GBE13_EMAC_OFFSET; - else if (gbe_dev->ss_version == XGBE_SS_VERSION_10) - emac_reg_ofs = XGBE10_EMAC_OFFSET; - - slave->port_regs = gbe_dev->ss_regs + port_reg_ofs + - (0x30 * port_reg_num); - slave->emac_regs = gbe_dev->ss_regs + emac_reg_ofs + - (0x40 * slave->slave_num); + slave->port_regs = gbe_dev->switch_regs + port_reg_ofs + + (port_reg_blk_sz * port_reg_num); + slave->emac_regs = gbe_dev->switch_regs + emac_reg_ofs + + (emac_reg_blk_sz * slave->slave_num); if (gbe_dev->ss_version == GBE_SS_VERSION_14) { /* Initialize slave port register offsets */ @@ -1595,6 +2357,23 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, GBE_SET_REG_OFS(slave, emac_regs, soft_reset); GBE_SET_REG_OFS(slave, emac_regs, rx_maxlen); + } else if (IS_SS_ID_MU(gbe_dev)) { + /* Initialize slave port register offsets */ + GBENU_SET_REG_OFS(slave, port_regs, port_vlan); + GBENU_SET_REG_OFS(slave, port_regs, tx_pri_map); + GBENU_SET_REG_OFS(slave, port_regs, sa_lo); + GBENU_SET_REG_OFS(slave, port_regs, sa_hi); + GBENU_SET_REG_OFS(slave, port_regs, ts_ctl); + GBENU_SET_REG_OFS(slave, port_regs, ts_seq_ltype); + GBENU_SET_REG_OFS(slave, port_regs, ts_vlan); + GBENU_SET_REG_OFS(slave, port_regs, ts_ctl_ltype2); + GBENU_SET_REG_OFS(slave, port_regs, ts_ctl2); + GBENU_SET_REG_OFS(slave, port_regs, rx_maxlen); + + /* Initialize EMAC register offsets */ + GBENU_SET_REG_OFS(slave, emac_regs, mac_control); + GBENU_SET_REG_OFS(slave, emac_regs, soft_reset); + } else if (gbe_dev->ss_version == XGBE_SS_VERSION_10) { /* Initialize slave port register offsets */ XGBE_SET_REG_OFS(slave, port_regs, port_vlan); @@ -1654,6 +2433,8 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev, mac_phy_link = true; slave->open = true; + if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) + break; } /* of_phy_connect() is needed only for MAC-PHY interface */ @@ -1724,24 +2505,41 @@ static int set_xgbe_ethss10_priv(struct gbe_priv *gbe_dev, void __iomem *regs; int ret, i; - ret = of_address_to_resource(node, 0, &res); + ret = of_address_to_resource(node, XGBE_SS_REG_INDEX, &res); if (ret) { - dev_err(gbe_dev->dev, "Can't translate of node(%s) address for xgbe subsystem regs\n", - node->name); + dev_err(gbe_dev->dev, + "Can't xlate xgbe of node(%s) ss address at %d\n", + node->name, XGBE_SS_REG_INDEX); return ret; } regs = devm_ioremap_resource(gbe_dev->dev, &res); if (IS_ERR(regs)) { - dev_err(gbe_dev->dev, "Failed to map xgbe register base\n"); + dev_err(gbe_dev->dev, "Failed to map xgbe ss register base\n"); return PTR_ERR(regs); } gbe_dev->ss_regs = regs; + ret = of_address_to_resource(node, XGBE_SM_REG_INDEX, &res); + if (ret) { + dev_err(gbe_dev->dev, + "Can't xlate xgbe of node(%s) sm address at %d\n", + node->name, XGBE_SM_REG_INDEX); + return ret; + } + + regs = devm_ioremap_resource(gbe_dev->dev, &res); + if (IS_ERR(regs)) { + dev_err(gbe_dev->dev, "Failed to map xgbe sm register base\n"); + return PTR_ERR(regs); + } + gbe_dev->switch_regs = regs; + ret = of_address_to_resource(node, XGBE_SERDES_REG_INDEX, &res); if (ret) { - dev_err(gbe_dev->dev, "Can't translate of node(%s) address for xgbe serdes regs\n", - node->name); + dev_err(gbe_dev->dev, + "Can't xlate xgbe serdes of node(%s) address at %d\n", + node->name, XGBE_SERDES_REG_INDEX); return ret; } @@ -1753,9 +2551,9 @@ static int set_xgbe_ethss10_priv(struct gbe_priv *gbe_dev, gbe_dev->xgbe_serdes_regs = regs; gbe_dev->hw_stats = devm_kzalloc(gbe_dev->dev, - XGBE10_NUM_STAT_ENTRIES * - (XGBE10_NUM_SLAVES + 1) * sizeof(u64), - GFP_KERNEL); + XGBE10_NUM_STAT_ENTRIES * + (gbe_dev->max_num_ports) * sizeof(u64), + GFP_KERNEL); if (!gbe_dev->hw_stats) { dev_err(gbe_dev->dev, "hw_stats memory allocation failed\n"); return -ENOMEM; @@ -1764,19 +2562,19 @@ static int set_xgbe_ethss10_priv(struct gbe_priv *gbe_dev, gbe_dev->ss_version = XGBE_SS_VERSION_10; gbe_dev->sgmii_port_regs = gbe_dev->ss_regs + XGBE10_SGMII_MODULE_OFFSET; - gbe_dev->switch_regs = gbe_dev->ss_regs + XGBE10_SWITCH_MODULE_OFFSET; gbe_dev->host_port_regs = gbe_dev->ss_regs + XGBE10_HOST_PORT_OFFSET; - for (i = 0; i < XGBE10_NUM_HW_STATS_MOD; i++) - gbe_dev->hw_stats_regs[i] = gbe_dev->ss_regs + + for (i = 0; i < gbe_dev->max_num_ports; i++) + gbe_dev->hw_stats_regs[i] = gbe_dev->switch_regs + XGBE10_HW_STATS_OFFSET + (GBE_HW_STATS_REG_MAP_SZ * i); - gbe_dev->ale_reg = gbe_dev->ss_regs + XGBE10_ALE_OFFSET; - gbe_dev->ale_ports = XGBE10_NUM_ALE_PORTS; + gbe_dev->ale_reg = gbe_dev->switch_regs + XGBE10_ALE_OFFSET; + gbe_dev->ale_ports = gbe_dev->max_num_ports; gbe_dev->host_port = XGBE10_HOST_PORT_NUM; gbe_dev->ale_entries = XGBE10_NUM_ALE_ENTRIES; gbe_dev->et_stats = xgbe10_et_stats; gbe_dev->num_et_stats = ARRAY_SIZE(xgbe10_et_stats); + gbe_dev->stats_en_mask = (1 << (gbe_dev->max_num_ports)) - 1; /* Subsystem registers */ XGBE_SET_REG_OFS(gbe_dev, ss_regs, id_ver); @@ -1803,10 +2601,11 @@ static int get_gbe_resource_version(struct gbe_priv *gbe_dev, void __iomem *regs; int ret; - ret = of_address_to_resource(node, 0, &res); + ret = of_address_to_resource(node, GBE_SS_REG_INDEX, &res); if (ret) { - dev_err(gbe_dev->dev, "Can't translate of node(%s) address\n", - node->name); + dev_err(gbe_dev->dev, + "Can't translate of node(%s) of gbe ss address at %d\n", + node->name, GBE_SS_REG_INDEX); return ret; } @@ -1823,34 +2622,67 @@ static int get_gbe_resource_version(struct gbe_priv *gbe_dev, static int set_gbe_ethss14_priv(struct gbe_priv *gbe_dev, struct device_node *node) { + struct resource res; void __iomem *regs; - int i; + int i, ret; + + ret = of_address_to_resource(node, GBE_SGMII34_REG_INDEX, &res); + if (ret) { + dev_err(gbe_dev->dev, + "Can't translate of gbe node(%s) address at index %d\n", + node->name, GBE_SGMII34_REG_INDEX); + return ret; + } + + regs = devm_ioremap_resource(gbe_dev->dev, &res); + if (IS_ERR(regs)) { + dev_err(gbe_dev->dev, + "Failed to map gbe sgmii port34 register base\n"); + return PTR_ERR(regs); + } + gbe_dev->sgmii_port34_regs = regs; + + ret = of_address_to_resource(node, GBE_SM_REG_INDEX, &res); + if (ret) { + dev_err(gbe_dev->dev, + "Can't translate of gbe node(%s) address at index %d\n", + node->name, GBE_SM_REG_INDEX); + return ret; + } + + regs = devm_ioremap_resource(gbe_dev->dev, &res); + if (IS_ERR(regs)) { + dev_err(gbe_dev->dev, + "Failed to map gbe switch module register base\n"); + return PTR_ERR(regs); + } + gbe_dev->switch_regs = regs; gbe_dev->hw_stats = devm_kzalloc(gbe_dev->dev, GBE13_NUM_HW_STAT_ENTRIES * - GBE13_NUM_SLAVES * sizeof(u64), + gbe_dev->max_num_slaves * sizeof(u64), GFP_KERNEL); if (!gbe_dev->hw_stats) { dev_err(gbe_dev->dev, "hw_stats memory allocation failed\n"); return -ENOMEM; } - regs = gbe_dev->ss_regs; - gbe_dev->sgmii_port_regs = regs + GBE13_SGMII_MODULE_OFFSET; - gbe_dev->sgmii_port34_regs = regs + GBE13_SGMII34_MODULE_OFFSET; - gbe_dev->switch_regs = regs + GBE13_SWITCH_MODULE_OFFSET; - gbe_dev->host_port_regs = regs + GBE13_HOST_PORT_OFFSET; + gbe_dev->sgmii_port_regs = gbe_dev->ss_regs + GBE13_SGMII_MODULE_OFFSET; + gbe_dev->host_port_regs = gbe_dev->switch_regs + GBE13_HOST_PORT_OFFSET; - for (i = 0; i < GBE13_NUM_HW_STATS_MOD; i++) - gbe_dev->hw_stats_regs[i] = regs + GBE13_HW_STATS_OFFSET + - (GBE_HW_STATS_REG_MAP_SZ * i); + for (i = 0; i < gbe_dev->max_num_slaves; i++) { + gbe_dev->hw_stats_regs[i] = + gbe_dev->switch_regs + GBE13_HW_STATS_OFFSET + + (GBE_HW_STATS_REG_MAP_SZ * i); + } - gbe_dev->ale_reg = regs + GBE13_ALE_OFFSET; - gbe_dev->ale_ports = GBE13_NUM_ALE_PORTS; + gbe_dev->ale_reg = gbe_dev->switch_regs + GBE13_ALE_OFFSET; + gbe_dev->ale_ports = gbe_dev->max_num_ports; gbe_dev->host_port = GBE13_HOST_PORT_NUM; gbe_dev->ale_entries = GBE13_NUM_ALE_ENTRIES; gbe_dev->et_stats = gbe13_et_stats; gbe_dev->num_et_stats = ARRAY_SIZE(gbe13_et_stats); + gbe_dev->stats_en_mask = GBE13_REG_VAL_STAT_ENABLE_ALL; /* Subsystem registers */ GBE_SET_REG_OFS(gbe_dev, ss_regs, id_ver); @@ -1869,6 +2701,80 @@ static int set_gbe_ethss14_priv(struct gbe_priv *gbe_dev, return 0; } +static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev, + struct device_node *node) +{ + struct resource res; + void __iomem *regs; + int i, ret; + + gbe_dev->hw_stats = devm_kzalloc(gbe_dev->dev, + GBENU_NUM_HW_STAT_ENTRIES * + (gbe_dev->max_num_ports) * sizeof(u64), + GFP_KERNEL); + if (!gbe_dev->hw_stats) { + dev_err(gbe_dev->dev, "hw_stats memory allocation failed\n"); + return -ENOMEM; + } + + ret = of_address_to_resource(node, GBENU_SM_REG_INDEX, &res); + if (ret) { + dev_err(gbe_dev->dev, + "Can't translate of gbenu node(%s) addr at index %d\n", + node->name, GBENU_SM_REG_INDEX); + return ret; + } + + regs = devm_ioremap_resource(gbe_dev->dev, &res); + if (IS_ERR(regs)) { + dev_err(gbe_dev->dev, + "Failed to map gbenu switch module register base\n"); + return PTR_ERR(regs); + } + gbe_dev->switch_regs = regs; + + gbe_dev->sgmii_port_regs = gbe_dev->ss_regs + GBENU_SGMII_MODULE_OFFSET; + gbe_dev->host_port_regs = gbe_dev->switch_regs + GBENU_HOST_PORT_OFFSET; + + for (i = 0; i < (gbe_dev->max_num_ports); i++) + gbe_dev->hw_stats_regs[i] = gbe_dev->switch_regs + + GBENU_HW_STATS_OFFSET + (GBENU_HW_STATS_REG_MAP_SZ * i); + + gbe_dev->ale_reg = gbe_dev->switch_regs + GBENU_ALE_OFFSET; + gbe_dev->ale_ports = gbe_dev->max_num_ports; + gbe_dev->host_port = GBENU_HOST_PORT_NUM; + gbe_dev->ale_entries = GBE13_NUM_ALE_ENTRIES; + gbe_dev->et_stats = gbenu_et_stats; + gbe_dev->stats_en_mask = (1 << (gbe_dev->max_num_ports)) - 1; + + if (IS_SS_ID_NU(gbe_dev)) + gbe_dev->num_et_stats = GBENU_ET_STATS_HOST_SIZE + + (gbe_dev->max_num_slaves * GBENU_ET_STATS_PORT_SIZE); + else + gbe_dev->num_et_stats = GBENU_ET_STATS_HOST_SIZE + + GBENU_ET_STATS_PORT_SIZE; + + /* Subsystem registers */ + GBENU_SET_REG_OFS(gbe_dev, ss_regs, id_ver); + + /* Switch module registers */ + GBENU_SET_REG_OFS(gbe_dev, switch_regs, id_ver); + GBENU_SET_REG_OFS(gbe_dev, switch_regs, control); + GBENU_SET_REG_OFS(gbe_dev, switch_regs, stat_port_en); + GBENU_SET_REG_OFS(gbe_dev, switch_regs, ptype); + + /* Host port registers */ + GBENU_SET_REG_OFS(gbe_dev, host_port_regs, port_vlan); + GBENU_SET_REG_OFS(gbe_dev, host_port_regs, rx_maxlen); + + /* For NU only. 2U does not need tx_pri_map. + * NU cppi port 0 tx pkt streaming interface has (n-1)*8 egress threads + * while 2U has only 1 such thread + */ + GBENU_SET_REG_OFS(gbe_dev, host_port_regs, tx_pri_map); + return 0; +} + static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, struct device_node *node, void **inst_priv) { @@ -1888,6 +2794,21 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, if (!gbe_dev) return -ENOMEM; + if (of_device_is_compatible(node, "ti,netcp-gbe-5") || + of_device_is_compatible(node, "ti,netcp-gbe")) { + gbe_dev->max_num_slaves = 4; + } else if (of_device_is_compatible(node, "ti,netcp-gbe-9")) { + gbe_dev->max_num_slaves = 8; + } else if (of_device_is_compatible(node, "ti,netcp-gbe-2")) { + gbe_dev->max_num_slaves = 1; + } else if (of_device_is_compatible(node, "ti,netcp-xgbe")) { + gbe_dev->max_num_slaves = 2; + } else { + dev_err(dev, "device tree node for unknown device\n"); + return -EINVAL; + } + gbe_dev->max_num_ports = gbe_dev->max_num_slaves + 1; + gbe_dev->dev = dev; gbe_dev->netcp_device = netcp_device; gbe_dev->rx_packet_max = NETCP_MAX_FRAME_SIZE; @@ -1923,7 +2844,15 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, if (ret) goto quit; - ret = set_gbe_ethss14_priv(gbe_dev, node); + dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version); + + if (gbe_dev->ss_version == GBE_SS_VERSION_14) + ret = set_gbe_ethss14_priv(gbe_dev, node); + else if (IS_SS_ID_MU(gbe_dev)) + ret = set_gbenu_ethss_priv(gbe_dev, node); + else + ret = -ENODEV; + if (ret) goto quit; } else if (!strcmp(node->name, "xgbe")) { @@ -1963,6 +2892,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, continue; } gbe_dev->num_slaves++; + if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) + break; } if (!gbe_dev->num_slaves) @@ -1971,7 +2902,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, /* Initialize Secondary slave ports */ secondary_ports = of_get_child_by_name(node, "secondary-slave-ports"); INIT_LIST_HEAD(&gbe_dev->secondary_slaves); - if (secondary_ports) + if (secondary_ports && (gbe_dev->num_slaves < gbe_dev->max_num_slaves)) init_secondary_ports(gbe_dev, secondary_ports); of_node_put(secondary_ports); diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index bea8cd2bb56c..a789a2054388 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -838,7 +838,8 @@ static int ptp_mpipe_adjtime(struct ptp_clock_info *ptp, s64 delta) return ret; } -static int ptp_mpipe_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int ptp_mpipe_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) { int ret = 0; struct mpipe_data *md = container_of(ptp, struct mpipe_data, caps); @@ -850,7 +851,7 @@ static int ptp_mpipe_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int ptp_mpipe_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { int ret = 0; struct mpipe_data *md = container_of(ptp, struct mpipe_data, caps); @@ -876,8 +877,8 @@ static struct ptp_clock_info ptp_mpipe_caps = { .pps = 0, .adjfreq = ptp_mpipe_adjfreq, .adjtime = ptp_mpipe_adjtime, - .gettime = ptp_mpipe_gettime, - .settime = ptp_mpipe_settime, + .gettime64 = ptp_mpipe_gettime, + .settime64 = ptp_mpipe_settime, .enable = ptp_mpipe_enable, }; diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 8fb807ea1caa..de2850497c09 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -288,7 +288,7 @@ MODULE_DEVICE_TABLE(pci, rhine_pci_tbl); * The .data field is currently only used to store quirks */ static u32 vt8500_quirks = rqWOL | rqForceReset | rq6patterns; -static struct of_device_id rhine_of_tbl[] = { +static const struct of_device_id rhine_of_tbl[] = { { .compatible = "via,vt8500-rhine", .data = &vt8500_quirks }, { } /* terminate list */ }; diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index c20206f83cc1..ae68afd50a15 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -392,7 +392,7 @@ MODULE_DEVICE_TABLE(pci, velocity_pci_id_table); * Describe the OF device identifiers that we support in this * device driver. Used for devicetree nodes. */ -static struct of_device_id velocity_of_ids[] = { +static const struct of_device_id velocity_of_ids[] = { { .compatible = "via,velocity-vt6110", .data = &chip_info_table[0] }, { /* Sentinel */ }, }; diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index f5498c26b3c7..8b282d0b169c 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -498,9 +498,9 @@ static int w5100_napi_poll(struct napi_struct *napi, int budget) } if (rx_count < budget) { + napi_complete(napi); w5100_write(priv, W5100_IMR, IR_S0); mmiowb(); - napi_complete(napi); } return rx_count; diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c index ca0c631ed628..8da7b930ff59 100644 --- a/drivers/net/ethernet/wiznet/w5300.c +++ b/drivers/net/ethernet/wiznet/w5300.c @@ -418,9 +418,9 @@ static int w5300_napi_poll(struct napi_struct *napi, int budget) } if (rx_count < budget) { + napi_complete(napi); w5300_write(priv, W5300_IMR, IR_S0); mmiowb(); - napi_complete(napi); } return rx_count; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index dbcbf0c5bcfa..690a4c36b316 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1157,7 +1157,7 @@ static int temac_of_remove(struct platform_device *op) return 0; } -static struct of_device_id temac_of_match[] = { +static const struct of_device_id temac_of_match[] = { { .compatible = "xlnx,xps-ll-temac-1.01.b", }, { .compatible = "xlnx,xps-ll-temac-2.00.a", }, { .compatible = "xlnx,xps-ll-temac-2.02.a", }, diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index a6d2860b712c..28b7e7d9c272 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -48,7 +48,7 @@ #define AXIENET_REGS_N 32 /* Match table for of_platform binding */ -static struct of_device_id axienet_of_match[] = { +static const struct of_device_id axienet_of_match[] = { { .compatible = "xlnx,axi-ethernet-1.00.a", }, { .compatible = "xlnx,axi-ethernet-1.01.a", }, { .compatible = "xlnx,axi-ethernet-2.01.a", }, diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 9d4ce388510a..2111b91f5e49 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -1231,7 +1231,7 @@ static struct net_device_ops xemaclite_netdev_ops = { }; /* Match table for OF platform binding */ -static struct of_device_id xemaclite_of_match[] = { +static const struct of_device_id xemaclite_of_match[] = { { .compatible = "xlnx,opb-ethernetlite-1.01.a", }, { .compatible = "xlnx,opb-ethernetlite-1.01.b", }, { .compatible = "xlnx,xps-ethernetlite-1.00.a", }, diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 4815843a6019..384f057d6570 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -131,6 +131,7 @@ struct hv_netvsc_packet { struct hv_device *device; bool is_data_pkt; + bool xmit_more; /* from skb */ u16 vlan_tci; u16 q_idx; @@ -596,7 +597,16 @@ struct nvsp_message { #define VRSS_SEND_TAB_SIZE 16 -/* Per netvsc channel-specific */ +#define RNDIS_MAX_PKT_DEFAULT 8 +#define RNDIS_PKT_ALIGN_DEFAULT 8 + +struct multi_send_data { + spinlock_t lock; /* protect struct multi_send_data */ + struct hv_netvsc_packet *pkt; /* netvsc pkt pending */ + u32 count; /* counter of batched packets */ +}; + +/* Per netvsc device */ struct netvsc_device { struct hv_device *dev; @@ -647,6 +657,10 @@ struct netvsc_device { unsigned char *cb_buffer; /* The sub channel callback buffer */ unsigned char *sub_cb_buf; + + struct multi_send_data msd[NR_CPUS]; + u32 max_pkt; /* max number of pkt in one send, e.g. 8 */ + u32 pkt_align; /* alignment bytes, e.g. 8 */ }; /* NdisInitialize message */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 208eb05446ba..b81bd37d3afb 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -37,6 +37,7 @@ static struct netvsc_device *alloc_net_device(struct hv_device *device) { struct netvsc_device *net_device; struct net_device *ndev = hv_get_drvdata(device); + int i; net_device = kzalloc(sizeof(struct netvsc_device), GFP_KERNEL); if (!net_device) @@ -53,6 +54,11 @@ static struct netvsc_device *alloc_net_device(struct hv_device *device) net_device->destroy = false; net_device->dev = device; net_device->ndev = ndev; + net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; + net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; + + for (i = 0; i < num_online_cpus(); i++) + spin_lock_init(&net_device->msd[i].lock); hv_set_drvdata(device, net_device); return net_device; @@ -687,12 +693,23 @@ static u32 netvsc_get_next_send_section(struct netvsc_device *net_device) static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device, unsigned int section_index, + u32 pend_size, struct hv_netvsc_packet *packet) { char *start = net_device->send_buf; - char *dest = (start + (section_index * net_device->send_section_size)); + char *dest = start + (section_index * net_device->send_section_size) + + pend_size; int i; u32 msg_size = 0; + u32 padding = 0; + u32 remain = packet->total_data_buflen % net_device->pkt_align; + + /* Add padding */ + if (packet->is_data_pkt && packet->xmit_more && remain) { + padding = net_device->pkt_align - remain; + packet->rndis_msg->msg_len += padding; + packet->total_data_buflen += padding; + } for (i = 0; i < packet->page_buf_cnt; i++) { char *src = phys_to_virt(packet->page_buf[i].pfn << PAGE_SHIFT); @@ -703,67 +720,48 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device, msg_size += len; dest += len; } + + if (padding) { + memset(dest, 0, padding); + msg_size += padding; + } + return msg_size; } -int netvsc_send(struct hv_device *device, - struct hv_netvsc_packet *packet) +static inline int netvsc_send_pkt( + struct hv_netvsc_packet *packet, + struct netvsc_device *net_device) { - struct netvsc_device *net_device; - int ret = 0; - struct nvsp_message sendMessage; - struct net_device *ndev; - struct vmbus_channel *out_channel = NULL; - u64 req_id; - unsigned int section_index = NETVSC_INVALID_INDEX; - u32 msg_size = 0; - struct sk_buff *skb = NULL; + struct nvsp_message nvmsg; + struct vmbus_channel *out_channel = packet->channel; u16 q_idx = packet->q_idx; + struct net_device *ndev = net_device->ndev; + u64 req_id; + int ret; - - net_device = get_outbound_net_device(device); - if (!net_device) - return -ENODEV; - ndev = net_device->ndev; - - sendMessage.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT; + nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT; if (packet->is_data_pkt) { /* 0 is RMC_DATA; */ - sendMessage.msg.v1_msg.send_rndis_pkt.channel_type = 0; + nvmsg.msg.v1_msg.send_rndis_pkt.channel_type = 0; } else { /* 1 is RMC_CONTROL; */ - sendMessage.msg.v1_msg.send_rndis_pkt.channel_type = 1; + nvmsg.msg.v1_msg.send_rndis_pkt.channel_type = 1; } - /* Attempt to send via sendbuf */ - if (packet->total_data_buflen < net_device->send_section_size) { - section_index = netvsc_get_next_send_section(net_device); - if (section_index != NETVSC_INVALID_INDEX) { - msg_size = netvsc_copy_to_send_buf(net_device, - section_index, - packet); - skb = (struct sk_buff *) - (unsigned long)packet->send_completion_tid; - packet->page_buf_cnt = 0; - } - } - packet->send_buf_index = section_index; - - - sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_index = - section_index; - sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_size = msg_size; + nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_index = + packet->send_buf_index; + if (packet->send_buf_index == NETVSC_INVALID_INDEX) + nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_size = 0; + else + nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_size = + packet->total_data_buflen; if (packet->send_completion) req_id = (ulong)packet; else req_id = 0; - out_channel = net_device->chn_table[packet->q_idx]; - if (out_channel == NULL) - out_channel = device->channel; - packet->channel = out_channel; - if (out_channel->rescind) return -ENODEV; @@ -771,11 +769,12 @@ int netvsc_send(struct hv_device *device, ret = vmbus_sendpacket_pagebuffer(out_channel, packet->page_buf, packet->page_buf_cnt, - &sendMessage, + &nvmsg, sizeof(struct nvsp_message), req_id); } else { - ret = vmbus_sendpacket(out_channel, &sendMessage, + ret = vmbus_sendpacket( + out_channel, &nvmsg, sizeof(struct nvsp_message), req_id, VM_PKT_DATA_INBAND, @@ -809,6 +808,102 @@ int netvsc_send(struct hv_device *device, packet, ret); } + return ret; +} + +int netvsc_send(struct hv_device *device, + struct hv_netvsc_packet *packet) +{ + struct netvsc_device *net_device; + int ret = 0, m_ret = 0; + struct vmbus_channel *out_channel; + u16 q_idx = packet->q_idx; + u32 pktlen = packet->total_data_buflen, msd_len = 0; + unsigned int section_index = NETVSC_INVALID_INDEX; + struct sk_buff *skb = NULL; + unsigned long flag; + struct multi_send_data *msdp; + struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL; + + net_device = get_outbound_net_device(device); + if (!net_device) + return -ENODEV; + + out_channel = net_device->chn_table[q_idx]; + if (!out_channel) { + out_channel = device->channel; + q_idx = 0; + packet->q_idx = 0; + } + packet->channel = out_channel; + packet->send_buf_index = NETVSC_INVALID_INDEX; + + msdp = &net_device->msd[q_idx]; + + /* batch packets in send buffer if possible */ + spin_lock_irqsave(&msdp->lock, flag); + if (msdp->pkt) + msd_len = msdp->pkt->total_data_buflen; + + if (packet->is_data_pkt && msd_len > 0 && + msdp->count < net_device->max_pkt && + msd_len + pktlen + net_device->pkt_align < + net_device->send_section_size) { + section_index = msdp->pkt->send_buf_index; + + } else if (packet->is_data_pkt && pktlen + net_device->pkt_align < + net_device->send_section_size) { + section_index = netvsc_get_next_send_section(net_device); + if (section_index != NETVSC_INVALID_INDEX) { + msd_send = msdp->pkt; + msdp->pkt = NULL; + msdp->count = 0; + msd_len = 0; + } + } + + if (section_index != NETVSC_INVALID_INDEX) { + netvsc_copy_to_send_buf(net_device, + section_index, msd_len, + packet); + skb = (struct sk_buff *) + (unsigned long)packet->send_completion_tid; + + packet->page_buf_cnt = 0; + packet->send_buf_index = section_index; + packet->total_data_buflen += msd_len; + + kfree(msdp->pkt); + if (packet->xmit_more) { + msdp->pkt = packet; + msdp->count++; + } else { + cur_send = packet; + msdp->pkt = NULL; + msdp->count = 0; + } + } else { + msd_send = msdp->pkt; + msdp->pkt = NULL; + msdp->count = 0; + cur_send = packet; + } + + spin_unlock_irqrestore(&msdp->lock, flag); + + if (msd_send) { + m_ret = netvsc_send_pkt(msd_send, net_device); + + if (m_ret != 0) { + netvsc_free_send_slot(net_device, + msd_send->send_buf_index); + kfree(msd_send); + } + } + + if (cur_send) + ret = netvsc_send_pkt(cur_send, net_device); + if (ret != 0) { if (section_index != NETVSC_INVALID_INDEX) netvsc_free_send_slot(net_device, section_index); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index a06bd6614007..0c998186039e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -413,6 +413,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) return NETDEV_TX_OK; } + packet->xmit_more = skb->xmit_more; + packet->vlan_tci = skb->vlan_tci; packet->q_idx = skb_get_queue_mapping(skb); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index ca81de04bc76..fdfab1feccfc 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -237,6 +237,7 @@ static int rndis_filter_send_request(struct rndis_device *dev, } packet->send_completion = NULL; + packet->xmit_more = false; ret = netvsc_send(dev->net_dev->dev, packet); return ret; @@ -855,6 +856,7 @@ static int rndis_filter_init_device(struct rndis_device *dev) u32 status; int ret; unsigned long t; + struct netvsc_device *nvdev = dev->net_dev; request = get_rndis_request(dev, RNDIS_MSG_INIT, RNDIS_MESSAGE_SIZE(struct rndis_initialize_request)); @@ -889,6 +891,8 @@ static int rndis_filter_init_device(struct rndis_device *dev) status = init_complete->status; if (status == RNDIS_STATUS_SUCCESS) { dev->state = RNDIS_DEV_INITIALIZED; + nvdev->max_pkt = init_complete->max_pkt_per_msg; + nvdev->pkt_align = 1 << init_complete->pkt_alignment_factor; ret = 0; } else { dev->state = RNDIS_DEV_UNINITIALIZED; @@ -1137,8 +1141,6 @@ int rndis_filter_device_add(struct hv_device *dev, net_device->num_chn = 1 + init_packet->msg.v5_msg.subchn_comp.num_subchannels; - vmbus_are_subchannels_present(dev->channel); - ret = rndis_filter_set_rss_param(rndis_device, net_device->num_chn); out: diff --git a/drivers/net/phy/amd-xgbe-phy.c b/drivers/net/phy/amd-xgbe-phy.c index 32efbd48f326..fb276f64cd64 100644 --- a/drivers/net/phy/amd-xgbe-phy.c +++ b/drivers/net/phy/amd-xgbe-phy.c @@ -78,6 +78,7 @@ #include <linux/bitops.h> #include <linux/property.h> #include <linux/acpi.h> +#include <linux/jiffies.h> MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>"); MODULE_LICENSE("Dual BSD/GPL"); @@ -100,6 +101,8 @@ MODULE_DESCRIPTION("AMD 10GbE (amd-xgbe) PHY driver"); #define XGBE_PHY_SPEED_2500 1 #define XGBE_PHY_SPEED_10000 2 +#define XGBE_AN_MS_TIMEOUT 500 + #define XGBE_AN_INT_CMPLT 0x01 #define XGBE_AN_INC_LINK 0x02 #define XGBE_AN_PG_RCV 0x04 @@ -434,6 +437,7 @@ struct amd_xgbe_phy_priv { unsigned int an_supported; unsigned int parallel_detect; unsigned int fec_ability; + unsigned long an_start; unsigned int lpm_ctrl; /* CTRL1 for resume */ }; @@ -902,8 +906,23 @@ static enum amd_xgbe_phy_an amd_xgbe_an_page_received(struct phy_device *phydev) { struct amd_xgbe_phy_priv *priv = phydev->priv; enum amd_xgbe_phy_rx *state; + unsigned long an_timeout; int ret; + if (!priv->an_start) { + priv->an_start = jiffies; + } else { + an_timeout = priv->an_start + + msecs_to_jiffies(XGBE_AN_MS_TIMEOUT); + if (time_after(jiffies, an_timeout)) { + /* Auto-negotiation timed out, reset state */ + priv->kr_state = AMD_XGBE_RX_BPA; + priv->kx_state = AMD_XGBE_RX_BPA; + + priv->an_start = jiffies; + } + } + state = amd_xgbe_phy_in_kr_mode(phydev) ? &priv->kr_state : &priv->kx_state; @@ -932,8 +951,8 @@ static enum amd_xgbe_phy_an amd_xgbe_an_incompat_link(struct phy_device *phydev) if (amd_xgbe_phy_in_kr_mode(phydev)) { priv->kr_state = AMD_XGBE_RX_ERROR; - if (!(phydev->supported & SUPPORTED_1000baseKX_Full) && - !(phydev->supported & SUPPORTED_2500baseX_Full)) + if (!(phydev->advertising & SUPPORTED_1000baseKX_Full) && + !(phydev->advertising & SUPPORTED_2500baseX_Full)) return AMD_XGBE_AN_NO_LINK; if (priv->kx_state != AMD_XGBE_RX_BPA) @@ -941,7 +960,7 @@ static enum amd_xgbe_phy_an amd_xgbe_an_incompat_link(struct phy_device *phydev) } else { priv->kx_state = AMD_XGBE_RX_ERROR; - if (!(phydev->supported & SUPPORTED_10000baseKR_Full)) + if (!(phydev->advertising & SUPPORTED_10000baseKR_Full)) return AMD_XGBE_AN_NO_LINK; if (priv->kr_state != AMD_XGBE_RX_BPA) @@ -1078,6 +1097,7 @@ again: priv->an_state = AMD_XGBE_AN_READY; priv->kr_state = AMD_XGBE_RX_BPA; priv->kx_state = AMD_XGBE_RX_BPA; + priv->an_start = 0; } if (cur_state != priv->an_state) @@ -1101,7 +1121,7 @@ static int amd_xgbe_an_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->supported & SUPPORTED_10000baseR_FEC) + if (phydev->advertising & SUPPORTED_10000baseR_FEC) ret |= 0xc000; else ret &= ~0xc000; @@ -1113,13 +1133,13 @@ static int amd_xgbe_an_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->supported & SUPPORTED_10000baseKR_Full) + if (phydev->advertising & SUPPORTED_10000baseKR_Full) ret |= 0x80; else ret &= ~0x80; - if ((phydev->supported & SUPPORTED_1000baseKX_Full) || - (phydev->supported & SUPPORTED_2500baseX_Full)) + if ((phydev->advertising & SUPPORTED_1000baseKX_Full) || + (phydev->advertising & SUPPORTED_2500baseX_Full)) ret |= 0x20; else ret &= ~0x20; @@ -1131,12 +1151,12 @@ static int amd_xgbe_an_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->supported & SUPPORTED_Pause) + if (phydev->advertising & SUPPORTED_Pause) ret |= 0x400; else ret &= ~0x400; - if (phydev->supported & SUPPORTED_Asym_Pause) + if (phydev->advertising & SUPPORTED_Asym_Pause) ret |= 0x800; else ret &= ~0x800; @@ -1212,38 +1232,14 @@ static int amd_xgbe_phy_config_init(struct phy_device *phydev) priv->an_irq_allocated = 1; } - ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FEC_ABILITY); - if (ret < 0) - return ret; - priv->fec_ability = ret & XGBE_PHY_FEC_MASK; - - /* Initialize supported features */ - phydev->supported = SUPPORTED_Autoneg; - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - phydev->supported |= SUPPORTED_Backplane; - phydev->supported |= SUPPORTED_10000baseKR_Full; - switch (priv->speed_set) { - case AMD_XGBE_PHY_SPEEDSET_1000_10000: - phydev->supported |= SUPPORTED_1000baseKX_Full; - break; - case AMD_XGBE_PHY_SPEEDSET_2500_10000: - phydev->supported |= SUPPORTED_2500baseX_Full; - break; - } - - if (priv->fec_ability & XGBE_PHY_FEC_ENABLE) - phydev->supported |= SUPPORTED_10000baseR_FEC; - - phydev->advertising = phydev->supported; - /* Set initial mode - call the mode setting routines * directly to insure we are properly configured */ - if (phydev->supported & SUPPORTED_10000baseKR_Full) + if (phydev->advertising & SUPPORTED_10000baseKR_Full) ret = amd_xgbe_phy_xgmii_mode(phydev); - else if (phydev->supported & SUPPORTED_1000baseKX_Full) + else if (phydev->advertising & SUPPORTED_1000baseKX_Full) ret = amd_xgbe_phy_gmii_mode(phydev); - else if (phydev->supported & SUPPORTED_2500baseX_Full) + else if (phydev->advertising & SUPPORTED_2500baseX_Full) ret = amd_xgbe_phy_gmii_2500_mode(phydev); else ret = -EINVAL; @@ -1315,10 +1311,10 @@ static int __amd_xgbe_phy_config_aneg(struct phy_device *phydev) disable_irq(priv->an_irq); /* Start auto-negotiation in a supported mode */ - if (phydev->supported & SUPPORTED_10000baseKR_Full) + if (phydev->advertising & SUPPORTED_10000baseKR_Full) ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KR); - else if ((phydev->supported & SUPPORTED_1000baseKX_Full) || - (phydev->supported & SUPPORTED_2500baseX_Full)) + else if ((phydev->advertising & SUPPORTED_1000baseKX_Full) || + (phydev->advertising & SUPPORTED_2500baseX_Full)) ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KX); else ret = -EINVAL; @@ -1746,6 +1742,29 @@ static int amd_xgbe_phy_probe(struct phy_device *phydev) sizeof(priv->serdes_dfe_tap_ena)); } + /* Initialize supported features */ + phydev->supported = SUPPORTED_Autoneg; + phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phydev->supported |= SUPPORTED_Backplane; + phydev->supported |= SUPPORTED_10000baseKR_Full; + switch (priv->speed_set) { + case AMD_XGBE_PHY_SPEEDSET_1000_10000: + phydev->supported |= SUPPORTED_1000baseKX_Full; + break; + case AMD_XGBE_PHY_SPEEDSET_2500_10000: + phydev->supported |= SUPPORTED_2500baseX_Full; + break; + } + + ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FEC_ABILITY); + if (ret < 0) + return ret; + priv->fec_ability = ret & XGBE_PHY_FEC_MASK; + if (priv->fec_ability & XGBE_PHY_FEC_ENABLE) + phydev->supported |= SUPPORTED_10000baseR_FEC; + + phydev->advertising = phydev->supported; + phydev->priv = priv; if (!priv->adev || acpi_disabled) @@ -1817,6 +1836,7 @@ static struct phy_driver amd_xgbe_phy_driver[] = { .phy_id_mask = XGBE_PHY_MASK, .name = "AMD XGBE PHY", .features = 0, + .flags = PHY_IS_INTERNAL, .probe = amd_xgbe_phy_probe, .remove = amd_xgbe_phy_remove, .soft_reset = amd_xgbe_phy_soft_reset, diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index e22e602beef3..a83f8e50844c 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -257,7 +257,7 @@ static void ext_write(int broadcast, struct phy_device *phydev, /* Caller must hold extreg_lock. */ static int tdr_write(int bc, struct phy_device *dev, - const struct timespec *ts, u16 cmd) + const struct timespec64 *ts, u16 cmd) { ext_write(bc, dev, PAGE4, PTP_TDR, ts->tv_nsec & 0xffff);/* ns[15:0] */ ext_write(bc, dev, PAGE4, PTP_TDR, ts->tv_nsec >> 16); /* ns[31:16] */ @@ -411,12 +411,12 @@ static int ptp_dp83640_adjtime(struct ptp_clock_info *ptp, s64 delta) struct dp83640_clock *clock = container_of(ptp, struct dp83640_clock, caps); struct phy_device *phydev = clock->chosen->phydev; - struct timespec ts; + struct timespec64 ts; int err; delta += ADJTIME_FIX; - ts = ns_to_timespec(delta); + ts = ns_to_timespec64(delta); mutex_lock(&clock->extreg_lock); @@ -427,7 +427,8 @@ static int ptp_dp83640_adjtime(struct ptp_clock_info *ptp, s64 delta) return err; } -static int ptp_dp83640_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int ptp_dp83640_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) { struct dp83640_clock *clock = container_of(ptp, struct dp83640_clock, caps); @@ -452,7 +453,7 @@ static int ptp_dp83640_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int ptp_dp83640_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { struct dp83640_clock *clock = container_of(ptp, struct dp83640_clock, caps); @@ -605,7 +606,7 @@ static void recalibrate(struct dp83640_clock *clock) { s64 now, diff; struct phy_txts event_ts; - struct timespec ts; + struct timespec64 ts; struct list_head *this; struct dp83640_private *tmp; struct phy_device *master = clock->chosen->phydev; @@ -697,7 +698,7 @@ static void recalibrate(struct dp83640_clock *clock) diff = now - (s64) phy2txts(&event_ts); pr_info("slave offset %lld nanoseconds\n", diff); diff += ADJTIME_FIX; - ts = ns_to_timespec(diff); + ts = ns_to_timespec64(diff); tdr_write(0, tmp->phydev, &ts, PTP_STEP_CLK); } @@ -998,8 +999,8 @@ static void dp83640_clock_init(struct dp83640_clock *clock, struct mii_bus *bus) clock->caps.pps = 0; clock->caps.adjfreq = ptp_dp83640_adjfreq; clock->caps.adjtime = ptp_dp83640_adjtime; - clock->caps.gettime = ptp_dp83640_gettime; - clock->caps.settime = ptp_dp83640_settime; + clock->caps.gettime64 = ptp_dp83640_gettime; + clock->caps.settime64 = ptp_dp83640_settime; clock->caps.enable = ptp_dp83640_enable; clock->caps.verify = ptp_dp83640_verify; /* diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c index 6deac6d32f57..414fdf1f343f 100644 --- a/drivers/net/phy/mdio-bcm-unimac.c +++ b/drivers/net/phy/mdio-bcm-unimac.c @@ -187,7 +187,7 @@ static int unimac_mdio_remove(struct platform_device *pdev) return 0; } -static struct of_device_id unimac_mdio_ids[] = { +static const struct of_device_id unimac_mdio_ids[] = { { .compatible = "brcm,genet-mdio-v4", }, { .compatible = "brcm,genet-mdio-v3", }, { .compatible = "brcm,genet-mdio-v2", }, diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c index 0a0578a592b8..49ce7ece5af3 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -249,7 +249,7 @@ static int mdio_gpio_remove(struct platform_device *pdev) return 0; } -static struct of_device_id mdio_gpio_of_match[] = { +static const struct of_device_id mdio_gpio_of_match[] = { { .compatible = "virtual,mdio-gpio", }, { /* sentinel */ } }; diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c index 320eb15315c8..1a87a585e74d 100644 --- a/drivers/net/phy/mdio-mux-gpio.c +++ b/drivers/net/phy/mdio-mux-gpio.c @@ -99,7 +99,7 @@ static int mdio_mux_gpio_remove(struct platform_device *pdev) return 0; } -static struct of_device_id mdio_mux_gpio_match[] = { +static const struct of_device_id mdio_mux_gpio_match[] = { { .compatible = "mdio-mux-gpio", }, diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/phy/mdio-mux-mmioreg.c index 0aa985c74014..2377c1341172 100644 --- a/drivers/net/phy/mdio-mux-mmioreg.c +++ b/drivers/net/phy/mdio-mux-mmioreg.c @@ -145,7 +145,7 @@ static int mdio_mux_mmioreg_remove(struct platform_device *pdev) return 0; } -static struct of_device_id mdio_mux_mmioreg_match[] = { +static const struct of_device_id mdio_mux_mmioreg_match[] = { { .compatible = "mdio-mux-mmioreg", }, diff --git a/drivers/net/phy/mdio-octeon.c b/drivers/net/phy/mdio-octeon.c index c81052486edc..c838ad6155f7 100644 --- a/drivers/net/phy/mdio-octeon.c +++ b/drivers/net/phy/mdio-octeon.c @@ -252,7 +252,7 @@ static int octeon_mdiobus_remove(struct platform_device *pdev) return 0; } -static struct of_device_id octeon_mdiobus_match[] = { +static const struct of_device_id octeon_mdiobus_match[] = { { .compatible = "cavium,octeon-3860-mdio", }, diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 1dc628ffce2b..e3bfbd4d0136 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) nf_reset(skb); skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(skb, NULL); + ip_select_ident(sock_net(sk), skb, NULL); ip_send_check(iph); ip_local_out(skb); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index a23319fc78ca..6928448f6b7f 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1979,6 +1979,7 @@ static const struct net_device_ops team_netdev_ops = { .ndo_change_carrier = team_change_carrier, .ndo_bridge_setlink = ndo_dflt_netdev_switch_port_bridge_setlink, .ndo_bridge_dellink = ndo_dflt_netdev_switch_port_bridge_dellink, + .ndo_features_check = passthru_features_check, }; /*********************** diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index 3eed708a6182..e221bfcee76b 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -46,8 +46,7 @@ enum cx82310_status { }; #define CMD_PACKET_SIZE 64 -/* first command after power on can take around 8 seconds */ -#define CMD_TIMEOUT 15000 +#define CMD_TIMEOUT 100 #define CMD_REPLY_RETRY 5 #define CX82310_MTU 1514 @@ -78,8 +77,9 @@ static int cx82310_cmd(struct usbnet *dev, enum cx82310_cmd cmd, bool reply, ret = usb_bulk_msg(udev, usb_sndbulkpipe(udev, CMD_EP), buf, CMD_PACKET_SIZE, &actual_len, CMD_TIMEOUT); if (ret < 0) { - dev_err(&dev->udev->dev, "send command %#x: error %d\n", - cmd, ret); + if (cmd != CMD_GET_LINK_STATUS) + dev_err(&dev->udev->dev, "send command %#x: error %d\n", + cmd, ret); goto end; } @@ -90,8 +90,10 @@ static int cx82310_cmd(struct usbnet *dev, enum cx82310_cmd cmd, bool reply, buf, CMD_PACKET_SIZE, &actual_len, CMD_TIMEOUT); if (ret < 0) { - dev_err(&dev->udev->dev, - "reply receive error %d\n", ret); + if (cmd != CMD_GET_LINK_STATUS) + dev_err(&dev->udev->dev, + "reply receive error %d\n", + ret); goto end; } if (actual_len > 0) @@ -134,6 +136,8 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) int ret; char buf[15]; struct usb_device *udev = dev->udev; + u8 link[3]; + int timeout = 50; /* avoid ADSL modems - continue only if iProduct is "USB NET CARD" */ if (usb_string(udev, udev->descriptor.iProduct, buf, sizeof(buf)) > 0 @@ -160,6 +164,20 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) if (!dev->partial_data) return -ENOMEM; + /* wait for firmware to become ready (indicated by the link being up) */ + while (--timeout) { + ret = cx82310_cmd(dev, CMD_GET_LINK_STATUS, true, NULL, 0, + link, sizeof(link)); + /* the command can time out during boot - it's not an error */ + if (!ret && link[0] == 1 && link[2] == 1) + break; + msleep(500); + } + if (!timeout) { + dev_err(&udev->dev, "firmware not ready in time\n"); + return -ETIMEDOUT; + } + /* enable ethernet mode (?) */ ret = cx82310_cmd(dev, CMD_ETHERNET_MODE, true, "\x01", 1, NULL, 0); if (ret) { @@ -300,9 +318,18 @@ static const struct driver_info cx82310_info = { .tx_fixup = cx82310_tx_fixup, }; +#define USB_DEVICE_CLASS(vend, prod, cl, sc, pr) \ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ + USB_DEVICE_ID_MATCH_DEV_INFO, \ + .idVendor = (vend), \ + .idProduct = (prod), \ + .bDeviceClass = (cl), \ + .bDeviceSubClass = (sc), \ + .bDeviceProtocol = (pr) + static const struct usb_device_id products[] = { { - USB_DEVICE_AND_INTERFACE_INFO(0x0572, 0xcb01, 0xff, 0, 0), + USB_DEVICE_CLASS(0x0572, 0xcb01, 0xff, 0, 0), .driver_info = (unsigned long) &cx82310_info }, { }, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index f1ff3666f090..a829930dac15 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -749,9 +749,9 @@ static int virtnet_poll(struct napi_struct *napi, int budget) { struct receive_queue *rq = container_of(napi, struct receive_queue, napi); - unsigned int r, received = 0; + unsigned int r, received; - received += virtnet_receive(rq, budget - received); + received = virtnet_receive(rq, budget); /* Out of packets? */ if (received < budget) { @@ -939,8 +939,12 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan(skb); nf_reset(skb); - /* Apparently nice girls don't return TX_BUSY; stop the queue - * before it gets out of hand. Naturally, this wastes entries. */ + /* It is better to stop queue if running out of space + * instead of forcing queuing layer to requeue the skb + * by returning TX_BUSY (and cause a BUG message). + * Since most packets only take 1 or 2 ring slots + * this means 16 slots are typically wasted. + */ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { netif_stop_subqueue(dev, qnum); if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { @@ -1448,8 +1452,10 @@ static void virtnet_free_queues(struct virtnet_info *vi) { int i; - for (i = 0; i < vi->max_queue_pairs; i++) + for (i = 0; i < vi->max_queue_pairs; i++) { + napi_hash_del(&vi->rq[i].napi); netif_napi_del(&vi->rq[i].napi); + } kfree(vi->rq); kfree(vi->sq); @@ -1948,11 +1954,8 @@ static int virtnet_freeze(struct virtio_device *vdev) cancel_delayed_work_sync(&vi->refill); if (netif_running(vi->dev)) { - for (i = 0; i < vi->max_queue_pairs; i++) { + for (i = 0; i < vi->max_queue_pairs; i++) napi_disable(&vi->rq[i].napi); - napi_hash_del(&vi->rq[i].napi); - netif_napi_del(&vi->rq[i].napi); - } } remove_vq_common(vi); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 25d92d4fc625..6080f8e7b0cd 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -127,10 +127,6 @@ struct vxlan_dev { __u8 ttl; u32 flags; /* VXLAN_F_* in vxlan.h */ - struct work_struct sock_work; - struct work_struct igmp_join; - struct work_struct igmp_leave; - unsigned long age_interval; struct timer_list age_timer; spinlock_t hash_lock; @@ -144,8 +140,6 @@ struct vxlan_dev { static u32 vxlan_salt __read_mostly; static struct workqueue_struct *vxlan_wq; -static void vxlan_sock_work(struct work_struct *work); - #if IS_ENABLED(CONFIG_IPV6) static inline bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b) @@ -1072,11 +1066,6 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) return false; } -static void vxlan_sock_hold(struct vxlan_sock *vs) -{ - atomic_inc(&vs->refcnt); -} - void vxlan_sock_release(struct vxlan_sock *vs) { struct sock *sk = vs->sock->sk; @@ -1095,17 +1084,16 @@ void vxlan_sock_release(struct vxlan_sock *vs) } EXPORT_SYMBOL_GPL(vxlan_sock_release); -/* Callback to update multicast group membership when first VNI on +/* Update multicast group membership when first VNI on * multicast asddress is brought up - * Done as workqueue because ip_mc_join_group acquires RTNL. */ -static void vxlan_igmp_join(struct work_struct *work) +static int vxlan_igmp_join(struct vxlan_dev *vxlan) { - struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join); struct vxlan_sock *vs = vxlan->vn_sock; struct sock *sk = vs->sock->sk; union vxlan_addr *ip = &vxlan->default_dst.remote_ip; int ifindex = vxlan->default_dst.remote_ifindex; + int ret = -EINVAL; lock_sock(sk); if (ip->sa.sa_family == AF_INET) { @@ -1114,27 +1102,26 @@ static void vxlan_igmp_join(struct work_struct *work) .imr_ifindex = ifindex, }; - ip_mc_join_group(sk, &mreq); + ret = ip_mc_join_group(sk, &mreq); #if IS_ENABLED(CONFIG_IPV6) } else { - ipv6_stub->ipv6_sock_mc_join(sk, ifindex, - &ip->sin6.sin6_addr); + ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex, + &ip->sin6.sin6_addr); #endif } release_sock(sk); - vxlan_sock_release(vs); - dev_put(vxlan->dev); + return ret; } /* Inverse of vxlan_igmp_join when last VNI is brought down */ -static void vxlan_igmp_leave(struct work_struct *work) +static int vxlan_igmp_leave(struct vxlan_dev *vxlan) { - struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave); struct vxlan_sock *vs = vxlan->vn_sock; struct sock *sk = vs->sock->sk; union vxlan_addr *ip = &vxlan->default_dst.remote_ip; int ifindex = vxlan->default_dst.remote_ifindex; + int ret = -EINVAL; lock_sock(sk); if (ip->sa.sa_family == AF_INET) { @@ -1143,18 +1130,16 @@ static void vxlan_igmp_leave(struct work_struct *work) .imr_ifindex = ifindex, }; - ip_mc_leave_group(sk, &mreq); + ret = ip_mc_leave_group(sk, &mreq); #if IS_ENABLED(CONFIG_IPV6) } else { - ipv6_stub->ipv6_sock_mc_drop(sk, ifindex, - &ip->sin6.sin6_addr); + ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex, + &ip->sin6.sin6_addr); #endif } - release_sock(sk); - vxlan_sock_release(vs); - dev_put(vxlan->dev); + return ret; } static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, @@ -1218,7 +1203,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto drop; flags &= ~VXLAN_HF_RCO; - vni &= VXLAN_VID_MASK; + vni &= VXLAN_VNI_MASK; } /* For backwards compatibility, only allow reserved fields to be @@ -1239,7 +1224,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) flags &= ~VXLAN_GBP_USED_BITS; } - if (flags || (vni & ~VXLAN_VID_MASK)) { + if (flags || vni & ~VXLAN_VNI_MASK) { /* If there are any unprocessed flags remaining treat * this as a malformed packet. This behavior diverges from * VXLAN RFC (RFC7348) which stipulates that bits in reserved @@ -2175,37 +2160,22 @@ static void vxlan_cleanup(unsigned long arg) static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) { + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __u32 vni = vxlan->default_dst.remote_vni; vxlan->vn_sock = vs; + spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni)); + spin_unlock(&vn->sock_lock); } /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { - struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); - struct vxlan_sock *vs; - bool ipv6 = vxlan->flags & VXLAN_F_IPV6; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, - vxlan->dst_port, vxlan->flags); - if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) { - /* If we have a socket with same port already, reuse it */ - vxlan_vs_add_dev(vs, vxlan); - } else { - /* otherwise make new socket outside of RTNL */ - dev_hold(dev); - queue_work(vxlan_wq, &vxlan->sock_work); - } - spin_unlock(&vn->sock_lock); - return 0; } @@ -2223,12 +2193,9 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan) static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_sock *vs = vxlan->vn_sock; vxlan_fdb_delete_default(vxlan); - if (vs) - vxlan_sock_release(vs); free_percpu(dev->tstats); } @@ -2236,22 +2203,28 @@ static void vxlan_uninit(struct net_device *dev) static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_sock *vs = vxlan->vn_sock; + struct vxlan_sock *vs; + int ret = 0; - /* socket hasn't been created */ - if (!vs) - return -ENOTCONN; + vs = vxlan_sock_add(vxlan->net, vxlan->dst_port, vxlan_rcv, NULL, + false, vxlan->flags); + if (IS_ERR(vs)) + return PTR_ERR(vs); + + vxlan_vs_add_dev(vs, vxlan); if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) { - vxlan_sock_hold(vs); - dev_hold(dev); - queue_work(vxlan_wq, &vxlan->igmp_join); + ret = vxlan_igmp_join(vxlan); + if (ret) { + vxlan_sock_release(vs); + return ret; + } } if (vxlan->age_interval) mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); - return 0; + return ret; } /* Purge the forwarding table */ @@ -2279,19 +2252,21 @@ static int vxlan_stop(struct net_device *dev) struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_sock *vs = vxlan->vn_sock; + int ret = 0; - if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) && + if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) && !vxlan_group_used(vn, vxlan)) { - vxlan_sock_hold(vs); - dev_hold(dev); - queue_work(vxlan_wq, &vxlan->igmp_leave); + ret = vxlan_igmp_leave(vxlan); + if (ret) + return ret; } del_timer_sync(&vxlan->age_timer); vxlan_flush(vxlan); + vxlan_sock_release(vs); - return 0; + return ret; } /* Stub, nothing needs to be done. */ @@ -2402,9 +2377,6 @@ static void vxlan_setup(struct net_device *dev) INIT_LIST_HEAD(&vxlan->next); spin_lock_init(&vxlan->hash_lock); - INIT_WORK(&vxlan->igmp_join, vxlan_igmp_join); - INIT_WORK(&vxlan->igmp_leave, vxlan_igmp_leave); - INIT_WORK(&vxlan->sock_work, vxlan_sock_work); init_timer_deferrable(&vxlan->age_timer); vxlan->age_timer.function = vxlan_cleanup; @@ -2551,6 +2523,8 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, sock = vxlan_create_sock(net, ipv6, port, flags); if (IS_ERR(sock)) { + pr_info("Cannot bind port %d, err=%ld\n", ntohs(port), + PTR_ERR(sock)); kfree(vs); return ERR_CAST(sock); } @@ -2590,45 +2564,23 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, struct vxlan_sock *vs; bool ipv6 = flags & VXLAN_F_IPV6; - vs = vxlan_socket_create(net, port, rcv, data, flags); - if (!IS_ERR(vs)) - return vs; - - if (no_share) /* Return error if sharing is not allowed. */ - return vs; - - spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port, flags); - if (vs && ((vs->rcv != rcv) || - !atomic_add_unless(&vs->refcnt, 1, 0))) - vs = ERR_PTR(-EBUSY); - spin_unlock(&vn->sock_lock); - - if (!vs) - vs = ERR_PTR(-EINVAL); + if (!no_share) { + spin_lock(&vn->sock_lock); + vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port, + flags); + if (vs && vs->rcv == rcv) { + if (!atomic_add_unless(&vs->refcnt, 1, 0)) + vs = ERR_PTR(-EBUSY); + spin_unlock(&vn->sock_lock); + return vs; + } + spin_unlock(&vn->sock_lock); + } - return vs; + return vxlan_socket_create(net, port, rcv, data, flags); } EXPORT_SYMBOL_GPL(vxlan_sock_add); -/* Scheduled at device creation to bind to a socket */ -static void vxlan_sock_work(struct work_struct *work) -{ - struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, sock_work); - struct net *net = vxlan->net; - struct vxlan_net *vn = net_generic(net, vxlan_net_id); - __be16 port = vxlan->dst_port; - struct vxlan_sock *nvs; - - nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags); - spin_lock(&vn->sock_lock); - if (!IS_ERR(nvs)) - vxlan_vs_add_dev(nvs, vxlan); - spin_unlock(&vn->sock_lock); - - dev_put(vxlan->dev); -} - static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c index ac99798570e8..ea4843be773c 100644 --- a/drivers/net/wireless/b43/main.c +++ b/drivers/net/wireless/b43/main.c @@ -5370,6 +5370,7 @@ static void b43_supported_bands(struct b43_wldev *dev, bool *have_2ghz_phy, case 0x432a: /* BCM4321 */ case 0x432d: /* BCM4322 */ case 0x4352: /* BCM43222 */ + case 0x435a: /* BCM43228 */ case 0x4333: /* BCM4331 */ case 0x43a2: /* BCM4360 */ case 0x43b3: /* BCM4352 */ diff --git a/drivers/net/wireless/brcm80211/brcmfmac/vendor.c b/drivers/net/wireless/brcm80211/brcmfmac/vendor.c index 50cdf7090198..8eff2753abad 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/vendor.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/vendor.c @@ -39,13 +39,22 @@ static int brcmf_cfg80211_vndr_cmds_dcmd_handler(struct wiphy *wiphy, void *dcmd_buf = NULL, *wr_pointer; u16 msglen, maxmsglen = PAGE_SIZE - 0x100; - brcmf_dbg(TRACE, "cmd %x set %d len %d\n", cmdhdr->cmd, cmdhdr->set, - cmdhdr->len); + if (len < sizeof(*cmdhdr)) { + brcmf_err("vendor command too short: %d\n", len); + return -EINVAL; + } vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev); ifp = vif->ifp; - len -= sizeof(struct brcmf_vndr_dcmd_hdr); + brcmf_dbg(TRACE, "ifidx=%d, cmd=%d\n", ifp->ifidx, cmdhdr->cmd); + + if (cmdhdr->offset > len) { + brcmf_err("bad buffer offset %d > %d\n", cmdhdr->offset, len); + return -EINVAL; + } + + len -= cmdhdr->offset; ret_len = cmdhdr->len; if (ret_len > 0 || len > 0) { if (len > BRCMF_DCMD_MAXLEN) { diff --git a/drivers/net/wireless/iwlwifi/iwl-1000.c b/drivers/net/wireless/iwlwifi/iwl-1000.c index c3817fae16c0..06f6cc08f451 100644 --- a/drivers/net/wireless/iwlwifi/iwl-1000.c +++ b/drivers/net/wireless/iwlwifi/iwl-1000.c @@ -95,7 +95,8 @@ static const struct iwl_eeprom_params iwl1000_eeprom_params = { .nvm_calib_ver = EEPROM_1000_TX_POWER_VERSION, \ .base_params = &iwl1000_base_params, \ .eeprom_params = &iwl1000_eeprom_params, \ - .led_mode = IWL_LED_BLINK + .led_mode = IWL_LED_BLINK, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl1000_bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N 1000 BGN", @@ -121,7 +122,8 @@ const struct iwl_cfg iwl1000_bg_cfg = { .base_params = &iwl1000_base_params, \ .eeprom_params = &iwl1000_eeprom_params, \ .led_mode = IWL_LED_RF_STATE, \ - .rx_with_siso_diversity = true + .rx_with_siso_diversity = true, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl100_bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N 100 BGN", diff --git a/drivers/net/wireless/iwlwifi/iwl-2000.c b/drivers/net/wireless/iwlwifi/iwl-2000.c index 21e5d0843a62..890b95f497d6 100644 --- a/drivers/net/wireless/iwlwifi/iwl-2000.c +++ b/drivers/net/wireless/iwlwifi/iwl-2000.c @@ -123,7 +123,9 @@ static const struct iwl_eeprom_params iwl20x0_eeprom_params = { .nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ .base_params = &iwl2000_base_params, \ .eeprom_params = &iwl20x0_eeprom_params, \ - .led_mode = IWL_LED_RF_STATE + .led_mode = IWL_LED_RF_STATE, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K + const struct iwl_cfg iwl2000_2bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N 2200 BGN", @@ -149,7 +151,8 @@ const struct iwl_cfg iwl2000_2bgn_d_cfg = { .nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ .base_params = &iwl2030_base_params, \ .eeprom_params = &iwl20x0_eeprom_params, \ - .led_mode = IWL_LED_RF_STATE + .led_mode = IWL_LED_RF_STATE, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl2030_2bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N 2230 BGN", @@ -170,7 +173,8 @@ const struct iwl_cfg iwl2030_2bgn_cfg = { .base_params = &iwl2000_base_params, \ .eeprom_params = &iwl20x0_eeprom_params, \ .led_mode = IWL_LED_RF_STATE, \ - .rx_with_siso_diversity = true + .rx_with_siso_diversity = true, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl105_bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N 105 BGN", @@ -197,7 +201,8 @@ const struct iwl_cfg iwl105_bgn_d_cfg = { .base_params = &iwl2030_base_params, \ .eeprom_params = &iwl20x0_eeprom_params, \ .led_mode = IWL_LED_RF_STATE, \ - .rx_with_siso_diversity = true + .rx_with_siso_diversity = true, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl135_bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N 135 BGN", diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c index 332bbede39e5..724194e23414 100644 --- a/drivers/net/wireless/iwlwifi/iwl-5000.c +++ b/drivers/net/wireless/iwlwifi/iwl-5000.c @@ -93,7 +93,8 @@ static const struct iwl_eeprom_params iwl5000_eeprom_params = { .nvm_calib_ver = EEPROM_5000_TX_POWER_VERSION, \ .base_params = &iwl5000_base_params, \ .eeprom_params = &iwl5000_eeprom_params, \ - .led_mode = IWL_LED_BLINK + .led_mode = IWL_LED_BLINK, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl5300_agn_cfg = { .name = "Intel(R) Ultimate N WiFi Link 5300 AGN", @@ -158,7 +159,8 @@ const struct iwl_cfg iwl5350_agn_cfg = { .base_params = &iwl5000_base_params, \ .eeprom_params = &iwl5000_eeprom_params, \ .led_mode = IWL_LED_BLINK, \ - .internal_wimax_coex = true + .internal_wimax_coex = true, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl5150_agn_cfg = { .name = "Intel(R) WiMAX/WiFi Link 5150 AGN", diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index 8f2c3c8c6b84..21b2630763dc 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -145,7 +145,8 @@ static const struct iwl_eeprom_params iwl6000_eeprom_params = { .nvm_calib_ver = EEPROM_6005_TX_POWER_VERSION, \ .base_params = &iwl6000_g2_base_params, \ .eeprom_params = &iwl6000_eeprom_params, \ - .led_mode = IWL_LED_RF_STATE + .led_mode = IWL_LED_RF_STATE, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl6005_2agn_cfg = { .name = "Intel(R) Centrino(R) Advanced-N 6205 AGN", @@ -199,7 +200,8 @@ const struct iwl_cfg iwl6005_2agn_mow2_cfg = { .nvm_calib_ver = EEPROM_6030_TX_POWER_VERSION, \ .base_params = &iwl6000_g2_base_params, \ .eeprom_params = &iwl6000_eeprom_params, \ - .led_mode = IWL_LED_RF_STATE + .led_mode = IWL_LED_RF_STATE, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl6030_2agn_cfg = { .name = "Intel(R) Centrino(R) Advanced-N 6230 AGN", @@ -235,7 +237,8 @@ const struct iwl_cfg iwl6030_2bg_cfg = { .nvm_calib_ver = EEPROM_6030_TX_POWER_VERSION, \ .base_params = &iwl6000_g2_base_params, \ .eeprom_params = &iwl6000_eeprom_params, \ - .led_mode = IWL_LED_RF_STATE + .led_mode = IWL_LED_RF_STATE, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl6035_2agn_cfg = { .name = "Intel(R) Centrino(R) Advanced-N 6235 AGN", @@ -290,7 +293,8 @@ const struct iwl_cfg iwl130_bg_cfg = { .nvm_calib_ver = EEPROM_6000_TX_POWER_VERSION, \ .base_params = &iwl6000_base_params, \ .eeprom_params = &iwl6000_eeprom_params, \ - .led_mode = IWL_LED_BLINK + .led_mode = IWL_LED_BLINK, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl6000i_2agn_cfg = { .name = "Intel(R) Centrino(R) Advanced-N 6200 AGN", @@ -322,7 +326,8 @@ const struct iwl_cfg iwl6000i_2bg_cfg = { .base_params = &iwl6050_base_params, \ .eeprom_params = &iwl6000_eeprom_params, \ .led_mode = IWL_LED_BLINK, \ - .internal_wimax_coex = true + .internal_wimax_coex = true, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl6050_2agn_cfg = { .name = "Intel(R) Centrino(R) Advanced-N + WiMAX 6250 AGN", @@ -347,7 +352,8 @@ const struct iwl_cfg iwl6050_2abg_cfg = { .base_params = &iwl6050_base_params, \ .eeprom_params = &iwl6000_eeprom_params, \ .led_mode = IWL_LED_BLINK, \ - .internal_wimax_coex = true + .internal_wimax_coex = true, \ + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K const struct iwl_cfg iwl6150_bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN", diff --git a/drivers/net/wireless/iwlwifi/mvm/coex.c b/drivers/net/wireless/iwlwifi/mvm/coex.c index ce99572a982d..638ec0945009 100644 --- a/drivers/net/wireless/iwlwifi/mvm/coex.c +++ b/drivers/net/wireless/iwlwifi/mvm/coex.c @@ -793,7 +793,8 @@ static void iwl_mvm_bt_notif_iterator(void *_data, u8 *mac, if (!vif->bss_conf.assoc) smps_mode = IEEE80211_SMPS_AUTOMATIC; - if (IWL_COEX_IS_RRC_ON(mvm->last_bt_notif.ttc_rrc_status, + if (mvmvif->phy_ctxt && + IWL_COEX_IS_RRC_ON(mvm->last_bt_notif.ttc_rrc_status, mvmvif->phy_ctxt->id)) smps_mode = IEEE80211_SMPS_AUTOMATIC; diff --git a/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c b/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c index 9717ee61928c..05d31713ed38 100644 --- a/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c +++ b/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c @@ -832,7 +832,8 @@ static void iwl_mvm_bt_notif_iterator(void *_data, u8 *mac, if (!vif->bss_conf.assoc) smps_mode = IEEE80211_SMPS_AUTOMATIC; - if (data->notif->rrc_enabled & BIT(mvmvif->phy_ctxt->id)) + if (mvmvif->phy_ctxt && + data->notif->rrc_enabled & BIT(mvmvif->phy_ctxt->id)) smps_mode = IEEE80211_SMPS_AUTOMATIC; IWL_DEBUG_COEX(data->mvm, diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index 204255423d99..7396b52262b5 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -402,7 +402,10 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) hw->wiphy->bands[IEEE80211_BAND_5GHZ] = &mvm->nvm_data->bands[IEEE80211_BAND_5GHZ]; - if (mvm->fw->ucode_capa.capa[0] & IWL_UCODE_TLV_CAPA_BEAMFORMER) + if ((mvm->fw->ucode_capa.capa[0] & + IWL_UCODE_TLV_CAPA_BEAMFORMER) && + (mvm->fw->ucode_capa.api[0] & + IWL_UCODE_TLV_API_LQ_SS_PARAMS)) hw->wiphy->bands[IEEE80211_BAND_5GHZ]->vht_cap.cap |= IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE; } @@ -2271,7 +2274,19 @@ static void iwl_mvm_mac_cancel_hw_scan(struct ieee80211_hw *hw, mutex_lock(&mvm->mutex); - iwl_mvm_cancel_scan(mvm); + /* Due to a race condition, it's possible that mac80211 asks + * us to stop a hw_scan when it's already stopped. This can + * happen, for instance, if we stopped the scan ourselves, + * called ieee80211_scan_completed() and the userspace called + * cancel scan scan before ieee80211_scan_work() could run. + * To handle that, simply return if the scan is not running. + */ + /* FIXME: for now, we ignore this race for UMAC scans, since + * they don't set the scan_status. + */ + if ((mvm->scan_status == IWL_MVM_SCAN_OS) || + (mvm->fw->ucode_capa.capa[0] & IWL_UCODE_TLV_CAPA_UMAC_SCAN)) + iwl_mvm_cancel_scan(mvm); mutex_unlock(&mvm->mutex); } @@ -2609,12 +2624,29 @@ static int iwl_mvm_mac_sched_scan_stop(struct ieee80211_hw *hw, int ret; mutex_lock(&mvm->mutex); + + /* Due to a race condition, it's possible that mac80211 asks + * us to stop a sched_scan when it's already stopped. This + * can happen, for instance, if we stopped the scan ourselves, + * called ieee80211_sched_scan_stopped() and the userspace called + * stop sched scan scan before ieee80211_sched_scan_stopped_work() + * could run. To handle this, simply return if the scan is + * not running. + */ + /* FIXME: for now, we ignore this race for UMAC scans, since + * they don't set the scan_status. + */ + if (mvm->scan_status != IWL_MVM_SCAN_SCHED && + !(mvm->fw->ucode_capa.capa[0] & IWL_UCODE_TLV_CAPA_UMAC_SCAN)) { + mutex_unlock(&mvm->mutex); + return 0; + } + ret = iwl_mvm_scan_offload_stop(mvm, false); mutex_unlock(&mvm->mutex); iwl_mvm_wait_for_async_handlers(mvm); return ret; - } static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c index f0946b5dd7c8..a75bb150ea27 100644 --- a/drivers/net/wireless/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/iwlwifi/mvm/scan.c @@ -587,8 +587,10 @@ int iwl_mvm_scan_offload_stop(struct iwl_mvm *mvm, bool notify) if (mvm->scan_status == IWL_MVM_SCAN_NONE) return 0; - if (iwl_mvm_is_radio_killed(mvm)) + if (iwl_mvm_is_radio_killed(mvm)) { + ret = 0; goto out; + } iwl_init_notification_wait(&mvm->notif_wait, &wait_scan_done, scan_done_notif, @@ -600,16 +602,14 @@ int iwl_mvm_scan_offload_stop(struct iwl_mvm *mvm, bool notify) IWL_DEBUG_SCAN(mvm, "Send stop %sscan failed %d\n", sched ? "offloaded " : "", ret); iwl_remove_notification(&mvm->notif_wait, &wait_scan_done); - return ret; + goto out; } IWL_DEBUG_SCAN(mvm, "Successfully sent stop %sscan\n", sched ? "offloaded " : ""); ret = iwl_wait_notification(&mvm->notif_wait, &wait_scan_done, 1 * HZ); - if (ret) - return ret; - +out: /* * Clear the scan status so the next scan requests will succeed. This * also ensures the Rx handler doesn't do anything, as the scan was @@ -619,7 +619,6 @@ int iwl_mvm_scan_offload_stop(struct iwl_mvm *mvm, bool notify) if (mvm->scan_status == IWL_MVM_SCAN_OS) iwl_mvm_unref(mvm, IWL_MVM_REF_SCAN); -out: mvm->scan_status = IWL_MVM_SCAN_NONE; if (notify) { @@ -629,7 +628,7 @@ out: ieee80211_scan_completed(mvm->hw, true); } - return 0; + return ret; } static void iwl_mvm_unified_scan_fill_tx_cmd(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/iwlwifi/mvm/time-event.c b/drivers/net/wireless/iwlwifi/mvm/time-event.c index 54fafbf9a711..f8d6f306dd76 100644 --- a/drivers/net/wireless/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/iwlwifi/mvm/time-event.c @@ -750,8 +750,7 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm) * request */ list_for_each_entry(te_data, &mvm->time_event_list, list) { - if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE && - te_data->running) { + if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) { mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); is_p2p = true; goto remove_te; @@ -766,10 +765,8 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm) * request */ list_for_each_entry(te_data, &mvm->aux_roc_te_list, list) { - if (te_data->running) { - mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); - goto remove_te; - } + mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); + goto remove_te; } remove_te: diff --git a/drivers/net/wireless/orinoco/airport.c b/drivers/net/wireless/orinoco/airport.c index 0ca8b1455cd9..77e6c53040a3 100644 --- a/drivers/net/wireless/orinoco/airport.c +++ b/drivers/net/wireless/orinoco/airport.c @@ -228,7 +228,7 @@ MODULE_AUTHOR("Benjamin Herrenschmidt <benh@kernel.crashing.org>"); MODULE_DESCRIPTION("Driver for the Apple Airport wireless card."); MODULE_LICENSE("Dual MPL/GPL"); -static struct of_device_id airport_match[] = { +static const struct of_device_id airport_match[] = { { .name = "radio", }, diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c index 1d4677460711..074f716020aa 100644 --- a/drivers/net/wireless/rtlwifi/base.c +++ b/drivers/net/wireless/rtlwifi/base.c @@ -1386,8 +1386,11 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx) } return true; - } else if (0x86DD == ether_type) { - return true; + } else if (ETH_P_IPV6 == ether_type) { + /* TODO: Handle any IPv6 cases that need special handling. + * For now, always return false + */ + goto end; } end: diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 589fa256256b..8a495b318b6f 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -238,6 +238,8 @@ struct xenvif { unsigned int num_queues; /* active queues, resource allocated */ unsigned int stalled_queues; + struct xenbus_watch credit_watch; + spinlock_t lock; #ifdef CONFIG_DEBUG_FS @@ -260,6 +262,8 @@ static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif) return to_xenbus_device(vif->dev->dev.parent); } +void xenvif_tx_credit_callback(unsigned long data); + struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, unsigned int handle); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index d2ada7cda97a..1a83e190fc15 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -463,6 +463,7 @@ int xenvif_init_queue(struct xenvif_queue *queue) queue->credit_bytes = queue->remaining_credit = ~0UL; queue->credit_usec = 0UL; init_timer(&queue->credit_timeout); + queue->credit_timeout.function = xenvif_tx_credit_callback; queue->credit_window_start = get_jiffies_64(); queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index cab9f5257f57..b8c471813f4c 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -96,6 +96,7 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, static void make_tx_response(struct xenvif_queue *queue, struct xen_netif_tx_request *txp, s8 st); +static void push_tx_responses(struct xenvif_queue *queue); static inline int tx_work_todo(struct xenvif_queue *queue); @@ -641,7 +642,7 @@ static void tx_add_credit(struct xenvif_queue *queue) queue->remaining_credit = min(max_credit, max_burst); } -static void tx_credit_callback(unsigned long data) +void xenvif_tx_credit_callback(unsigned long data) { struct xenvif_queue *queue = (struct xenvif_queue *)data; tx_add_credit(queue); @@ -655,15 +656,10 @@ static void xenvif_tx_err(struct xenvif_queue *queue, unsigned long flags; do { - int notify; - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, XEN_NETIF_RSP_ERROR); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + push_tx_responses(queue); spin_unlock_irqrestore(&queue->response_lock, flags); - if (notify) - notify_remote_via_irq(queue->tx_irq); - if (cons == end) break; txp = RING_GET_REQUEST(&queue->tx, cons++); @@ -1169,8 +1165,6 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) if (size > queue->remaining_credit) { queue->credit_timeout.data = (unsigned long)queue; - queue->credit_timeout.function = - tx_credit_callback; mod_timer(&queue->credit_timeout, next_credit); queue->credit_window_start = next_credit; @@ -1657,7 +1651,6 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, { struct pending_tx_info *pending_tx_info; pending_ring_idx_t index; - int notify; unsigned long flags; pending_tx_info = &queue->pending_tx_info[pending_idx]; @@ -1673,12 +1666,9 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, index = pending_index(queue->pending_prod++); queue->pending_ring[index] = pending_idx; - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + push_tx_responses(queue); spin_unlock_irqrestore(&queue->response_lock, flags); - - if (notify) - notify_remote_via_irq(queue->tx_irq); } @@ -1699,6 +1689,15 @@ static void make_tx_response(struct xenvif_queue *queue, queue->tx.rsp_prod_pvt = ++i; } +static void push_tx_responses(struct xenvif_queue *queue) +{ + int notify; + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + if (notify) + notify_remote_via_irq(queue->tx_irq); +} + static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, u16 id, s8 st, diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 794204e34fba..3d8dbf5f2d39 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -41,6 +41,7 @@ static void connect(struct backend_info *be); static int read_xenbus_vif_flags(struct backend_info *be); static int backend_create_xenvif(struct backend_info *be); static void unregister_hotplug_status_watch(struct backend_info *be); +static void xen_unregister_watchers(struct xenvif *vif); static void set_backend_state(struct backend_info *be, enum xenbus_state state); @@ -232,6 +233,7 @@ static int netback_remove(struct xenbus_device *dev) unregister_hotplug_status_watch(be); if (be->vif) { kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); + xen_unregister_watchers(be->vif); xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); xenvif_free(be->vif); be->vif = NULL; @@ -430,6 +432,7 @@ static int backend_create_xenvif(struct backend_info *be) static void backend_disconnect(struct backend_info *be) { if (be->vif) { + xen_unregister_watchers(be->vif); #ifdef CONFIG_DEBUG_FS xenvif_debugfs_delif(be->vif); #endif /* CONFIG_DEBUG_FS */ @@ -645,6 +648,59 @@ static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[]) return 0; } +static void xen_net_rate_changed(struct xenbus_watch *watch, + const char **vec, unsigned int len) +{ + struct xenvif *vif = container_of(watch, struct xenvif, credit_watch); + struct xenbus_device *dev = xenvif_to_xenbus_device(vif); + unsigned long credit_bytes; + unsigned long credit_usec; + unsigned int queue_index; + + xen_net_read_rate(dev, &credit_bytes, &credit_usec); + for (queue_index = 0; queue_index < vif->num_queues; queue_index++) { + struct xenvif_queue *queue = &vif->queues[queue_index]; + + queue->credit_bytes = credit_bytes; + queue->credit_usec = credit_usec; + if (!mod_timer_pending(&queue->credit_timeout, jiffies) && + queue->remaining_credit > queue->credit_bytes) { + queue->remaining_credit = queue->credit_bytes; + } + } +} + +static int xen_register_watchers(struct xenbus_device *dev, struct xenvif *vif) +{ + int err = 0; + char *node; + unsigned maxlen = strlen(dev->nodename) + sizeof("/rate"); + + node = kmalloc(maxlen, GFP_KERNEL); + if (!node) + return -ENOMEM; + snprintf(node, maxlen, "%s/rate", dev->nodename); + vif->credit_watch.node = node; + vif->credit_watch.callback = xen_net_rate_changed; + err = register_xenbus_watch(&vif->credit_watch); + if (err) { + pr_err("Failed to set watcher %s\n", vif->credit_watch.node); + kfree(node); + vif->credit_watch.node = NULL; + vif->credit_watch.callback = NULL; + } + return err; +} + +static void xen_unregister_watchers(struct xenvif *vif) +{ + if (vif->credit_watch.node) { + unregister_xenbus_watch(&vif->credit_watch); + kfree(vif->credit_watch.node); + vif->credit_watch.node = NULL; + } +} + static void unregister_hotplug_status_watch(struct backend_info *be) { if (be->have_hotplug_status_watch) { @@ -709,6 +765,7 @@ static void connect(struct backend_info *be) } xen_net_read_rate(dev, &credit_bytes, &credit_usec); + xen_register_watchers(dev, be->vif); read_xenbus_vif_flags(be); /* Use the number of queues requested by the frontend */ diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 38d1c51f58b1..7bcaeec876c0 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -84,8 +84,7 @@ config OF_RESOLVE bool config OF_OVERLAY - bool - depends on OF + bool "Device Tree overlays" select OF_DYNAMIC select OF_RESOLVE diff --git a/drivers/of/base.c b/drivers/of/base.c index 0a8aeb8523fe..8f165b112e03 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -714,16 +714,12 @@ static struct device_node *__of_find_node_by_path(struct device_node *parent, const char *path) { struct device_node *child; - int len = strchrnul(path, '/') - path; - int term; + int len; + len = strcspn(path, "/:"); if (!len) return NULL; - term = strchrnul(path, ':') - path; - if (term < len) - len = term; - __for_each_child_of_node(parent, child) { const char *name = strrchr(child->full_name, '/'); if (WARN(!name, "malformed device_node %s\n", child->full_name)) @@ -768,8 +764,12 @@ struct device_node *of_find_node_opts_by_path(const char *path, const char **opt /* The path could begin with an alias */ if (*path != '/') { - char *p = strchrnul(path, '/'); - int len = separator ? separator - path : p - path; + int len; + const char *p = separator; + + if (!p) + p = strchrnul(path, '/'); + len = p - path; /* of_aliases must not be NULL */ if (!of_aliases) @@ -794,6 +794,8 @@ struct device_node *of_find_node_opts_by_path(const char *path, const char **opt path++; /* Increment past '/' delimiter */ np = __of_find_node_by_path(np, path); path = strchrnul(path, '/'); + if (separator && separator < path) + break; } raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 0d7765807f49..1a7980692f25 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -290,7 +290,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar struct device_node *p; const __be32 *intspec, *tmp, *addr; u32 intsize, intlen; - int i, res = -EINVAL; + int i, res; pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index); @@ -323,15 +323,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Get size of interrupt specifier */ tmp = of_get_property(p, "#interrupt-cells", NULL); - if (tmp == NULL) + if (tmp == NULL) { + res = -EINVAL; goto out; + } intsize = be32_to_cpu(*tmp); pr_debug(" intsize=%d intlen=%d\n", intsize, intlen); /* Check index */ - if ((index + 1) * intsize > intlen) + if ((index + 1) * intsize > intlen) { + res = -EINVAL; goto out; + } /* Copy intspec into irq structure */ intspec += index * intsize; diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 352b4f28f82c..dee9270ba547 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -19,6 +19,7 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/err.h> +#include <linux/idr.h> #include "of_private.h" @@ -85,7 +86,7 @@ static int of_overlay_apply_single_device_node(struct of_overlay *ov, struct device_node *target, struct device_node *child) { const char *cname; - struct device_node *tchild, *grandchild; + struct device_node *tchild; int ret = 0; cname = kbasename(child->full_name); diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 0cf9a236d438..52c45c7df07f 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -92,6 +92,16 @@ static void __init of_selftest_find_node_by_name(void) "option path test failed\n"); of_node_put(np); + np = of_find_node_opts_by_path("/testcase-data:test/option", &options); + selftest(np && !strcmp("test/option", options), + "option path test, subcase #1 failed\n"); + of_node_put(np); + + np = of_find_node_opts_by_path("/testcase-data/testcase-device1:test/option", &options); + selftest(np && !strcmp("test/option", options), + "option path test, subcase #2 failed\n"); + of_node_put(np); + np = of_find_node_opts_by_path("/testcase-data:testoption", NULL); selftest(np, "NULL option path test failed\n"); of_node_put(np); @@ -102,6 +112,12 @@ static void __init of_selftest_find_node_by_name(void) "option alias path test failed\n"); of_node_put(np); + np = of_find_node_opts_by_path("testcase-alias:test/alias/option", + &options); + selftest(np && !strcmp("test/alias/option", options), + "option alias path test, subcase #1 failed\n"); + of_node_put(np); + np = of_find_node_opts_by_path("testcase-alias:testaliasoption", NULL); selftest(np, "NULL option alias path test failed\n"); of_node_put(np); @@ -378,9 +394,9 @@ static void __init of_selftest_property_string(void) rc = of_property_match_string(np, "phandle-list-names", "first"); selftest(rc == 0, "first expected:0 got:%i\n", rc); rc = of_property_match_string(np, "phandle-list-names", "second"); - selftest(rc == 1, "second expected:0 got:%i\n", rc); + selftest(rc == 1, "second expected:1 got:%i\n", rc); rc = of_property_match_string(np, "phandle-list-names", "third"); - selftest(rc == 2, "third expected:0 got:%i\n", rc); + selftest(rc == 2, "third expected:2 got:%i\n", rc); rc = of_property_match_string(np, "phandle-list-names", "fourth"); selftest(rc == -ENODATA, "unmatched string; rc=%i\n", rc); rc = of_property_match_string(np, "missing-property", "blah"); @@ -478,7 +494,6 @@ static void __init of_selftest_changeset(void) struct device_node *n1, *n2, *n21, *nremove, *parent, *np; struct of_changeset chgset; - of_changeset_init(&chgset); n1 = __of_node_dup(NULL, "/testcase-data/changeset/n1"); selftest(n1, "testcase setup failure\n"); n2 = __of_node_dup(NULL, "/testcase-data/changeset/n2"); @@ -979,7 +994,7 @@ static int of_path_platform_device_exists(const char *path) return pdev != NULL; } -#if IS_ENABLED(CONFIG_I2C) +#if IS_BUILTIN(CONFIG_I2C) /* get the i2c client device instantiated at the path */ static struct i2c_client *of_path_to_i2c_client(const char *path) @@ -1445,7 +1460,7 @@ static void of_selftest_overlay_11(void) return; } -#if IS_ENABLED(CONFIG_I2C) && IS_ENABLED(CONFIG_OF_OVERLAY) +#if IS_BUILTIN(CONFIG_I2C) && IS_ENABLED(CONFIG_OF_OVERLAY) struct selftest_i2c_bus_data { struct platform_device *pdev; @@ -1584,7 +1599,7 @@ static struct i2c_driver selftest_i2c_dev_driver = { .id_table = selftest_i2c_dev_id, }; -#if IS_ENABLED(CONFIG_I2C_MUX) +#if IS_BUILTIN(CONFIG_I2C_MUX) struct selftest_i2c_mux_data { int nchans; @@ -1695,7 +1710,7 @@ static int of_selftest_overlay_i2c_init(void) "could not register selftest i2c bus driver\n")) return ret; -#if IS_ENABLED(CONFIG_I2C_MUX) +#if IS_BUILTIN(CONFIG_I2C_MUX) ret = i2c_add_driver(&selftest_i2c_mux_driver); if (selftest(ret == 0, "could not register selftest i2c mux driver\n")) @@ -1707,7 +1722,7 @@ static int of_selftest_overlay_i2c_init(void) static void of_selftest_overlay_i2c_cleanup(void) { -#if IS_ENABLED(CONFIG_I2C_MUX) +#if IS_BUILTIN(CONFIG_I2C_MUX) i2c_del_driver(&selftest_i2c_mux_driver); #endif platform_driver_unregister(&selftest_i2c_bus_driver); @@ -1814,7 +1829,7 @@ static void __init of_selftest_overlay(void) of_selftest_overlay_10(); of_selftest_overlay_11(); -#if IS_ENABLED(CONFIG_I2C) +#if IS_BUILTIN(CONFIG_I2C) if (selftest(of_selftest_overlay_i2c_init() == 0, "i2c init failed\n")) goto out; diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c index aab55474dd0d..ee082c0366ec 100644 --- a/drivers/pci/host/pci-xgene.c +++ b/drivers/pci/host/pci-xgene.c @@ -127,7 +127,7 @@ static bool xgene_pcie_hide_rc_bars(struct pci_bus *bus, int offset) return false; } -static int xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, +static void __iomem *xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, int offset) { struct xgene_pcie_port *port = bus->sysdata; @@ -137,7 +137,7 @@ static int xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, return NULL; xgene_pcie_set_rtdid_reg(bus, devfn); - return xgene_pcie_get_cfg_base(bus); + return xgene_pcie_get_cfg_base(bus) + offset; } static struct pci_ops xgene_pcie_ops = { diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index aa012fb3834b..312f23a8429c 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -521,7 +521,8 @@ static ssize_t driver_override_store(struct device *dev, struct pci_dev *pdev = to_pci_dev(dev); char *driver_override, *old = pdev->driver_override, *cp; - if (count > PATH_MAX) + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) return -EINVAL; driver_override = kstrndup(buf, count, GFP_KERNEL); @@ -549,7 +550,7 @@ static ssize_t driver_override_show(struct device *dev, { struct pci_dev *pdev = to_pci_dev(dev); - return sprintf(buf, "%s\n", pdev->driver_override); + return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); } static DEVICE_ATTR_RW(driver_override); diff --git a/drivers/pcmcia/Kconfig b/drivers/pcmcia/Kconfig index 3bb49252a098..45f67c63d385 100644 --- a/drivers/pcmcia/Kconfig +++ b/drivers/pcmcia/Kconfig @@ -69,8 +69,7 @@ config YENTA tristate "CardBus yenta-compatible bridge support" depends on PCI select CARDBUS if !EXPERT - select PCCARD_NONSTATIC if PCMCIA != n && ISA - select PCCARD_PCI if PCMCIA !=n && !ISA + select PCCARD_NONSTATIC if PCMCIA != n ---help--- This option enables support for CardBus host bridges. Virtually all modern PCMCIA bridges are CardBus compatible. A "bridge" is @@ -110,8 +109,7 @@ config YENTA_TOSHIBA config PD6729 tristate "Cirrus PD6729 compatible bridge support" depends on PCMCIA && PCI - select PCCARD_NONSTATIC if PCMCIA != n && ISA - select PCCARD_PCI if PCMCIA !=n && !ISA + select PCCARD_NONSTATIC help This provides support for the Cirrus PD6729 PCI-to-PCMCIA bridge device, found in some older laptops and PCMCIA card readers. @@ -119,8 +117,7 @@ config PD6729 config I82092 tristate "i82092 compatible bridge support" depends on PCMCIA && PCI - select PCCARD_NONSTATIC if PCMCIA != n && ISA - select PCCARD_PCI if PCMCIA !=n && !ISA + select PCCARD_NONSTATIC help This provides support for the Intel I82092AA PCI-to-PCMCIA bridge device, found in some older laptops and more commonly in evaluation boards for the @@ -291,9 +288,6 @@ config ELECTRA_CF Say Y here to support the CompactFlash controller on the PA Semi Electra eval board. -config PCCARD_PCI - bool - config PCCARD_NONSTATIC bool diff --git a/drivers/pcmcia/Makefile b/drivers/pcmcia/Makefile index f1a7ca04d89e..27e94b30cf96 100644 --- a/drivers/pcmcia/Makefile +++ b/drivers/pcmcia/Makefile @@ -12,7 +12,6 @@ obj-$(CONFIG_PCMCIA) += pcmcia.o pcmcia_rsrc-y += rsrc_mgr.o pcmcia_rsrc-$(CONFIG_PCCARD_NONSTATIC) += rsrc_nonstatic.o pcmcia_rsrc-$(CONFIG_PCCARD_IODYN) += rsrc_iodyn.o -pcmcia_rsrc-$(CONFIG_PCCARD_PCI) += rsrc_pci.o obj-$(CONFIG_PCCARD) += pcmcia_rsrc.o diff --git a/drivers/pcmcia/rsrc_pci.c b/drivers/pcmcia/rsrc_pci.c deleted file mode 100644 index 1f67b3ba70fb..000000000000 --- a/drivers/pcmcia/rsrc_pci.c +++ /dev/null @@ -1,173 +0,0 @@ -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/pci.h> - -#include <pcmcia/ss.h> -#include <pcmcia/cistpl.h> -#include "cs_internal.h" - - -struct pcmcia_align_data { - unsigned long mask; - unsigned long offset; -}; - -static resource_size_t pcmcia_align(void *align_data, - const struct resource *res, - resource_size_t size, resource_size_t align) -{ - struct pcmcia_align_data *data = align_data; - resource_size_t start; - - start = (res->start & ~data->mask) + data->offset; - if (start < res->start) - start += data->mask + 1; - return start; -} - -static struct resource *find_io_region(struct pcmcia_socket *s, - unsigned long base, int num, - unsigned long align) -{ - struct resource *res = pcmcia_make_resource(0, num, IORESOURCE_IO, - dev_name(&s->dev)); - struct pcmcia_align_data data; - int ret; - - data.mask = align - 1; - data.offset = base & data.mask; - - ret = pci_bus_alloc_resource(s->cb_dev->bus, res, num, 1, - base, 0, pcmcia_align, &data); - if (ret != 0) { - kfree(res); - res = NULL; - } - return res; -} - -static int res_pci_find_io(struct pcmcia_socket *s, unsigned int attr, - unsigned int *base, unsigned int num, - unsigned int align, struct resource **parent) -{ - int i, ret = 0; - - /* Check for an already-allocated window that must conflict with - * what was asked for. It is a hack because it does not catch all - * potential conflicts, just the most obvious ones. - */ - for (i = 0; i < MAX_IO_WIN; i++) { - if (!s->io[i].res) - continue; - - if (!*base) - continue; - - if ((s->io[i].res->start & (align-1)) == *base) - return -EBUSY; - } - - for (i = 0; i < MAX_IO_WIN; i++) { - struct resource *res = s->io[i].res; - unsigned int try; - - if (res && (res->flags & IORESOURCE_BITS) != - (attr & IORESOURCE_BITS)) - continue; - - if (!res) { - if (align == 0) - align = 0x10000; - - res = s->io[i].res = find_io_region(s, *base, num, - align); - if (!res) - return -EINVAL; - - *base = res->start; - s->io[i].res->flags = - ((res->flags & ~IORESOURCE_BITS) | - (attr & IORESOURCE_BITS)); - s->io[i].InUse = num; - *parent = res; - return 0; - } - - /* Try to extend top of window */ - try = res->end + 1; - if ((*base == 0) || (*base == try)) { - ret = adjust_resource(s->io[i].res, res->start, - resource_size(res) + num); - if (ret) - continue; - *base = try; - s->io[i].InUse += num; - *parent = res; - return 0; - } - - /* Try to extend bottom of window */ - try = res->start - num; - if ((*base == 0) || (*base == try)) { - ret = adjust_resource(s->io[i].res, - res->start - num, - resource_size(res) + num); - if (ret) - continue; - *base = try; - s->io[i].InUse += num; - *parent = res; - return 0; - } - } - return -EINVAL; -} - -static struct resource *res_pci_find_mem(u_long base, u_long num, - u_long align, int low, struct pcmcia_socket *s) -{ - struct resource *res = pcmcia_make_resource(0, num, IORESOURCE_MEM, - dev_name(&s->dev)); - struct pcmcia_align_data data; - unsigned long min; - int ret; - - if (align < 0x20000) - align = 0x20000; - data.mask = align - 1; - data.offset = base & data.mask; - - min = 0; - if (!low) - min = 0x100000UL; - - ret = pci_bus_alloc_resource(s->cb_dev->bus, - res, num, 1, min, 0, - pcmcia_align, &data); - - if (ret != 0) { - kfree(res); - res = NULL; - } - return res; -} - - -static int res_pci_init(struct pcmcia_socket *s) -{ - if (!s->cb_dev || !(s->features & SS_CAP_PAGE_REGS)) { - dev_err(&s->dev, "not supported by res_pci\n"); - return -EOPNOTSUPP; - } - return 0; -} - -struct pccard_resource_ops pccard_nonstatic_ops = { - .validate_mem = NULL, - .find_io = res_pci_find_io, - .find_mem = res_pci_find_mem, - .init = res_pci_init, - .exit = NULL, -}; -EXPORT_SYMBOL(pccard_nonstatic_ops); diff --git a/drivers/phy/phy-armada375-usb2.c b/drivers/phy/phy-armada375-usb2.c index 7c99ca256f05..8ccc3952c13d 100644 --- a/drivers/phy/phy-armada375-usb2.c +++ b/drivers/phy/phy-armada375-usb2.c @@ -37,7 +37,7 @@ static int armada375_usb_phy_init(struct phy *phy) struct armada375_cluster_phy *cluster_phy; u32 reg; - cluster_phy = dev_get_drvdata(phy->dev.parent); + cluster_phy = phy_get_drvdata(phy); if (!cluster_phy) return -ENODEV; @@ -131,6 +131,7 @@ static int armada375_usb_phy_probe(struct platform_device *pdev) cluster_phy->reg = usb_cluster_base; dev_set_drvdata(dev, cluster_phy); + phy_set_drvdata(phy, cluster_phy); phy_provider = devm_of_phy_provider_register(&pdev->dev, armada375_usb_phy_xlate); diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index a12d35338313..3791838f4bd4 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -52,7 +52,9 @@ static void devm_phy_consume(struct device *dev, void *res) static int devm_phy_match(struct device *dev, void *res, void *match_data) { - return res == match_data; + struct phy **phy = res; + + return *phy == match_data; } /** @@ -223,6 +225,7 @@ int phy_init(struct phy *phy) ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) return ret; + ret = 0; /* Override possible ret == -ENOTSUPP */ mutex_lock(&phy->mutex); if (phy->init_count == 0 && phy->ops->init) { @@ -231,8 +234,6 @@ int phy_init(struct phy *phy) dev_err(&phy->dev, "phy init failed --> %d\n", ret); goto out; } - } else { - ret = 0; /* Override possible ret == -ENOTSUPP */ } ++phy->init_count; @@ -253,6 +254,7 @@ int phy_exit(struct phy *phy) ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) return ret; + ret = 0; /* Override possible ret == -ENOTSUPP */ mutex_lock(&phy->mutex); if (phy->init_count == 1 && phy->ops->exit) { @@ -287,6 +289,7 @@ int phy_power_on(struct phy *phy) ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) return ret; + ret = 0; /* Override possible ret == -ENOTSUPP */ mutex_lock(&phy->mutex); if (phy->power_count == 0 && phy->ops->power_on) { @@ -295,8 +298,6 @@ int phy_power_on(struct phy *phy) dev_err(&phy->dev, "phy poweron failed --> %d\n", ret); goto out; } - } else { - ret = 0; /* Override possible ret == -ENOTSUPP */ } ++phy->power_count; mutex_unlock(&phy->mutex); diff --git a/drivers/phy/phy-exynos-dp-video.c b/drivers/phy/phy-exynos-dp-video.c index f86cbe68ddaf..179cbf9451aa 100644 --- a/drivers/phy/phy-exynos-dp-video.c +++ b/drivers/phy/phy-exynos-dp-video.c @@ -30,28 +30,13 @@ struct exynos_dp_video_phy { const struct exynos_dp_video_phy_drvdata *drvdata; }; -static void exynos_dp_video_phy_pwr_isol(struct exynos_dp_video_phy *state, - unsigned int on) -{ - unsigned int val; - - if (IS_ERR(state->regs)) - return; - - val = on ? 0 : EXYNOS5_PHY_ENABLE; - - regmap_update_bits(state->regs, state->drvdata->phy_ctrl_offset, - EXYNOS5_PHY_ENABLE, val); -} - static int exynos_dp_video_phy_power_on(struct phy *phy) { struct exynos_dp_video_phy *state = phy_get_drvdata(phy); /* Disable power isolation on DP-PHY */ - exynos_dp_video_phy_pwr_isol(state, 0); - - return 0; + return regmap_update_bits(state->regs, state->drvdata->phy_ctrl_offset, + EXYNOS5_PHY_ENABLE, EXYNOS5_PHY_ENABLE); } static int exynos_dp_video_phy_power_off(struct phy *phy) @@ -59,9 +44,8 @@ static int exynos_dp_video_phy_power_off(struct phy *phy) struct exynos_dp_video_phy *state = phy_get_drvdata(phy); /* Enable power isolation on DP-PHY */ - exynos_dp_video_phy_pwr_isol(state, 1); - - return 0; + return regmap_update_bits(state->regs, state->drvdata->phy_ctrl_offset, + EXYNOS5_PHY_ENABLE, 0); } static struct phy_ops exynos_dp_video_phy_ops = { diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c index f017b2f2a54e..df7519a39ba0 100644 --- a/drivers/phy/phy-exynos-mipi-video.c +++ b/drivers/phy/phy-exynos-mipi-video.c @@ -43,7 +43,6 @@ struct exynos_mipi_video_phy { } phys[EXYNOS_MIPI_PHYS_NUM]; spinlock_t slock; void __iomem *regs; - struct mutex mutex; struct regmap *regmap; }; @@ -59,8 +58,9 @@ static int __set_phy_state(struct exynos_mipi_video_phy *state, else reset = EXYNOS4_MIPI_PHY_SRESETN; - if (state->regmap) { - mutex_lock(&state->mutex); + spin_lock(&state->slock); + + if (!IS_ERR(state->regmap)) { regmap_read(state->regmap, offset, &val); if (on) val |= reset; @@ -72,11 +72,9 @@ static int __set_phy_state(struct exynos_mipi_video_phy *state, else if (!(val & EXYNOS4_MIPI_PHY_RESET_MASK)) val &= ~EXYNOS4_MIPI_PHY_ENABLE; regmap_write(state->regmap, offset, val); - mutex_unlock(&state->mutex); } else { addr = state->regs + EXYNOS_MIPI_PHY_CONTROL(id / 2); - spin_lock(&state->slock); val = readl(addr); if (on) val |= reset; @@ -90,9 +88,9 @@ static int __set_phy_state(struct exynos_mipi_video_phy *state, val &= ~EXYNOS4_MIPI_PHY_ENABLE; writel(val, addr); - spin_unlock(&state->slock); } + spin_unlock(&state->slock); return 0; } @@ -158,7 +156,6 @@ static int exynos_mipi_video_phy_probe(struct platform_device *pdev) dev_set_drvdata(dev, state); spin_lock_init(&state->slock); - mutex_init(&state->mutex); for (i = 0; i < EXYNOS_MIPI_PHYS_NUM; i++) { struct phy *phy = devm_phy_create(dev, NULL, diff --git a/drivers/phy/phy-exynos4210-usb2.c b/drivers/phy/phy-exynos4210-usb2.c index 236a52ad94eb..f30bbb0fb3b2 100644 --- a/drivers/phy/phy-exynos4210-usb2.c +++ b/drivers/phy/phy-exynos4210-usb2.c @@ -250,7 +250,6 @@ static const struct samsung_usb2_common_phy exynos4210_phys[] = { .power_on = exynos4210_power_on, .power_off = exynos4210_power_off, }, - {}, }; const struct samsung_usb2_phy_config exynos4210_usb2_phy_config = { diff --git a/drivers/phy/phy-exynos4x12-usb2.c b/drivers/phy/phy-exynos4x12-usb2.c index 0b9de88579b1..765da90a536f 100644 --- a/drivers/phy/phy-exynos4x12-usb2.c +++ b/drivers/phy/phy-exynos4x12-usb2.c @@ -361,7 +361,6 @@ static const struct samsung_usb2_common_phy exynos4x12_phys[] = { .power_on = exynos4x12_power_on, .power_off = exynos4x12_power_off, }, - {}, }; const struct samsung_usb2_phy_config exynos3250_usb2_phy_config = { diff --git a/drivers/phy/phy-exynos5-usbdrd.c b/drivers/phy/phy-exynos5-usbdrd.c index 04374018425f..e2a0be750ad9 100644 --- a/drivers/phy/phy-exynos5-usbdrd.c +++ b/drivers/phy/phy-exynos5-usbdrd.c @@ -531,7 +531,7 @@ static struct phy *exynos5_usbdrd_phy_xlate(struct device *dev, { struct exynos5_usbdrd_phy *phy_drd = dev_get_drvdata(dev); - if (WARN_ON(args->args[0] > EXYNOS5_DRDPHYS_NUM)) + if (WARN_ON(args->args[0] >= EXYNOS5_DRDPHYS_NUM)) return ERR_PTR(-ENODEV); return phy_drd->phys[args->args[0]].phy; diff --git a/drivers/phy/phy-exynos5250-usb2.c b/drivers/phy/phy-exynos5250-usb2.c index 1c139aa0d074..2ed1735a076a 100644 --- a/drivers/phy/phy-exynos5250-usb2.c +++ b/drivers/phy/phy-exynos5250-usb2.c @@ -391,7 +391,6 @@ static const struct samsung_usb2_common_phy exynos5250_phys[] = { .power_on = exynos5250_power_on, .power_off = exynos5250_power_off, }, - {}, }; const struct samsung_usb2_phy_config exynos5250_usb2_phy_config = { diff --git a/drivers/phy/phy-hix5hd2-sata.c b/drivers/phy/phy-hix5hd2-sata.c index 34915b4202f1..d6b22659cac1 100644 --- a/drivers/phy/phy-hix5hd2-sata.c +++ b/drivers/phy/phy-hix5hd2-sata.c @@ -147,6 +147,9 @@ static int hix5hd2_sata_phy_probe(struct platform_device *pdev) return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -EINVAL; + priv->base = devm_ioremap(dev, res->start, resource_size(res)); if (!priv->base) return -ENOMEM; diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c index 9b2848e6115d..933435214acc 100644 --- a/drivers/phy/phy-miphy28lp.c +++ b/drivers/phy/phy-miphy28lp.c @@ -228,6 +228,7 @@ struct miphy28lp_dev { struct regmap *regmap; struct mutex miphy_mutex; struct miphy28lp_phy **phys; + int nphys; }; struct miphy_initval { @@ -1116,7 +1117,7 @@ static struct phy *miphy28lp_xlate(struct device *dev, return ERR_PTR(-EINVAL); } - for (index = 0; index < of_get_child_count(dev->of_node); index++) + for (index = 0; index < miphy_dev->nphys; index++) if (phynode == miphy_dev->phys[index]->phy->dev.of_node) { miphy_phy = miphy_dev->phys[index]; break; @@ -1138,6 +1139,7 @@ static struct phy *miphy28lp_xlate(struct device *dev, static struct phy_ops miphy28lp_ops = { .init = miphy28lp_init, + .owner = THIS_MODULE, }; static int miphy28lp_probe_resets(struct device_node *node, @@ -1200,16 +1202,15 @@ static int miphy28lp_probe(struct platform_device *pdev) struct miphy28lp_dev *miphy_dev; struct phy_provider *provider; struct phy *phy; - int chancount, port = 0; - int ret; + int ret, port = 0; miphy_dev = devm_kzalloc(&pdev->dev, sizeof(*miphy_dev), GFP_KERNEL); if (!miphy_dev) return -ENOMEM; - chancount = of_get_child_count(np); - miphy_dev->phys = devm_kzalloc(&pdev->dev, sizeof(phy) * chancount, - GFP_KERNEL); + miphy_dev->nphys = of_get_child_count(np); + miphy_dev->phys = devm_kcalloc(&pdev->dev, miphy_dev->nphys, + sizeof(*miphy_dev->phys), GFP_KERNEL); if (!miphy_dev->phys) return -ENOMEM; diff --git a/drivers/phy/phy-miphy365x.c b/drivers/phy/phy-miphy365x.c index 6c80154e8bff..51b459db9137 100644 --- a/drivers/phy/phy-miphy365x.c +++ b/drivers/phy/phy-miphy365x.c @@ -150,6 +150,7 @@ struct miphy365x_dev { struct regmap *regmap; struct mutex miphy_mutex; struct miphy365x_phy **phys; + int nphys; }; /* @@ -485,7 +486,7 @@ static struct phy *miphy365x_xlate(struct device *dev, return ERR_PTR(-EINVAL); } - for (index = 0; index < of_get_child_count(dev->of_node); index++) + for (index = 0; index < miphy_dev->nphys; index++) if (phynode == miphy_dev->phys[index]->phy->dev.of_node) { miphy_phy = miphy_dev->phys[index]; break; @@ -541,16 +542,15 @@ static int miphy365x_probe(struct platform_device *pdev) struct miphy365x_dev *miphy_dev; struct phy_provider *provider; struct phy *phy; - int chancount, port = 0; - int ret; + int ret, port = 0; miphy_dev = devm_kzalloc(&pdev->dev, sizeof(*miphy_dev), GFP_KERNEL); if (!miphy_dev) return -ENOMEM; - chancount = of_get_child_count(np); - miphy_dev->phys = devm_kzalloc(&pdev->dev, sizeof(phy) * chancount, - GFP_KERNEL); + miphy_dev->nphys = of_get_child_count(np); + miphy_dev->phys = devm_kcalloc(&pdev->dev, miphy_dev->nphys, + sizeof(*miphy_dev->phys), GFP_KERNEL); if (!miphy_dev->phys) return -ENOMEM; diff --git a/drivers/phy/phy-omap-control.c b/drivers/phy/phy-omap-control.c index efe724f97e02..93252e053a31 100644 --- a/drivers/phy/phy-omap-control.c +++ b/drivers/phy/phy-omap-control.c @@ -360,7 +360,7 @@ static void __exit omap_control_phy_exit(void) } module_exit(omap_control_phy_exit); -MODULE_ALIAS("platform: omap_control_phy"); +MODULE_ALIAS("platform:omap_control_phy"); MODULE_AUTHOR("Texas Instruments Inc."); MODULE_DESCRIPTION("OMAP Control Module PHY Driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c index 6f4aef3db248..4757e765696a 100644 --- a/drivers/phy/phy-omap-usb2.c +++ b/drivers/phy/phy-omap-usb2.c @@ -296,10 +296,11 @@ static int omap_usb2_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "found usb_otg_ss_refclk960m, please fix DTS\n"); } - } else { - clk_prepare(phy->optclk); } + if (!IS_ERR(phy->optclk)) + clk_prepare(phy->optclk); + usb_add_phy_dev(&phy->phy); return 0; @@ -383,7 +384,7 @@ static struct platform_driver omap_usb2_driver = { module_platform_driver(omap_usb2_driver); -MODULE_ALIAS("platform: omap_usb2"); +MODULE_ALIAS("platform:omap_usb2"); MODULE_AUTHOR("Texas Instruments Inc."); MODULE_DESCRIPTION("OMAP USB2 phy driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/phy-rockchip-usb.c b/drivers/phy/phy-rockchip-usb.c index 22011c3b6a4b..7d4c33643768 100644 --- a/drivers/phy/phy-rockchip-usb.c +++ b/drivers/phy/phy-rockchip-usb.c @@ -61,8 +61,6 @@ static int rockchip_usb_phy_power_off(struct phy *_phy) return ret; clk_disable_unprepare(phy->clk); - if (ret) - return ret; return 0; } @@ -78,8 +76,10 @@ static int rockchip_usb_phy_power_on(struct phy *_phy) /* Power up usb phy analog blocks by set siddq 0 */ ret = rockchip_usb_phy_power(phy, 0); - if (ret) + if (ret) { + clk_disable_unprepare(phy->clk); return ret; + } return 0; } diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c index 95c88f929f27..2ba610b72ca2 100644 --- a/drivers/phy/phy-ti-pipe3.c +++ b/drivers/phy/phy-ti-pipe3.c @@ -165,15 +165,11 @@ static int ti_pipe3_dpll_wait_lock(struct ti_pipe3 *phy) cpu_relax(); val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_STATUS); if (val & PLL_LOCK) - break; + return 0; } while (!time_after(jiffies, timeout)); - if (!(val & PLL_LOCK)) { - dev_err(phy->dev, "DPLL failed to lock\n"); - return -EBUSY; - } - - return 0; + dev_err(phy->dev, "DPLL failed to lock\n"); + return -EBUSY; } static int ti_pipe3_dpll_program(struct ti_pipe3 *phy) @@ -608,7 +604,7 @@ static struct platform_driver ti_pipe3_driver = { module_platform_driver(ti_pipe3_driver); -MODULE_ALIAS("platform: ti_pipe3"); +MODULE_ALIAS("platform:ti_pipe3"); MODULE_AUTHOR("Texas Instruments Inc."); MODULE_DESCRIPTION("TI PIPE3 phy driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 8e87f54671f3..bc42d6a8939f 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -666,7 +666,6 @@ static int twl4030_usb_probe(struct platform_device *pdev) twl->dev = &pdev->dev; twl->irq = platform_get_irq(pdev, 0); twl->vbus_supplied = false; - twl->linkstat = -EINVAL; twl->linkstat = OMAP_MUSB_UNKNOWN; twl->phy.dev = twl->dev; diff --git a/drivers/phy/phy-xgene.c b/drivers/phy/phy-xgene.c index 29214a36ea28..2263cd010032 100644 --- a/drivers/phy/phy-xgene.c +++ b/drivers/phy/phy-xgene.c @@ -1704,7 +1704,6 @@ static int xgene_phy_probe(struct platform_device *pdev) for (i = 0; i < MAX_LANE; i++) ctx->sata_param.speed[i] = 2; /* Default to Gen3 */ - ctx->dev = &pdev->dev; platform_set_drvdata(pdev, ctx); ctx->phy = devm_phy_create(ctx->dev, NULL, &xgene_phy_ops); diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 5afe03e28b91..2062c224e32f 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -66,6 +66,10 @@ #define BYT_DIR_MASK (BIT(1) | BIT(2)) #define BYT_TRIG_MASK (BIT(26) | BIT(25) | BIT(24)) +#define BYT_CONF0_RESTORE_MASK (BYT_DIRECT_IRQ_EN | BYT_TRIG_MASK | \ + BYT_PIN_MUX) +#define BYT_VAL_RESTORE_MASK (BYT_DIR_MASK | BYT_LEVEL) + #define BYT_NGPIO_SCORE 102 #define BYT_NGPIO_NCORE 28 #define BYT_NGPIO_SUS 44 @@ -134,12 +138,18 @@ static struct pinctrl_gpio_range byt_ranges[] = { }, }; +struct byt_gpio_pin_context { + u32 conf0; + u32 val; +}; + struct byt_gpio { struct gpio_chip chip; struct platform_device *pdev; spinlock_t lock; void __iomem *reg_base; struct pinctrl_gpio_range *range; + struct byt_gpio_pin_context *saved_context; }; #define to_byt_gpio(c) container_of(c, struct byt_gpio, chip) @@ -158,40 +168,62 @@ static void __iomem *byt_gpio_reg(struct gpio_chip *chip, unsigned offset, return vg->reg_base + reg_offset + reg; } -static bool is_special_pin(struct byt_gpio *vg, unsigned offset) +static void byt_gpio_clear_triggering(struct byt_gpio *vg, unsigned offset) +{ + void __iomem *reg = byt_gpio_reg(&vg->chip, offset, BYT_CONF0_REG); + unsigned long flags; + u32 value; + + spin_lock_irqsave(&vg->lock, flags); + value = readl(reg); + value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); + writel(value, reg); + spin_unlock_irqrestore(&vg->lock, flags); +} + +static u32 byt_get_gpio_mux(struct byt_gpio *vg, unsigned offset) { /* SCORE pin 92-93 */ if (!strcmp(vg->range->name, BYT_SCORE_ACPI_UID) && offset >= 92 && offset <= 93) - return true; + return 1; /* SUS pin 11-21 */ if (!strcmp(vg->range->name, BYT_SUS_ACPI_UID) && offset >= 11 && offset <= 21) - return true; + return 1; - return false; + return 0; } static int byt_gpio_request(struct gpio_chip *chip, unsigned offset) { struct byt_gpio *vg = to_byt_gpio(chip); void __iomem *reg = byt_gpio_reg(chip, offset, BYT_CONF0_REG); - u32 value; - bool special; + u32 value, gpio_mux; /* * In most cases, func pin mux 000 means GPIO function. * But, some pins may have func pin mux 001 represents - * GPIO function. Only allow user to export pin with - * func pin mux preset as GPIO function by BIOS/FW. + * GPIO function. + * + * Because there are devices out there where some pins were not + * configured correctly we allow changing the mux value from + * request (but print out warning about that). */ value = readl(reg) & BYT_PIN_MUX; - special = is_special_pin(vg, offset); - if ((special && value != 1) || (!special && value)) { - dev_err(&vg->pdev->dev, - "pin %u cannot be used as GPIO.\n", offset); - return -EINVAL; + gpio_mux = byt_get_gpio_mux(vg, offset); + if (WARN_ON(gpio_mux != value)) { + unsigned long flags; + + spin_lock_irqsave(&vg->lock, flags); + value = readl(reg) & ~BYT_PIN_MUX; + value |= gpio_mux; + writel(value, reg); + spin_unlock_irqrestore(&vg->lock, flags); + + dev_warn(&vg->pdev->dev, + "pin %u forcibly re-configured as GPIO\n", offset); } pm_runtime_get(&vg->pdev->dev); @@ -202,14 +234,8 @@ static int byt_gpio_request(struct gpio_chip *chip, unsigned offset) static void byt_gpio_free(struct gpio_chip *chip, unsigned offset) { struct byt_gpio *vg = to_byt_gpio(chip); - void __iomem *reg = byt_gpio_reg(&vg->chip, offset, BYT_CONF0_REG); - u32 value; - - /* clear interrupt triggering */ - value = readl(reg); - value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); - writel(value, reg); + byt_gpio_clear_triggering(vg, offset); pm_runtime_put(&vg->pdev->dev); } @@ -236,23 +262,13 @@ static int byt_irq_type(struct irq_data *d, unsigned type) value &= ~(BYT_DIRECT_IRQ_EN | BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); - switch (type) { - case IRQ_TYPE_LEVEL_HIGH: - value |= BYT_TRIG_LVL; - case IRQ_TYPE_EDGE_RISING: - value |= BYT_TRIG_POS; - break; - case IRQ_TYPE_LEVEL_LOW: - value |= BYT_TRIG_LVL; - case IRQ_TYPE_EDGE_FALLING: - value |= BYT_TRIG_NEG; - break; - case IRQ_TYPE_EDGE_BOTH: - value |= (BYT_TRIG_NEG | BYT_TRIG_POS); - break; - } writel(value, reg); + if (type & IRQ_TYPE_EDGE_BOTH) + __irq_set_handler_locked(d->irq, handle_edge_irq); + else if (type & IRQ_TYPE_LEVEL_MASK) + __irq_set_handler_locked(d->irq, handle_level_irq); + spin_unlock_irqrestore(&vg->lock, flags); return 0; @@ -410,58 +426,80 @@ static void byt_gpio_irq_handler(unsigned irq, struct irq_desc *desc) struct irq_data *data = irq_desc_get_irq_data(desc); struct byt_gpio *vg = to_byt_gpio(irq_desc_get_handler_data(desc)); struct irq_chip *chip = irq_data_get_irq_chip(data); - u32 base, pin, mask; + u32 base, pin; void __iomem *reg; - u32 pending; + unsigned long pending; unsigned virq; - int looplimit = 0; /* check from GPIO controller which pin triggered the interrupt */ for (base = 0; base < vg->chip.ngpio; base += 32) { - reg = byt_gpio_reg(&vg->chip, base, BYT_INT_STAT_REG); - - while ((pending = readl(reg))) { - pin = __ffs(pending); - mask = BIT(pin); - /* Clear before handling so we can't lose an edge */ - writel(mask, reg); - + pending = readl(reg); + for_each_set_bit(pin, &pending, 32) { virq = irq_find_mapping(vg->chip.irqdomain, base + pin); generic_handle_irq(virq); - - /* In case bios or user sets triggering incorretly a pin - * might remain in "interrupt triggered" state. - */ - if (looplimit++ > 32) { - dev_err(&vg->pdev->dev, - "Gpio %d interrupt flood, disabling\n", - base + pin); - - reg = byt_gpio_reg(&vg->chip, base + pin, - BYT_CONF0_REG); - mask = readl(reg); - mask &= ~(BYT_TRIG_NEG | BYT_TRIG_POS | - BYT_TRIG_LVL); - writel(mask, reg); - mask = readl(reg); /* flush */ - break; - } } } chip->irq_eoi(data); } +static void byt_irq_ack(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct byt_gpio *vg = to_byt_gpio(gc); + unsigned offset = irqd_to_hwirq(d); + void __iomem *reg; + + reg = byt_gpio_reg(&vg->chip, offset, BYT_INT_STAT_REG); + writel(BIT(offset % 32), reg); +} + static void byt_irq_unmask(struct irq_data *d) { + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct byt_gpio *vg = to_byt_gpio(gc); + unsigned offset = irqd_to_hwirq(d); + unsigned long flags; + void __iomem *reg; + u32 value; + + spin_lock_irqsave(&vg->lock, flags); + + reg = byt_gpio_reg(&vg->chip, offset, BYT_CONF0_REG); + value = readl(reg); + + switch (irqd_get_trigger_type(d)) { + case IRQ_TYPE_LEVEL_HIGH: + value |= BYT_TRIG_LVL; + case IRQ_TYPE_EDGE_RISING: + value |= BYT_TRIG_POS; + break; + case IRQ_TYPE_LEVEL_LOW: + value |= BYT_TRIG_LVL; + case IRQ_TYPE_EDGE_FALLING: + value |= BYT_TRIG_NEG; + break; + case IRQ_TYPE_EDGE_BOTH: + value |= (BYT_TRIG_NEG | BYT_TRIG_POS); + break; + } + + writel(value, reg); + + spin_unlock_irqrestore(&vg->lock, flags); } static void byt_irq_mask(struct irq_data *d) { + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct byt_gpio *vg = to_byt_gpio(gc); + + byt_gpio_clear_triggering(vg, irqd_to_hwirq(d)); } static struct irq_chip byt_irqchip = { .name = "BYT-GPIO", + .irq_ack = byt_irq_ack, .irq_mask = byt_irq_mask, .irq_unmask = byt_irq_unmask, .irq_set_type = byt_irq_type, @@ -472,6 +510,21 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg) { void __iomem *reg; u32 base, value; + int i; + + /* + * Clear interrupt triggers for all pins that are GPIOs and + * do not use direct IRQ mode. This will prevent spurious + * interrupts from misconfigured pins. + */ + for (i = 0; i < vg->chip.ngpio; i++) { + value = readl(byt_gpio_reg(&vg->chip, i, BYT_CONF0_REG)); + if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i) && + !(value & BYT_DIRECT_IRQ_EN)) { + byt_gpio_clear_triggering(vg, i); + dev_dbg(&vg->pdev->dev, "disabling GPIO %d\n", i); + } + } /* clear interrupt status trigger registers */ for (base = 0; base < vg->chip.ngpio; base += 32) { @@ -541,6 +594,11 @@ static int byt_gpio_probe(struct platform_device *pdev) gc->can_sleep = false; gc->dev = dev; +#ifdef CONFIG_PM_SLEEP + vg->saved_context = devm_kcalloc(&pdev->dev, gc->ngpio, + sizeof(*vg->saved_context), GFP_KERNEL); +#endif + ret = gpiochip_add(gc); if (ret) { dev_err(&pdev->dev, "failed adding byt-gpio chip\n"); @@ -569,6 +627,69 @@ static int byt_gpio_probe(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int byt_gpio_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct byt_gpio *vg = platform_get_drvdata(pdev); + int i; + + for (i = 0; i < vg->chip.ngpio; i++) { + void __iomem *reg; + u32 value; + + reg = byt_gpio_reg(&vg->chip, i, BYT_CONF0_REG); + value = readl(reg) & BYT_CONF0_RESTORE_MASK; + vg->saved_context[i].conf0 = value; + + reg = byt_gpio_reg(&vg->chip, i, BYT_VAL_REG); + value = readl(reg) & BYT_VAL_RESTORE_MASK; + vg->saved_context[i].val = value; + } + + return 0; +} + +static int byt_gpio_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct byt_gpio *vg = platform_get_drvdata(pdev); + int i; + + for (i = 0; i < vg->chip.ngpio; i++) { + void __iomem *reg; + u32 value; + + reg = byt_gpio_reg(&vg->chip, i, BYT_CONF0_REG); + value = readl(reg); + if ((value & BYT_CONF0_RESTORE_MASK) != + vg->saved_context[i].conf0) { + value &= ~BYT_CONF0_RESTORE_MASK; + value |= vg->saved_context[i].conf0; + writel(value, reg); + dev_info(dev, "restored pin %d conf0 %#08x", i, value); + } + + reg = byt_gpio_reg(&vg->chip, i, BYT_VAL_REG); + value = readl(reg); + if ((value & BYT_VAL_RESTORE_MASK) != + vg->saved_context[i].val) { + u32 v; + + v = value & ~BYT_VAL_RESTORE_MASK; + v |= vg->saved_context[i].val; + if (v != value) { + writel(v, reg); + dev_dbg(dev, "restored pin %d val %#08x\n", + i, v); + } + } + } + + return 0; +} +#endif + static int byt_gpio_runtime_suspend(struct device *dev) { return 0; @@ -580,8 +701,9 @@ static int byt_gpio_runtime_resume(struct device *dev) } static const struct dev_pm_ops byt_gpio_pm_ops = { - .runtime_suspend = byt_gpio_runtime_suspend, - .runtime_resume = byt_gpio_runtime_resume, + SET_LATE_SYSTEM_SLEEP_PM_OPS(byt_gpio_suspend, byt_gpio_resume) + SET_RUNTIME_PM_OPS(byt_gpio_runtime_suspend, byt_gpio_runtime_resume, + NULL) }; static const struct acpi_device_id byt_gpio_acpi_match[] = { diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 3034fd03bced..82f691eeeec4 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1226,6 +1226,7 @@ static int chv_gpio_direction_input(struct gpio_chip *chip, unsigned offset) static int chv_gpio_direction_output(struct gpio_chip *chip, unsigned offset, int value) { + chv_gpio_set(chip, offset, value); return pinctrl_gpio_direction_output(chip->base + offset); } diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index f4cd0b9b2438..a4814066ea08 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1477,28 +1477,25 @@ static void gpio_irq_ack(struct irq_data *d) /* the interrupt is already cleared before by reading ISR */ } -static unsigned int gpio_irq_startup(struct irq_data *d) +static int gpio_irq_request_res(struct irq_data *d) { struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d); unsigned pin = d->hwirq; int ret; ret = gpiochip_lock_as_irq(&at91_gpio->chip, pin); - if (ret) { + if (ret) dev_err(at91_gpio->chip.dev, "unable to lock pind %lu IRQ\n", d->hwirq); - return ret; - } - gpio_irq_unmask(d); - return 0; + + return ret; } -static void gpio_irq_shutdown(struct irq_data *d) +static void gpio_irq_release_res(struct irq_data *d) { struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d); unsigned pin = d->hwirq; - gpio_irq_mask(d); gpiochip_unlock_as_irq(&at91_gpio->chip, pin); } @@ -1577,8 +1574,8 @@ void at91_pinctrl_gpio_resume(void) static struct irq_chip gpio_irqchip = { .name = "GPIO", .irq_ack = gpio_irq_ack, - .irq_startup = gpio_irq_startup, - .irq_shutdown = gpio_irq_shutdown, + .irq_request_resources = gpio_irq_request_res, + .irq_release_resources = gpio_irq_release_res, .irq_disable = gpio_irq_mask, .irq_mask = gpio_irq_mask, .irq_unmask = gpio_irq_unmask, diff --git a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c index 24c5d88f943f..3c68a8e5e0dd 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c @@ -1011,6 +1011,7 @@ static const struct sunxi_pinctrl_desc sun4i_a10_pinctrl_data = { .pins = sun4i_a10_pins, .npins = ARRAY_SIZE(sun4i_a10_pins), .irq_banks = 1, + .irq_read_needs_mux = true, }; static int sun4i_a10_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 3d0744337736..f8e171b76693 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -29,6 +29,7 @@ #include <linux/slab.h> #include "../core.h" +#include "../../gpio/gpiolib.h" #include "pinctrl-sunxi.h" static struct irq_chip sunxi_pinctrl_edge_irq_chip; @@ -464,10 +465,19 @@ static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip, static int sunxi_pinctrl_gpio_get(struct gpio_chip *chip, unsigned offset) { struct sunxi_pinctrl *pctl = dev_get_drvdata(chip->dev); - u32 reg = sunxi_data_reg(offset); u8 index = sunxi_data_offset(offset); - u32 val = (readl(pctl->membase + reg) >> index) & DATA_PINS_MASK; + u32 set_mux = pctl->desc->irq_read_needs_mux && + test_bit(FLAG_USED_AS_IRQ, &chip->desc[offset].flags); + u32 val; + + if (set_mux) + sunxi_pmx_set(pctl->pctl_dev, offset, SUN4I_FUNC_INPUT); + + val = (readl(pctl->membase + reg) >> index) & DATA_PINS_MASK; + + if (set_mux) + sunxi_pmx_set(pctl->pctl_dev, offset, SUN4I_FUNC_IRQ); return val; } diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h index 5a51523a3459..e248e81a0f9e 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h @@ -77,6 +77,9 @@ #define IRQ_LEVEL_LOW 0x03 #define IRQ_EDGE_BOTH 0x04 +#define SUN4I_FUNC_INPUT 0 +#define SUN4I_FUNC_IRQ 6 + struct sunxi_desc_function { const char *name; u8 muxval; @@ -94,6 +97,7 @@ struct sunxi_pinctrl_desc { int npins; unsigned pin_base; unsigned irq_banks; + bool irq_read_needs_mux; }; struct sunxi_pinctrl_function { diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 97b5e4ee1ca4..63d4033eb683 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -73,7 +73,7 @@ #define TIME_WINDOW_MAX_MSEC 40000 #define TIME_WINDOW_MIN_MSEC 250 - +#define ENERGY_UNIT_SCALE 1000 /* scale from driver unit to powercap unit */ enum unit_type { ARBITRARY_UNIT, /* no translation */ POWER_UNIT, @@ -158,6 +158,7 @@ struct rapl_domain { struct rapl_power_limit rpl[NR_POWER_LIMITS]; u64 attr_map; /* track capabilities */ unsigned int state; + unsigned int domain_energy_unit; int package_id; }; #define power_zone_to_rapl_domain(_zone) \ @@ -190,6 +191,7 @@ struct rapl_defaults { void (*set_floor_freq)(struct rapl_domain *rd, bool mode); u64 (*compute_time_window)(struct rapl_package *rp, u64 val, bool to_raw); + unsigned int dram_domain_energy_unit; }; static struct rapl_defaults *rapl_defaults; @@ -227,7 +229,8 @@ static int rapl_read_data_raw(struct rapl_domain *rd, static int rapl_write_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, unsigned long long value); -static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value, +static u64 rapl_unit_xlate(struct rapl_domain *rd, int package, + enum unit_type type, u64 value, int to_raw); static void package_power_limit_irq_save(int package_id); @@ -305,7 +308,9 @@ static int get_energy_counter(struct powercap_zone *power_zone, u64 *energy_raw) static int get_max_energy_counter(struct powercap_zone *pcd_dev, u64 *energy) { - *energy = rapl_unit_xlate(0, ENERGY_UNIT, ENERGY_STATUS_MASK, 0); + struct rapl_domain *rd = power_zone_to_rapl_domain(pcd_dev); + + *energy = rapl_unit_xlate(rd, 0, ENERGY_UNIT, ENERGY_STATUS_MASK, 0); return 0; } @@ -639,6 +644,11 @@ static void rapl_init_domains(struct rapl_package *rp) rd->msrs[4] = MSR_DRAM_POWER_INFO; rd->rpl[0].prim_id = PL1_ENABLE; rd->rpl[0].name = pl1_name; + rd->domain_energy_unit = + rapl_defaults->dram_domain_energy_unit; + if (rd->domain_energy_unit) + pr_info("DRAM domain energy unit %dpj\n", + rd->domain_energy_unit); break; } if (mask) { @@ -648,11 +658,13 @@ static void rapl_init_domains(struct rapl_package *rp) } } -static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value, +static u64 rapl_unit_xlate(struct rapl_domain *rd, int package, + enum unit_type type, u64 value, int to_raw) { u64 units = 1; struct rapl_package *rp; + u64 scale = 1; rp = find_package_by_id(package); if (!rp) @@ -663,7 +675,12 @@ static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value, units = rp->power_unit; break; case ENERGY_UNIT: - units = rp->energy_unit; + scale = ENERGY_UNIT_SCALE; + /* per domain unit takes precedence */ + if (rd && rd->domain_energy_unit) + units = rd->domain_energy_unit; + else + units = rp->energy_unit; break; case TIME_UNIT: return rapl_defaults->compute_time_window(rp, value, to_raw); @@ -673,11 +690,11 @@ static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value, }; if (to_raw) - return div64_u64(value, units); + return div64_u64(value, units) * scale; value *= units; - return value; + return div64_u64(value, scale); } /* in the order of enum rapl_primitives */ @@ -773,7 +790,7 @@ static int rapl_read_data_raw(struct rapl_domain *rd, final = value & rp->mask; final = final >> rp->shift; if (xlate) - *data = rapl_unit_xlate(rd->package_id, rp->unit, final, 0); + *data = rapl_unit_xlate(rd, rd->package_id, rp->unit, final, 0); else *data = final; @@ -799,7 +816,7 @@ static int rapl_write_data_raw(struct rapl_domain *rd, "failed to read msr 0x%x on cpu %d\n", msr, cpu); return -EIO; } - value = rapl_unit_xlate(rd->package_id, rp->unit, value, 1); + value = rapl_unit_xlate(rd, rd->package_id, rp->unit, value, 1); msr_val &= ~rp->mask; msr_val |= value << rp->shift; if (wrmsrl_safe_on_cpu(cpu, msr, msr_val)) { @@ -818,7 +835,7 @@ static int rapl_write_data_raw(struct rapl_domain *rd, * calculate units differ on different CPUs. * We convert the units to below format based on CPUs. * i.e. - * energy unit: microJoules : Represented in microJoules by default + * energy unit: picoJoules : Represented in picoJoules by default * power unit : microWatts : Represented in milliWatts by default * time unit : microseconds: Represented in seconds by default */ @@ -834,7 +851,7 @@ static int rapl_check_unit_core(struct rapl_package *rp, int cpu) } value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET; - rp->energy_unit = 1000000 / (1 << value); + rp->energy_unit = ENERGY_UNIT_SCALE * 1000000 / (1 << value); value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET; rp->power_unit = 1000000 / (1 << value); @@ -842,7 +859,7 @@ static int rapl_check_unit_core(struct rapl_package *rp, int cpu) value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET; rp->time_unit = 1000000 / (1 << value); - pr_debug("Core CPU package %d energy=%duJ, time=%dus, power=%duW\n", + pr_debug("Core CPU package %d energy=%dpJ, time=%dus, power=%duW\n", rp->id, rp->energy_unit, rp->time_unit, rp->power_unit); return 0; @@ -859,7 +876,7 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu) return -ENODEV; } value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET; - rp->energy_unit = 1 << value; + rp->energy_unit = ENERGY_UNIT_SCALE * 1 << value; value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET; rp->power_unit = (1 << value) * 1000; @@ -867,7 +884,7 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu) value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET; rp->time_unit = 1000000 / (1 << value); - pr_debug("Atom package %d energy=%duJ, time=%dus, power=%duW\n", + pr_debug("Atom package %d energy=%dpJ, time=%dus, power=%duW\n", rp->id, rp->energy_unit, rp->time_unit, rp->power_unit); return 0; @@ -1017,6 +1034,13 @@ static const struct rapl_defaults rapl_defaults_core = { .compute_time_window = rapl_compute_time_window_core, }; +static const struct rapl_defaults rapl_defaults_hsw_server = { + .check_unit = rapl_check_unit_core, + .set_floor_freq = set_floor_freq_default, + .compute_time_window = rapl_compute_time_window_core, + .dram_domain_energy_unit = 15300, +}; + static const struct rapl_defaults rapl_defaults_atom = { .check_unit = rapl_check_unit_atom, .set_floor_freq = set_floor_freq_atom, @@ -1037,7 +1061,7 @@ static const struct x86_cpu_id rapl_ids[] = { RAPL_CPU(0x3a, rapl_defaults_core),/* Ivy Bridge */ RAPL_CPU(0x3c, rapl_defaults_core),/* Haswell */ RAPL_CPU(0x3d, rapl_defaults_core),/* Broadwell */ - RAPL_CPU(0x3f, rapl_defaults_core),/* Haswell */ + RAPL_CPU(0x3f, rapl_defaults_hsw_server),/* Haswell servers */ RAPL_CPU(0x45, rapl_defaults_core),/* Haswell ULT */ RAPL_CPU(0x4C, rapl_defaults_atom),/* Braswell */ RAPL_CPU(0x4A, rapl_defaults_atom),/* Tangier */ diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index f8a76090cbca..da7bae991552 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -124,7 +124,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); struct ptp_clock_info *ops = ptp->info; struct ptp_clock_time *pct; - struct timespec ts; + struct timespec64 ts; int enable, err = 0; unsigned int i, pin_index; @@ -197,16 +197,16 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) } pct = &sysoff->ts[0]; for (i = 0; i < sysoff->n_samples; i++) { - getnstimeofday(&ts); + getnstimeofday64(&ts); pct->sec = ts.tv_sec; pct->nsec = ts.tv_nsec; pct++; - ptp->info->gettime(ptp->info, &ts); + ptp->info->gettime64(ptp->info, &ts); pct->sec = ts.tv_sec; pct->nsec = ts.tv_nsec; pct++; } - getnstimeofday(&ts); + getnstimeofday64(&ts); pct->sec = ts.tv_sec; pct->nsec = ts.tv_nsec; if (copy_to_user((void __user *)arg, sysoff, sizeof(*sysoff))) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 296b0ec8744d..2e481b9e8ea5 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -107,13 +107,21 @@ static int ptp_clock_getres(struct posix_clock *pc, struct timespec *tp) static int ptp_clock_settime(struct posix_clock *pc, const struct timespec *tp) { struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); - return ptp->info->settime(ptp->info, tp); + struct timespec64 ts = timespec_to_timespec64(*tp); + + return ptp->info->settime64(ptp->info, &ts); } static int ptp_clock_gettime(struct posix_clock *pc, struct timespec *tp) { struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); - return ptp->info->gettime(ptp->info, tp); + struct timespec64 ts; + int err; + + err = ptp->info->gettime64(ptp->info, &ts); + if (!err) + *tp = timespec64_to_timespec(ts); + return err; } static int ptp_clock_adjtime(struct posix_clock *pc, struct timex *tx) diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/ptp/ptp_ixp46x.c index 604d340f2095..934c139916c6 100644 --- a/drivers/ptp/ptp_ixp46x.c +++ b/drivers/ptp/ptp_ixp46x.c @@ -175,7 +175,7 @@ static int ptp_ixp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; u32 remainder; @@ -195,7 +195,7 @@ static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int ptp_ixp_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { u64 ns; unsigned long flags; @@ -248,8 +248,8 @@ static struct ptp_clock_info ptp_ixp_caps = { .pps = 0, .adjfreq = ptp_ixp_adjfreq, .adjtime = ptp_ixp_adjtime, - .gettime = ptp_ixp_gettime, - .settime = ptp_ixp_settime, + .gettime64 = ptp_ixp_gettime, + .settime64 = ptp_ixp_settime, .enable = ptp_ixp_enable, }; diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c index 255487272859..3aa22ae4d94c 100644 --- a/drivers/ptp/ptp_pch.c +++ b/drivers/ptp/ptp_pch.c @@ -449,7 +449,7 @@ static int ptp_pch_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int ptp_pch_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int ptp_pch_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; u32 remainder; @@ -467,7 +467,7 @@ static int ptp_pch_gettime(struct ptp_clock_info *ptp, struct timespec *ts) } static int ptp_pch_settime(struct ptp_clock_info *ptp, - const struct timespec *ts) + const struct timespec64 *ts) { u64 ns; unsigned long flags; @@ -518,8 +518,8 @@ static struct ptp_clock_info ptp_pch_caps = { .pps = 0, .adjfreq = ptp_pch_adjfreq, .adjtime = ptp_pch_adjtime, - .gettime = ptp_pch_gettime, - .settime = ptp_pch_settime, + .gettime64 = ptp_pch_gettime, + .settime64 = ptp_pch_settime, .enable = ptp_pch_enable, }; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 1245dca79009..a4a8a6dc60c4 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1839,10 +1839,12 @@ static int _regulator_do_enable(struct regulator_dev *rdev) } if (rdev->ena_pin) { - ret = regulator_ena_gpio_ctrl(rdev, true); - if (ret < 0) - return ret; - rdev->ena_gpio_state = 1; + if (!rdev->ena_gpio_state) { + ret = regulator_ena_gpio_ctrl(rdev, true); + if (ret < 0) + return ret; + rdev->ena_gpio_state = 1; + } } else if (rdev->desc->ops->enable) { ret = rdev->desc->ops->enable(rdev); if (ret < 0) @@ -1939,10 +1941,12 @@ static int _regulator_do_disable(struct regulator_dev *rdev) trace_regulator_disable(rdev_get_name(rdev)); if (rdev->ena_pin) { - ret = regulator_ena_gpio_ctrl(rdev, false); - if (ret < 0) - return ret; - rdev->ena_gpio_state = 0; + if (rdev->ena_gpio_state) { + ret = regulator_ena_gpio_ctrl(rdev, false); + if (ret < 0) + return ret; + rdev->ena_gpio_state = 0; + } } else if (rdev->desc->ops->disable) { ret = rdev->desc->ops->disable(rdev); @@ -3626,12 +3630,6 @@ regulator_register(const struct regulator_desc *regulator_desc, config->ena_gpio, ret); goto wash; } - - if (config->ena_gpio_flags & GPIOF_OUT_INIT_HIGH) - rdev->ena_gpio_state = 1; - - if (config->ena_gpio_invert) - rdev->ena_gpio_state = !rdev->ena_gpio_state; } /* set regulator constraints */ @@ -3800,9 +3798,11 @@ int regulator_suspend_finish(void) list_for_each_entry(rdev, ®ulator_list, list) { mutex_lock(&rdev->mutex); if (rdev->use_count > 0 || rdev->constraints->always_on) { - error = _regulator_do_enable(rdev); - if (error) - ret = error; + if (!_regulator_is_enabled(rdev)) { + error = _regulator_do_enable(rdev); + if (error) + ret = error; + } } else { if (!have_full_constraints()) goto unlock; diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c index e2cffe01b807..fb991ec76423 100644 --- a/drivers/regulator/tps65910-regulator.c +++ b/drivers/regulator/tps65910-regulator.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/err.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 92f6af6da699..73354ee27877 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -951,6 +951,7 @@ static int rpmsg_probe(struct virtio_device *vdev) void *bufs_va; int err = 0, i; size_t total_buf_space; + bool notify; vrp = kzalloc(sizeof(*vrp), GFP_KERNEL); if (!vrp) @@ -1030,8 +1031,22 @@ static int rpmsg_probe(struct virtio_device *vdev) } } + /* + * Prepare to kick but don't notify yet - we can't do this before + * device is ready. + */ + notify = virtqueue_kick_prepare(vrp->rvq); + + /* From this point on, we can notify and get callbacks. */ + virtio_device_ready(vdev); + /* tell the remote processor it can start sending messages */ - virtqueue_kick(vrp->rvq); + /* + * this might be concurrent with callbacks, but we are only + * doing notify, not a full kick here, so that's ok. + */ + if (notify) + virtqueue_notify(vrp->rvq); dev_info(&vdev->dev, "rpmsg host is online\n"); diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c index b4f7744f6751..b283a1a573b3 100644 --- a/drivers/rtc/rtc-at91rm9200.c +++ b/drivers/rtc/rtc-at91rm9200.c @@ -324,7 +324,7 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id) ret = IRQ_HANDLED; } - spin_lock(&suspended_lock); + spin_unlock(&suspended_lock); return ret; } diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 4241eeab3386..f4cf6851fae9 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -849,6 +849,7 @@ static struct s3c_rtc_data const s3c2443_rtc_data = { static struct s3c_rtc_data const s3c6410_rtc_data = { .max_user_freq = 32768, + .needs_src_clk = true, .irq_handler = s3c6410_rtc_irq, .set_freq = s3c6410_rtc_setfreq, .enable_tick = s3c6410_rtc_enable_tick, diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c index d9631e15f7b5..dbe416ff46c2 100644 --- a/drivers/scsi/csiostor/csio_init.c +++ b/drivers/scsi/csiostor/csio_init.c @@ -1172,7 +1172,7 @@ static struct pci_error_handlers csio_err_handler = { * Macros needed to support the PCI Device ID Table ... */ #define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \ - static struct pci_device_id csio_pci_tbl[] = { + static const struct pci_device_id csio_pci_tbl[] = { /* Define for FCoE uses PF6 */ #define CH_PCI_DEVICE_ID_FUNCTION 0x6 diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 62b58d38ce2e..60de66252fa2 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -500,6 +500,7 @@ static void sas_revalidate_domain(struct work_struct *work) struct sas_discovery_event *ev = to_sas_discovery_event(work); struct asd_sas_port *port = ev->port; struct sas_ha_struct *ha = port->ha; + struct domain_device *ddev = port->port_dev; /* prevent revalidation from finding sata links in recovery */ mutex_lock(&ha->disco_mutex); @@ -514,8 +515,9 @@ static void sas_revalidate_domain(struct work_struct *work) SAS_DPRINTK("REVALIDATING DOMAIN on port %d, pid:%d\n", port->id, task_pid_nr(current)); - if (port->port_dev) - res = sas_ex_revalidate_domain(port->port_dev); + if (ddev && (ddev->dev_type == SAS_FANOUT_EXPANDER_DEVICE || + ddev->dev_type == SAS_EDGE_EXPANDER_DEVICE)) + res = sas_ex_revalidate_domain(ddev); SAS_DPRINTK("done REVALIDATING DOMAIN on port %d, pid:%d, res 0x%x\n", port->id, task_pid_nr(current), res); diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 99f43b7fc9ab..ab4879e12ea7 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -1596,7 +1596,7 @@ static int tcm_qla2xxx_check_initiator_node_acl( /* * Finally register the new FC Nexus with TCM */ - __transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess); + transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess); return 0; } diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index 4324282afe49..03b2a90b9ac0 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -330,16 +330,6 @@ static void device_init_registers(struct vnt_private *pDevice) /* zonetype initial */ pDevice->byOriginalZonetype = pDevice->abyEEPROM[EEP_OFS_ZONETYPE]; - /* Get RFType */ - pDevice->byRFType = SROMbyReadEmbedded(pDevice->PortOffset, EEP_OFS_RFTYPE); - - /* force change RevID for VT3253 emu */ - if ((pDevice->byRFType & RF_EMU) != 0) - pDevice->byRevId = 0x80; - - pDevice->byRFType &= RF_MASK; - pr_debug("pDevice->byRFType = %x\n", pDevice->byRFType); - if (!pDevice->bZoneRegExist) pDevice->byZoneType = pDevice->abyEEPROM[EEP_OFS_ZONETYPE]; @@ -1187,12 +1177,14 @@ static int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; PSTxDesc head_td; - u32 dma_idx = TYPE_AC0DMA; + u32 dma_idx; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); - if (!ieee80211_is_data(hdr->frame_control)) + if (ieee80211_is_data(hdr->frame_control)) + dma_idx = TYPE_AC0DMA; + else dma_idx = TYPE_TXDMA0; if (AVAIL_TD(priv, dma_idx) < 1) { @@ -1206,6 +1198,9 @@ static int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb) head_td->pTDInfo->skb = skb; + if (dma_idx == TYPE_AC0DMA) + head_td->pTDInfo->byFlags = TD_FLAGS_NETIF_SKB; + priv->iTDUsed[dma_idx]++; /* Take ownership */ @@ -1234,13 +1229,10 @@ static int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb) head_td->buff_addr = cpu_to_le32(head_td->pTDInfo->skb_dma); - if (dma_idx == TYPE_AC0DMA) { - head_td->pTDInfo->byFlags = TD_FLAGS_NETIF_SKB; - + if (head_td->pTDInfo->byFlags & TD_FLAGS_NETIF_SKB) MACvTransmitAC0(priv->PortOffset); - } else { + else MACvTransmit0(priv->PortOffset); - } spin_unlock_irqrestore(&priv->lock, flags); @@ -1778,6 +1770,12 @@ vt6655_probe(struct pci_dev *pcid, const struct pci_device_id *ent) MACvInitialize(priv->PortOffset); MACvReadEtherAddress(priv->PortOffset, priv->abyCurrentNetAddr); + /* Get RFType */ + priv->byRFType = SROMbyReadEmbedded(priv->PortOffset, EEP_OFS_RFTYPE); + priv->byRFType &= RF_MASK; + + dev_dbg(&pcid->dev, "RF Type = %x\n", priv->byRFType); + device_get_options(priv); device_set_options(priv); /* Mask out the options cannot be set to the chip */ diff --git a/drivers/staging/vt6655/rf.c b/drivers/staging/vt6655/rf.c index 941b2adca95a..7626f635f160 100644 --- a/drivers/staging/vt6655/rf.c +++ b/drivers/staging/vt6655/rf.c @@ -794,6 +794,7 @@ bool RFbSetPower( break; case RATE_6M: case RATE_9M: + case RATE_12M: case RATE_18M: byPwr = priv->abyOFDMPwrTbl[uCH]; if (priv->byRFType == RF_UW2452) diff --git a/drivers/staging/vt6656/rf.c b/drivers/staging/vt6656/rf.c index c42cde59f598..c4286ccac320 100644 --- a/drivers/staging/vt6656/rf.c +++ b/drivers/staging/vt6656/rf.c @@ -640,6 +640,7 @@ int vnt_rf_setpower(struct vnt_private *priv, u32 rate, u32 channel) break; case RATE_6M: case RATE_9M: + case RATE_12M: case RATE_18M: case RATE_24M: case RATE_36M: diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 50bad55a0c42..2accb6e47beb 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4256,11 +4256,17 @@ int iscsit_close_connection( pr_debug("Closing iSCSI connection CID %hu on SID:" " %u\n", conn->cid, sess->sid); /* - * Always up conn_logout_comp just in case the RX Thread is sleeping - * and the logout response never got sent because the connection - * failed. + * Always up conn_logout_comp for the traditional TCP case just in case + * the RX Thread in iscsi_target_rx_opcode() is sleeping and the logout + * response never got sent because the connection failed. + * + * However for iser-target, isert_wait4logout() is using conn_logout_comp + * to signal logout response TX interrupt completion. Go ahead and skip + * this for iser since isert_rx_opcode() does not wait on logout failure, + * and to avoid iscsi_conn pointer dereference in iser-target code. */ - complete(&conn->conn_logout_comp); + if (conn->conn_transport->transport_type == ISCSI_TCP) + complete(&conn->conn_logout_comp); iscsi_release_thread_set(conn); diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c index 1c197bad6132..bdd8731a4daa 100644 --- a/drivers/target/iscsi/iscsi_target_erl0.c +++ b/drivers/target/iscsi/iscsi_target_erl0.c @@ -22,7 +22,6 @@ #include <target/target_core_fabric.h> #include <target/iscsi/iscsi_target_core.h> -#include <target/iscsi/iscsi_transport.h> #include "iscsi_target_seq_pdu_list.h" #include "iscsi_target_tq.h" #include "iscsi_target_erl0.h" @@ -940,8 +939,7 @@ void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn) if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) { spin_unlock_bh(&conn->state_lock); - if (conn->conn_transport->transport_type == ISCSI_TCP) - iscsit_close_connection(conn); + iscsit_close_connection(conn); return; } diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 6b3c32954689..c36bd7c29136 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -953,11 +953,8 @@ static int tcm_loop_make_nexus( transport_free_session(tl_nexus->se_sess); goto out; } - /* - * Now, register the SAS I_T Nexus as active with the call to - * transport_register_session() - */ - __transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl, + /* Now, register the SAS I_T Nexus as active. */ + transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl, tl_nexus->se_sess, tl_nexus); tl_tpg->tl_nexus = tl_nexus; pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated" diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 58f49ff69b14..79b4ec3ca2db 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -650,6 +650,18 @@ static u32 se_dev_align_max_sectors(u32 max_sectors, u32 block_size) return aligned_max_sectors; } +bool se_dev_check_wce(struct se_device *dev) +{ + bool wce = false; + + if (dev->transport->get_write_cache) + wce = dev->transport->get_write_cache(dev); + else if (dev->dev_attrib.emulate_write_cache > 0) + wce = true; + + return wce; +} + int se_dev_set_max_unmap_lba_count( struct se_device *dev, u32 max_unmap_lba_count) @@ -767,6 +779,16 @@ int se_dev_set_emulate_fua_write(struct se_device *dev, int flag) pr_err("Illegal value %d\n", flag); return -EINVAL; } + if (flag && + dev->transport->get_write_cache) { + pr_err("emulate_fua_write not supported for this device\n"); + return -EINVAL; + } + if (dev->export_count) { + pr_err("emulate_fua_write cannot be changed with active" + " exports: %d\n", dev->export_count); + return -EINVAL; + } dev->dev_attrib.emulate_fua_write = flag; pr_debug("dev[%p]: SE Device Forced Unit Access WRITEs: %d\n", dev, dev->dev_attrib.emulate_fua_write); @@ -801,7 +823,11 @@ int se_dev_set_emulate_write_cache(struct se_device *dev, int flag) pr_err("emulate_write_cache not supported for this device\n"); return -EINVAL; } - + if (dev->export_count) { + pr_err("emulate_write_cache cannot be changed with active" + " exports: %d\n", dev->export_count); + return -EINVAL; + } dev->dev_attrib.emulate_write_cache = flag; pr_debug("dev[%p]: SE Device WRITE_CACHE_EMULATION flag: %d\n", dev, dev->dev_attrib.emulate_write_cache); @@ -1534,8 +1560,6 @@ int target_configure_device(struct se_device *dev) ret = dev->transport->configure_device(dev); if (ret) goto out; - dev->dev_flags |= DF_CONFIGURED; - /* * XXX: there is not much point to have two different values here.. */ @@ -1597,6 +1621,8 @@ int target_configure_device(struct se_device *dev) list_add_tail(&dev->g_dev_node, &g_device_list); mutex_unlock(&g_device_mutex); + dev->dev_flags |= DF_CONFIGURED; + return 0; out_free_alua: diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 1045dcd7bf65..f6c954c4635f 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1121,7 +1121,7 @@ static u32 pscsi_get_device_type(struct se_device *dev) struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); struct scsi_device *sd = pdv->pdv_sd; - return sd->type; + return (sd) ? sd->type : TYPE_NO_LUN; } static sector_t pscsi_get_blocks(struct se_device *dev) diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 9a2f9d3a6e70..3e7297411110 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -708,8 +708,7 @@ sbc_check_dpofua(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb) } } if (cdb[1] & 0x8) { - if (!dev->dev_attrib.emulate_fua_write || - !dev->dev_attrib.emulate_write_cache) { + if (!dev->dev_attrib.emulate_fua_write || !se_dev_check_wce(dev)) { pr_err("Got CDB: 0x%02x with FUA bit set, but device" " does not advertise support for FUA write\n", cdb[0]); diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 460e93109473..6c8bd6bc175c 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -454,19 +454,6 @@ check_scsi_name: } EXPORT_SYMBOL(spc_emulate_evpd_83); -static bool -spc_check_dev_wce(struct se_device *dev) -{ - bool wce = false; - - if (dev->transport->get_write_cache) - wce = dev->transport->get_write_cache(dev); - else if (dev->dev_attrib.emulate_write_cache > 0) - wce = true; - - return wce; -} - /* Extended INQUIRY Data VPD Page */ static sense_reason_t spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) @@ -490,7 +477,7 @@ spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) buf[5] = 0x07; /* If WriteCache emulation is enabled, set V_SUP */ - if (spc_check_dev_wce(dev)) + if (se_dev_check_wce(dev)) buf[6] = 0x01; /* If an LBA map is present set R_SUP */ spin_lock(&cmd->se_dev->t10_alua.lba_map_lock); @@ -897,7 +884,7 @@ static int spc_modesense_caching(struct se_cmd *cmd, u8 pc, u8 *p) if (pc == 1) goto out; - if (spc_check_dev_wce(dev)) + if (se_dev_check_wce(dev)) p[2] = 0x04; /* Write Cache Enable */ p[12] = 0x20; /* Disabled Read Ahead */ @@ -1009,7 +996,7 @@ static sense_reason_t spc_emulate_modesense(struct se_cmd *cmd) (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY))) spc_modesense_write_protect(&buf[length], type); - if ((spc_check_dev_wce(dev)) && + if ((se_dev_check_wce(dev)) && (dev->dev_attrib.emulate_fua_write > 0)) spc_modesense_dpofua(&buf[length], type); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 0adc0f650213..ac3cbabdbdf0 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2389,6 +2389,10 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list); out: spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + + if (ret && ack_kref) + target_put_sess_cmd(se_sess, se_cmd); + return ret; } EXPORT_SYMBOL(target_get_sess_cmd); diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c index 97b486c3dda1..583e755d8091 100644 --- a/drivers/target/tcm_fc/tfc_io.c +++ b/drivers/target/tcm_fc/tfc_io.c @@ -359,7 +359,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd) ep = fc_seq_exch(seq); if (ep) { lport = ep->lp; - if (lport && (ep->xid <= lport->lro_xid)) + if (lport && (ep->xid <= lport->lro_xid)) { /* * "ddp_done" trigger invalidation of HW * specific DDP context @@ -374,6 +374,7 @@ void ft_invl_hw_context(struct ft_cmd *cmd) * identified using ep->xid) */ cmd->was_ddp_setup = 0; + } } } } diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 2ab229ddee38..6ae5b8560e4d 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -119,7 +119,10 @@ static void dw8250_serial_out(struct uart_port *p, int offset, int value) dw8250_force_idle(p); writeb(value, p->membase + (UART_LCR << p->regshift)); } - dev_err(p->dev, "Couldn't set LCR to %d\n", value); + /* + * FIXME: this deadlocks if port->lock is already held + * dev_err(p->dev, "Couldn't set LCR to %d\n", value); + */ } } @@ -163,7 +166,10 @@ static void dw8250_serial_outq(struct uart_port *p, int offset, int value) __raw_writeq(value & 0xff, p->membase + (UART_LCR << p->regshift)); } - dev_err(p->dev, "Couldn't set LCR to %d\n", value); + /* + * FIXME: this deadlocks if port->lock is already held + * dev_err(p->dev, "Couldn't set LCR to %d\n", value); + */ } } #endif /* CONFIG_64BIT */ @@ -187,7 +193,10 @@ static void dw8250_serial_out32(struct uart_port *p, int offset, int value) dw8250_force_idle(p); writel(value, p->membase + (UART_LCR << p->regshift)); } - dev_err(p->dev, "Couldn't set LCR to %d\n", value); + /* + * FIXME: this deadlocks if port->lock is already held + * dev_err(p->dev, "Couldn't set LCR to %d\n", value); + */ } } diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index ff451048c1ac..4bfb7ac0239f 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -929,6 +929,13 @@ __acquires(hwep->lock) return retval; } +static int otg_a_alt_hnp_support(struct ci_hdrc *ci) +{ + dev_warn(&ci->gadget.dev, + "connect the device to an alternate port if you want HNP\n"); + return isr_setup_status_phase(ci); +} + /** * isr_setup_packet_handler: setup packet handler * @ci: UDC descriptor @@ -1061,6 +1068,10 @@ __acquires(ci->lock) ci); } break; + case USB_DEVICE_A_ALT_HNP_SUPPORT: + if (ci_otg_is_fsm_mode(ci)) + err = otg_a_alt_hnp_support(ci); + break; default: goto delegate; } diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c index c6b35b77dab7..61d538aa2346 100644 --- a/drivers/usb/common/usb-otg-fsm.c +++ b/drivers/usb/common/usb-otg-fsm.c @@ -150,9 +150,9 @@ static int otg_set_state(struct otg_fsm *fsm, enum usb_otg_state new_state) break; case OTG_STATE_B_PERIPHERAL: otg_chrg_vbus(fsm, 0); - otg_loc_conn(fsm, 1); otg_loc_sof(fsm, 0); otg_set_protocol(fsm, PROTO_GADGET); + otg_loc_conn(fsm, 1); break; case OTG_STATE_B_WAIT_ACON: otg_chrg_vbus(fsm, 0); @@ -213,10 +213,10 @@ static int otg_set_state(struct otg_fsm *fsm, enum usb_otg_state new_state) break; case OTG_STATE_A_PERIPHERAL: - otg_loc_conn(fsm, 1); otg_loc_sof(fsm, 0); otg_set_protocol(fsm, PROTO_GADGET); otg_drv_vbus(fsm, 1); + otg_loc_conn(fsm, 1); otg_add_timer(fsm, A_BIDL_ADIS); break; case OTG_STATE_A_WAIT_VFALL: diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index 02e3e2d4ea56..6cf047878dba 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -377,6 +377,9 @@ static void dwc2_handle_disconnect_intr(struct dwc2_hsotg *hsotg) dwc2_is_host_mode(hsotg) ? "Host" : "Device", dwc2_op_state_str(hsotg)); + if (hsotg->op_state == OTG_STATE_A_HOST) + dwc2_hcd_disconnect(hsotg); + /* Change to L3 (OFF) state */ hsotg->lx_state = DWC2_L3; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index af98b096af2f..175c9956cbe3 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -144,10 +144,9 @@ struct ffs_io_data { bool read; struct kiocb *kiocb; - const struct iovec *iovec; - unsigned long nr_segs; - char __user *buf; - size_t len; + struct iov_iter data; + const void *to_free; + char *buf; struct mm_struct *mm; struct work_struct work; @@ -649,29 +648,10 @@ static void ffs_user_copy_worker(struct work_struct *work) io_data->req->actual; if (io_data->read && ret > 0) { - int i; - size_t pos = 0; - - /* - * Since req->length may be bigger than io_data->len (after - * being rounded up to maxpacketsize), we may end up with more - * data then user space has space for. - */ - ret = min_t(int, ret, io_data->len); - use_mm(io_data->mm); - for (i = 0; i < io_data->nr_segs; i++) { - size_t len = min_t(size_t, ret - pos, - io_data->iovec[i].iov_len); - if (!len) - break; - if (unlikely(copy_to_user(io_data->iovec[i].iov_base, - &io_data->buf[pos], len))) { - ret = -EFAULT; - break; - } - pos += len; - } + ret = copy_to_iter(io_data->buf, ret, &io_data->data); + if (iov_iter_count(&io_data->data)) + ret = -EFAULT; unuse_mm(io_data->mm); } @@ -684,7 +664,7 @@ static void ffs_user_copy_worker(struct work_struct *work) io_data->kiocb->private = NULL; if (io_data->read) - kfree(io_data->iovec); + kfree(io_data->to_free); kfree(io_data->buf); kfree(io_data); } @@ -743,6 +723,7 @@ static ssize_t ffs_epfile_io(struct file *file, struct ffs_io_data *io_data) * before the waiting completes, so do not assign to 'gadget' earlier */ struct usb_gadget *gadget = epfile->ffs->gadget; + size_t copied; spin_lock_irq(&epfile->ffs->eps_lock); /* In the meantime, endpoint got disabled or changed. */ @@ -750,34 +731,21 @@ static ssize_t ffs_epfile_io(struct file *file, struct ffs_io_data *io_data) spin_unlock_irq(&epfile->ffs->eps_lock); return -ESHUTDOWN; } + data_len = iov_iter_count(&io_data->data); /* * Controller may require buffer size to be aligned to * maxpacketsize of an out endpoint. */ - data_len = io_data->read ? - usb_ep_align_maybe(gadget, ep->ep, io_data->len) : - io_data->len; + if (io_data->read) + data_len = usb_ep_align_maybe(gadget, ep->ep, data_len); spin_unlock_irq(&epfile->ffs->eps_lock); data = kmalloc(data_len, GFP_KERNEL); if (unlikely(!data)) return -ENOMEM; - if (io_data->aio && !io_data->read) { - int i; - size_t pos = 0; - for (i = 0; i < io_data->nr_segs; i++) { - if (unlikely(copy_from_user(&data[pos], - io_data->iovec[i].iov_base, - io_data->iovec[i].iov_len))) { - ret = -EFAULT; - goto error; - } - pos += io_data->iovec[i].iov_len; - } - } else { - if (!io_data->read && - unlikely(__copy_from_user(data, io_data->buf, - io_data->len))) { + if (!io_data->read) { + copied = copy_from_iter(data, data_len, &io_data->data); + if (copied != data_len) { ret = -EFAULT; goto error; } @@ -876,10 +844,8 @@ static ssize_t ffs_epfile_io(struct file *file, struct ffs_io_data *io_data) */ ret = ep->status; if (io_data->read && ret > 0) { - ret = min_t(size_t, ret, io_data->len); - - if (unlikely(copy_to_user(io_data->buf, - data, ret))) + ret = copy_to_iter(data, ret, &io_data->data); + if (unlikely(iov_iter_count(&io_data->data))) ret = -EFAULT; } } @@ -898,37 +864,6 @@ error: return ret; } -static ssize_t -ffs_epfile_write(struct file *file, const char __user *buf, size_t len, - loff_t *ptr) -{ - struct ffs_io_data io_data; - - ENTER(); - - io_data.aio = false; - io_data.read = false; - io_data.buf = (char * __user)buf; - io_data.len = len; - - return ffs_epfile_io(file, &io_data); -} - -static ssize_t -ffs_epfile_read(struct file *file, char __user *buf, size_t len, loff_t *ptr) -{ - struct ffs_io_data io_data; - - ENTER(); - - io_data.aio = false; - io_data.read = true; - io_data.buf = buf; - io_data.len = len; - - return ffs_epfile_io(file, &io_data); -} - static int ffs_epfile_open(struct inode *inode, struct file *file) { @@ -965,67 +900,86 @@ static int ffs_aio_cancel(struct kiocb *kiocb) return value; } -static ssize_t ffs_epfile_aio_write(struct kiocb *kiocb, - const struct iovec *iovec, - unsigned long nr_segs, loff_t loff) +static ssize_t ffs_epfile_write_iter(struct kiocb *kiocb, struct iov_iter *from) { - struct ffs_io_data *io_data; + struct ffs_io_data io_data, *p = &io_data; + ssize_t res; ENTER(); - io_data = kmalloc(sizeof(*io_data), GFP_KERNEL); - if (unlikely(!io_data)) - return -ENOMEM; + if (!is_sync_kiocb(kiocb)) { + p = kmalloc(sizeof(io_data), GFP_KERNEL); + if (unlikely(!p)) + return -ENOMEM; + p->aio = true; + } else { + p->aio = false; + } - io_data->aio = true; - io_data->read = false; - io_data->kiocb = kiocb; - io_data->iovec = iovec; - io_data->nr_segs = nr_segs; - io_data->len = kiocb->ki_nbytes; - io_data->mm = current->mm; + p->read = false; + p->kiocb = kiocb; + p->data = *from; + p->mm = current->mm; - kiocb->private = io_data; + kiocb->private = p; kiocb_set_cancel_fn(kiocb, ffs_aio_cancel); - return ffs_epfile_io(kiocb->ki_filp, io_data); + res = ffs_epfile_io(kiocb->ki_filp, p); + if (res == -EIOCBQUEUED) + return res; + if (p->aio) + kfree(p); + else + *from = p->data; + return res; } -static ssize_t ffs_epfile_aio_read(struct kiocb *kiocb, - const struct iovec *iovec, - unsigned long nr_segs, loff_t loff) +static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) { - struct ffs_io_data *io_data; - struct iovec *iovec_copy; + struct ffs_io_data io_data, *p = &io_data; + ssize_t res; ENTER(); - iovec_copy = kmalloc_array(nr_segs, sizeof(*iovec_copy), GFP_KERNEL); - if (unlikely(!iovec_copy)) - return -ENOMEM; - - memcpy(iovec_copy, iovec, sizeof(struct iovec)*nr_segs); - - io_data = kmalloc(sizeof(*io_data), GFP_KERNEL); - if (unlikely(!io_data)) { - kfree(iovec_copy); - return -ENOMEM; + if (!is_sync_kiocb(kiocb)) { + p = kmalloc(sizeof(io_data), GFP_KERNEL); + if (unlikely(!p)) + return -ENOMEM; + p->aio = true; + } else { + p->aio = false; } - io_data->aio = true; - io_data->read = true; - io_data->kiocb = kiocb; - io_data->iovec = iovec_copy; - io_data->nr_segs = nr_segs; - io_data->len = kiocb->ki_nbytes; - io_data->mm = current->mm; + p->read = true; + p->kiocb = kiocb; + if (p->aio) { + p->to_free = dup_iter(&p->data, to, GFP_KERNEL); + if (!p->to_free) { + kfree(p); + return -ENOMEM; + } + } else { + p->data = *to; + p->to_free = NULL; + } + p->mm = current->mm; - kiocb->private = io_data; + kiocb->private = p; kiocb_set_cancel_fn(kiocb, ffs_aio_cancel); - return ffs_epfile_io(kiocb->ki_filp, io_data); + res = ffs_epfile_io(kiocb->ki_filp, p); + if (res == -EIOCBQUEUED) + return res; + + if (p->aio) { + kfree(p->to_free); + kfree(p); + } else { + *to = p->data; + } + return res; } static int @@ -1105,10 +1059,10 @@ static const struct file_operations ffs_epfile_operations = { .llseek = no_llseek, .open = ffs_epfile_open, - .write = ffs_epfile_write, - .read = ffs_epfile_read, - .aio_write = ffs_epfile_aio_write, - .aio_read = ffs_epfile_aio_read, + .write = new_sync_write, + .read = new_sync_read, + .write_iter = ffs_epfile_write_iter, + .read_iter = ffs_epfile_read_iter, .release = ffs_epfile_release, .unlocked_ioctl = ffs_epfile_ioctl, }; diff --git a/drivers/usb/gadget/function/f_loopback.c b/drivers/usb/gadget/function/f_loopback.c index 298b46112b1a..39f49f1ad22f 100644 --- a/drivers/usb/gadget/function/f_loopback.c +++ b/drivers/usb/gadget/function/f_loopback.c @@ -289,8 +289,7 @@ static void disable_loopback(struct f_loopback *loop) struct usb_composite_dev *cdev; cdev = loop->function.config->cdev; - disable_endpoints(cdev, loop->in_ep, loop->out_ep, NULL, NULL, NULL, - NULL); + disable_endpoints(cdev, loop->in_ep, loop->out_ep, NULL, NULL); VDBG(cdev, "%s disabled\n", loop->function.name); } diff --git a/drivers/usb/gadget/function/f_sourcesink.c b/drivers/usb/gadget/function/f_sourcesink.c index e3dae47baef3..3a5ae9900b1e 100644 --- a/drivers/usb/gadget/function/f_sourcesink.c +++ b/drivers/usb/gadget/function/f_sourcesink.c @@ -23,15 +23,6 @@ #include "gadget_chips.h" #include "u_f.h" -#define USB_MS_TO_SS_INTERVAL(x) USB_MS_TO_HS_INTERVAL(x) - -enum eptype { - EP_CONTROL = 0, - EP_BULK, - EP_ISOC, - EP_INTERRUPT, -}; - /* * SOURCE/SINK FUNCTION ... a primary testing vehicle for USB peripheral * controller drivers. @@ -64,8 +55,6 @@ struct f_sourcesink { struct usb_ep *out_ep; struct usb_ep *iso_in_ep; struct usb_ep *iso_out_ep; - struct usb_ep *int_in_ep; - struct usb_ep *int_out_ep; int cur_alt; }; @@ -79,10 +68,6 @@ static unsigned isoc_interval; static unsigned isoc_maxpacket; static unsigned isoc_mult; static unsigned isoc_maxburst; -static unsigned int_interval; /* In ms */ -static unsigned int_maxpacket; -static unsigned int_mult; -static unsigned int_maxburst; static unsigned buflen; /*-------------------------------------------------------------------------*/ @@ -107,16 +92,6 @@ static struct usb_interface_descriptor source_sink_intf_alt1 = { /* .iInterface = DYNAMIC */ }; -static struct usb_interface_descriptor source_sink_intf_alt2 = { - .bLength = USB_DT_INTERFACE_SIZE, - .bDescriptorType = USB_DT_INTERFACE, - - .bAlternateSetting = 2, - .bNumEndpoints = 2, - .bInterfaceClass = USB_CLASS_VENDOR_SPEC, - /* .iInterface = DYNAMIC */ -}; - /* full speed support: */ static struct usb_endpoint_descriptor fs_source_desc = { @@ -155,26 +130,6 @@ static struct usb_endpoint_descriptor fs_iso_sink_desc = { .bInterval = 4, }; -static struct usb_endpoint_descriptor fs_int_source_desc = { - .bLength = USB_DT_ENDPOINT_SIZE, - .bDescriptorType = USB_DT_ENDPOINT, - - .bEndpointAddress = USB_DIR_IN, - .bmAttributes = USB_ENDPOINT_XFER_INT, - .wMaxPacketSize = cpu_to_le16(64), - .bInterval = GZERO_INT_INTERVAL, -}; - -static struct usb_endpoint_descriptor fs_int_sink_desc = { - .bLength = USB_DT_ENDPOINT_SIZE, - .bDescriptorType = USB_DT_ENDPOINT, - - .bEndpointAddress = USB_DIR_OUT, - .bmAttributes = USB_ENDPOINT_XFER_INT, - .wMaxPacketSize = cpu_to_le16(64), - .bInterval = GZERO_INT_INTERVAL, -}; - static struct usb_descriptor_header *fs_source_sink_descs[] = { (struct usb_descriptor_header *) &source_sink_intf_alt0, (struct usb_descriptor_header *) &fs_sink_desc, @@ -185,10 +140,6 @@ static struct usb_descriptor_header *fs_source_sink_descs[] = { (struct usb_descriptor_header *) &fs_source_desc, (struct usb_descriptor_header *) &fs_iso_sink_desc, (struct usb_descriptor_header *) &fs_iso_source_desc, - (struct usb_descriptor_header *) &source_sink_intf_alt2, -#define FS_ALT_IFC_2_OFFSET 8 - (struct usb_descriptor_header *) &fs_int_sink_desc, - (struct usb_descriptor_header *) &fs_int_source_desc, NULL, }; @@ -228,24 +179,6 @@ static struct usb_endpoint_descriptor hs_iso_sink_desc = { .bInterval = 4, }; -static struct usb_endpoint_descriptor hs_int_source_desc = { - .bLength = USB_DT_ENDPOINT_SIZE, - .bDescriptorType = USB_DT_ENDPOINT, - - .bmAttributes = USB_ENDPOINT_XFER_INT, - .wMaxPacketSize = cpu_to_le16(1024), - .bInterval = USB_MS_TO_HS_INTERVAL(GZERO_INT_INTERVAL), -}; - -static struct usb_endpoint_descriptor hs_int_sink_desc = { - .bLength = USB_DT_ENDPOINT_SIZE, - .bDescriptorType = USB_DT_ENDPOINT, - - .bmAttributes = USB_ENDPOINT_XFER_INT, - .wMaxPacketSize = cpu_to_le16(1024), - .bInterval = USB_MS_TO_HS_INTERVAL(GZERO_INT_INTERVAL), -}; - static struct usb_descriptor_header *hs_source_sink_descs[] = { (struct usb_descriptor_header *) &source_sink_intf_alt0, (struct usb_descriptor_header *) &hs_source_desc, @@ -256,10 +189,6 @@ static struct usb_descriptor_header *hs_source_sink_descs[] = { (struct usb_descriptor_header *) &hs_sink_desc, (struct usb_descriptor_header *) &hs_iso_source_desc, (struct usb_descriptor_header *) &hs_iso_sink_desc, - (struct usb_descriptor_header *) &source_sink_intf_alt2, -#define HS_ALT_IFC_2_OFFSET 8 - (struct usb_descriptor_header *) &hs_int_source_desc, - (struct usb_descriptor_header *) &hs_int_sink_desc, NULL, }; @@ -335,42 +264,6 @@ static struct usb_ss_ep_comp_descriptor ss_iso_sink_comp_desc = { .wBytesPerInterval = cpu_to_le16(1024), }; -static struct usb_endpoint_descriptor ss_int_source_desc = { - .bLength = USB_DT_ENDPOINT_SIZE, - .bDescriptorType = USB_DT_ENDPOINT, - - .bmAttributes = USB_ENDPOINT_XFER_INT, - .wMaxPacketSize = cpu_to_le16(1024), - .bInterval = USB_MS_TO_SS_INTERVAL(GZERO_INT_INTERVAL), -}; - -static struct usb_ss_ep_comp_descriptor ss_int_source_comp_desc = { - .bLength = USB_DT_SS_EP_COMP_SIZE, - .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, - - .bMaxBurst = 0, - .bmAttributes = 0, - .wBytesPerInterval = cpu_to_le16(1024), -}; - -static struct usb_endpoint_descriptor ss_int_sink_desc = { - .bLength = USB_DT_ENDPOINT_SIZE, - .bDescriptorType = USB_DT_ENDPOINT, - - .bmAttributes = USB_ENDPOINT_XFER_INT, - .wMaxPacketSize = cpu_to_le16(1024), - .bInterval = USB_MS_TO_SS_INTERVAL(GZERO_INT_INTERVAL), -}; - -static struct usb_ss_ep_comp_descriptor ss_int_sink_comp_desc = { - .bLength = USB_DT_SS_EP_COMP_SIZE, - .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, - - .bMaxBurst = 0, - .bmAttributes = 0, - .wBytesPerInterval = cpu_to_le16(1024), -}; - static struct usb_descriptor_header *ss_source_sink_descs[] = { (struct usb_descriptor_header *) &source_sink_intf_alt0, (struct usb_descriptor_header *) &ss_source_desc, @@ -387,12 +280,6 @@ static struct usb_descriptor_header *ss_source_sink_descs[] = { (struct usb_descriptor_header *) &ss_iso_source_comp_desc, (struct usb_descriptor_header *) &ss_iso_sink_desc, (struct usb_descriptor_header *) &ss_iso_sink_comp_desc, - (struct usb_descriptor_header *) &source_sink_intf_alt2, -#define SS_ALT_IFC_2_OFFSET 14 - (struct usb_descriptor_header *) &ss_int_source_desc, - (struct usb_descriptor_header *) &ss_int_source_comp_desc, - (struct usb_descriptor_header *) &ss_int_sink_desc, - (struct usb_descriptor_header *) &ss_int_sink_comp_desc, NULL, }; @@ -414,21 +301,6 @@ static struct usb_gadget_strings *sourcesink_strings[] = { }; /*-------------------------------------------------------------------------*/ -static const char *get_ep_string(enum eptype ep_type) -{ - switch (ep_type) { - case EP_ISOC: - return "ISOC-"; - case EP_INTERRUPT: - return "INTERRUPT-"; - case EP_CONTROL: - return "CTRL-"; - case EP_BULK: - return "BULK-"; - default: - return "UNKNOWN-"; - } -} static inline struct usb_request *ss_alloc_ep_req(struct usb_ep *ep, int len) { @@ -456,8 +328,7 @@ static void disable_ep(struct usb_composite_dev *cdev, struct usb_ep *ep) void disable_endpoints(struct usb_composite_dev *cdev, struct usb_ep *in, struct usb_ep *out, - struct usb_ep *iso_in, struct usb_ep *iso_out, - struct usb_ep *int_in, struct usb_ep *int_out) + struct usb_ep *iso_in, struct usb_ep *iso_out) { disable_ep(cdev, in); disable_ep(cdev, out); @@ -465,10 +336,6 @@ void disable_endpoints(struct usb_composite_dev *cdev, disable_ep(cdev, iso_in); if (iso_out) disable_ep(cdev, iso_out); - if (int_in) - disable_ep(cdev, int_in); - if (int_out) - disable_ep(cdev, int_out); } static int @@ -485,7 +352,6 @@ sourcesink_bind(struct usb_configuration *c, struct usb_function *f) return id; source_sink_intf_alt0.bInterfaceNumber = id; source_sink_intf_alt1.bInterfaceNumber = id; - source_sink_intf_alt2.bInterfaceNumber = id; /* allocate bulk endpoints */ ss->in_ep = usb_ep_autoconfig(cdev->gadget, &fs_source_desc); @@ -546,55 +412,14 @@ no_iso: if (isoc_maxpacket > 1024) isoc_maxpacket = 1024; - /* sanity check the interrupt module parameters */ - if (int_interval < 1) - int_interval = 1; - if (int_interval > 4096) - int_interval = 4096; - if (int_mult > 2) - int_mult = 2; - if (int_maxburst > 15) - int_maxburst = 15; - - /* fill in the FS interrupt descriptors from the module parameters */ - fs_int_source_desc.wMaxPacketSize = int_maxpacket > 64 ? - 64 : int_maxpacket; - fs_int_source_desc.bInterval = int_interval > 255 ? - 255 : int_interval; - fs_int_sink_desc.wMaxPacketSize = int_maxpacket > 64 ? - 64 : int_maxpacket; - fs_int_sink_desc.bInterval = int_interval > 255 ? - 255 : int_interval; - - /* allocate int endpoints */ - ss->int_in_ep = usb_ep_autoconfig(cdev->gadget, &fs_int_source_desc); - if (!ss->int_in_ep) - goto no_int; - ss->int_in_ep->driver_data = cdev; /* claim */ - - ss->int_out_ep = usb_ep_autoconfig(cdev->gadget, &fs_int_sink_desc); - if (ss->int_out_ep) { - ss->int_out_ep->driver_data = cdev; /* claim */ - } else { - ss->int_in_ep->driver_data = NULL; - ss->int_in_ep = NULL; -no_int: - fs_source_sink_descs[FS_ALT_IFC_2_OFFSET] = NULL; - hs_source_sink_descs[HS_ALT_IFC_2_OFFSET] = NULL; - ss_source_sink_descs[SS_ALT_IFC_2_OFFSET] = NULL; - } - - if (int_maxpacket > 1024) - int_maxpacket = 1024; - /* support high speed hardware */ hs_source_desc.bEndpointAddress = fs_source_desc.bEndpointAddress; hs_sink_desc.bEndpointAddress = fs_sink_desc.bEndpointAddress; /* - * Fill in the HS isoc and interrupt descriptors from the module - * parameters. We assume that the user knows what they are doing and - * won't give parameters that their UDC doesn't support. + * Fill in the HS isoc descriptors from the module parameters. + * We assume that the user knows what they are doing and won't + * give parameters that their UDC doesn't support. */ hs_iso_source_desc.wMaxPacketSize = isoc_maxpacket; hs_iso_source_desc.wMaxPacketSize |= isoc_mult << 11; @@ -607,17 +432,6 @@ no_int: hs_iso_sink_desc.bInterval = isoc_interval; hs_iso_sink_desc.bEndpointAddress = fs_iso_sink_desc.bEndpointAddress; - hs_int_source_desc.wMaxPacketSize = int_maxpacket; - hs_int_source_desc.wMaxPacketSize |= int_mult << 11; - hs_int_source_desc.bInterval = USB_MS_TO_HS_INTERVAL(int_interval); - hs_int_source_desc.bEndpointAddress = - fs_int_source_desc.bEndpointAddress; - - hs_int_sink_desc.wMaxPacketSize = int_maxpacket; - hs_int_sink_desc.wMaxPacketSize |= int_mult << 11; - hs_int_sink_desc.bInterval = USB_MS_TO_HS_INTERVAL(int_interval); - hs_int_sink_desc.bEndpointAddress = fs_int_sink_desc.bEndpointAddress; - /* support super speed hardware */ ss_source_desc.bEndpointAddress = fs_source_desc.bEndpointAddress; @@ -625,9 +439,9 @@ no_int: fs_sink_desc.bEndpointAddress; /* - * Fill in the SS isoc and interrupt descriptors from the module - * parameters. We assume that the user knows what they are doing and - * won't give parameters that their UDC doesn't support. + * Fill in the SS isoc descriptors from the module parameters. + * We assume that the user knows what they are doing and won't + * give parameters that their UDC doesn't support. */ ss_iso_source_desc.wMaxPacketSize = isoc_maxpacket; ss_iso_source_desc.bInterval = isoc_interval; @@ -646,37 +460,17 @@ no_int: isoc_maxpacket * (isoc_mult + 1) * (isoc_maxburst + 1); ss_iso_sink_desc.bEndpointAddress = fs_iso_sink_desc.bEndpointAddress; - ss_int_source_desc.wMaxPacketSize = int_maxpacket; - ss_int_source_desc.bInterval = USB_MS_TO_SS_INTERVAL(int_interval); - ss_int_source_comp_desc.bmAttributes = int_mult; - ss_int_source_comp_desc.bMaxBurst = int_maxburst; - ss_int_source_comp_desc.wBytesPerInterval = - int_maxpacket * (int_mult + 1) * (int_maxburst + 1); - ss_int_source_desc.bEndpointAddress = - fs_int_source_desc.bEndpointAddress; - - ss_int_sink_desc.wMaxPacketSize = int_maxpacket; - ss_int_sink_desc.bInterval = USB_MS_TO_SS_INTERVAL(int_interval); - ss_int_sink_comp_desc.bmAttributes = int_mult; - ss_int_sink_comp_desc.bMaxBurst = int_maxburst; - ss_int_sink_comp_desc.wBytesPerInterval = - int_maxpacket * (int_mult + 1) * (int_maxburst + 1); - ss_int_sink_desc.bEndpointAddress = fs_int_sink_desc.bEndpointAddress; - ret = usb_assign_descriptors(f, fs_source_sink_descs, hs_source_sink_descs, ss_source_sink_descs); if (ret) return ret; - DBG(cdev, "%s speed %s: IN/%s, OUT/%s, ISO-IN/%s, ISO-OUT/%s, " - "INT-IN/%s, INT-OUT/%s\n", + DBG(cdev, "%s speed %s: IN/%s, OUT/%s, ISO-IN/%s, ISO-OUT/%s\n", (gadget_is_superspeed(c->cdev->gadget) ? "super" : (gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full")), f->name, ss->in_ep->name, ss->out_ep->name, ss->iso_in_ep ? ss->iso_in_ep->name : "<none>", - ss->iso_out_ep ? ss->iso_out_ep->name : "<none>", - ss->int_in_ep ? ss->int_in_ep->name : "<none>", - ss->int_out_ep ? ss->int_out_ep->name : "<none>"); + ss->iso_out_ep ? ss->iso_out_ep->name : "<none>"); return 0; } @@ -807,15 +601,14 @@ static void source_sink_complete(struct usb_ep *ep, struct usb_request *req) } static int source_sink_start_ep(struct f_sourcesink *ss, bool is_in, - enum eptype ep_type, int speed) + bool is_iso, int speed) { struct usb_ep *ep; struct usb_request *req; int i, size, status; for (i = 0; i < 8; i++) { - switch (ep_type) { - case EP_ISOC: + if (is_iso) { switch (speed) { case USB_SPEED_SUPER: size = isoc_maxpacket * (isoc_mult + 1) * @@ -831,28 +624,9 @@ static int source_sink_start_ep(struct f_sourcesink *ss, bool is_in, } ep = is_in ? ss->iso_in_ep : ss->iso_out_ep; req = ss_alloc_ep_req(ep, size); - break; - case EP_INTERRUPT: - switch (speed) { - case USB_SPEED_SUPER: - size = int_maxpacket * (int_mult + 1) * - (int_maxburst + 1); - break; - case USB_SPEED_HIGH: - size = int_maxpacket * (int_mult + 1); - break; - default: - size = int_maxpacket > 1023 ? - 1023 : int_maxpacket; - break; - } - ep = is_in ? ss->int_in_ep : ss->int_out_ep; - req = ss_alloc_ep_req(ep, size); - break; - default: + } else { ep = is_in ? ss->in_ep : ss->out_ep; req = ss_alloc_ep_req(ep, 0); - break; } if (!req) @@ -870,12 +644,12 @@ static int source_sink_start_ep(struct f_sourcesink *ss, bool is_in, cdev = ss->function.config->cdev; ERROR(cdev, "start %s%s %s --> %d\n", - get_ep_string(ep_type), is_in ? "IN" : "OUT", - ep->name, status); + is_iso ? "ISO-" : "", is_in ? "IN" : "OUT", + ep->name, status); free_ep_req(ep, req); } - if (!(ep_type == EP_ISOC)) + if (!is_iso) break; } @@ -888,7 +662,7 @@ static void disable_source_sink(struct f_sourcesink *ss) cdev = ss->function.config->cdev; disable_endpoints(cdev, ss->in_ep, ss->out_ep, ss->iso_in_ep, - ss->iso_out_ep, ss->int_in_ep, ss->int_out_ep); + ss->iso_out_ep); VDBG(cdev, "%s disabled\n", ss->function.name); } @@ -900,62 +674,6 @@ enable_source_sink(struct usb_composite_dev *cdev, struct f_sourcesink *ss, int speed = cdev->gadget->speed; struct usb_ep *ep; - if (alt == 2) { - /* Configure for periodic interrupt endpoint */ - ep = ss->int_in_ep; - if (ep) { - result = config_ep_by_speed(cdev->gadget, - &(ss->function), ep); - if (result) - return result; - - result = usb_ep_enable(ep); - if (result < 0) - return result; - - ep->driver_data = ss; - result = source_sink_start_ep(ss, true, EP_INTERRUPT, - speed); - if (result < 0) { -fail1: - ep = ss->int_in_ep; - if (ep) { - usb_ep_disable(ep); - ep->driver_data = NULL; - } - return result; - } - } - - /* - * one interrupt endpoint reads (sinks) anything OUT (from the - * host) - */ - ep = ss->int_out_ep; - if (ep) { - result = config_ep_by_speed(cdev->gadget, - &(ss->function), ep); - if (result) - goto fail1; - - result = usb_ep_enable(ep); - if (result < 0) - goto fail1; - - ep->driver_data = ss; - result = source_sink_start_ep(ss, false, EP_INTERRUPT, - speed); - if (result < 0) { - ep = ss->int_out_ep; - usb_ep_disable(ep); - ep->driver_data = NULL; - goto fail1; - } - } - - goto out; - } - /* one bulk endpoint writes (sources) zeroes IN (to the host) */ ep = ss->in_ep; result = config_ep_by_speed(cdev->gadget, &(ss->function), ep); @@ -966,7 +684,7 @@ fail1: return result; ep->driver_data = ss; - result = source_sink_start_ep(ss, true, EP_BULK, speed); + result = source_sink_start_ep(ss, true, false, speed); if (result < 0) { fail: ep = ss->in_ep; @@ -985,7 +703,7 @@ fail: goto fail; ep->driver_data = ss; - result = source_sink_start_ep(ss, false, EP_BULK, speed); + result = source_sink_start_ep(ss, false, false, speed); if (result < 0) { fail2: ep = ss->out_ep; @@ -1008,7 +726,7 @@ fail2: goto fail2; ep->driver_data = ss; - result = source_sink_start_ep(ss, true, EP_ISOC, speed); + result = source_sink_start_ep(ss, true, true, speed); if (result < 0) { fail3: ep = ss->iso_in_ep; @@ -1031,14 +749,13 @@ fail3: goto fail3; ep->driver_data = ss; - result = source_sink_start_ep(ss, false, EP_ISOC, speed); + result = source_sink_start_ep(ss, false, true, speed); if (result < 0) { usb_ep_disable(ep); ep->driver_data = NULL; goto fail3; } } - out: ss->cur_alt = alt; @@ -1054,8 +771,6 @@ static int sourcesink_set_alt(struct usb_function *f, if (ss->in_ep->driver_data) disable_source_sink(ss); - else if (alt == 2 && ss->int_in_ep->driver_data) - disable_source_sink(ss); return enable_source_sink(cdev, ss, alt); } @@ -1168,10 +883,6 @@ static struct usb_function *source_sink_alloc_func( isoc_maxpacket = ss_opts->isoc_maxpacket; isoc_mult = ss_opts->isoc_mult; isoc_maxburst = ss_opts->isoc_maxburst; - int_interval = ss_opts->int_interval; - int_maxpacket = ss_opts->int_maxpacket; - int_mult = ss_opts->int_mult; - int_maxburst = ss_opts->int_maxburst; buflen = ss_opts->bulk_buflen; ss->function.name = "source/sink"; @@ -1468,182 +1179,6 @@ static struct f_ss_opts_attribute f_ss_opts_bulk_buflen = f_ss_opts_bulk_buflen_show, f_ss_opts_bulk_buflen_store); -static ssize_t f_ss_opts_int_interval_show(struct f_ss_opts *opts, char *page) -{ - int result; - - mutex_lock(&opts->lock); - result = sprintf(page, "%u", opts->int_interval); - mutex_unlock(&opts->lock); - - return result; -} - -static ssize_t f_ss_opts_int_interval_store(struct f_ss_opts *opts, - const char *page, size_t len) -{ - int ret; - u32 num; - - mutex_lock(&opts->lock); - if (opts->refcnt) { - ret = -EBUSY; - goto end; - } - - ret = kstrtou32(page, 0, &num); - if (ret) - goto end; - - if (num > 4096) { - ret = -EINVAL; - goto end; - } - - opts->int_interval = num; - ret = len; -end: - mutex_unlock(&opts->lock); - return ret; -} - -static struct f_ss_opts_attribute f_ss_opts_int_interval = - __CONFIGFS_ATTR(int_interval, S_IRUGO | S_IWUSR, - f_ss_opts_int_interval_show, - f_ss_opts_int_interval_store); - -static ssize_t f_ss_opts_int_maxpacket_show(struct f_ss_opts *opts, char *page) -{ - int result; - - mutex_lock(&opts->lock); - result = sprintf(page, "%u", opts->int_maxpacket); - mutex_unlock(&opts->lock); - - return result; -} - -static ssize_t f_ss_opts_int_maxpacket_store(struct f_ss_opts *opts, - const char *page, size_t len) -{ - int ret; - u16 num; - - mutex_lock(&opts->lock); - if (opts->refcnt) { - ret = -EBUSY; - goto end; - } - - ret = kstrtou16(page, 0, &num); - if (ret) - goto end; - - if (num > 1024) { - ret = -EINVAL; - goto end; - } - - opts->int_maxpacket = num; - ret = len; -end: - mutex_unlock(&opts->lock); - return ret; -} - -static struct f_ss_opts_attribute f_ss_opts_int_maxpacket = - __CONFIGFS_ATTR(int_maxpacket, S_IRUGO | S_IWUSR, - f_ss_opts_int_maxpacket_show, - f_ss_opts_int_maxpacket_store); - -static ssize_t f_ss_opts_int_mult_show(struct f_ss_opts *opts, char *page) -{ - int result; - - mutex_lock(&opts->lock); - result = sprintf(page, "%u", opts->int_mult); - mutex_unlock(&opts->lock); - - return result; -} - -static ssize_t f_ss_opts_int_mult_store(struct f_ss_opts *opts, - const char *page, size_t len) -{ - int ret; - u8 num; - - mutex_lock(&opts->lock); - if (opts->refcnt) { - ret = -EBUSY; - goto end; - } - - ret = kstrtou8(page, 0, &num); - if (ret) - goto end; - - if (num > 2) { - ret = -EINVAL; - goto end; - } - - opts->int_mult = num; - ret = len; -end: - mutex_unlock(&opts->lock); - return ret; -} - -static struct f_ss_opts_attribute f_ss_opts_int_mult = - __CONFIGFS_ATTR(int_mult, S_IRUGO | S_IWUSR, - f_ss_opts_int_mult_show, - f_ss_opts_int_mult_store); - -static ssize_t f_ss_opts_int_maxburst_show(struct f_ss_opts *opts, char *page) -{ - int result; - - mutex_lock(&opts->lock); - result = sprintf(page, "%u", opts->int_maxburst); - mutex_unlock(&opts->lock); - - return result; -} - -static ssize_t f_ss_opts_int_maxburst_store(struct f_ss_opts *opts, - const char *page, size_t len) -{ - int ret; - u8 num; - - mutex_lock(&opts->lock); - if (opts->refcnt) { - ret = -EBUSY; - goto end; - } - - ret = kstrtou8(page, 0, &num); - if (ret) - goto end; - - if (num > 15) { - ret = -EINVAL; - goto end; - } - - opts->int_maxburst = num; - ret = len; -end: - mutex_unlock(&opts->lock); - return ret; -} - -static struct f_ss_opts_attribute f_ss_opts_int_maxburst = - __CONFIGFS_ATTR(int_maxburst, S_IRUGO | S_IWUSR, - f_ss_opts_int_maxburst_show, - f_ss_opts_int_maxburst_store); - static struct configfs_attribute *ss_attrs[] = { &f_ss_opts_pattern.attr, &f_ss_opts_isoc_interval.attr, @@ -1651,10 +1186,6 @@ static struct configfs_attribute *ss_attrs[] = { &f_ss_opts_isoc_mult.attr, &f_ss_opts_isoc_maxburst.attr, &f_ss_opts_bulk_buflen.attr, - &f_ss_opts_int_interval.attr, - &f_ss_opts_int_maxpacket.attr, - &f_ss_opts_int_mult.attr, - &f_ss_opts_int_maxburst.attr, NULL, }; @@ -1684,8 +1215,6 @@ static struct usb_function_instance *source_sink_alloc_inst(void) ss_opts->isoc_interval = GZERO_ISOC_INTERVAL; ss_opts->isoc_maxpacket = GZERO_ISOC_MAXPACKET; ss_opts->bulk_buflen = GZERO_BULK_BUFLEN; - ss_opts->int_interval = GZERO_INT_INTERVAL; - ss_opts->int_maxpacket = GZERO_INT_MAXPACKET; config_group_init_type_name(&ss_opts->func_inst.group, "", &ss_func_type); diff --git a/drivers/usb/gadget/function/g_zero.h b/drivers/usb/gadget/function/g_zero.h index 2ce28b9d97cc..15f180904f8a 100644 --- a/drivers/usb/gadget/function/g_zero.h +++ b/drivers/usb/gadget/function/g_zero.h @@ -10,8 +10,6 @@ #define GZERO_QLEN 32 #define GZERO_ISOC_INTERVAL 4 #define GZERO_ISOC_MAXPACKET 1024 -#define GZERO_INT_INTERVAL 1 /* Default interrupt interval = 1 ms */ -#define GZERO_INT_MAXPACKET 1024 struct usb_zero_options { unsigned pattern; @@ -19,10 +17,6 @@ struct usb_zero_options { unsigned isoc_maxpacket; unsigned isoc_mult; unsigned isoc_maxburst; - unsigned int_interval; /* In ms */ - unsigned int_maxpacket; - unsigned int_mult; - unsigned int_maxburst; unsigned bulk_buflen; unsigned qlen; }; @@ -34,10 +28,6 @@ struct f_ss_opts { unsigned isoc_maxpacket; unsigned isoc_mult; unsigned isoc_maxburst; - unsigned int_interval; /* In ms */ - unsigned int_maxpacket; - unsigned int_mult; - unsigned int_maxburst; unsigned bulk_buflen; /* @@ -72,7 +62,6 @@ int lb_modinit(void); void free_ep_req(struct usb_ep *ep, struct usb_request *req); void disable_endpoints(struct usb_composite_dev *cdev, struct usb_ep *in, struct usb_ep *out, - struct usb_ep *iso_in, struct usb_ep *iso_out, - struct usb_ep *int_in, struct usb_ep *int_out); + struct usb_ep *iso_in, struct usb_ep *iso_out); #endif /* __G_ZERO_H */ diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index db49ec4c748e..200f9a584064 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -74,6 +74,8 @@ MODULE_DESCRIPTION (DRIVER_DESC); MODULE_AUTHOR ("David Brownell"); MODULE_LICENSE ("GPL"); +static int ep_open(struct inode *, struct file *); + /*----------------------------------------------------------------------*/ @@ -283,14 +285,15 @@ static void epio_complete (struct usb_ep *ep, struct usb_request *req) * still need dev->lock to use epdata->ep. */ static int -get_ready_ep (unsigned f_flags, struct ep_data *epdata) +get_ready_ep (unsigned f_flags, struct ep_data *epdata, bool is_write) { int val; if (f_flags & O_NONBLOCK) { if (!mutex_trylock(&epdata->lock)) goto nonblock; - if (epdata->state != STATE_EP_ENABLED) { + if (epdata->state != STATE_EP_ENABLED && + (!is_write || epdata->state != STATE_EP_READY)) { mutex_unlock(&epdata->lock); nonblock: val = -EAGAIN; @@ -305,18 +308,20 @@ nonblock: switch (epdata->state) { case STATE_EP_ENABLED: + return 0; + case STATE_EP_READY: /* not configured yet */ + if (is_write) + return 0; + // FALLTHRU + case STATE_EP_UNBOUND: /* clean disconnect */ break; // case STATE_EP_DISABLED: /* "can't happen" */ - // case STATE_EP_READY: /* "can't happen" */ default: /* error! */ pr_debug ("%s: ep %p not available, state %d\n", shortname, epdata, epdata->state); - // FALLTHROUGH - case STATE_EP_UNBOUND: /* clean disconnect */ - val = -ENODEV; - mutex_unlock(&epdata->lock); } - return val; + mutex_unlock(&epdata->lock); + return -ENODEV; } static ssize_t @@ -363,97 +368,6 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) return value; } - -/* handle a synchronous OUT bulk/intr/iso transfer */ -static ssize_t -ep_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) -{ - struct ep_data *data = fd->private_data; - void *kbuf; - ssize_t value; - - if ((value = get_ready_ep (fd->f_flags, data)) < 0) - return value; - - /* halt any endpoint by doing a "wrong direction" i/o call */ - if (usb_endpoint_dir_in(&data->desc)) { - if (usb_endpoint_xfer_isoc(&data->desc)) { - mutex_unlock(&data->lock); - return -EINVAL; - } - DBG (data->dev, "%s halt\n", data->name); - spin_lock_irq (&data->dev->lock); - if (likely (data->ep != NULL)) - usb_ep_set_halt (data->ep); - spin_unlock_irq (&data->dev->lock); - mutex_unlock(&data->lock); - return -EBADMSG; - } - - /* FIXME readahead for O_NONBLOCK and poll(); careful with ZLPs */ - - value = -ENOMEM; - kbuf = kmalloc (len, GFP_KERNEL); - if (unlikely (!kbuf)) - goto free1; - - value = ep_io (data, kbuf, len); - VDEBUG (data->dev, "%s read %zu OUT, status %d\n", - data->name, len, (int) value); - if (value >= 0 && copy_to_user (buf, kbuf, value)) - value = -EFAULT; - -free1: - mutex_unlock(&data->lock); - kfree (kbuf); - return value; -} - -/* handle a synchronous IN bulk/intr/iso transfer */ -static ssize_t -ep_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) -{ - struct ep_data *data = fd->private_data; - void *kbuf; - ssize_t value; - - if ((value = get_ready_ep (fd->f_flags, data)) < 0) - return value; - - /* halt any endpoint by doing a "wrong direction" i/o call */ - if (!usb_endpoint_dir_in(&data->desc)) { - if (usb_endpoint_xfer_isoc(&data->desc)) { - mutex_unlock(&data->lock); - return -EINVAL; - } - DBG (data->dev, "%s halt\n", data->name); - spin_lock_irq (&data->dev->lock); - if (likely (data->ep != NULL)) - usb_ep_set_halt (data->ep); - spin_unlock_irq (&data->dev->lock); - mutex_unlock(&data->lock); - return -EBADMSG; - } - - /* FIXME writebehind for O_NONBLOCK and poll(), qlen = 1 */ - - value = -ENOMEM; - kbuf = memdup_user(buf, len); - if (IS_ERR(kbuf)) { - value = PTR_ERR(kbuf); - kbuf = NULL; - goto free1; - } - - value = ep_io (data, kbuf, len); - VDEBUG (data->dev, "%s write %zu IN, status %d\n", - data->name, len, (int) value); -free1: - mutex_unlock(&data->lock); - kfree (kbuf); - return value; -} - static int ep_release (struct inode *inode, struct file *fd) { @@ -481,7 +395,7 @@ static long ep_ioctl(struct file *fd, unsigned code, unsigned long value) struct ep_data *data = fd->private_data; int status; - if ((status = get_ready_ep (fd->f_flags, data)) < 0) + if ((status = get_ready_ep (fd->f_flags, data, false)) < 0) return status; spin_lock_irq (&data->dev->lock); @@ -517,8 +431,8 @@ struct kiocb_priv { struct mm_struct *mm; struct work_struct work; void *buf; - const struct iovec *iv; - unsigned long nr_segs; + struct iov_iter to; + const void *to_free; unsigned actual; }; @@ -541,35 +455,6 @@ static int ep_aio_cancel(struct kiocb *iocb) return value; } -static ssize_t ep_copy_to_user(struct kiocb_priv *priv) -{ - ssize_t len, total; - void *to_copy; - int i; - - /* copy stuff into user buffers */ - total = priv->actual; - len = 0; - to_copy = priv->buf; - for (i=0; i < priv->nr_segs; i++) { - ssize_t this = min((ssize_t)(priv->iv[i].iov_len), total); - - if (copy_to_user(priv->iv[i].iov_base, to_copy, this)) { - if (len == 0) - len = -EFAULT; - break; - } - - total -= this; - len += this; - to_copy += this; - if (total == 0) - break; - } - - return len; -} - static void ep_user_copy_worker(struct work_struct *work) { struct kiocb_priv *priv = container_of(work, struct kiocb_priv, work); @@ -578,13 +463,16 @@ static void ep_user_copy_worker(struct work_struct *work) size_t ret; use_mm(mm); - ret = ep_copy_to_user(priv); + ret = copy_to_iter(priv->buf, priv->actual, &priv->to); unuse_mm(mm); + if (!ret) + ret = -EFAULT; /* completing the iocb can drop the ctx and mm, don't touch mm after */ aio_complete(iocb, ret, ret); kfree(priv->buf); + kfree(priv->to_free); kfree(priv); } @@ -603,8 +491,9 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) * don't need to copy anything to userspace, so we can * complete the aio request immediately. */ - if (priv->iv == NULL || unlikely(req->actual == 0)) { + if (priv->to_free == NULL || unlikely(req->actual == 0)) { kfree(req->buf); + kfree(priv->to_free); kfree(priv); iocb->private = NULL; /* aio_complete() reports bytes-transferred _and_ faults */ @@ -618,6 +507,7 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) priv->buf = req->buf; priv->actual = req->actual; + INIT_WORK(&priv->work, ep_user_copy_worker); schedule_work(&priv->work); } spin_unlock(&epdata->dev->lock); @@ -626,38 +516,17 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) put_ep(epdata); } -static ssize_t -ep_aio_rwtail( - struct kiocb *iocb, - char *buf, - size_t len, - struct ep_data *epdata, - const struct iovec *iv, - unsigned long nr_segs -) +static ssize_t ep_aio(struct kiocb *iocb, + struct kiocb_priv *priv, + struct ep_data *epdata, + char *buf, + size_t len) { - struct kiocb_priv *priv; - struct usb_request *req; - ssize_t value; + struct usb_request *req; + ssize_t value; - priv = kmalloc(sizeof *priv, GFP_KERNEL); - if (!priv) { - value = -ENOMEM; -fail: - kfree(buf); - return value; - } iocb->private = priv; priv->iocb = iocb; - priv->iv = iv; - priv->nr_segs = nr_segs; - INIT_WORK(&priv->work, ep_user_copy_worker); - - value = get_ready_ep(iocb->ki_filp->f_flags, epdata); - if (unlikely(value < 0)) { - kfree(priv); - goto fail; - } kiocb_set_cancel_fn(iocb, ep_aio_cancel); get_ep(epdata); @@ -669,75 +538,154 @@ fail: * allocate or submit those if the host disconnected. */ spin_lock_irq(&epdata->dev->lock); - if (likely(epdata->ep)) { - req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC); - if (likely(req)) { - priv->req = req; - req->buf = buf; - req->length = len; - req->complete = ep_aio_complete; - req->context = iocb; - value = usb_ep_queue(epdata->ep, req, GFP_ATOMIC); - if (unlikely(0 != value)) - usb_ep_free_request(epdata->ep, req); - } else - value = -EAGAIN; - } else - value = -ENODEV; - spin_unlock_irq(&epdata->dev->lock); + value = -ENODEV; + if (unlikely(epdata->ep)) + goto fail; - mutex_unlock(&epdata->lock); + req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC); + value = -ENOMEM; + if (unlikely(!req)) + goto fail; - if (unlikely(value)) { - kfree(priv); - put_ep(epdata); - } else - value = -EIOCBQUEUED; + priv->req = req; + req->buf = buf; + req->length = len; + req->complete = ep_aio_complete; + req->context = iocb; + value = usb_ep_queue(epdata->ep, req, GFP_ATOMIC); + if (unlikely(0 != value)) { + usb_ep_free_request(epdata->ep, req); + goto fail; + } + spin_unlock_irq(&epdata->dev->lock); + return -EIOCBQUEUED; + +fail: + spin_unlock_irq(&epdata->dev->lock); + kfree(priv->to_free); + kfree(priv); + put_ep(epdata); return value; } static ssize_t -ep_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t o) +ep_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct ep_data *epdata = iocb->ki_filp->private_data; - char *buf; + struct file *file = iocb->ki_filp; + struct ep_data *epdata = file->private_data; + size_t len = iov_iter_count(to); + ssize_t value; + char *buf; - if (unlikely(usb_endpoint_dir_in(&epdata->desc))) - return -EINVAL; + if ((value = get_ready_ep(file->f_flags, epdata, false)) < 0) + return value; - buf = kmalloc(iocb->ki_nbytes, GFP_KERNEL); - if (unlikely(!buf)) - return -ENOMEM; + /* halt any endpoint by doing a "wrong direction" i/o call */ + if (usb_endpoint_dir_in(&epdata->desc)) { + if (usb_endpoint_xfer_isoc(&epdata->desc) || + !is_sync_kiocb(iocb)) { + mutex_unlock(&epdata->lock); + return -EINVAL; + } + DBG (epdata->dev, "%s halt\n", epdata->name); + spin_lock_irq(&epdata->dev->lock); + if (likely(epdata->ep != NULL)) + usb_ep_set_halt(epdata->ep); + spin_unlock_irq(&epdata->dev->lock); + mutex_unlock(&epdata->lock); + return -EBADMSG; + } - return ep_aio_rwtail(iocb, buf, iocb->ki_nbytes, epdata, iov, nr_segs); + buf = kmalloc(len, GFP_KERNEL); + if (unlikely(!buf)) { + mutex_unlock(&epdata->lock); + return -ENOMEM; + } + if (is_sync_kiocb(iocb)) { + value = ep_io(epdata, buf, len); + if (value >= 0 && copy_to_iter(buf, value, to)) + value = -EFAULT; + } else { + struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); + value = -ENOMEM; + if (!priv) + goto fail; + priv->to_free = dup_iter(&priv->to, to, GFP_KERNEL); + if (!priv->to_free) { + kfree(priv); + goto fail; + } + value = ep_aio(iocb, priv, epdata, buf, len); + if (value == -EIOCBQUEUED) + buf = NULL; + } +fail: + kfree(buf); + mutex_unlock(&epdata->lock); + return value; } +static ssize_t ep_config(struct ep_data *, const char *, size_t); + static ssize_t -ep_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t o) +ep_write_iter(struct kiocb *iocb, struct iov_iter *from) { - struct ep_data *epdata = iocb->ki_filp->private_data; - char *buf; - size_t len = 0; - int i = 0; + struct file *file = iocb->ki_filp; + struct ep_data *epdata = file->private_data; + size_t len = iov_iter_count(from); + bool configured; + ssize_t value; + char *buf; + + if ((value = get_ready_ep(file->f_flags, epdata, true)) < 0) + return value; - if (unlikely(!usb_endpoint_dir_in(&epdata->desc))) - return -EINVAL; + configured = epdata->state == STATE_EP_ENABLED; - buf = kmalloc(iocb->ki_nbytes, GFP_KERNEL); - if (unlikely(!buf)) + /* halt any endpoint by doing a "wrong direction" i/o call */ + if (configured && !usb_endpoint_dir_in(&epdata->desc)) { + if (usb_endpoint_xfer_isoc(&epdata->desc) || + !is_sync_kiocb(iocb)) { + mutex_unlock(&epdata->lock); + return -EINVAL; + } + DBG (epdata->dev, "%s halt\n", epdata->name); + spin_lock_irq(&epdata->dev->lock); + if (likely(epdata->ep != NULL)) + usb_ep_set_halt(epdata->ep); + spin_unlock_irq(&epdata->dev->lock); + mutex_unlock(&epdata->lock); + return -EBADMSG; + } + + buf = kmalloc(len, GFP_KERNEL); + if (unlikely(!buf)) { + mutex_unlock(&epdata->lock); return -ENOMEM; + } - for (i=0; i < nr_segs; i++) { - if (unlikely(copy_from_user(&buf[len], iov[i].iov_base, - iov[i].iov_len) != 0)) { - kfree(buf); - return -EFAULT; + if (unlikely(copy_from_iter(buf, len, from) != len)) { + value = -EFAULT; + goto out; + } + + if (unlikely(!configured)) { + value = ep_config(epdata, buf, len); + } else if (is_sync_kiocb(iocb)) { + value = ep_io(epdata, buf, len); + } else { + struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); + value = -ENOMEM; + if (priv) { + value = ep_aio(iocb, priv, epdata, buf, len); + if (value == -EIOCBQUEUED) + buf = NULL; } - len += iov[i].iov_len; } - return ep_aio_rwtail(iocb, buf, len, epdata, NULL, 0); +out: + kfree(buf); + mutex_unlock(&epdata->lock); + return value; } /*----------------------------------------------------------------------*/ @@ -745,15 +693,15 @@ ep_aio_write(struct kiocb *iocb, const struct iovec *iov, /* used after endpoint configuration */ static const struct file_operations ep_io_operations = { .owner = THIS_MODULE, - .llseek = no_llseek, - .read = ep_read, - .write = ep_write, - .unlocked_ioctl = ep_ioctl, + .open = ep_open, .release = ep_release, - - .aio_read = ep_aio_read, - .aio_write = ep_aio_write, + .llseek = no_llseek, + .read = new_sync_read, + .write = new_sync_write, + .unlocked_ioctl = ep_ioctl, + .read_iter = ep_read_iter, + .write_iter = ep_write_iter, }; /* ENDPOINT INITIALIZATION @@ -770,17 +718,12 @@ static const struct file_operations ep_io_operations = { * speed descriptor, then optional high speed descriptor. */ static ssize_t -ep_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) +ep_config (struct ep_data *data, const char *buf, size_t len) { - struct ep_data *data = fd->private_data; struct usb_ep *ep; u32 tag; int value, length = len; - value = mutex_lock_interruptible(&data->lock); - if (value < 0) - return value; - if (data->state != STATE_EP_READY) { value = -EL2HLT; goto fail; @@ -791,9 +734,7 @@ ep_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) goto fail0; /* we might need to change message format someday */ - if (copy_from_user (&tag, buf, 4)) { - goto fail1; - } + memcpy(&tag, buf, 4); if (tag != 1) { DBG(data->dev, "config %s, bad tag %d\n", data->name, tag); goto fail0; @@ -806,19 +747,15 @@ ep_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) */ /* full/low speed descriptor, then high speed */ - if (copy_from_user (&data->desc, buf, USB_DT_ENDPOINT_SIZE)) { - goto fail1; - } + memcpy(&data->desc, buf, USB_DT_ENDPOINT_SIZE); if (data->desc.bLength != USB_DT_ENDPOINT_SIZE || data->desc.bDescriptorType != USB_DT_ENDPOINT) goto fail0; if (len != USB_DT_ENDPOINT_SIZE) { if (len != 2 * USB_DT_ENDPOINT_SIZE) goto fail0; - if (copy_from_user (&data->hs_desc, buf + USB_DT_ENDPOINT_SIZE, - USB_DT_ENDPOINT_SIZE)) { - goto fail1; - } + memcpy(&data->hs_desc, buf + USB_DT_ENDPOINT_SIZE, + USB_DT_ENDPOINT_SIZE); if (data->hs_desc.bLength != USB_DT_ENDPOINT_SIZE || data->hs_desc.bDescriptorType != USB_DT_ENDPOINT) { @@ -840,24 +777,20 @@ ep_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) case USB_SPEED_LOW: case USB_SPEED_FULL: ep->desc = &data->desc; - value = usb_ep_enable(ep); - if (value == 0) - data->state = STATE_EP_ENABLED; break; case USB_SPEED_HIGH: /* fails if caller didn't provide that descriptor... */ ep->desc = &data->hs_desc; - value = usb_ep_enable(ep); - if (value == 0) - data->state = STATE_EP_ENABLED; break; default: DBG(data->dev, "unconnected, %s init abandoned\n", data->name); value = -EINVAL; + goto gone; } + value = usb_ep_enable(ep); if (value == 0) { - fd->f_op = &ep_io_operations; + data->state = STATE_EP_ENABLED; value = length; } gone: @@ -867,14 +800,10 @@ fail: data->desc.bDescriptorType = 0; data->hs_desc.bDescriptorType = 0; } - mutex_unlock(&data->lock); return value; fail0: value = -EINVAL; goto fail; -fail1: - value = -EFAULT; - goto fail; } static int @@ -902,15 +831,6 @@ ep_open (struct inode *inode, struct file *fd) return value; } -/* used before endpoint configuration */ -static const struct file_operations ep_config_operations = { - .llseek = no_llseek, - - .open = ep_open, - .write = ep_config, - .release = ep_release, -}; - /*----------------------------------------------------------------------*/ /* EP0 IMPLEMENTATION can be partly in userspace. @@ -989,6 +909,10 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) enum ep0_state state; spin_lock_irq (&dev->lock); + if (dev->state <= STATE_DEV_OPENED) { + retval = -EINVAL; + goto done; + } /* report fd mode change before acting on it */ if (dev->setup_abort) { @@ -1187,8 +1111,6 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) struct dev_data *dev = fd->private_data; ssize_t retval = -ESRCH; - spin_lock_irq (&dev->lock); - /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; @@ -1234,7 +1156,6 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) } else DBG (dev, "fail %s, state %d\n", __func__, dev->state); - spin_unlock_irq (&dev->lock); return retval; } @@ -1281,6 +1202,9 @@ ep0_poll (struct file *fd, poll_table *wait) struct dev_data *dev = fd->private_data; int mask = 0; + if (dev->state <= STATE_DEV_OPENED) + return DEFAULT_POLLMASK; + poll_wait(fd, &dev->wait, wait); spin_lock_irq (&dev->lock); @@ -1316,19 +1240,6 @@ static long dev_ioctl (struct file *fd, unsigned code, unsigned long value) return ret; } -/* used after device configuration */ -static const struct file_operations ep0_io_operations = { - .owner = THIS_MODULE, - .llseek = no_llseek, - - .read = ep0_read, - .write = ep0_write, - .fasync = ep0_fasync, - .poll = ep0_poll, - .unlocked_ioctl = dev_ioctl, - .release = dev_release, -}; - /*----------------------------------------------------------------------*/ /* The in-kernel gadget driver handles most ep0 issues, in particular @@ -1650,7 +1561,7 @@ static int activate_ep_files (struct dev_data *dev) goto enomem1; data->dentry = gadgetfs_create_file (dev->sb, data->name, - data, &ep_config_operations); + data, &ep_io_operations); if (!data->dentry) goto enomem2; list_add_tail (&data->epfiles, &dev->epfiles); @@ -1852,6 +1763,14 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) u32 tag; char *kbuf; + spin_lock_irq(&dev->lock); + if (dev->state > STATE_DEV_OPENED) { + value = ep0_write(fd, buf, len, ptr); + spin_unlock_irq(&dev->lock); + return value; + } + spin_unlock_irq(&dev->lock); + if (len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4)) return -EINVAL; @@ -1925,7 +1844,6 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) * on, they can work ... except in cleanup paths that * kick in after the ep0 descriptor is closed. */ - fd->f_op = &ep0_io_operations; value = len; } return value; @@ -1956,12 +1874,14 @@ dev_open (struct inode *inode, struct file *fd) return value; } -static const struct file_operations dev_init_operations = { +static const struct file_operations ep0_operations = { .llseek = no_llseek, .open = dev_open, + .read = ep0_read, .write = dev_config, .fasync = ep0_fasync, + .poll = ep0_poll, .unlocked_ioctl = dev_ioctl, .release = dev_release, }; @@ -2077,7 +1997,7 @@ gadgetfs_fill_super (struct super_block *sb, void *opts, int silent) goto Enomem; dev->sb = sb; - dev->dentry = gadgetfs_create_file(sb, CHIP, dev, &dev_init_operations); + dev->dentry = gadgetfs_create_file(sb, CHIP, dev, &ep0_operations); if (!dev->dentry) { put_dev(dev); goto Enomem; diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.c b/drivers/usb/gadget/legacy/tcm_usb_gadget.c index 3a494168661e..6e0a019aad54 100644 --- a/drivers/usb/gadget/legacy/tcm_usb_gadget.c +++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.c @@ -1740,10 +1740,9 @@ static int tcm_usbg_make_nexus(struct usbg_tpg *tpg, char *name) goto err_session; } /* - * Now register the TCM vHost virtual I_T Nexus as active with the - * call to __transport_register_session() + * Now register the TCM vHost virtual I_T Nexus as active. */ - __transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, + transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, tv_nexus->tvn_se_sess, tv_nexus); tpg->tpg_nexus = tv_nexus; mutex_unlock(&tpg->tpg_mutex); diff --git a/drivers/usb/gadget/legacy/zero.c b/drivers/usb/gadget/legacy/zero.c index ff97ac93ac03..5ee95152493c 100644 --- a/drivers/usb/gadget/legacy/zero.c +++ b/drivers/usb/gadget/legacy/zero.c @@ -68,8 +68,6 @@ static struct usb_zero_options gzero_options = { .isoc_maxpacket = GZERO_ISOC_MAXPACKET, .bulk_buflen = GZERO_BULK_BUFLEN, .qlen = GZERO_QLEN, - .int_interval = GZERO_INT_INTERVAL, - .int_maxpacket = GZERO_INT_MAXPACKET, }; /*-------------------------------------------------------------------------*/ @@ -268,21 +266,6 @@ module_param_named(isoc_maxburst, gzero_options.isoc_maxburst, uint, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(isoc_maxburst, "0 - 15 (ss only)"); -module_param_named(int_interval, gzero_options.int_interval, uint, - S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(int_interval, "1 - 16"); - -module_param_named(int_maxpacket, gzero_options.int_maxpacket, uint, - S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(int_maxpacket, "0 - 1023 (fs), 0 - 1024 (hs/ss)"); - -module_param_named(int_mult, gzero_options.int_mult, uint, S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(int_mult, "0 - 2 (hs/ss only)"); - -module_param_named(int_maxburst, gzero_options.int_maxburst, uint, - S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(int_maxburst, "0 - 15 (ss only)"); - static struct usb_function *func_lb; static struct usb_function_instance *func_inst_lb; @@ -318,10 +301,6 @@ static int __init zero_bind(struct usb_composite_dev *cdev) ss_opts->isoc_maxpacket = gzero_options.isoc_maxpacket; ss_opts->isoc_mult = gzero_options.isoc_mult; ss_opts->isoc_maxburst = gzero_options.isoc_maxburst; - ss_opts->int_interval = gzero_options.int_interval; - ss_opts->int_maxpacket = gzero_options.int_maxpacket; - ss_opts->int_mult = gzero_options.int_mult; - ss_opts->int_maxburst = gzero_options.int_maxburst; ss_opts->bulk_buflen = gzero_options.bulk_buflen; func_ss = usb_get_function(func_inst_ss); diff --git a/drivers/usb/host/ehci-atmel.c b/drivers/usb/host/ehci-atmel.c index 663f7908b15c..be0964a801e8 100644 --- a/drivers/usb/host/ehci-atmel.c +++ b/drivers/usb/host/ehci-atmel.c @@ -34,7 +34,6 @@ static const char hcd_name[] = "ehci-atmel"; struct atmel_ehci_priv { struct clk *iclk; - struct clk *fclk; struct clk *uclk; bool clocked; }; @@ -51,12 +50,9 @@ static void atmel_start_clock(struct atmel_ehci_priv *atmel_ehci) { if (atmel_ehci->clocked) return; - if (IS_ENABLED(CONFIG_COMMON_CLK)) { - clk_set_rate(atmel_ehci->uclk, 48000000); - clk_prepare_enable(atmel_ehci->uclk); - } + + clk_prepare_enable(atmel_ehci->uclk); clk_prepare_enable(atmel_ehci->iclk); - clk_prepare_enable(atmel_ehci->fclk); atmel_ehci->clocked = true; } @@ -64,10 +60,9 @@ static void atmel_stop_clock(struct atmel_ehci_priv *atmel_ehci) { if (!atmel_ehci->clocked) return; - clk_disable_unprepare(atmel_ehci->fclk); + clk_disable_unprepare(atmel_ehci->iclk); - if (IS_ENABLED(CONFIG_COMMON_CLK)) - clk_disable_unprepare(atmel_ehci->uclk); + clk_disable_unprepare(atmel_ehci->uclk); atmel_ehci->clocked = false; } @@ -146,20 +141,13 @@ static int ehci_atmel_drv_probe(struct platform_device *pdev) retval = -ENOENT; goto fail_request_resource; } - atmel_ehci->fclk = devm_clk_get(&pdev->dev, "uhpck"); - if (IS_ERR(atmel_ehci->fclk)) { - dev_err(&pdev->dev, "Error getting function clock\n"); - retval = -ENOENT; + + atmel_ehci->uclk = devm_clk_get(&pdev->dev, "usb_clk"); + if (IS_ERR(atmel_ehci->uclk)) { + dev_err(&pdev->dev, "failed to get uclk\n"); + retval = PTR_ERR(atmel_ehci->uclk); goto fail_request_resource; } - if (IS_ENABLED(CONFIG_COMMON_CLK)) { - atmel_ehci->uclk = devm_clk_get(&pdev->dev, "usb_clk"); - if (IS_ERR(atmel_ehci->uclk)) { - dev_err(&pdev->dev, "failed to get uclk\n"); - retval = PTR_ERR(atmel_ehci->uclk); - goto fail_request_resource; - } - } ehci = hcd_to_ehci(hcd); /* registers start at offset 0x0 */ diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 5fb66db89e05..73485fa4372f 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1729,7 +1729,7 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, if (!command) return; - ep->ep_state |= EP_HALTED | EP_RECENTLY_HALTED; + ep->ep_state |= EP_HALTED; ep->stopped_stream = stream_id; xhci_queue_reset_ep(xhci, command, slot_id, ep_index); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b06d1a53652d..ec8ac1674854 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1338,12 +1338,6 @@ int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flags) goto exit; } - /* Reject urb if endpoint is in soft reset, queue must stay empty */ - if (xhci->devs[slot_id]->eps[ep_index].ep_state & EP_CONFIG_PENDING) { - xhci_warn(xhci, "Can't enqueue URB while ep is in soft reset\n"); - ret = -EINVAL; - } - if (usb_endpoint_xfer_isoc(&urb->ep->desc)) size = urb->number_of_packets; else @@ -2954,36 +2948,23 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, } } -/* Called after clearing a halted device. USB core should have sent the control +/* Called when clearing halted device. The core should have sent the control * message to clear the device halt condition. The host side of the halt should - * already be cleared with a reset endpoint command issued immediately when the - * STALL tx event was received. + * already be cleared with a reset endpoint command issued when the STALL tx + * event was received. + * + * Context: in_interrupt */ void xhci_endpoint_reset(struct usb_hcd *hcd, struct usb_host_endpoint *ep) { struct xhci_hcd *xhci; - struct usb_device *udev; - struct xhci_virt_device *virt_dev; - struct xhci_virt_ep *virt_ep; - struct xhci_input_control_ctx *ctrl_ctx; - struct xhci_command *command; - unsigned int ep_index, ep_state; - unsigned long flags; - u32 ep_flag; xhci = hcd_to_xhci(hcd); - udev = (struct usb_device *) ep->hcpriv; - if (!ep->hcpriv) - return; - virt_dev = xhci->devs[udev->slot_id]; - ep_index = xhci_get_endpoint_index(&ep->desc); - virt_ep = &virt_dev->eps[ep_index]; - ep_state = virt_ep->ep_state; /* - * Implement the config ep command in xhci 4.6.8 additional note: + * We might need to implement the config ep cmd in xhci 4.8.1 note: * The Reset Endpoint Command may only be issued to endpoints in the * Halted state. If software wishes reset the Data Toggle or Sequence * Number of an endpoint that isn't in the Halted state, then software @@ -2991,72 +2972,9 @@ void xhci_endpoint_reset(struct usb_hcd *hcd, * for the target endpoint. that is in the Stopped state. */ - if (ep_state & SET_DEQ_PENDING || ep_state & EP_RECENTLY_HALTED) { - virt_ep->ep_state &= ~EP_RECENTLY_HALTED; - xhci_dbg(xhci, "ep recently halted, no toggle reset needed\n"); - return; - } - - /* Only interrupt and bulk ep's use Data toggle, USB2 spec 5.5.4-> */ - if (usb_endpoint_xfer_control(&ep->desc) || - usb_endpoint_xfer_isoc(&ep->desc)) - return; - - ep_flag = xhci_get_endpoint_flag(&ep->desc); - - if (ep_flag == SLOT_FLAG || ep_flag == EP0_FLAG) - return; - - command = xhci_alloc_command(xhci, true, true, GFP_NOWAIT); - if (!command) { - xhci_err(xhci, "Could not allocate xHCI command structure.\n"); - return; - } - - spin_lock_irqsave(&xhci->lock, flags); - - /* block ringing ep doorbell */ - virt_ep->ep_state |= EP_CONFIG_PENDING; - - /* - * Make sure endpoint ring is empty before resetting the toggle/seq. - * Driver is required to synchronously cancel all transfer request. - * - * xhci 4.6.6 says we can issue a configure endpoint command on a - * running endpoint ring as long as it's idle (queue empty) - */ - - if (!list_empty(&virt_ep->ring->td_list)) { - dev_err(&udev->dev, "EP not empty, refuse reset\n"); - spin_unlock_irqrestore(&xhci->lock, flags); - goto cleanup; - } - - xhci_dbg(xhci, "Reset toggle/seq for slot %d, ep_index: %d\n", - udev->slot_id, ep_index); - - ctrl_ctx = xhci_get_input_control_ctx(command->in_ctx); - if (!ctrl_ctx) { - xhci_err(xhci, "Could not get input context, bad type. virt_dev: %p, in_ctx %p\n", - virt_dev, virt_dev->in_ctx); - spin_unlock_irqrestore(&xhci->lock, flags); - goto cleanup; - } - xhci_setup_input_ctx_for_config_ep(xhci, command->in_ctx, - virt_dev->out_ctx, ctrl_ctx, - ep_flag, ep_flag); - xhci_endpoint_copy(xhci, command->in_ctx, virt_dev->out_ctx, ep_index); - - xhci_queue_configure_endpoint(xhci, command, command->in_ctx->dma, - udev->slot_id, false); - xhci_ring_cmd_db(xhci); - spin_unlock_irqrestore(&xhci->lock, flags); - - wait_for_completion(command->completion); - -cleanup: - virt_ep->ep_state &= ~EP_CONFIG_PENDING; - xhci_free_command(xhci, command); + /* For now just print debug to follow the situation */ + xhci_dbg(xhci, "Endpoint 0x%x ep reset callback called\n", + ep->desc.bEndpointAddress); } static int xhci_check_streams_endpoint(struct xhci_hcd *xhci, diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 265ab1771d24..8e421b89632d 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -865,8 +865,6 @@ struct xhci_virt_ep { #define EP_HAS_STREAMS (1 << 4) /* Transitioning the endpoint to not using streams, don't enqueue URBs */ #define EP_GETTING_NO_STREAMS (1 << 5) -#define EP_RECENTLY_HALTED (1 << 6) -#define EP_CONFIG_PENDING (1 << 7) /* ---- Related to URB cancellation ---- */ struct list_head cancelled_td_list; struct xhci_td *stopped_td; diff --git a/drivers/usb/isp1760/isp1760-core.c b/drivers/usb/isp1760/isp1760-core.c index b9827556455f..bfa402cf3a27 100644 --- a/drivers/usb/isp1760/isp1760-core.c +++ b/drivers/usb/isp1760/isp1760-core.c @@ -151,8 +151,7 @@ int isp1760_register(struct resource *mem, int irq, unsigned long irqflags, } if (IS_ENABLED(CONFIG_USB_ISP1761_UDC) && !udc_disabled) { - ret = isp1760_udc_register(isp, irq, irqflags | IRQF_SHARED | - IRQF_DISABLED); + ret = isp1760_udc_register(isp, irq, irqflags); if (ret < 0) { isp1760_hcd_unregister(&isp->hcd); return ret; diff --git a/drivers/usb/isp1760/isp1760-udc.c b/drivers/usb/isp1760/isp1760-udc.c index 9612d7990565..f32c292cc868 100644 --- a/drivers/usb/isp1760/isp1760-udc.c +++ b/drivers/usb/isp1760/isp1760-udc.c @@ -1191,6 +1191,7 @@ static int isp1760_udc_start(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { struct isp1760_udc *udc = gadget_to_udc(gadget); + unsigned long flags; /* The hardware doesn't support low speed. */ if (driver->max_speed < USB_SPEED_FULL) { @@ -1198,7 +1199,7 @@ static int isp1760_udc_start(struct usb_gadget *gadget, return -EINVAL; } - spin_lock(&udc->lock); + spin_lock_irqsave(&udc->lock, flags); if (udc->driver) { dev_err(udc->isp->dev, "UDC already has a gadget driver\n"); @@ -1208,7 +1209,7 @@ static int isp1760_udc_start(struct usb_gadget *gadget, udc->driver = driver; - spin_unlock(&udc->lock); + spin_unlock_irqrestore(&udc->lock, flags); dev_dbg(udc->isp->dev, "starting UDC with driver %s\n", driver->function); @@ -1232,6 +1233,7 @@ static int isp1760_udc_start(struct usb_gadget *gadget, static int isp1760_udc_stop(struct usb_gadget *gadget) { struct isp1760_udc *udc = gadget_to_udc(gadget); + unsigned long flags; dev_dbg(udc->isp->dev, "%s\n", __func__); @@ -1239,9 +1241,9 @@ static int isp1760_udc_stop(struct usb_gadget *gadget) isp1760_udc_write(udc, DC_MODE, 0); - spin_lock(&udc->lock); + spin_lock_irqsave(&udc->lock, flags); udc->driver = NULL; - spin_unlock(&udc->lock); + spin_unlock_irqrestore(&udc->lock, flags); return 0; } @@ -1411,7 +1413,7 @@ static int isp1760_udc_init(struct isp1760_udc *udc) return -ENODEV; } - if (chipid != 0x00011582) { + if (chipid != 0x00011582 && chipid != 0x00158210) { dev_err(udc->isp->dev, "udc: invalid chip ID 0x%08x\n", chipid); return -ENODEV; } @@ -1451,8 +1453,8 @@ int isp1760_udc_register(struct isp1760_device *isp, int irq, sprintf(udc->irqname, "%s (udc)", devname); - ret = request_irq(irq, isp1760_udc_irq, IRQF_SHARED | IRQF_DISABLED | - irqflags, udc->irqname, udc); + ret = request_irq(irq, isp1760_udc_irq, IRQF_SHARED | irqflags, + udc->irqname, udc); if (ret < 0) goto error; diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig index 14e1628483d9..39db8b603627 100644 --- a/drivers/usb/musb/Kconfig +++ b/drivers/usb/musb/Kconfig @@ -79,7 +79,8 @@ config USB_MUSB_TUSB6010 config USB_MUSB_OMAP2PLUS tristate "OMAP2430 and onwards" - depends on ARCH_OMAP2PLUS && USB && OMAP_CONTROL_PHY + depends on ARCH_OMAP2PLUS && USB + depends on OMAP_CONTROL_PHY || !OMAP_CONTROL_PHY select GENERIC_PHY config USB_MUSB_AM35X diff --git a/drivers/usb/phy/phy-am335x-control.c b/drivers/usb/phy/phy-am335x-control.c index 403fab772724..7b3035ff9434 100644 --- a/drivers/usb/phy/phy-am335x-control.c +++ b/drivers/usb/phy/phy-am335x-control.c @@ -126,6 +126,9 @@ struct phy_control *am335x_get_phy_control(struct device *dev) return NULL; dev = bus_find_device(&platform_bus_type, NULL, node, match); + if (!dev) + return NULL; + ctrl_usb = dev_get_drvdata(dev); if (!ctrl_usb) return NULL; diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 82570425fdfe..c85ea530085f 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -113,6 +113,13 @@ UNUSUAL_DEV(0x0bc2, 0xab2a, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_ATA_1X), +/* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */ +UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999, + "Initio Corporation", + "", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_ATA_1X), + /* Reported-by: Tom Arild Naess <tanaess@gmail.com> */ UNUSUAL_DEV(0x152d, 0x0539, 0x0000, 0x9999, "JMicron", diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index f88bfdf5b6a0..2027a27546ef 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -868,12 +868,14 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags, func = vfio_pci_set_err_trigger; break; } + break; case VFIO_PCI_REQ_IRQ_INDEX: switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) { case VFIO_IRQ_SET_ACTION_TRIGGER: func = vfio_pci_set_req_trigger; break; } + break; } if (!func) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 8d4f3f1ff799..71df240a467a 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1956,10 +1956,9 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, goto out; } /* - * Now register the TCM vhost virtual I_T Nexus as active with the - * call to __transport_register_session() + * Now register the TCM vhost virtual I_T Nexus as active. */ - __transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, + transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, tv_nexus->tvn_se_sess, tv_nexus); tpg->tpg_nexus = tv_nexus; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 0413157f3b49..6a356e344f82 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/balloon_compaction.h> #include <linux/oom.h> +#include <linux/wait.h> /* * Balloon device works in 4K page units. So each page is pointed to by @@ -334,17 +335,25 @@ static int virtballoon_oom_notify(struct notifier_block *self, static int balloon(void *_vballoon) { struct virtio_balloon *vb = _vballoon; + DEFINE_WAIT_FUNC(wait, woken_wake_function); set_freezable(); while (!kthread_should_stop()) { s64 diff; try_to_freeze(); - wait_event_interruptible(vb->config_change, - (diff = towards_target(vb)) != 0 - || vb->need_stats_update - || kthread_should_stop() - || freezing(current)); + + add_wait_queue(&vb->config_change, &wait); + for (;;) { + if ((diff = towards_target(vb)) != 0 || + vb->need_stats_update || + kthread_should_stop() || + freezing(current)) + break; + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); + } + remove_wait_queue(&vb->config_change, &wait); + if (vb->need_stats_update) stats_handle_request(vb); if (diff > 0) @@ -499,6 +508,8 @@ static int virtballoon_probe(struct virtio_device *vdev) if (err < 0) goto out_oom_notify; + virtio_device_ready(vdev); + vb->thread = kthread_run(balloon, vb, "vballoon"); if (IS_ERR(vb->thread)) { err = PTR_ERR(vb->thread); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index cad569890908..6010d7ec0a0f 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -156,22 +156,95 @@ static void vm_get(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); - u8 *ptr = buf; - int i; + void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG; + u8 b; + __le16 w; + __le32 l; - for (i = 0; i < len; i++) - ptr[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i); + if (vm_dev->version == 1) { + u8 *ptr = buf; + int i; + + for (i = 0; i < len; i++) + ptr[i] = readb(base + offset + i); + return; + } + + switch (len) { + case 1: + b = readb(base + offset); + memcpy(buf, &b, sizeof b); + break; + case 2: + w = cpu_to_le16(readw(base + offset)); + memcpy(buf, &w, sizeof w); + break; + case 4: + l = cpu_to_le32(readl(base + offset)); + memcpy(buf, &l, sizeof l); + break; + case 8: + l = cpu_to_le32(readl(base + offset)); + memcpy(buf, &l, sizeof l); + l = cpu_to_le32(ioread32(base + offset + sizeof l)); + memcpy(buf + sizeof l, &l, sizeof l); + break; + default: + BUG(); + } } static void vm_set(struct virtio_device *vdev, unsigned offset, const void *buf, unsigned len) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); - const u8 *ptr = buf; - int i; + void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG; + u8 b; + __le16 w; + __le32 l; - for (i = 0; i < len; i++) - writeb(ptr[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i); + if (vm_dev->version == 1) { + const u8 *ptr = buf; + int i; + + for (i = 0; i < len; i++) + writeb(ptr[i], base + offset + i); + + return; + } + + switch (len) { + case 1: + memcpy(&b, buf, sizeof b); + writeb(b, base + offset); + break; + case 2: + memcpy(&w, buf, sizeof w); + writew(le16_to_cpu(w), base + offset); + break; + case 4: + memcpy(&l, buf, sizeof l); + writel(le32_to_cpu(l), base + offset); + break; + case 8: + memcpy(&l, buf, sizeof l); + writel(le32_to_cpu(l), base + offset); + memcpy(&l, buf + sizeof l, sizeof l); + writel(le32_to_cpu(l), base + offset + sizeof l); + break; + default: + BUG(); + } +} + +static u32 vm_generation(struct virtio_device *vdev) +{ + struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); + + if (vm_dev->version == 1) + return 0; + else + return readl(vm_dev->base + VIRTIO_MMIO_CONFIG_GENERATION); } static u8 vm_get_status(struct virtio_device *vdev) @@ -440,6 +513,7 @@ static const char *vm_bus_name(struct virtio_device *vdev) static const struct virtio_config_ops virtio_mmio_config_ops = { .get = vm_get, .set = vm_set, + .generation = vm_generation, .get_status = vm_get_status, .set_status = vm_set_status, .reset = vm_reset, diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index b4bca2d4a7e5..70fba973a107 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -526,20 +526,26 @@ static unsigned int __startup_pirq(unsigned int irq) pirq_query_unmask(irq); rc = set_evtchn_to_irq(evtchn, irq); - if (rc != 0) { - pr_err("irq%d: Failed to set port to irq mapping (%d)\n", - irq, rc); - xen_evtchn_close(evtchn); - return 0; - } + if (rc) + goto err; + bind_evtchn_to_cpu(evtchn, 0); info->evtchn = evtchn; + rc = xen_evtchn_port_setup(info); + if (rc) + goto err; + out: unmask_evtchn(evtchn); eoi_pirq(irq_get_irq_data(irq)); return 0; + +err: + pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc); + xen_evtchn_close(evtchn); + return 0; } static unsigned int startup_pirq(struct irq_data *data) diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 46ae0f9f02ad..75fe3d466515 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -16,7 +16,7 @@ #include "conf_space.h" #include "conf_space_quirks.h" -static bool permissive; +bool permissive; module_param(permissive, bool, 0644); /* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word, diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h index e56c934ad137..2e1d73d1d5d0 100644 --- a/drivers/xen/xen-pciback/conf_space.h +++ b/drivers/xen/xen-pciback/conf_space.h @@ -64,6 +64,8 @@ struct config_field_entry { void *data; }; +extern bool permissive; + #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset) /* Add fields to a device - the add_fields macro expects to get a pointer to diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index c5ee82587e8c..2d7369391472 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -11,6 +11,10 @@ #include "pciback.h" #include "conf_space.h" +struct pci_cmd_info { + u16 val; +}; + struct pci_bar_info { u32 val; u32 len_val; @@ -20,22 +24,36 @@ struct pci_bar_info { #define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO)) #define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER) -static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +/* Bits guests are allowed to control in permissive mode. */ +#define PCI_COMMAND_GUEST (PCI_COMMAND_MASTER|PCI_COMMAND_SPECIAL| \ + PCI_COMMAND_INVALIDATE|PCI_COMMAND_VGA_PALETTE| \ + PCI_COMMAND_WAIT|PCI_COMMAND_FAST_BACK) + +static void *command_init(struct pci_dev *dev, int offset) { - int i; - int ret; - - ret = xen_pcibk_read_config_word(dev, offset, value, data); - if (!pci_is_enabled(dev)) - return ret; - - for (i = 0; i < PCI_ROM_RESOURCE; i++) { - if (dev->resource[i].flags & IORESOURCE_IO) - *value |= PCI_COMMAND_IO; - if (dev->resource[i].flags & IORESOURCE_MEM) - *value |= PCI_COMMAND_MEMORY; + struct pci_cmd_info *cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + int err; + + if (!cmd) + return ERR_PTR(-ENOMEM); + + err = pci_read_config_word(dev, PCI_COMMAND, &cmd->val); + if (err) { + kfree(cmd); + return ERR_PTR(err); } + return cmd; +} + +static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) +{ + int ret = pci_read_config_word(dev, offset, value); + const struct pci_cmd_info *cmd = data; + + *value &= PCI_COMMAND_GUEST; + *value |= cmd->val & ~PCI_COMMAND_GUEST; + return ret; } @@ -43,6 +61,8 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) { struct xen_pcibk_dev_data *dev_data; int err; + u16 val; + struct pci_cmd_info *cmd = data; dev_data = pci_get_drvdata(dev); if (!pci_is_enabled(dev) && is_enable_cmd(value)) { @@ -83,6 +103,19 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) } } + cmd->val = value; + + if (!permissive && (!dev_data || !dev_data->permissive)) + return 0; + + /* Only allow the guest to control certain bits. */ + err = pci_read_config_word(dev, offset, &val); + if (err || val == value) + return err; + + value &= PCI_COMMAND_GUEST; + value |= val & ~PCI_COMMAND_GUEST; + return pci_write_config_word(dev, offset, value); } @@ -282,6 +315,8 @@ static const struct config_field header_common[] = { { .offset = PCI_COMMAND, .size = 2, + .init = command_init, + .release = bar_release, .u.w.read = command_read, .u.w.write = command_write, }, diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 9faca6a60bb0..42bd55a6c237 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1659,11 +1659,8 @@ static int scsiback_make_nexus(struct scsiback_tpg *tpg, name); goto out; } - /* - * Now register the TCM pvscsi virtual I_T Nexus as active with the - * call to __transport_register_session() - */ - __transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, + /* Now register the TCM pvscsi virtual I_T Nexus as active. */ + transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl, tv_nexus->tvn_se_sess, tv_nexus); tpg->tpg_nexus = tv_nexus; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 84c3b00f3de8..f9c89cae39ee 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3387,6 +3387,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root); +int btrfs_setup_space_cache(struct btrfs_trans_handle *trans, + struct btrfs_root *root); int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr); int btrfs_free_block_groups(struct btrfs_fs_info *info); int btrfs_read_block_groups(struct btrfs_root *root); @@ -3909,6 +3911,9 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, loff_t actual_len, u64 *alloc_hint); int btrfs_inode_check_errors(struct inode *inode); extern const struct dentry_operations btrfs_dentry_operations; +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +void btrfs_test_inode_set_ops(struct inode *inode); +#endif /* ioctl.c */ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f79f38542a73..639f2663ed3f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3921,7 +3921,7 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, } if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key) + sizeof(struct btrfs_chunk)) { - printk(KERN_ERR "BTRFS: system chunk array too small %u < %lu\n", + printk(KERN_ERR "BTRFS: system chunk array too small %u < %zu\n", btrfs_super_sys_array_size(sb), sizeof(struct btrfs_disk_key) + sizeof(struct btrfs_chunk)); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6f080451fcb1..8b353ad02f03 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3325,6 +3325,32 @@ out: return ret; } +int btrfs_setup_space_cache(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct btrfs_block_group_cache *cache, *tmp; + struct btrfs_transaction *cur_trans = trans->transaction; + struct btrfs_path *path; + + if (list_empty(&cur_trans->dirty_bgs) || + !btrfs_test_opt(root, SPACE_CACHE)) + return 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + /* Could add new block groups, use _safe just in case */ + list_for_each_entry_safe(cache, tmp, &cur_trans->dirty_bgs, + dirty_list) { + if (cache->disk_cache_state == BTRFS_DC_CLEAR) + cache_save_setup(cache, trans, path); + } + + btrfs_free_path(path); + return 0; +} + int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -5110,7 +5136,11 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) num_bytes = ALIGN(num_bytes, root->sectorsize); spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents++; + nr_extents = (unsigned)div64_u64(num_bytes + + BTRFS_MAX_EXTENT_SIZE - 1, + BTRFS_MAX_EXTENT_SIZE); + BTRFS_I(inode)->outstanding_extents += nr_extents; + nr_extents = 0; if (BTRFS_I(inode)->outstanding_extents > BTRFS_I(inode)->reserved_extents) @@ -5255,6 +5285,9 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) if (dropped > 0) to_free += btrfs_calc_trans_metadata_size(root, dropped); + if (btrfs_test_is_dummy_root(root)) + return; + trace_btrfs_space_reservation(root->fs_info, "delalloc", btrfs_ino(inode), to_free, 0); if (root->fs_info->quota_enabled) { diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c7233ff1d533..d688cfe5d496 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4968,6 +4968,12 @@ static int release_extent_buffer(struct extent_buffer *eb) /* Should be safe to release our pages at this point */ btrfs_release_extent_buffer_page(eb); +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) { + __free_extent_buffer(eb); + return 1; + } +#endif call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu); return 1; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index da828cf5e8f8..d2e732d7af52 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -108,6 +108,13 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start, static int btrfs_dirty_inode(struct inode *inode); +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +void btrfs_test_inode_set_ops(struct inode *inode) +{ + BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops; +} +#endif + static int btrfs_init_inode_security(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir, const struct qstr *qstr) @@ -1542,30 +1549,17 @@ static void btrfs_split_extent_hook(struct inode *inode, u64 new_size; /* - * We need the largest size of the remaining extent to see if we - * need to add a new outstanding extent. Think of the following - * case - * - * [MEAX_EXTENT_SIZEx2 - 4k][4k] - * - * The new_size would just be 4k and we'd think we had enough - * outstanding extents for this if we only took one side of the - * split, same goes for the other direction. We need to see if - * the larger size still is the same amount of extents as the - * original size, because if it is we need to add a new - * outstanding extent. But if we split up and the larger size - * is less than the original then we are good to go since we've - * already accounted for the extra extent in our original - * accounting. + * See the explanation in btrfs_merge_extent_hook, the same + * applies here, just in reverse. */ new_size = orig->end - split + 1; - if ((split - orig->start) > new_size) - new_size = split - orig->start; - - num_extents = div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, + num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE); - if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE) < num_extents) + new_size = split - orig->start; + num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1, + BTRFS_MAX_EXTENT_SIZE); + if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, + BTRFS_MAX_EXTENT_SIZE) >= num_extents) return; } @@ -1591,8 +1585,10 @@ static void btrfs_merge_extent_hook(struct inode *inode, if (!(other->state & EXTENT_DELALLOC)) return; - old_size = other->end - other->start + 1; - new_size = old_size + (new->end - new->start + 1); + if (new->start > other->start) + new_size = new->end - other->start + 1; + else + new_size = other->end - new->start + 1; /* we're not bigger than the max, unreserve the space and go */ if (new_size <= BTRFS_MAX_EXTENT_SIZE) { @@ -1603,13 +1599,32 @@ static void btrfs_merge_extent_hook(struct inode *inode, } /* - * If we grew by another max_extent, just return, we want to keep that - * reserved amount. + * We have to add up either side to figure out how many extents were + * accounted for before we merged into one big extent. If the number of + * extents we accounted for is <= the amount we need for the new range + * then we can return, otherwise drop. Think of it like this + * + * [ 4k][MAX_SIZE] + * + * So we've grown the extent by a MAX_SIZE extent, this would mean we + * need 2 outstanding extents, on one side we have 1 and the other side + * we have 1 so they are == and we can return. But in this case + * + * [MAX_SIZE+4k][MAX_SIZE+4k] + * + * Each range on their own accounts for 2 extents, but merged together + * they are only 3 extents worth of accounting, so we need to drop in + * this case. */ + old_size = other->end - other->start + 1; num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE); + old_size = new->end - new->start + 1; + num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1, + BTRFS_MAX_EXTENT_SIZE); + if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE) > num_extents) + BTRFS_MAX_EXTENT_SIZE) >= num_extents) return; spin_lock(&BTRFS_I(inode)->lock); @@ -1686,6 +1701,10 @@ static void btrfs_set_bit_hook(struct inode *inode, spin_unlock(&BTRFS_I(inode)->lock); } + /* For sanity tests */ + if (btrfs_test_is_dummy_root(root)) + return; + __percpu_counter_add(&root->fs_info->delalloc_bytes, len, root->fs_info->delalloc_batch); spin_lock(&BTRFS_I(inode)->lock); @@ -1741,6 +1760,10 @@ static void btrfs_clear_bit_hook(struct inode *inode, root != root->fs_info->tree_root) btrfs_delalloc_release_metadata(inode, len); + /* For sanity tests. */ + if (btrfs_test_is_dummy_root(root)) + return; + if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID && do_list && !(state->state & EXTENT_NORESERVE)) btrfs_free_reserved_data_space(inode, len); @@ -7213,7 +7236,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, u64 start = iblock << inode->i_blkbits; u64 lockstart, lockend; u64 len = bh_result->b_size; - u64 orig_len = len; + u64 *outstanding_extents = NULL; int unlock_bits = EXTENT_LOCKED; int ret = 0; @@ -7225,6 +7248,16 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, lockstart = start; lockend = start + len - 1; + if (current->journal_info) { + /* + * Need to pull our outstanding extents and set journal_info to NULL so + * that anything that needs to check if there's a transction doesn't get + * confused. + */ + outstanding_extents = current->journal_info; + current->journal_info = NULL; + } + /* * If this errors out it's because we couldn't invalidate pagecache for * this range and we need to fallback to buffered. @@ -7348,11 +7381,20 @@ unlock: if (start + len > i_size_read(inode)) i_size_write(inode, start + len); - if (len < orig_len) { + /* + * If we have an outstanding_extents count still set then we're + * within our reservation, otherwise we need to adjust our inode + * counter appropriately. + */ + if (*outstanding_extents) { + (*outstanding_extents)--; + } else { spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); } + + current->journal_info = outstanding_extents; btrfs_free_reserved_data_space(inode, len); } @@ -7376,6 +7418,8 @@ unlock: unlock_err: clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, unlock_bits, 1, 0, &cached_state, GFP_NOFS); + if (outstanding_extents) + current->journal_info = outstanding_extents; return ret; } @@ -8075,6 +8119,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + u64 outstanding_extents = 0; size_t count = 0; int flags = 0; bool wakeup = true; @@ -8112,6 +8157,16 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, ret = btrfs_delalloc_reserve_space(inode, count); if (ret) goto out; + outstanding_extents = div64_u64(count + + BTRFS_MAX_EXTENT_SIZE - 1, + BTRFS_MAX_EXTENT_SIZE); + + /* + * We need to know how many extents we reserved so that we can + * do the accounting properly if we go over the number we + * originally calculated. Abuse current->journal_info for this. + */ + current->journal_info = &outstanding_extents; } else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags)) { inode_dio_done(inode); @@ -8124,6 +8179,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, iter, offset, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, flags); if (rw & WRITE) { + current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) btrfs_delalloc_release_space(inode, count); else if (ret >= 0 && (size_t)ret < count) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 97159a8e91d4..058c79eecbfb 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1259,7 +1259,7 @@ static int comp_oper(struct btrfs_qgroup_operation *oper1, if (oper1->seq < oper2->seq) return -1; if (oper1->seq > oper2->seq) - return -1; + return 1; if (oper1->ref_root < oper2->ref_root) return -1; if (oper1->ref_root > oper2->ref_root) diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index a116b55ce788..054fc0d97131 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -911,6 +911,197 @@ out: return ret; } +static int test_extent_accounting(void) +{ + struct inode *inode = NULL; + struct btrfs_root *root = NULL; + int ret = -ENOMEM; + + inode = btrfs_new_test_inode(); + if (!inode) { + test_msg("Couldn't allocate inode\n"); + return ret; + } + + root = btrfs_alloc_dummy_root(); + if (IS_ERR(root)) { + test_msg("Couldn't allocate root\n"); + goto out; + } + + root->fs_info = btrfs_alloc_dummy_fs_info(); + if (!root->fs_info) { + test_msg("Couldn't allocate dummy fs info\n"); + goto out; + } + + BTRFS_I(inode)->root = root; + btrfs_test_inode_set_ops(inode); + + /* [BTRFS_MAX_EXTENT_SIZE] */ + BTRFS_I(inode)->outstanding_extents++; + ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, + NULL); + if (ret) { + test_msg("btrfs_set_extent_delalloc returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 1) { + ret = -EINVAL; + test_msg("Miscount, wanted 1, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* [BTRFS_MAX_EXTENT_SIZE][4k] */ + BTRFS_I(inode)->outstanding_extents++; + ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE, + BTRFS_MAX_EXTENT_SIZE + 4095, NULL); + if (ret) { + test_msg("btrfs_set_extent_delalloc returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 2) { + ret = -EINVAL; + test_msg("Miscount, wanted 2, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* [BTRFS_MAX_EXTENT_SIZE/2][4K HOLE][the rest] */ + ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, + BTRFS_MAX_EXTENT_SIZE >> 1, + (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095, + EXTENT_DELALLOC | EXTENT_DIRTY | + EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0, + NULL, GFP_NOFS); + if (ret) { + test_msg("clear_extent_bit returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 2) { + ret = -EINVAL; + test_msg("Miscount, wanted 2, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* [BTRFS_MAX_EXTENT_SIZE][4K] */ + BTRFS_I(inode)->outstanding_extents++; + ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1, + (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095, + NULL); + if (ret) { + test_msg("btrfs_set_extent_delalloc returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 2) { + ret = -EINVAL; + test_msg("Miscount, wanted 2, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* + * [BTRFS_MAX_EXTENT_SIZE+4K][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4K] + * + * I'm artificially adding 2 to outstanding_extents because in the + * buffered IO case we'd add things up as we go, but I don't feel like + * doing that here, this isn't the interesting case we want to test. + */ + BTRFS_I(inode)->outstanding_extents += 2; + ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 8192, + (BTRFS_MAX_EXTENT_SIZE << 1) + 12287, + NULL); + if (ret) { + test_msg("btrfs_set_extent_delalloc returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 4) { + ret = -EINVAL; + test_msg("Miscount, wanted 4, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* [BTRFS_MAX_EXTENT_SIZE+4k][4k][BTRFS_MAX_EXTENT_SIZE+4k] */ + BTRFS_I(inode)->outstanding_extents++; + ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096, + BTRFS_MAX_EXTENT_SIZE+8191, NULL); + if (ret) { + test_msg("btrfs_set_extent_delalloc returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 3) { + ret = -EINVAL; + test_msg("Miscount, wanted 3, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* [BTRFS_MAX_EXTENT_SIZE+4k][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4k] */ + ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, + BTRFS_MAX_EXTENT_SIZE+4096, + BTRFS_MAX_EXTENT_SIZE+8191, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, + NULL, GFP_NOFS); + if (ret) { + test_msg("clear_extent_bit returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 4) { + ret = -EINVAL; + test_msg("Miscount, wanted 4, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* + * Refill the hole again just for good measure, because I thought it + * might fail and I'd rather satisfy my paranoia at this point. + */ + BTRFS_I(inode)->outstanding_extents++; + ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096, + BTRFS_MAX_EXTENT_SIZE+8191, NULL); + if (ret) { + test_msg("btrfs_set_extent_delalloc returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents != 3) { + ret = -EINVAL; + test_msg("Miscount, wanted 3, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + + /* Empty */ + ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, + NULL, GFP_NOFS); + if (ret) { + test_msg("clear_extent_bit returned %d\n", ret); + goto out; + } + if (BTRFS_I(inode)->outstanding_extents) { + ret = -EINVAL; + test_msg("Miscount, wanted 0, got %u\n", + BTRFS_I(inode)->outstanding_extents); + goto out; + } + ret = 0; +out: + if (ret) + clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, + NULL, GFP_NOFS); + iput(inode); + btrfs_free_dummy_root(root); + return ret; +} + int btrfs_test_inodes(void) { int ret; @@ -924,5 +1115,9 @@ int btrfs_test_inodes(void) if (ret) return ret; test_msg("Running hole first btrfs_get_extent test\n"); - return test_hole_first(); + ret = test_hole_first(); + if (ret) + return ret; + test_msg("Running outstanding_extents tests\n"); + return test_extent_accounting(); } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 88e51aded6bd..8be4278e25e8 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1023,17 +1023,13 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans, u64 old_root_bytenr; u64 old_root_used; struct btrfs_root *tree_root = root->fs_info->tree_root; - bool extent_root = (root->objectid == BTRFS_EXTENT_TREE_OBJECTID); old_root_used = btrfs_root_used(&root->root_item); - btrfs_write_dirty_block_groups(trans, root); while (1) { old_root_bytenr = btrfs_root_bytenr(&root->root_item); if (old_root_bytenr == root->node->start && - old_root_used == btrfs_root_used(&root->root_item) && - (!extent_root || - list_empty(&trans->transaction->dirty_bgs))) + old_root_used == btrfs_root_used(&root->root_item)) break; btrfs_set_root_node(&root->root_item, root->node); @@ -1044,14 +1040,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans, return ret; old_root_used = btrfs_root_used(&root->root_item); - if (extent_root) { - ret = btrfs_write_dirty_block_groups(trans, root); - if (ret) - return ret; - } - ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); - if (ret) - return ret; } return 0; @@ -1068,6 +1056,7 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; + struct list_head *dirty_bgs = &trans->transaction->dirty_bgs; struct list_head *next; struct extent_buffer *eb; int ret; @@ -1095,11 +1084,15 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, if (ret) return ret; + ret = btrfs_setup_space_cache(trans, root); + if (ret) + return ret; + /* run_qgroups might have added some more refs */ ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); if (ret) return ret; - +again: while (!list_empty(&fs_info->dirty_cowonly_roots)) { next = fs_info->dirty_cowonly_roots.next; list_del_init(next); @@ -1112,8 +1105,23 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, ret = update_cowonly_root(trans, root); if (ret) return ret; + ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); + if (ret) + return ret; } + while (!list_empty(dirty_bgs)) { + ret = btrfs_write_dirty_block_groups(trans, root); + if (ret) + return ret; + ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); + if (ret) + return ret; + } + + if (!list_empty(&fs_info->dirty_cowonly_roots)) + goto again; + list_add_tail(&fs_info->extent_root->dirty_list, &trans->transaction->switch_commits); btrfs_after_dev_replace_commit(fs_info); @@ -1811,6 +1819,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, wait_for_commit(root, cur_trans); + if (unlikely(cur_trans->aborted)) + ret = cur_trans->aborted; + btrfs_put_transaction(cur_trans); return ret; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index ed19a7d622fa..39706c57ad3c 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -890,8 +890,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) newpage = buf->page; - if (WARN_ON(!PageUptodate(newpage))) - return -EIO; + if (!PageUptodate(newpage)) + SetPageUptodate(newpage); ClearPageMappedToDisk(newpage); @@ -1353,6 +1353,17 @@ static ssize_t fuse_dev_do_read(struct fuse_conn *fc, struct file *file, return err; } +static int fuse_dev_open(struct inode *inode, struct file *file) +{ + /* + * The fuse device's file's private_data is used to hold + * the fuse_conn(ection) when it is mounted, and is used to + * keep track of whether the file has been mounted already. + */ + file->private_data = NULL; + return 0; +} + static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -1797,6 +1808,9 @@ copy_finish: static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, unsigned int size, struct fuse_copy_state *cs) { + /* Don't try to move pages (yet) */ + cs->move_pages = 0; + switch (code) { case FUSE_NOTIFY_POLL: return fuse_notify_poll(fc, size, cs); @@ -2217,6 +2231,7 @@ static int fuse_dev_fasync(int fd, struct file *file, int on) const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, + .open = fuse_dev_open, .llseek = no_llseek, .read = do_sync_read, .aio_read = fuse_dev_read, diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index b684e8a132e6..2bacb9988566 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -207,6 +207,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, goto out_free; } + of->event = atomic_read(&of->kn->attr.open->event); ops = kernfs_ops(of->kn); if (ops->read) len = ops->read(of, buf, len, *ppos); diff --git a/fs/locks.c b/fs/locks.c index f1bad681fc1c..528fedfda15e 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1728,7 +1728,7 @@ static int generic_delete_lease(struct file *filp, void *owner) break; } } - trace_generic_delete_lease(inode, fl); + trace_generic_delete_lease(inode, victim); if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 3c1bfa155571..1028a0629543 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -587,8 +587,6 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str)); - nfsd4_cb_layout_fail(ls); - printk(KERN_WARNING "nfsd: client %s failed to respond to layout recall. " " Fencing..\n", addr_str); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 469086b9f99b..0c3f303baf32 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1907,6 +1907,7 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { struct nilfs_inode_info *ii, *n; + int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE); int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); @@ -1919,10 +1920,10 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, brelse(ii->i_bh); ii->i_bh = NULL; list_del_init(&ii->i_dirty); - if (!ii->vfs_inode.i_nlink) { + if (!ii->vfs_inode.i_nlink || during_mount) { /* - * Defer calling iput() to avoid a deadlock - * over I_SYNC flag for inodes with i_nlink == 0 + * Defer calling iput() to avoid deadlocks if + * i_nlink == 0 or mount is not yet finished. */ list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); defer_iput = true; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 9a66ff79ff27..d2f97ecca6a5 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -143,7 +143,8 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark, !(marks_mask & FS_ISDIR & ~marks_ignored_mask)) return false; - if (event_mask & marks_mask & ~marks_ignored_mask) + if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask & + ~marks_ignored_mask) return true; return false; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 8490c64d34fe..460c6c37e683 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -502,7 +502,7 @@ static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb) static inline int ocfs2_supports_append_dio(struct ocfs2_super *osb) { - if (osb->s_feature_ro_compat & OCFS2_FEATURE_RO_COMPAT_APPEND_DIO) + if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_APPEND_DIO) return 1; return 0; } diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 20e37a3ed26f..db64ce2d4667 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -102,11 +102,11 @@ | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS \ | OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE \ | OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG \ - | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO) + | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO \ + | OCFS2_FEATURE_INCOMPAT_APPEND_DIO) #define OCFS2_FEATURE_RO_COMPAT_SUPP (OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \ | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \ - | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA \ - | OCFS2_FEATURE_RO_COMPAT_APPEND_DIO) + | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA) /* * Heartbeat-only devices are missing journals and other files. The @@ -179,6 +179,11 @@ #define OCFS2_FEATURE_INCOMPAT_CLUSTERINFO 0x4000 /* + * Append Direct IO support + */ +#define OCFS2_FEATURE_INCOMPAT_APPEND_DIO 0x8000 + +/* * backup superblock flag is used to indicate that this volume * has backup superblocks. */ @@ -200,10 +205,6 @@ #define OCFS2_FEATURE_RO_COMPAT_USRQUOTA 0x0002 #define OCFS2_FEATURE_RO_COMPAT_GRPQUOTA 0x0004 -/* - * Append Direct IO support - */ -#define OCFS2_FEATURE_RO_COMPAT_APPEND_DIO 0x0008 /* The byte offset of the first backup block will be 1G. * The following will be 4G, 16G, 64G, 256G and 1T. diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index b90952f528b1..5f0d1993e6e3 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -529,8 +529,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data) { struct ovl_fs *ufs = sb->s_fs_info; - if (!(*flags & MS_RDONLY) && - (!ufs->upper_mnt || (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY))) + if (!(*flags & MS_RDONLY) && !ufs->upper_mnt) return -EROFS; return 0; @@ -615,9 +614,19 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) break; default: + pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p); return -EINVAL; } } + + /* Workdir is useless in non-upper mount */ + if (!config->upperdir && config->workdir) { + pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n", + config->workdir); + kfree(config->workdir); + config->workdir = NULL; + } + return 0; } @@ -837,7 +846,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_stack_depth = 0; if (ufs->config.upperdir) { - /* FIXME: workdir is not needed for a R/O mount */ if (!ufs->config.workdir) { pr_err("overlayfs: missing 'workdir'\n"); goto out_free_config; @@ -847,6 +855,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (err) goto out_free_config; + /* Upper fs should not be r/o */ + if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) { + pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n"); + err = -EINVAL; + goto out_put_upperpath; + } + err = ovl_mount_dir(ufs->config.workdir, &workpath); if (err) goto out_put_upperpath; @@ -869,8 +884,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) err = -EINVAL; stacklen = ovl_split_lowerdirs(lowertmp); - if (stacklen > OVL_MAX_STACK) + if (stacklen > OVL_MAX_STACK) { + pr_err("overlayfs: too many lower directries, limit is %d\n", + OVL_MAX_STACK); goto out_free_lowertmp; + } else if (!ufs->config.upperdir && stacklen == 1) { + pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n"); + goto out_free_lowertmp; + } stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL); if (!stack) @@ -932,8 +953,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) ufs->numlower++; } - /* If the upper fs is r/o or nonexistent, we mark overlayfs r/o too */ - if (!ufs->upper_mnt || (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY)) + /* If the upper fs is nonexistent, we mark overlayfs r/o too */ + if (!ufs->upper_mnt) sb->s_flags |= MS_RDONLY; sb->s_d_op = &ovl_dentry_operations; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 956b75d61809..6dee68d013ff 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1325,6 +1325,9 @@ out: static int pagemap_open(struct inode *inode, struct file *file) { + /* do not disclose physical addresses: attack vector */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about " "to stop being page-shift some time soon. See the " "linux/Documentation/vm/pagemap.txt for details.\n"); diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 178525e5f430..018afb264ac2 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -58,8 +58,9 @@ struct af_alg_type { }; struct af_alg_sgl { - struct scatterlist sg[ALG_MAX_PAGES]; + struct scatterlist sg[ALG_MAX_PAGES + 1]; struct page *pages[ALG_MAX_PAGES]; + unsigned int npages; }; int af_alg_register_type(const struct af_alg_type *type); @@ -70,6 +71,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); +void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new); int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con); diff --git a/include/dt-bindings/pinctrl/am33xx.h b/include/dt-bindings/pinctrl/am33xx.h index 2fbc804e1a45..226f77246a70 100644 --- a/include/dt-bindings/pinctrl/am33xx.h +++ b/include/dt-bindings/pinctrl/am33xx.h @@ -13,7 +13,8 @@ #define PULL_DISABLE (1 << 3) #define INPUT_EN (1 << 5) -#define SLEWCTRL_FAST (1 << 6) +#define SLEWCTRL_SLOW (1 << 6) +#define SLEWCTRL_FAST 0 /* update macro depending on INPUT_EN and PULL_ENA */ #undef PIN_OUTPUT diff --git a/include/dt-bindings/pinctrl/am43xx.h b/include/dt-bindings/pinctrl/am43xx.h index 9c2e4f82381e..5f4d01898c9c 100644 --- a/include/dt-bindings/pinctrl/am43xx.h +++ b/include/dt-bindings/pinctrl/am43xx.h @@ -18,7 +18,8 @@ #define PULL_DISABLE (1 << 16) #define PULL_UP (1 << 17) #define INPUT_EN (1 << 18) -#define SLEWCTRL_FAST (1 << 19) +#define SLEWCTRL_SLOW (1 << 19) +#define SLEWCTRL_FAST 0 #define DS0_PULL_UP_DOWN_EN (1 << 27) #define PIN_OUTPUT (PULL_DISABLE) diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 7c55dd5dd2c9..66203b268984 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -114,6 +114,7 @@ struct vgic_ops { void (*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr); u64 (*get_elrsr)(const struct kvm_vcpu *vcpu); u64 (*get_eisr)(const struct kvm_vcpu *vcpu); + void (*clear_eisr)(struct kvm_vcpu *vcpu); u32 (*get_interrupt_status)(const struct kvm_vcpu *vcpu); void (*enable_underflow)(struct kvm_vcpu *vcpu); void (*disable_underflow)(struct kvm_vcpu *vcpu); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80f2e0fc3d02..d5cda067115a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -59,6 +59,7 @@ enum bpf_arg_type { ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ + ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ }; @@ -103,6 +104,9 @@ struct bpf_verifier_ops { * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type); + + u32 (*convert_ctx_access)(int dst_reg, int src_reg, int ctx_off, + struct bpf_insn *insn); }; struct bpf_prog_type_list { @@ -133,7 +137,7 @@ struct bpf_map *bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl) { @@ -154,4 +158,7 @@ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_get_prandom_u32_proto; +extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c05ff0f9f9a5..c3a9c8fc60fa 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -61,6 +61,8 @@ struct can_priv { char tx_led_trig_name[CAN_LED_NAME_SZ]; struct led_trigger *rx_led_trig; char rx_led_trig_name[CAN_LED_NAME_SZ]; + struct led_trigger *rxtx_led_trig; + char rxtx_led_trig_name[CAN_LED_NAME_SZ]; #endif }; diff --git a/include/linux/can/led.h b/include/linux/can/led.h index e0475c5cbb92..146de4506d21 100644 --- a/include/linux/can/led.h +++ b/include/linux/can/led.h @@ -21,8 +21,10 @@ enum can_led_event { #ifdef CONFIG_CAN_LEDS -/* keep space for interface name + "-tx"/"-rx" suffix and null terminator */ -#define CAN_LED_NAME_SZ (IFNAMSIZ + 4) +/* keep space for interface name + "-tx"/"-rx"/"-rxtx" + * suffix and null terminator + */ +#define CAN_LED_NAME_SZ (IFNAMSIZ + 6) void can_led_event(struct net_device *netdev, enum can_led_event event); void devm_can_led_init(struct net_device *netdev); diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index cc00d15c6107..b6a52a4b457a 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -44,16 +44,11 @@ static inline void can_skb_reserve(struct sk_buff *skb) skb_reserve(skb, sizeof(struct can_skb_priv)); } -static inline void can_skb_destructor(struct sk_buff *skb) -{ - sock_put(skb->sk); -} - static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk) { if (sk) { sock_hold(sk); - skb->destructor = can_skb_destructor; + skb->destructor = sock_efree; skb->sk = sk; } } diff --git a/include/linux/clk.h b/include/linux/clk.h index 8381bbfbc308..68c16a6bedb3 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -125,6 +125,19 @@ int clk_set_phase(struct clk *clk, int degrees); */ int clk_get_phase(struct clk *clk); +/** + * clk_is_match - check if two clk's point to the same hardware clock + * @p: clk compared against q + * @q: clk compared against p + * + * Returns true if the two struct clk pointers both point to the same hardware + * clock node. Put differently, returns true if struct clk *p and struct clk *q + * share the same struct clk_core object. + * + * Returns false otherwise. Note that two NULL clks are treated as matching. + */ +bool clk_is_match(const struct clk *p, const struct clk *q); + #else static inline long clk_get_accuracy(struct clk *clk) @@ -142,6 +155,11 @@ static inline long clk_get_phase(struct clk *clk) return -ENOTSUPP; } +static inline bool clk_is_match(const struct clk *p, const struct clk *q) +{ + return p == q; +} + #endif /** diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 439ff698000a..221025423e6c 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -43,6 +43,7 @@ enum dccp_state { DCCP_CLOSING = TCP_CLOSING, DCCP_TIME_WAIT = TCP_TIME_WAIT, DCCP_CLOSED = TCP_CLOSE, + DCCP_NEW_SYN_RECV = TCP_NEW_SYN_RECV, DCCP_PARTOPEN = TCP_MAX_STATES, DCCP_PASSIVE_CLOSEREQ, /* clients receiving CloseReq */ DCCP_MAX_STATES @@ -57,6 +58,7 @@ enum { DCCPF_CLOSING = TCPF_CLOSING, DCCPF_TIME_WAIT = TCPF_TIME_WAIT, DCCPF_CLOSED = TCPF_CLOSE, + DCCPF_NEW_SYN_RECV = TCPF_NEW_SYN_RECV, DCCPF_PARTOPEN = (1 << DCCP_PARTOPEN), }; @@ -317,6 +319,6 @@ static inline const char *dccp_role(const struct sock *sk) return NULL; } -extern void dccp_syn_ack_timeout(struct sock *sk, struct request_sock *req); +extern void dccp_syn_ack_timeout(const struct request_sock *req); #endif /* _LINUX_DCCP_H */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 2646aed1d3fe..fd23978d93fe 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -375,6 +375,7 @@ int dm_create(int minor, struct mapped_device **md); */ struct mapped_device *dm_get_md(dev_t dev); void dm_get(struct mapped_device *md); +int dm_hold(struct mapped_device *md); void dm_put(struct mapped_device *md); /* diff --git a/include/linux/filter.h b/include/linux/filter.h index 9ee8c67ea249..fa11b3a367be 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -454,6 +454,7 @@ static inline u16 bpf_anc_helper(const struct sock_filter *ftest) BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); + BPF_ANCILLARY(VLAN_TPID); } /* Fallthrough. */ default: diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b11b28a30b9e..920e4457ce6e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -561,4 +561,71 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, skb->protocol = htons(ETH_P_802_2); } +/** + * skb_vlan_tagged - check if skb is vlan tagged. + * @skb: skbuff to query + * + * Returns true if the skb is tagged, regardless of whether it is hardware + * accelerated or not. + */ +static inline bool skb_vlan_tagged(const struct sk_buff *skb) +{ + if (!skb_vlan_tag_present(skb) && + likely(skb->protocol != htons(ETH_P_8021Q) && + skb->protocol != htons(ETH_P_8021AD))) + return false; + + return true; +} + +/** + * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. + * @skb: skbuff to query + * + * Returns true if the skb is tagged with multiple vlan headers, regardless + * of whether it is hardware accelerated or not. + */ +static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) +{ + __be16 protocol = skb->protocol; + + if (!skb_vlan_tag_present(skb)) { + struct vlan_ethhdr *veh; + + if (likely(protocol != htons(ETH_P_8021Q) && + protocol != htons(ETH_P_8021AD))) + return false; + + veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } + + if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) + return false; + + return true; +} + +/** + * vlan_features_check - drop unsafe features for skb with multiple tags. + * @skb: skbuff to query + * @features: features to be checked + * + * Returns features without unsafe ones if the skb has multiple tags. + */ +static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, + netdev_features_t features) +{ + if (skb_vlan_tagged_multi(skb)) + features = netdev_intersect_features(features, + NETIF_F_SG | + NETIF_F_HIGHDMA | + NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + return features; +} + #endif /* !(_LINUX_IF_VLAN_H_) */ diff --git a/include/linux/igmp.h b/include/linux/igmp.h index b5a6470e686c..2c677afeea47 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -111,9 +111,7 @@ struct ip_mc_list { extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); extern int igmp_rcv(struct sk_buff *); -extern int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); -extern int __ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4d5169f5d7d1..82806c60aa42 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -53,6 +53,10 @@ struct ipv6_devconf { __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; + struct ipv6_stable_secret { + bool initialized; + struct in6_addr secret; + } stable_secret; void *sysctl; }; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 800544bc7bfd..781974afff9f 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -166,6 +166,11 @@ #define GITS_TRANSLATER 0x10040 +#define GITS_CTLR_ENABLE (1U << 0) +#define GITS_CTLR_QUIESCENT (1U << 31) + +#define GITS_TYPER_DEVBITS_SHIFT 13 +#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) #define GITS_TYPER_PTA (1UL << 19) #define GITS_CBASER_VALID (1UL << 63) diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 72ba725ddf9c..5bb074431eb0 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -5,6 +5,7 @@ struct kmem_cache; struct page; +struct vm_struct; #ifdef CONFIG_KASAN @@ -49,15 +50,11 @@ void kasan_krealloc(const void *object, size_t new_size); void kasan_slab_alloc(struct kmem_cache *s, void *object); void kasan_slab_free(struct kmem_cache *s, void *object); -#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) - int kasan_module_alloc(void *addr, size_t size); -void kasan_module_free(void *addr); +void kasan_free_shadow(const struct vm_struct *vm); #else /* CONFIG_KASAN */ -#define MODULE_ALIGN 1 - static inline void kasan_unpoison_shadow(const void *address, size_t size) {} static inline void kasan_enable_current(void) {} @@ -82,7 +79,7 @@ static inline void kasan_slab_alloc(struct kmem_cache *s, void *object) {} static inline void kasan_slab_free(struct kmem_cache *s, void *object) {} static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } -static inline void kasan_module_free(void *addr) {} +static inline void kasan_free_shadow(const struct vm_struct *vm) {} #endif /* CONFIG_KASAN */ diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 1cc54822b931..4550c67b92e4 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -205,6 +205,7 @@ enum { MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20, MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21, MLX4_DEV_CAP_FLAG2_QCN = 1LL << 22, + MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT = 1LL << 23 }; enum { @@ -450,6 +451,21 @@ enum mlx4_module_id { MLX4_MODULE_ID_QSFP28 = 0x11, }; +enum { /* rl */ + MLX4_QP_RATE_LIMIT_NONE = 0, + MLX4_QP_RATE_LIMIT_KBS = 1, + MLX4_QP_RATE_LIMIT_MBS = 2, + MLX4_QP_RATE_LIMIT_GBS = 3 +}; + +struct mlx4_rate_limit_caps { + u16 num_rates; /* Number of different rates */ + u8 min_unit; + u16 min_val; + u8 max_unit; + u16 max_val; +}; + static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor) { return (major << 32) | (minor << 16) | subminor; @@ -565,6 +581,7 @@ struct mlx4_caps { u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; u32 vf_caps; + struct mlx4_rate_limit_caps rl_caps; }; struct mlx4_buf_list { diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 551f85456c11..1023ebe035b7 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -207,14 +207,16 @@ struct mlx4_qp_context { __be32 msn; __be16 rq_wqe_counter; __be16 sq_wqe_counter; - u32 reserved3[2]; + u32 reserved3; + __be16 rate_limit_params; + __be16 reserved4; __be32 param3; __be32 nummmcpeers_basemkey; u8 log_page_size; - u8 reserved4[2]; + u8 reserved5[2]; u8 mtt_base_addr_h; __be32 mtt_base_addr_l; - u32 reserved5[10]; + u32 reserved6[10]; }; struct mlx4_update_qp_context { @@ -229,6 +231,7 @@ struct mlx4_update_qp_context { enum { MLX4_UPD_QP_MASK_PM_STATE = 32, MLX4_UPD_QP_MASK_VSD = 33, + MLX4_UPD_QP_MASK_RATE_LIMIT = 35, }; enum { @@ -428,7 +431,8 @@ struct mlx4_wqe_inline_seg { enum mlx4_update_qp_attr { MLX4_UPDATE_QP_SMAC = 1 << 0, MLX4_UPDATE_QP_VSD = 1 << 1, - MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 2) - 1 + MLX4_UPDATE_QP_RATE_LIMIT = 1 << 2, + MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 3) - 1 }; enum mlx4_update_qp_params_flags { @@ -438,6 +442,8 @@ enum mlx4_update_qp_params_flags { struct mlx4_update_qp_params { u8 smac_index; u32 flags; + u16 rate_unit; + u16 rate_val; }; int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn, diff --git a/include/linux/module.h b/include/linux/module.h index 42999fe2dbd0..b03485bcb82a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -344,6 +344,10 @@ struct module { unsigned long *ftrace_callsites; #endif +#ifdef CONFIG_LIVEPATCH + bool klp_alive; +#endif + #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head source_list; diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index f7556261fe3c..4d0cb9bba93e 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -84,4 +84,12 @@ void module_arch_cleanup(struct module *mod); /* Any cleanup before freeing mod->module_init */ void module_arch_freeing_init(struct module *mod); + +#ifdef CONFIG_KASAN +#include <linux/kasan.h> +#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else +#define MODULE_ALIGN PAGE_SIZE +#endif + #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddab1a2a07a0..967bb4c8caf1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -587,6 +587,7 @@ struct netdev_queue { #ifdef CONFIG_BQL struct dql dql; #endif + unsigned long tx_maxrate; } ____cacheline_aligned_in_smp; static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) @@ -768,8 +769,6 @@ struct netdev_phys_item_id { typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -struct fib_info; - /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -966,9 +965,12 @@ struct fib_info; * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * - * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh) + * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, + * u16 flags) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, * struct net_device *dev, u32 filter_mask) + * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, + * u16 flags); * * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); * Called to change device carrier. Soft-devices (like dummy, team, etc) @@ -1024,23 +1026,10 @@ struct fib_info; * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. - * - * int (*ndo_switch_parent_id_get)(struct net_device *dev, - * struct netdev_phys_item_id *psid); - * Called to get an ID of the switch chip this port is part of. - * If driver implements this, it indicates that it represents a port - * of a switch chip. - * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state); - * Called to notify switch device port of bridge port STP - * state change. - * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 nlflags, u32 tb_id); - * Called to add/modify IPv4 route to switch device. - * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 tb_id); - * Called to delete IPv4 route from switch device. + * int (*ndo_set_tx_maxrate)(struct net_device *dev, + * int queue_index, u32 maxrate); + * Called when a user wants to set a max-rate limitation of specific + * TX queue. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1178,6 +1167,8 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); + int (*ndo_get_phys_port_name)(struct net_device *dev, + char *name, size_t len); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, __be16 port); @@ -1197,25 +1188,9 @@ struct net_device_ops { netdev_features_t (*ndo_features_check) (struct sk_buff *skb, struct net_device *dev, netdev_features_t features); -#ifdef CONFIG_NET_SWITCHDEV - int (*ndo_switch_parent_id_get)(struct net_device *dev, - struct netdev_phys_item_id *psid); - int (*ndo_switch_port_stp_update)(struct net_device *dev, - u8 state); - int (*ndo_switch_fib_ipv4_add)(struct net_device *dev, - __be32 dst, - int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 nlflags, - u32 tb_id); - int (*ndo_switch_fib_ipv4_del)(struct net_device *dev, - __be32 dst, - int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 tb_id); -#endif + int (*ndo_set_tx_maxrate)(struct net_device *dev, + int queue_index, + u32 maxrate); }; /** @@ -1367,7 +1342,6 @@ enum netdev_priv_flags { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations - * @fwd_ops: Management operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * @@ -1576,7 +1550,9 @@ struct net_device { #endif const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; - const struct forwarding_accel_ops *fwd_ops; +#ifdef CONFIG_NET_SWITCHDEV + const struct swdev_ops *swdev_ops; +#endif const struct header_ops *header_ops; @@ -2181,6 +2157,7 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); +int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); @@ -2974,6 +2951,8 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); +int dev_get_phys_port_name(struct net_device *dev, + char *name, size_t len); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); @@ -3678,6 +3657,9 @@ void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); +netdev_features_t passthru_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); netdev_features_t netif_skb_features(struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index bb39113ea596..2734977199ca 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -19,23 +19,10 @@ enum nf_br_hook_priorities { #define BRNF_PKT_TYPE 0x01 #define BRNF_BRIDGED_DNAT 0x02 -#define BRNF_BRIDGED 0x04 #define BRNF_NF_BRIDGE_PREROUTING 0x08 #define BRNF_8021Q 0x10 #define BRNF_PPPoE 0x20 -static inline unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) -{ - switch (skb->protocol) { - case __cpu_to_be16(ETH_P_8021Q): - return VLAN_HLEN; - case __cpu_to_be16(ETH_P_PPP_SES): - return PPPOE_SES_HLEN; - default: - return 0; - } -} - static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { if (unlikely(skb->nf_bridge->mask & BRNF_PPPoE)) @@ -45,21 +32,6 @@ static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) int br_handle_frame_finish(struct sk_buff *skb); -/* This is called by the IP fragmenting code and it ensures there is - * enough room for the encapsulating header (if there is one). */ -static inline unsigned int nf_bridge_pad(const struct sk_buff *skb) -{ - if (skb->nf_bridge) - return nf_bridge_encap_header_len(skb); - return 0; -} - -struct bridge_skb_cb { - union { - __be32 ipv4; - } daddr; -}; - static inline void br_drop_fake_rtable(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -69,7 +41,6 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb) } #else -#define nf_bridge_pad(skb) (0) #define br_drop_fake_rtable(skb) do { } while (0) #endif /* CONFIG_BRIDGE_NETFILTER */ diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 8a860f096c35..611a691145c4 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -84,7 +84,7 @@ static inline int of_platform_populate(struct device_node *root, static inline void of_platform_depopulate(struct device *parent) { } #endif -#ifdef CONFIG_OF_DYNAMIC +#if defined(CONFIG_OF_DYNAMIC) && defined(CONFIG_OF_ADDRESS) extern void of_platform_register_reconfig_notifier(void); #else static inline void of_platform_register_reconfig_notifier(void) { } diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h index 72c0415d6c21..18eccefea06e 100644 --- a/include/linux/pinctrl/consumer.h +++ b/include/linux/pinctrl/consumer.h @@ -82,7 +82,7 @@ static inline int pinctrl_gpio_direction_output(unsigned gpio) static inline struct pinctrl * __must_check pinctrl_get(struct device *dev) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline void pinctrl_put(struct pinctrl *p) @@ -93,7 +93,7 @@ static inline struct pinctrl_state * __must_check pinctrl_lookup_state( struct pinctrl *p, const char *name) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline int pinctrl_select_state(struct pinctrl *p, @@ -104,7 +104,7 @@ static inline int pinctrl_select_state(struct pinctrl *p, static inline struct pinctrl * __must_check devm_pinctrl_get(struct device *dev) { - return ERR_PTR(-ENOSYS); + return NULL; } static inline void devm_pinctrl_put(struct pinctrl *p) diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 0d8ff3fb84ba..b8b73066d137 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -64,11 +64,11 @@ struct ptp_clock_request { * @adjtime: Shifts the time of the hardware clock. * parameter delta: Desired change in nanoseconds. * - * @gettime: Reads the current time from the hardware clock. - * parameter ts: Holds the result. + * @gettime64: Reads the current time from the hardware clock. + * parameter ts: Holds the result. * - * @settime: Set the current time on the hardware clock. - * parameter ts: Time value to set. + * @settime64: Set the current time on the hardware clock. + * parameter ts: Time value to set. * * @enable: Request driver to enable or disable an ancillary feature. * parameter request: Desired resource to enable or disable. @@ -104,8 +104,8 @@ struct ptp_clock_info { struct ptp_pin_desc *pin_config; int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); - int (*gettime)(struct ptp_clock_info *ptp, struct timespec *ts); - int (*settime)(struct ptp_clock_info *ptp, const struct timespec *ts); + int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); int (*enable)(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index c93ff8ac474a..e23d242d1230 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,14 +1,13 @@ /* * Resizable, Scalable, Concurrent Hash Table * - * Copyright (c) 2014 Thomas Graf <tgraf@suug.ch> + * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> + * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * - * Based on the following paper by Josh Triplett, Paul E. McKenney - * and Jonathan Walpole: - * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf - * * Code partially derived from nft_hash + * Rewritten with rehash code from br_multicast plus single list + * pointer as suggested by Josh Triplett * * 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 @@ -19,9 +18,12 @@ #define _LINUX_RHASHTABLE_H #include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/jhash.h> #include <linux/list_nulls.h> #include <linux/workqueue.h> #include <linux/mutex.h> +#include <linux/rcupdate.h> /* * The end of the chain is marked with a special nulls marks which has @@ -42,6 +44,9 @@ #define RHT_HASH_BITS 27 #define RHT_BASE_SHIFT RHT_HASH_BITS +/* Base bits plus 1 bit for nulls marker */ +#define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) + struct rhash_head { struct rhash_head __rcu *next; }; @@ -49,24 +54,43 @@ struct rhash_head { /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets + * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash - * @shift: Current size (1 << shift) * @locks_mask: Mask to apply before accessing locks[] * @locks: Array of spinlocks protecting individual buckets + * @walkers: List of active walkers + * @rcu: RCU structure for freeing the table + * @future_tbl: Table under construction during rehashing * @buckets: size * hash buckets */ struct bucket_table { - size_t size; + unsigned int size; + unsigned int rehash; u32 hash_rnd; - u32 shift; unsigned int locks_mask; spinlock_t *locks; + struct list_head walkers; + struct rcu_head rcu; + + struct bucket_table __rcu *future_tbl; struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; +/** + * struct rhashtable_compare_arg - Key for the function rhashtable_compare + * @ht: Hash table + * @key: Key to compare against + */ +struct rhashtable_compare_arg { + struct rhashtable *ht; + const void *key; +}; + typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); -typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 seed); +typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); +typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, + const void *obj); struct rhashtable; @@ -76,56 +100,62 @@ struct rhashtable; * @key_len: Length of key * @key_offset: Offset of key in struct to be hashed * @head_offset: Offset of rhash_head in struct to be hashed - * @max_shift: Maximum number of shifts while expanding - * @min_shift: Minimum number of shifts while shrinking + * @max_size: Maximum size while expanding + * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker + * @insecure_elasticity: Set to true to disable chain length checks + * @automatic_shrinking: Enable automatic shrinking of tables * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) - * @hashfn: Function to hash key + * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object + * @obj_cmpfn: Function to compare key with object */ struct rhashtable_params { size_t nelem_hint; size_t key_len; size_t key_offset; size_t head_offset; - size_t max_shift; - size_t min_shift; + unsigned int max_size; + unsigned int min_size; u32 nulls_base; + bool insecure_elasticity; + bool automatic_shrinking; size_t locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; + rht_obj_cmpfn_t obj_cmpfn; }; /** * struct rhashtable - Hash table handle * @tbl: Bucket table - * @future_tbl: Table under construction during expansion/shrinking * @nelems: Number of elements in table + * @key_len: Key length for hashfn + * @elasticity: Maximum chain length before rehash * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping - * @walkers: List of active walkers - * @being_destroyed: True if table is set up for destruction + * @lock: Spin lock to protect walker list */ struct rhashtable { struct bucket_table __rcu *tbl; - struct bucket_table __rcu *future_tbl; atomic_t nelems; - bool being_destroyed; + unsigned int key_len; + unsigned int elasticity; struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; - struct list_head walkers; + spinlock_t lock; }; /** * struct rhashtable_walker - Hash table walker * @list: List entry on list of walkers - * @resize: Resize event occured + * @tbl: The table that we were walking over */ struct rhashtable_walker { struct list_head list; - bool resize; + struct bucket_table *tbl; }; /** @@ -162,6 +192,118 @@ static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr) return ((unsigned long) ptr) >> 1; } +static inline void *rht_obj(const struct rhashtable *ht, + const struct rhash_head *he) +{ + return (char *)he - ht->p.head_offset; +} + +static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, + unsigned int hash) +{ + return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1); +} + +static inline unsigned int rht_key_hashfn( + struct rhashtable *ht, const struct bucket_table *tbl, + const void *key, const struct rhashtable_params params) +{ + unsigned int hash; + + /* params must be equal to ht->p if it isn't constant. */ + if (!__builtin_constant_p(params.key_len)) + hash = ht->p.hashfn(key, ht->key_len, tbl->hash_rnd); + else if (params.key_len) { + unsigned int key_len = params.key_len; + + if (params.hashfn) + hash = params.hashfn(key, key_len, tbl->hash_rnd); + else if (key_len & (sizeof(u32) - 1)) + hash = jhash(key, key_len, tbl->hash_rnd); + else + hash = jhash2(key, key_len / sizeof(u32), + tbl->hash_rnd); + } else { + unsigned int key_len = ht->p.key_len; + + if (params.hashfn) + hash = params.hashfn(key, key_len, tbl->hash_rnd); + else + hash = jhash(key, key_len, tbl->hash_rnd); + } + + return rht_bucket_index(tbl, hash); +} + +static inline unsigned int rht_head_hashfn( + struct rhashtable *ht, const struct bucket_table *tbl, + const struct rhash_head *he, const struct rhashtable_params params) +{ + const char *ptr = rht_obj(ht, he); + + return likely(params.obj_hashfn) ? + rht_bucket_index(tbl, params.obj_hashfn(ptr, params.key_len ?: + ht->p.key_len, + tbl->hash_rnd)) : + rht_key_hashfn(ht, tbl, ptr + params.key_offset, params); +} + +/** + * rht_grow_above_75 - returns true if nelems > 0.75 * table-size + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_grow_above_75(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + /* Expand table when exceeding 75% load */ + return atomic_read(&ht->nelems) > (tbl->size / 4 * 3) && + (!ht->p.max_size || tbl->size < ht->p.max_size); +} + +/** + * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_shrink_below_30(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + /* Shrink table beneath 30% load */ + return atomic_read(&ht->nelems) < (tbl->size * 3 / 10) && + tbl->size > ht->p.min_size; +} + +/** + * rht_grow_above_100 - returns true if nelems > table-size + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_grow_above_100(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + return atomic_read(&ht->nelems) > tbl->size; +} + +/* The bucket lock is selected based on the hash and protects mutations + * on a group of hash buckets. + * + * A maximum of tbl->size/2 bucket locks is allocated. This ensures that + * a single lock always covers both buckets which may both contains + * entries which link to the same bucket of the old table during resizing. + * This allows to simplify the locking as locking the bucket in both + * tables during resize always guarantee protection. + * + * IMPORTANT: When holding the bucket lock of both the old and new table + * during expansions and shrinking, the old bucket lock must always be + * acquired first. + */ +static inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl, + unsigned int hash) +{ + return &tbl->locks[hash & tbl->locks_mask]; +} + #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); @@ -178,23 +320,13 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, } #endif /* CONFIG_PROVE_LOCKING */ -int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params); - -void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node); -bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node); - -int rhashtable_expand(struct rhashtable *ht); -int rhashtable_shrink(struct rhashtable *ht); - -void *rhashtable_lookup(struct rhashtable *ht, const void *key); -void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key, - bool (*compare)(void *, void *), void *arg); +int rhashtable_init(struct rhashtable *ht, + const struct rhashtable_params *params); -bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj); -bool rhashtable_lookup_compare_insert(struct rhashtable *ht, - struct rhash_head *obj, - bool (*compare)(void *, void *), - void *arg); +int rhashtable_insert_slow(struct rhashtable *ht, const void *key, + struct rhash_head *obj, + struct bucket_table *old_tbl); +int rhashtable_insert_rehash(struct rhashtable *ht); int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); @@ -202,6 +334,9 @@ int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU); void *rhashtable_walk_next(struct rhashtable_iter *iter); void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); +void rhashtable_free_and_destroy(struct rhashtable *ht, + void (*free_fn)(void *ptr, void *arg), + void *arg); void rhashtable_destroy(struct rhashtable *ht); #define rht_dereference(p, ht) \ @@ -352,4 +487,316 @@ void rhashtable_destroy(struct rhashtable *ht); rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\ tbl, hash, member) +static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, + const void *obj) +{ + struct rhashtable *ht = arg->ht; + const char *ptr = obj; + + return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); +} + +/** + * rhashtable_lookup_fast - search hash table, inlined version + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup_fast( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + struct rhashtable_compare_arg arg = { + .ht = ht, + .key = key, + }; + const struct bucket_table *tbl; + struct rhash_head *he; + unsigned int hash; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); +restart: + hash = rht_key_hashfn(ht, tbl, key, params); + rht_for_each_rcu(he, tbl, hash) { + if (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, he)) : + rhashtable_compare(&arg, rht_obj(ht, he))) + continue; + rcu_read_unlock(); + return rht_obj(ht, he); + } + + /* Ensure we see any new tables. */ + smp_rmb(); + + tbl = rht_dereference_rcu(tbl->future_tbl, ht); + if (unlikely(tbl)) + goto restart; + rcu_read_unlock(); + + return NULL; +} + +/* Internal function, please use rhashtable_insert_fast() instead */ +static inline int __rhashtable_insert_fast( + struct rhashtable *ht, const void *key, struct rhash_head *obj, + const struct rhashtable_params params) +{ + struct rhashtable_compare_arg arg = { + .ht = ht, + .key = key, + }; + struct bucket_table *tbl, *new_tbl; + struct rhash_head *head; + spinlock_t *lock; + unsigned int elasticity; + unsigned int hash; + int err; + +restart: + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); + + /* All insertions must grab the oldest table containing + * the hashed bucket that is yet to be rehashed. + */ + for (;;) { + hash = rht_head_hashfn(ht, tbl, obj, params); + lock = rht_bucket_lock(tbl, hash); + spin_lock_bh(lock); + + if (tbl->rehash <= hash) + break; + + spin_unlock_bh(lock); + tbl = rht_dereference_rcu(tbl->future_tbl, ht); + } + + new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); + if (unlikely(new_tbl)) { + err = rhashtable_insert_slow(ht, key, obj, new_tbl); + if (err == -EAGAIN) + goto slow_path; + goto out; + } + + if (unlikely(rht_grow_above_100(ht, tbl))) { +slow_path: + spin_unlock_bh(lock); + err = rhashtable_insert_rehash(ht); + rcu_read_unlock(); + if (err) + return err; + + goto restart; + } + + err = -EEXIST; + elasticity = ht->elasticity; + rht_for_each(head, tbl, hash) { + if (key && + unlikely(!(params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, head)) : + rhashtable_compare(&arg, rht_obj(ht, head))))) + goto out; + if (!--elasticity) + goto slow_path; + } + + err = 0; + + head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); + + RCU_INIT_POINTER(obj->next, head); + + rcu_assign_pointer(tbl->buckets[hash], obj); + + atomic_inc(&ht->nelems); + if (rht_grow_above_75(ht, tbl)) + schedule_work(&ht->run_work); + +out: + spin_unlock_bh(lock); + rcu_read_unlock(); + + return err; +} + +/** + * rhashtable_insert_fast - insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Will take a per bucket spinlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket lock. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhashtable_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + return __rhashtable_insert_fast(ht, NULL, obj, params); +} + +/** + * rhashtable_lookup_insert_fast - lookup and insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Locks down the bucket chain in both the old and new table if a resize + * is in progress to ensure that writers can't remove from the old table + * and can't insert to the new table during the atomic operation of search + * and insertion. Searches for duplicates in both the old and new table if + * a resize is in progress. + * + * This lookup function may only be used for fixed key hash table (key_len + * parameter set). It will BUG() if used inappropriately. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhashtable_lookup_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + const char *key = rht_obj(ht, obj); + + BUG_ON(ht->p.obj_hashfn); + + return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, + params); +} + +/** + * rhashtable_lookup_insert_key - search and insert object to hash table + * with explicit key + * @ht: hash table + * @key: key + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Locks down the bucket chain in both the old and new table if a resize + * is in progress to ensure that writers can't remove from the old table + * and can't insert to the new table during the atomic operation of search + * and insertion. Searches for duplicates in both the old and new table if + * a resize is in progress. + * + * Lookups may occur in parallel with hashtable mutations and resizing. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + * + * Returns zero on success. + */ +static inline int rhashtable_lookup_insert_key( + struct rhashtable *ht, const void *key, struct rhash_head *obj, + const struct rhashtable_params params) +{ + BUG_ON(!ht->p.obj_hashfn || !key); + + return __rhashtable_insert_fast(ht, key, obj, params); +} + +/* Internal function, please use rhashtable_remove_fast() instead */ +static inline int __rhashtable_remove_fast( + struct rhashtable *ht, struct bucket_table *tbl, + struct rhash_head *obj, const struct rhashtable_params params) +{ + struct rhash_head __rcu **pprev; + struct rhash_head *he; + spinlock_t * lock; + unsigned int hash; + int err = -ENOENT; + + hash = rht_head_hashfn(ht, tbl, obj, params); + lock = rht_bucket_lock(tbl, hash); + + spin_lock_bh(lock); + + pprev = &tbl->buckets[hash]; + rht_for_each(he, tbl, hash) { + if (he != obj) { + pprev = &he->next; + continue; + } + + rcu_assign_pointer(*pprev, obj->next); + err = 0; + break; + } + + spin_unlock_bh(lock); + + return err; +} + +/** + * rhashtable_remove_fast - remove object from hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table via rhashtable_expand() if the + * shrink_decision function specified at rhashtable_init() returns true. + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ +static inline int rhashtable_remove_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + struct bucket_table *tbl; + int err; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); + + /* Because we have already taken (and released) the bucket + * lock in old_tbl, if we find that future_tbl is not yet + * visible then that guarantees the entry to still be in + * the old tbl if it exists. + */ + while ((err = __rhashtable_remove_fast(ht, tbl, obj, params)) && + (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) + ; + + if (err) + goto out; + + atomic_dec(&ht->nelems); + if (unlikely(ht->p.automatic_shrinking && + rht_shrink_below_30(ht, tbl))) + schedule_work(&ht->run_work); + +out: + rcu_read_unlock(); + + return err; +} + #endif /* _LINUX_RHASHTABLE_H */ diff --git a/include/linux/security.h b/include/linux/security.h index a1b7dbd127ff..25a079a7c3b3 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1716,7 +1716,6 @@ struct security_operations { int (*tun_dev_attach_queue) (void *security); int (*tun_dev_attach) (struct sock *sk, void *security); int (*tun_dev_open) (void *security); - void (*skb_owned_by) (struct sk_buff *skb, struct sock *sk); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2735,8 +2734,6 @@ int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); -void security_skb_owned_by(struct sk_buff *skb, struct sock *sk); - #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, struct sock *other, @@ -2928,11 +2925,6 @@ static inline int security_tun_dev_open(void *security) { return 0; } - -static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) -{ -} - #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bba1330757c0..36f3f43c0117 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -945,6 +945,13 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; +static inline void skb_sender_cpu_clear(struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + skb->sender_cpu = 0; +#endif +} + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { diff --git a/include/linux/socket.h b/include/linux/socket.h index fab4d0ddf4ed..c9852ef7e317 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -51,6 +51,7 @@ struct msghdr { void *msg_control; /* ancillary data */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ unsigned int msg_flags; /* flags on received message */ + struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; struct user_msghdr { diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 97dbf16f7d9d..f869ae8afbaf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -111,7 +111,7 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; - struct sock *listener; /* needed for TFO */ + bool tfo_listener; u32 rcv_isn; u32 snt_isn; u32 snt_synack; /* synack sent time */ diff --git a/include/linux/udp.h b/include/linux/udp.h index 247cfdcc4b08..87c094961bd5 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -34,7 +34,7 @@ static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) -static inline int udp_hashfn(struct net *net, unsigned num, unsigned mask) +static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) { return (num + net_hash_mix(net)) & mask; } diff --git a/include/linux/uio.h b/include/linux/uio.h index 07a022641996..71880299ed48 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -98,6 +98,8 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); + static inline size_t iov_iter_count(struct iov_iter *i) { return i->count; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 7d7acb35603d..0ec598381f97 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -17,6 +17,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ #define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ +#define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ /* bits [20..32] reserved for arch specific ioremap internals */ /* diff --git a/include/net/dsa.h b/include/net/dsa.h index 47917e5e1e12..fbca63ba8f73 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -296,6 +296,12 @@ struct dsa_switch_driver { u32 br_port_mask); int (*port_stp_update)(struct dsa_switch *ds, int port, u8 state); + int (*fdb_add)(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); + int (*fdb_del)(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); + int (*fdb_getnext)(struct dsa_switch *ds, int port, + unsigned char *addr, bool *is_static); }; void register_switch_driver(struct dsa_switch_driver *type); diff --git a/include/net/dst.h b/include/net/dst.h index a8ae4e760778..0fb99a26e973 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -481,6 +481,7 @@ void dst_init(void); enum { XFRM_LOOKUP_ICMP = 1 << 0, XFRM_LOOKUP_QUEUE = 1 << 1, + XFRM_LOOKUP_KEEP_DST_REF = 1 << 2, }; struct flowi; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 98e5f9578f86..1c8b6820b694 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -41,18 +41,18 @@ enum { struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; - + /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 valid_lft; __u32 prefered_lft; atomic_t refcnt; spinlock_t lock; - spinlock_t state_lock; int state; __u32 flags; __u8 dad_probes; + __u8 stable_privacy_retry; __u16 scope; diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 74af137304be..6d539e4e5ba7 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -28,8 +28,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, const struct request_sock *req); -struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, +struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 9201afe083fa..7ff588ca6817 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -38,8 +38,6 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, return jhash_3words(lhash, fhash, ports, initval); } -int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp); - /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b9a6b0a94cc6..7b5887cd1172 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -256,8 +256,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); -struct request_sock *inet_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, +struct request_sock *inet_csk_search_req(struct sock *sk, const __be16 rport, const __be32 raddr, const __be32 laddr); @@ -283,15 +282,13 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, static inline void inet_csk_reqsk_queue_removed(struct sock *sk, struct request_sock *req) { - if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0) - inet_csk_delete_keepalive_timer(sk); + reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); } static inline void inet_csk_reqsk_queue_added(struct sock *sk, const unsigned long timeout) { - if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0) - inet_csk_reset_keepalive_timer(sk, timeout); + reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_len(const struct sock *sk) @@ -310,26 +307,19 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) } static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev); + reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req); } static inline void inet_csk_reqsk_queue_drop(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); - reqsk_free(req); + reqsk_put(req); } -void inet_csk_reqsk_queue_prune(struct sock *parent, - const unsigned long interval, - const unsigned long timeout, - const unsigned long max_rto); - void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index bcd64756e5fe..73fe0f9525d9 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -221,8 +221,8 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); -static inline int inet_bhashfn(struct net *net, const __u16 lport, - const int bhash_size) +static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, + const u32 bhash_size) { return (lport + net_hash_mix(net)) & (bhash_size - 1); } @@ -231,7 +231,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, const unsigned short snum); /* These can have wildcards, don't try too hard. */ -static inline int inet_lhashfn(struct net *net, const unsigned short num) +static inline u32 inet_lhashfn(const struct net *net, const unsigned short num) { return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1); } @@ -249,6 +249,7 @@ void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw); +int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw); void inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); @@ -383,13 +384,32 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, iph->daddr, dport, inet_iif(skb)); } +u32 sk_ehashfn(const struct sock *sk); +u32 inet6_ehashfn(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport); + +static inline void sk_daddr_set(struct sock *sk, __be32 addr) +{ + sk->sk_daddr = addr; /* alias of inet_daddr */ +#if IS_ENABLED(CONFIG_IPV6) + ipv6_addr_set_v4mapped(addr, &sk->sk_v6_daddr); +#endif +} + +static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) +{ + sk->sk_rcv_saddr = addr; /* alias of inet_rcv_saddr */ +#if IS_ENABLED(CONFIG_IPV6) + ipv6_addr_set_v4mapped(addr, &sk->sk_v6_rcv_saddr); +#endif +} + int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, - struct inet_timewait_sock **), - int (*hash)(struct sock *sk, - struct inet_timewait_sock *twp)); + struct inet_timewait_sock **)); int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index b3053fdd871e..b6c3737da4e9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -81,7 +81,6 @@ struct inet_request_sock { #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state -#define ireq_refcnt req.__req_common.skc_refcnt #define ireq_family req.__req_common.skc_family kmemcheck_bitfield_begin(flags); @@ -94,11 +93,11 @@ struct inet_request_sock { acked : 1, no_srccheck: 1; kmemcheck_bitfield_end(flags); + u32 ir_mark; union { struct ip_options_rcu *opt; struct sk_buff *pktopts; }; - u32 ir_mark; }; static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) @@ -106,13 +105,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) return (struct inet_request_sock *)sk; } -static inline u32 inet_request_mark(struct sock *sk, struct sk_buff *skb) +static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) { + if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) return skb->mark; - } else { - return sk->sk_mark; - } + + return sk->sk_mark; } struct inet_cork { @@ -245,20 +243,8 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, initval); } -static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops) -{ - struct request_sock *req = reqsk_alloc(ops); - struct inet_request_sock *ireq = inet_rsk(req); - - if (req != NULL) { - kmemcheck_annotate_bitfield(ireq, flags); - ireq->opt = NULL; - atomic64_set(&ireq->ir_cookie, 0); - ireq->ireq_state = TCP_NEW_SYN_RECV; - } - - return req; -} +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { diff --git a/include/net/ip.h b/include/net/ip.h index 025c61c0dffb..d0808a323763 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -318,9 +318,10 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) } u32 ip_idents_reserve(u32 hash, int segs); -void __ip_select_ident(struct iphdr *iph, int segs); +void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); -static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) +static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, + struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); @@ -337,13 +338,14 @@ static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, in iph->id = 0; } } else { - __ip_select_ident(iph, segs); + __ip_select_ident(net, iph, segs); } } -static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) +static inline void ip_select_ident(struct net *net, struct sk_buff *skb, + struct sock *sk) { - ip_select_ident_segs(skb, sk, 1); + ip_select_ident_segs(net, skb, sk, 1); } static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b7673065c074..65142e6af440 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -671,8 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt); -void ipv6_proxy_select_ident(struct sk_buff *skb); +void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, + struct rt6_info *rt); +void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); @@ -942,10 +943,6 @@ void ipv6_sysctl_unregister(void); int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); -int __ipv6_sock_mc_join(struct sock *sk, int ifindex, - const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); -int __ipv6_sock_mc_drop(struct sock *sk, int ifindex, - const struct in6_addr *addr); #endif /* _NET_IPV6_H */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e7bdf5170802..bd33e66f49aa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -42,6 +42,7 @@ enum { NEIGH_VAR_MCAST_PROBES, NEIGH_VAR_UCAST_PROBES, NEIGH_VAR_APP_PROBES, + NEIGH_VAR_MCAST_REPROBES, NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 534e1f2ac4fc..57639fca223a 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -79,6 +79,16 @@ void nf_log_packet(struct net *net, const struct nf_loginfo *li, const char *fmt, ...); +__printf(8, 9) +void nf_log_trace(struct net *net, + u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *li, + const char *fmt, ...); + struct nf_log_buf; struct nf_log_buf *nf_log_buf_open(void); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d756af559977..b8cd60dcb4e1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -138,19 +138,12 @@ struct nft_userdata { /** * struct nft_set_elem - generic representation of set elements * - * @cookie: implementation specific element cookie * @key: element key - * @data: element data (maps only) - * @flags: element flags (end of interval) - * - * The cookie can be used to store a handle to the element for subsequent - * removal. + * @priv: element private data and extensions */ struct nft_set_elem { - void *cookie; struct nft_data key; - struct nft_data data; - u32 flags; + void *priv; }; struct nft_set; @@ -202,11 +195,15 @@ struct nft_set_estimate { enum nft_set_class class; }; +struct nft_set_ext; + /** * struct nft_set_ops - nf_tables set operations * * @lookup: look up an element within the set * @insert: insert new element into set + * @activate: activate new element in the next generation + * @deactivate: deactivate element in the next generation * @remove: remove element from set * @walk: iterate over all set elemeennts * @privsize: function to return size of set private data @@ -214,16 +211,19 @@ struct nft_set_estimate { * @destroy: destroy private data of set instance * @list: nf_tables_set_ops list node * @owner: module reference + * @elemsize: element private size * @features: features supported by the implementation */ struct nft_set_ops { bool (*lookup)(const struct nft_set *set, const struct nft_data *key, - struct nft_data *data); - int (*get)(const struct nft_set *set, - struct nft_set_elem *elem); + const struct nft_set_ext **ext); int (*insert)(const struct nft_set *set, const struct nft_set_elem *elem); + void (*activate)(const struct nft_set *set, + const struct nft_set_elem *elem); + void * (*deactivate)(const struct nft_set *set, + const struct nft_set_elem *elem); void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); void (*walk)(const struct nft_ctx *ctx, @@ -241,6 +241,7 @@ struct nft_set_ops { struct list_head list; struct module *owner; + unsigned int elemsize; u32 features; }; @@ -259,6 +260,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @nelems: number of elements * @policy: set parameterization (see enum nft_set_policies) * @ops: set ops + * @pnet: network namespace * @flags: set flags * @klen: key length * @dlen: data length @@ -275,6 +277,7 @@ struct nft_set { u16 policy; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; + possible_net_t pnet; u16 flags; u8 klen; u8 dlen; @@ -311,6 +314,121 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); +/** + * enum nft_set_extensions - set extension type IDs + * + * @NFT_SET_EXT_KEY: element key + * @NFT_SET_EXT_DATA: mapping data + * @NFT_SET_EXT_FLAGS: element flags + * @NFT_SET_EXT_NUM: number of extension types + */ +enum nft_set_extensions { + NFT_SET_EXT_KEY, + NFT_SET_EXT_DATA, + NFT_SET_EXT_FLAGS, + NFT_SET_EXT_NUM +}; + +/** + * struct nft_set_ext_type - set extension type + * + * @len: fixed part length of the extension + * @align: alignment requirements of the extension + */ +struct nft_set_ext_type { + u8 len; + u8 align; +}; + +extern const struct nft_set_ext_type nft_set_ext_types[]; + +/** + * struct nft_set_ext_tmpl - set extension template + * + * @len: length of extension area + * @offset: offsets of individual extension types + */ +struct nft_set_ext_tmpl { + u16 len; + u8 offset[NFT_SET_EXT_NUM]; +}; + +/** + * struct nft_set_ext - set extensions + * + * @genmask: generation mask + * @offset: offsets of individual extension types + * @data: beginning of extension data + */ +struct nft_set_ext { + u8 genmask; + u8 offset[NFT_SET_EXT_NUM]; + char data[0]; +}; + +static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) +{ + memset(tmpl, 0, sizeof(*tmpl)); + tmpl->len = sizeof(struct nft_set_ext); +} + +static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, + unsigned int len) +{ + tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); + BUG_ON(tmpl->len > U8_MAX); + tmpl->offset[id] = tmpl->len; + tmpl->len += nft_set_ext_types[id].len + len; +} + +static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) +{ + nft_set_ext_add_length(tmpl, id, 0); +} + +static inline void nft_set_ext_init(struct nft_set_ext *ext, + const struct nft_set_ext_tmpl *tmpl) +{ + memcpy(ext->offset, tmpl->offset, sizeof(ext->offset)); +} + +static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) +{ + return !!ext->offset[id]; +} + +static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) +{ + return ext && __nft_set_ext_exists(ext, id); +} + +static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id) +{ + return (void *)ext + ext->offset[id]; +} + +static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_KEY); +} + +static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_DATA); +} + +static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_FLAGS); +} + +static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, + void *elem) +{ + return elem + set->ops->elemsize; +} + +void nft_set_elem_destroy(const struct nft_set *set, void *elem); /** * struct nft_expr_type - nf_tables expression type @@ -449,7 +567,6 @@ enum nft_chain_flags { * * @rules: list of rules in the chain * @list: used internally - * @net: net namespace that this chain belongs to * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain @@ -460,7 +577,6 @@ enum nft_chain_flags { struct nft_chain { struct list_head rules; struct list_head list; - struct net *net; struct nft_table *table; u64 handle; u32 use; @@ -512,6 +628,7 @@ struct nft_stats { * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops + * @pnet: net namespace that this chain belongs to * @type: chain type * @policy: default policy * @stats: per-cpu chain stats @@ -519,6 +636,7 @@ struct nft_stats { */ struct nft_base_chain { struct nf_hook_ops ops[NFT_HOOK_OPS_MAX]; + possible_net_t pnet; const struct nf_chain_type *type; u8 policy; struct nft_stats __percpu *stats; @@ -605,6 +723,50 @@ void nft_unregister_expr(struct nft_expr_type *); #define MODULE_ALIAS_NFT_SET() \ MODULE_ALIAS("nft-set") +/* + * The gencursor defines two generations, the currently active and the + * next one. Objects contain a bitmask of 2 bits specifying the generations + * they're active in. A set bit means they're inactive in the generation + * represented by that bit. + * + * New objects start out as inactive in the current and active in the + * next generation. When committing the ruleset the bitmask is cleared, + * meaning they're active in all generations. When removing an object, + * it is set inactive in the next generation. After committing the ruleset, + * the objects are removed. + */ +static inline unsigned int nft_gencursor_next(const struct net *net) +{ + return net->nft.gencursor + 1 == 1 ? 1 : 0; +} + +static inline u8 nft_genmask_next(const struct net *net) +{ + return 1 << nft_gencursor_next(net); +} + +static inline u8 nft_genmask_cur(const struct net *net) +{ + /* Use ACCESS_ONCE() to prevent refetching the value for atomicity */ + return 1 << ACCESS_ONCE(net->nft.gencursor); +} + +/* + * Set element transaction helpers + */ + +static inline bool nft_set_elem_active(const struct nft_set_ext *ext, + u8 genmask) +{ + return !(ext->genmask & genmask); +} + +static inline void nft_set_elem_change_active(const struct nft_set *set, + struct nft_set_ext *ext) +{ + ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet)); +} + /** * struct nft_trans - nf_tables object update in transaction * diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h index c06ac58ca107..69a6715d9f3f 100644 --- a/include/net/netns/hash.h +++ b/include/net/netns/hash.h @@ -5,7 +5,7 @@ struct net; -static inline unsigned int net_hash_mix(struct net *net) +static inline u32 net_hash_mix(const struct net *net) { #ifdef CONFIG_NET_NS /* @@ -13,7 +13,7 @@ static inline unsigned int net_hash_mix(struct net *net) * always zeroed */ - return (unsigned)(((unsigned long)net) >> L1_CACHE_SHIFT); + return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT); #else return 0; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index ca0db12cd089..d2527bf81142 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -32,6 +32,8 @@ struct netns_sysctl_ipv6 { int icmpv6_time; int anycast_src_echo_reply; int fwmark_reflect; + int idgen_retries; + int idgen_delay; }; struct netns_ipv6 { diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 3275cf31f731..fe41f3ceb008 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -39,8 +39,7 @@ struct request_sock_ops { void (*send_reset)(struct sock *sk, struct sk_buff *skb); void (*destructor)(struct request_sock *req); - void (*syn_ack_timeout)(struct sock *sk, - struct request_sock *req); + void (*syn_ack_timeout)(const struct request_sock *req); }; int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); @@ -50,8 +49,10 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); struct request_sock { struct sock_common __req_common; #define rsk_refcnt __req_common.skc_refcnt +#define rsk_hash __req_common.skc_hash struct request_sock *dl_next; + struct sock *rsk_listener; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ @@ -60,20 +61,28 @@ struct request_sock { u32 window_clamp; /* window clamp at creation time */ u32 rcv_wnd; /* rcv_wnd offered first time */ u32 ts_recent; - unsigned long expires; + struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; u32 secid; u32 peer_secid; }; -static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *ops) +static inline struct request_sock * +reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC); - if (req != NULL) + if (req) { req->rsk_ops = ops; - + sock_hold(sk_listener); + req->rsk_listener = sk_listener; + + /* Following is temporary. It is coupled with debugging + * helpers in reqsk_put() & reqsk_free() + */ + atomic_set(&req->rsk_refcnt, 0); + } return req; } @@ -82,15 +91,20 @@ static inline struct request_sock *inet_reqsk(struct sock *sk) return (struct request_sock *)sk; } -static inline void __reqsk_free(struct request_sock *req) +static inline struct sock *req_to_sk(struct request_sock *req) { - kmem_cache_free(req->rsk_ops->slab, req); + return (struct sock *)req; } static inline void reqsk_free(struct request_sock *req) { + /* temporary debugging */ + WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0); + req->rsk_ops->destructor(req); - __reqsk_free(req); + if (req->rsk_listener) + sock_put(req->rsk_listener); + kmem_cache_free(req->rsk_ops->slab, req); } static inline void reqsk_put(struct request_sock *req) @@ -106,12 +120,16 @@ extern int sysctl_max_syn_backlog; * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs */ struct listen_sock { - u8 max_qlen_log; + int qlen_inc; /* protected by listener lock */ + int young_inc;/* protected by listener lock */ + + /* following fields can be updated by timer */ + atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ + atomic_t young_dec; + + u8 max_qlen_log ____cacheline_aligned_in_smp; u8 synflood_warned; /* 2 bytes hole, try to use */ - int qlen; - int qlen_young; - int clock_hand; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; @@ -155,18 +173,11 @@ struct fastopen_queue { * %syn_wait_lock is necessary only to avoid proc interface having to grab the main * lock sock while browsing the listening hash (otherwise it's deadlock prone). * - * This lock is acquired in read mode only from listening_get_next() seq_file - * op and it's acquired in write mode _only_ from code that is actively - * changing rskq_accept_head. All readers that are holding the master sock lock - * don't need to grab this lock in read mode too as rskq_accept_head. writes - * are always protected from the main sock lock. */ struct request_sock_queue { struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; - rwlock_t syn_wait_lock; u8 rskq_defer_accept; - /* 3 bytes hole, try to pack */ struct listen_sock *listen_opt; struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been * enabled on this listener. Check @@ -174,6 +185,9 @@ struct request_sock_queue { * to determine if TFO is enabled * right at this moment. */ + + /* temporary alignment, our goal is to get rid of this lock */ + spinlock_t syn_wait_lock ____cacheline_aligned_in_smp; }; int reqsk_queue_alloc(struct request_sock_queue *queue, @@ -199,12 +213,21 @@ static inline int reqsk_queue_empty(struct request_sock_queue *queue) } static inline void reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req, - struct request_sock **prev_req) + struct request_sock *req) { - write_lock(&queue->syn_wait_lock); - *prev_req = req->dl_next; - write_unlock(&queue->syn_wait_lock); + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + + spin_lock(&queue->syn_wait_lock); + + prev = &lopt->syn_table[req->rsk_hash]; + while (*prev != req) + prev = &(*prev)->dl_next; + *prev = req->dl_next; + + spin_unlock(&queue->syn_wait_lock); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); } static inline void reqsk_queue_add(struct request_sock_queue *queue, @@ -237,57 +260,53 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue return req; } -static inline int reqsk_queue_removed(struct request_sock_queue *queue, - struct request_sock *req) +static inline void reqsk_queue_removed(struct request_sock_queue *queue, + const struct request_sock *req) { struct listen_sock *lopt = queue->listen_opt; if (req->num_timeout == 0) - --lopt->qlen_young; - - return --lopt->qlen; + atomic_inc(&lopt->young_dec); + atomic_inc(&lopt->qlen_dec); } -static inline int reqsk_queue_added(struct request_sock_queue *queue) +static inline void reqsk_queue_added(struct request_sock_queue *queue) { struct listen_sock *lopt = queue->listen_opt; - const int prev_qlen = lopt->qlen; - lopt->qlen_young++; - lopt->qlen++; - return prev_qlen; + lopt->young_inc++; + lopt->qlen_inc++; } -static inline int reqsk_queue_len(const struct request_sock_queue *queue) +static inline int listen_sock_qlen(const struct listen_sock *lopt) { - return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0; + return lopt->qlen_inc - atomic_read(&lopt->qlen_dec); } -static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) +static inline int listen_sock_young(const struct listen_sock *lopt) { - return queue->listen_opt->qlen_young; + return lopt->young_inc - atomic_read(&lopt->young_dec); } -static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) +static inline int reqsk_queue_len(const struct request_sock_queue *queue) { - return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log; + const struct listen_sock *lopt = queue->listen_opt; + + return lopt ? listen_sock_qlen(lopt) : 0; } -static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, - u32 hash, struct request_sock *req, - unsigned long timeout) +static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) { - struct listen_sock *lopt = queue->listen_opt; - - req->expires = jiffies + timeout; - req->num_retrans = 0; - req->num_timeout = 0; - req->sk = NULL; - req->dl_next = lopt->syn_table[hash]; + return listen_sock_young(queue->listen_opt); +} - write_lock(&queue->syn_wait_lock); - lopt->syn_table[hash] = req; - write_unlock(&queue->syn_wait_lock); +static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) +{ + return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log; } +void reqsk_queue_hash_req(struct request_sock_queue *queue, + u32 hash, struct request_sock *req, + unsigned long timeout); + #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 856f01cb51dd..c56a438c3a1e 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -166,6 +166,9 @@ void sctp_remaddr_proc_exit(struct net *net); */ extern struct kmem_cache *sctp_chunk_cachep __read_mostly; extern struct kmem_cache *sctp_bucket_cachep __read_mostly; +extern long sysctl_sctp_mem[3]; +extern int sysctl_sctp_rmem[3]; +extern int sysctl_sctp_wmem[3]; /* * Section: Macros, externs, and inlines diff --git a/include/net/sock.h b/include/net/sock.h index f10832ca2e90..3f9b8ce56948 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -67,6 +67,7 @@ #include <linux/atomic.h> #include <net/dst.h> #include <net/checksum.h> +#include <net/tcp_states.h> #include <linux/net_tstamp.h> struct cgroup; @@ -404,8 +405,8 @@ struct sock { rwlock_t sk_callback_lock; int sk_err, sk_err_soft; - unsigned short sk_ack_backlog; - unsigned short sk_max_ack_backlog; + u32 sk_ack_backlog; + u32 sk_max_ack_backlog; __u32 sk_priority; #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) __u32 sk_cgrp_prioidx; @@ -2218,6 +2219,14 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb) return NULL; } +/* This helper checks if a socket is a full socket, + * ie _not_ a timewait or request socket. + */ +static inline bool sk_fullsock(const struct sock *sk) +{ + return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1a9382febcc3..d2e69ee3019a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -14,6 +14,35 @@ #include <linux/netdevice.h> #include <linux/notifier.h> +struct fib_info; + +/** + * struct switchdev_ops - switchdev operations + * + * @swdev_parent_id_get: Called to get an ID of the switch chip this port + * is part of. If driver implements this, it indicates that it + * represents a port of a switch chip. + * + * @swdev_port_stp_update: Called to notify switch device port of bridge + * port STP state change. + * + * @swdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. + * + * @swdev_fib_ipv4_del: Called to delete IPv4 route from switch device. + */ +struct swdev_ops { + int (*swdev_parent_id_get)(struct net_device *dev, + struct netdev_phys_item_id *psid); + int (*swdev_port_stp_update)(struct net_device *dev, u8 state); + int (*swdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, + int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, + u32 tb_id); + int (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, + int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); +}; + enum netdev_switch_notifier_type { NETDEV_SWITCH_FDB_ADD = 1, NETDEV_SWITCH_FDB_DEL, diff --git a/include/net/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h index 86a070ffc930..a152e9858b2c 100644 --- a/include/net/tc_act/tc_bpf.h +++ b/include/net/tc_act/tc_bpf.h @@ -16,8 +16,12 @@ struct tcf_bpf { struct tcf_common common; struct bpf_prog *filter; + union { + u32 bpf_fd; + u16 bpf_num_ops; + }; struct sock_filter *bpf_ops; - u16 bpf_num_ops; + const char *bpf_name; }; #define to_bpf(a) \ container_of(a->priv, struct tcf_bpf, common) diff --git a/include/net/tcp.h b/include/net/tcp.h index 2e11e38205c2..963303fb96ae 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -406,8 +406,7 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, struct request_sock **prev, - bool fastopen); + struct request_sock *req, bool fastopen); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); @@ -434,7 +433,7 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); -void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req); +void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); void tcp_parse_options(const struct sk_buff *skb, @@ -448,6 +447,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); +void tcp_req_err(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, @@ -529,8 +529,6 @@ int tcp_write_wakeup(struct sock *); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); -bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb, - const char *proto); void tcp_push_one(struct sock *, unsigned int mss_now); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); @@ -1137,31 +1135,6 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_openreq_init(struct request_sock *req, - struct tcp_options_received *rx_opt, - struct sk_buff *skb, struct sock *sk) -{ - struct inet_request_sock *ireq = inet_rsk(req); - - req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->cookie_ts = 0; - tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; - tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->last_oow_ack_time = 0; - req->mss = rx_opt->mss_clamp; - req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; - ireq->tstamp_ok = rx_opt->tstamp_ok; - ireq->sack_ok = rx_opt->sack_ok; - ireq->snd_wscale = rx_opt->snd_wscale; - ireq->wscale_ok = rx_opt->wscale_ok; - ireq->acked = 0; - ireq->ecn_ok = 0; - ireq->ir_rmt_port = tcp_hdr(skb)->source; - ireq->ir_num = ntohs(tcp_hdr(skb)->dest); - ireq->ir_mark = inet_request_mark(sk, skb); -} - extern void tcp_openreq_init_rwin(struct request_sock *req, struct sock *sk, struct dst_entry *dst); @@ -1241,36 +1214,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, return true; } -/* Return true if we're currently rate-limiting out-of-window ACKs and - * thus shouldn't send a dupack right now. We rate-limit dupacks in - * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS - * attacks that send repeated SYNs or ACKs for the same connection. To - * do this, we do not send a duplicate SYNACK or ACK if the remote - * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. - */ -static inline bool tcp_oow_rate_limited(struct net *net, - const struct sk_buff *skb, - int mib_idx, u32 *last_oow_ack_time) -{ - /* Data packets without SYNs are not likely part of an ACK loop. */ - if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && - !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; - -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ -} +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { @@ -1349,15 +1294,14 @@ struct tcp_md5sig_pool { }; /* - functions */ -int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - const struct sock *sk, const struct request_sock *req, - const struct sk_buff *skb); +int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, - struct sock *addr_sk); + const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, @@ -1668,28 +1612,26 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct sock *addr_sk); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); - int (*md5_parse) (struct sock *sk, - char __user *optval, - int optlen); + const struct sock *addr_sk); + int (*calc_md5_hash)(char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); + int (*md5_parse)(struct sock *sk, + char __user *optval, + int optlen); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct request_sock *req); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); + struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk, + const struct sock *addr_sk); + int (*calc_md5_hash) (char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); #endif void (*init_req)(struct request_sock *req, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 9564b779246f..756e4636bad8 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -91,6 +91,7 @@ struct vxlanhdr { #define VXLAN_N_VID (1u << 24) #define VXLAN_VID_MASK (VXLAN_N_VID - 1) +#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8) #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) struct vxlan_metadata { diff --git a/include/soc/at91/at91sam9_ddrsdr.h b/include/soc/at91/at91sam9_ddrsdr.h index 0210797abf2e..dc10c52e0e91 100644 --- a/include/soc/at91/at91sam9_ddrsdr.h +++ b/include/soc/at91/at91sam9_ddrsdr.h @@ -92,7 +92,7 @@ #define AT91_DDRSDRC_UPD_MR (3 << 20) /* Update load mode register and extended mode register */ #define AT91_DDRSDRC_MDR 0x20 /* Memory Device Register */ -#define AT91_DDRSDRC_MD (3 << 0) /* Memory Device Type */ +#define AT91_DDRSDRC_MD (7 << 0) /* Memory Device Type */ #define AT91_DDRSDRC_MD_SDR 0 #define AT91_DDRSDRC_MD_LOW_POWER_SDR 1 #define AT91_DDRSDRC_MD_LOW_POWER_DDR 3 diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index db81c65b8f48..d61be7297b2c 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -111,6 +111,7 @@ void array_free(void *array, int n); void target_core_setup_sub_cits(struct se_subsystem_api *); /* attribute helpers from target_core_device.c for backend drivers */ +bool se_dev_check_wce(struct se_device *); int se_dev_set_max_unmap_lba_count(struct se_device *, u32); int se_dev_set_max_unmap_block_desc_count(struct se_device *, u32); int se_dev_set_unmap_granularity(struct se_device *, u32); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3fa1af8a58d7..74aab6e0d964 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -119,6 +119,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_UNSPEC, BPF_PROG_TYPE_SOCKET_FILTER, BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, }; #define BPF_PSEUDO_MAP_FD 1 @@ -165,7 +166,24 @@ enum bpf_func_id { BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */ BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */ BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ + BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ + BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ + BPF_FUNC_skb_store_bytes, /* int skb_store_bytes(skb, offset, from, len) */ __BPF_FUNC_MAX_ID, }; +/* user accessible mirror of in-kernel sk_buff. + * new fields can only be added to the end of this structure + */ +struct __sk_buff { + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; + __u32 vlan_proto; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h index 47785d5ecf17..34c7936ca114 100644 --- a/include/uapi/linux/filter.h +++ b/include/uapi/linux/filter.h @@ -77,7 +77,8 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define SKF_AD_VLAN_TAG_PRESENT 48 #define SKF_AD_PAY_OFFSET 52 #define SKF_AD_RANDOM 56 -#define SKF_AD_MAX 60 +#define SKF_AD_VLAN_TPID 60 +#define SKF_AD_MAX 64 #define SKF_NET_OFF (-0x100000) #define SKF_LL_OFF (-0x200000) diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index 40fdfea39714..4318ab1635ce 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -51,6 +51,7 @@ enum { #define IFA_F_MANAGETEMPADDR 0x100 #define IFA_F_NOPREFIXROUTE 0x200 #define IFA_F_MCAUTOJOIN 0x400 +#define IFA_F_STABLE_PRIVACY 0x800 struct ifa_cacheinfo { __u32 ifa_prefered; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 756436e1ce89..7ffb18df01ca 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -147,6 +147,7 @@ enum { IFLA_CARRIER_CHANGES, IFLA_PHYS_SWITCH_ID, IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, __IFLA_MAX }; @@ -215,6 +216,7 @@ enum { enum in6_addr_gen_mode { IN6_ADDR_GEN_MODE_EUI64, IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, }; /* Bridge section */ @@ -224,6 +226,9 @@ enum { IFLA_BR_FORWARD_DELAY, IFLA_BR_HELLO_TIME, IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, __IFLA_BR_MAX, }; diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index da2d668b8cf1..053bd102fbe0 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -99,6 +99,7 @@ struct tpacket_auxdata { #define TP_STATUS_VLAN_VALID (1 << 4) /* auxdata has valid tp_vlan_tci */ #define TP_STATUS_BLK_TMO (1 << 5) #define TP_STATUS_VLAN_TPID_VALID (1 << 6) /* auxdata has valid tp_vlan_tpid */ +#define TP_STATUS_CSUM_VALID (1 << 7) /* Tx ring - header status */ #define TP_STATUS_AVAILABLE 0 diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 437a6a4b125a..5efa54ae567c 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -170,6 +170,7 @@ enum { DEVCONF_ACCEPT_RA_FROM_LOCAL, DEVCONF_USE_OPTIMISTIC, DEVCONF_ACCEPT_RA_MTU, + DEVCONF_STABLE_SECRET, DEVCONF_MAX }; diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 3873a35509aa..2e35c61bbdd1 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -126,6 +126,7 @@ enum { NDTPA_PROXY_QLEN, /* u32 */ NDTPA_LOCKTIME, /* u64, msecs */ NDTPA_QUEUE_LENBYTES, /* u32 */ + NDTPA_MCAST_REPROBES, /* u32 */ __NDTPA_MAX }; #define NDTPA_MAX (__NDTPA_MAX - 1) diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index 5288bd77e63b..07f17cc70bb3 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -24,6 +24,8 @@ enum { TCA_ACT_BPF_PARMS, TCA_ACT_BPF_OPS_LEN, TCA_ACT_BPF_OPS, + TCA_ACT_BPF_FD, + TCA_ACT_BPF_NAME, __TCA_ACT_BPF_MAX, }; #define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 3c53eec4ae22..19c66fcbab8a 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -60,7 +60,7 @@ struct virtio_blk_config { __u32 size_max; /* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */ __u32 seg_max; - /* geometry the device (if VIRTIO_BLK_F_GEOMETRY) */ + /* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */ struct virtio_blk_geometry { __u16 cylinders; __u8 heads; @@ -119,7 +119,11 @@ struct virtio_blk_config { #define VIRTIO_BLK_T_BARRIER 0x80000000 #endif /* !VIRTIO_BLK_NO_LEGACY */ -/* This is the first element of the read scatter-gather list. */ +/* + * This comes first in the read scatter-gather list. + * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, + * this is the first element of the read scatter-gather list. + */ struct virtio_blk_outhdr { /* VIRTIO_BLK_T* */ __virtio32 type; diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h index 42b9370771b0..cc18ef8825c0 100644 --- a/include/uapi/linux/virtio_scsi.h +++ b/include/uapi/linux/virtio_scsi.h @@ -29,8 +29,16 @@ #include <linux/virtio_types.h> -#define VIRTIO_SCSI_CDB_SIZE 32 -#define VIRTIO_SCSI_SENSE_SIZE 96 +/* Default values of the CDB and sense data size configuration fields */ +#define VIRTIO_SCSI_CDB_DEFAULT_SIZE 32 +#define VIRTIO_SCSI_SENSE_DEFAULT_SIZE 96 + +#ifndef VIRTIO_SCSI_CDB_SIZE +#define VIRTIO_SCSI_CDB_SIZE VIRTIO_SCSI_CDB_DEFAULT_SIZE +#endif +#ifndef VIRTIO_SCSI_SENSE_SIZE +#define VIRTIO_SCSI_SENSE_SIZE VIRTIO_SCSI_SENSE_DEFAULT_SIZE +#endif /* SCSI command request, followed by data-out */ struct virtio_scsi_cmd_req { diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b78f21caf55a..b0f1c9e5d687 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -114,9 +114,9 @@ int __must_check __xenbus_register_backend(struct xenbus_driver *drv, const char *mod_name); #define xenbus_register_frontend(drv) \ - __xenbus_register_frontend(drv, THIS_MODULE, KBUILD_MODNAME); + __xenbus_register_frontend(drv, THIS_MODULE, KBUILD_MODNAME) #define xenbus_register_backend(drv) \ - __xenbus_register_backend(drv, THIS_MODULE, KBUILD_MODNAME); + __xenbus_register_backend(drv, THIS_MODULE, KBUILD_MODNAME) void xenbus_unregister_driver(struct xenbus_driver *drv); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 50603aec766a..4139a0f8b558 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -661,6 +661,9 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; +const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; +const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a3c7701a8b5e..bd7f5988ed9c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -11,6 +11,8 @@ */ #include <linux/bpf.h> #include <linux/rcupdate.h> +#include <linux/random.h> +#include <linux/smp.h> /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -87,3 +89,25 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, }; + +static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return prandom_u32(); +} + +const struct bpf_func_proto bpf_get_prandom_u32_proto = { + .func = bpf_get_prandom_u32, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return raw_smp_processor_id(); +} + +const struct bpf_func_proto bpf_get_smp_processor_id_proto = { + .func = bpf_get_smp_processor_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 669719ccc9ee..ea75c654af1b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -519,7 +519,7 @@ static int bpf_prog_load(union bpf_attr *attr) goto free_prog; /* run eBPF verifier */ - err = bpf_check(prog, attr); + err = bpf_check(&prog, attr); if (err < 0) goto free_used_maps; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e6b522496250..630a7bac1e51 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -773,6 +773,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, expected_type = CONST_IMM; } else if (arg_type == ARG_CONST_MAP_PTR) { expected_type = CONST_PTR_TO_MAP; + } else if (arg_type == ARG_PTR_TO_CTX) { + expected_type = PTR_TO_CTX; } else { verbose("unsupported arg_type %d\n", arg_type); return -EFAULT; @@ -1180,6 +1182,7 @@ static bool may_access_skb(enum bpf_prog_type type) switch (type) { case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: return true; default: return false; @@ -1620,11 +1623,10 @@ static int do_check(struct verifier_env *env) return err; } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM || - insn->imm != 0) { - verbose("BPF_LDX uses reserved fields\n"); - return -EINVAL; - } + enum bpf_reg_type src_reg_type; + + /* check for reserved fields is already done */ + /* check src operand */ err = check_reg_arg(regs, insn->src_reg, SRC_OP); if (err) @@ -1643,6 +1645,29 @@ static int do_check(struct verifier_env *env) if (err) return err; + src_reg_type = regs[insn->src_reg].type; + + if (insn->imm == 0 && BPF_SIZE(insn->code) == BPF_W) { + /* saw a valid insn + * dst_reg = *(u32 *)(src_reg + off) + * use reserved 'imm' field to mark this insn + */ + insn->imm = src_reg_type; + + } else if (src_reg_type != insn->imm && + (src_reg_type == PTR_TO_CTX || + insn->imm == PTR_TO_CTX)) { + /* ABuser program is trying to use the same insn + * dst_reg = *(u32*) (src_reg + off) + * with different pointer types: + * src_reg == ctx in one branch and + * src_reg == stack|map in some other branch. + * Reject it. + */ + verbose("same insn cannot be used with different pointers\n"); + return -EINVAL; + } + } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_XADD) { err = check_xadd(env, insn); @@ -1790,6 +1815,13 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) int i, j; for (i = 0; i < insn_cnt; i++, insn++) { + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) != BPF_MEM || + insn->imm != 0)) { + verbose("BPF_LDX uses reserved fields\n"); + return -EINVAL; + } + if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { struct bpf_map *map; struct fd f; @@ -1881,6 +1913,92 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env) insn->src_reg = 0; } +static void adjust_branches(struct bpf_prog *prog, int pos, int delta) +{ + struct bpf_insn *insn = prog->insnsi; + int insn_cnt = prog->len; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (BPF_CLASS(insn->code) != BPF_JMP || + BPF_OP(insn->code) == BPF_CALL || + BPF_OP(insn->code) == BPF_EXIT) + continue; + + /* adjust offset of jmps if necessary */ + if (i < pos && i + insn->off + 1 > pos) + insn->off += delta; + else if (i > pos && i + insn->off + 1 < pos) + insn->off -= delta; + } +} + +/* convert load instructions that access fields of 'struct __sk_buff' + * into sequence of instructions that access fields of 'struct sk_buff' + */ +static int convert_ctx_accesses(struct verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + struct bpf_insn insn_buf[16]; + struct bpf_prog *new_prog; + u32 cnt; + int i; + + if (!env->prog->aux->ops->convert_ctx_access) + return 0; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_LDX | BPF_MEM | BPF_W)) + continue; + + if (insn->imm != PTR_TO_CTX) { + /* clear internal mark */ + insn->imm = 0; + continue; + } + + cnt = env->prog->aux->ops-> + convert_ctx_access(insn->dst_reg, insn->src_reg, + insn->off, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose("bpf verifier is misconfigured\n"); + return -EINVAL; + } + + if (cnt == 1) { + memcpy(insn, insn_buf, sizeof(*insn)); + continue; + } + + /* several new insns need to be inserted. Make room for them */ + insn_cnt += cnt - 1; + new_prog = bpf_prog_realloc(env->prog, + bpf_prog_size(insn_cnt), + GFP_USER); + if (!new_prog) + return -ENOMEM; + + new_prog->len = insn_cnt; + + memmove(new_prog->insnsi + i + cnt, new_prog->insns + i + 1, + sizeof(*insn) * (insn_cnt - i - cnt)); + + /* copy substitute insns in place of load instruction */ + memcpy(new_prog->insnsi + i, insn_buf, sizeof(*insn) * cnt); + + /* adjust branches in the whole program */ + adjust_branches(new_prog, i, cnt - 1); + + /* keep walking new program and skip insns we just inserted */ + env->prog = new_prog; + insn = new_prog->insnsi + i + cnt - 1; + i += cnt - 1; + } + + return 0; +} + static void free_states(struct verifier_env *env) { struct verifier_state_list *sl, *sln; @@ -1903,13 +2021,13 @@ static void free_states(struct verifier_env *env) kfree(env->explored_states); } -int bpf_check(struct bpf_prog *prog, union bpf_attr *attr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) { char __user *log_ubuf = NULL; struct verifier_env *env; int ret = -EINVAL; - if (prog->len <= 0 || prog->len > BPF_MAXINSNS) + if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS) return -E2BIG; /* 'struct verifier_env' can be global, but since it's not small, @@ -1919,7 +2037,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr) if (!env) return -ENOMEM; - env->prog = prog; + env->prog = *prog; /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); @@ -1951,7 +2069,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr) if (ret < 0) goto skip_full_check; - env->explored_states = kcalloc(prog->len, + env->explored_states = kcalloc(env->prog->len, sizeof(struct verifier_state_list *), GFP_USER); ret = -ENOMEM; @@ -1968,6 +2086,10 @@ skip_full_check: while (pop_stack(env, NULL) >= 0); free_states(env); + if (ret == 0) + /* program is valid, convert *(u32*)(ctx + off) accesses */ + ret = convert_ctx_accesses(env); + if (log_level && log_len >= log_size - 1) { BUG_ON(log_len >= log_size); /* verifier log exceeded user supplied buffer */ @@ -1983,18 +2105,18 @@ skip_full_check: if (ret == 0 && env->used_map_cnt) { /* if program passed verifier, update used_maps in bpf_prog_info */ - prog->aux->used_maps = kmalloc_array(env->used_map_cnt, - sizeof(env->used_maps[0]), - GFP_KERNEL); + env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt, + sizeof(env->used_maps[0]), + GFP_KERNEL); - if (!prog->aux->used_maps) { + if (!env->prog->aux->used_maps) { ret = -ENOMEM; goto free_log_buf; } - memcpy(prog->aux->used_maps, env->used_maps, + memcpy(env->prog->aux->used_maps, env->used_maps, sizeof(env->used_maps[0]) * env->used_map_cnt); - prog->aux->used_map_cnt = env->used_map_cnt; + env->prog->aux->used_map_cnt = env->used_map_cnt; /* program is valid. Convert pseudo bpf_ld_imm64 into generic * bpf_ld_imm64 instructions @@ -2006,11 +2128,12 @@ free_log_buf: if (log_level) vfree(log_buf); free_env: - if (!prog->aux->used_maps) + if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_bpf_prog_info() will release them. */ release_maps(env); + *prog = env->prog; kfree(env); mutex_unlock(&bpf_verifier_lock); return ret; diff --git a/kernel/events/core.c b/kernel/events/core.c index f04daabfd1cf..453ef61311d4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3591,7 +3591,7 @@ static void put_event(struct perf_event *event) ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING); WARN_ON_ONCE(ctx->parent_ctx); perf_remove_from_context(event, true); - mutex_unlock(&ctx->mutex); + perf_event_ctx_unlock(event, ctx); _free_event(event); } diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 01ca08804f51..3f9f1d6b4c2e 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -89,16 +89,28 @@ static bool klp_is_object_loaded(struct klp_object *obj) /* sets obj->mod if object is not vmlinux and module is found */ static void klp_find_object_module(struct klp_object *obj) { + struct module *mod; + if (!klp_is_module(obj)) return; mutex_lock(&module_mutex); /* - * We don't need to take a reference on the module here because we have - * the klp_mutex, which is also taken by the module notifier. This - * prevents any module from unloading until we release the klp_mutex. + * We do not want to block removal of patched modules and therefore + * we do not take a reference here. The patches are removed by + * a going module handler instead. + */ + mod = find_module(obj->name); + /* + * Do not mess work of the module coming and going notifiers. + * Note that the patch might still be needed before the going handler + * is called. Module functions can be called even in the GOING state + * until mod->exit() finishes. This is especially important for + * patches that modify semantic of the functions. */ - obj->mod = find_module(obj->name); + if (mod && mod->klp_alive) + obj->mod = mod; + mutex_unlock(&module_mutex); } @@ -767,6 +779,7 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) return -EINVAL; obj->state = KLP_DISABLED; + obj->mod = NULL; klp_find_object_module(obj); @@ -961,6 +974,15 @@ static int klp_module_notify(struct notifier_block *nb, unsigned long action, mutex_lock(&klp_mutex); + /* + * Each module has to know that the notifier has been called. + * We never know what module will get patched by a new patch. + */ + if (action == MODULE_STATE_COMING) + mod->klp_alive = true; + else /* MODULE_STATE_GOING */ + mod->klp_alive = false; + list_for_each_entry(patch, &klp_patches, list) { for (obj = patch->objs; obj->funcs; obj++) { if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) diff --git a/kernel/module.c b/kernel/module.c index cc93cf68653c..b3d634ed06c9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -56,7 +56,6 @@ #include <linux/async.h> #include <linux/percpu.h> #include <linux/kmemleak.h> -#include <linux/kasan.h> #include <linux/jump_label.h> #include <linux/pfn.h> #include <linux/bsearch.h> @@ -1814,7 +1813,6 @@ static void unset_module_init_ro_nx(struct module *mod) { } void __weak module_memfree(void *module_region) { vfree(module_region); - kasan_module_free(module_region); } void __weak module_arch_cleanup(struct module *mod) diff --git a/lib/Makefile b/lib/Makefile index 87eb3bffc283..58f74d2dd396 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -24,7 +24,7 @@ obj-y += lockref.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \ - gcd.o lcm.o list_sort.o uuid.o flex_array.o clz_ctz.o \ + gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \ percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o obj-y += string_helpers.o diff --git a/mm/iov_iter.c b/lib/iov_iter.c index 827732047da1..9d96e283520c 100644 --- a/mm/iov_iter.c +++ b/lib/iov_iter.c @@ -751,3 +751,18 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) return npages; } EXPORT_SYMBOL(iov_iter_npages); + +const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) +{ + *new = *old; + if (new->type & ITER_BVEC) + return new->bvec = kmemdup(new->bvec, + new->nr_segs * sizeof(struct bio_vec), + flags); + else + /* iovec and kvec have identical layout */ + return new->iov = kmemdup(new->iov, + new->nr_segs * sizeof(struct iovec), + flags); +} +EXPORT_SYMBOL(dup_iter); diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 7a85967060a5..f0f5c5c3de12 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -139,6 +139,9 @@ static int lz4_uncompress(const char *source, char *dest, int osize) /* Error: request to write beyond destination buffer */ if (cpy > oend) goto _output_error; + if ((ref + COPYLENGTH) > oend || + (op + COPYLENGTH) > oend) + goto _output_error; LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); while (op < cpy) *op++ = *ref++; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index fc0d451279f0..4898442b837f 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -1,13 +1,13 @@ /* * Resizable, Scalable, Concurrent Hash Table * + * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * - * Based on the following paper: - * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf - * * Code partially derived from nft_hash + * Rewritten with rehash code from br_multicast plus single list + * pointer as suggested by Josh Triplett * * 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 @@ -27,61 +27,14 @@ #include <linux/err.h> #define HASH_DEFAULT_SIZE 64UL -#define HASH_MIN_SIZE 4UL +#define HASH_MIN_SIZE 4U #define BUCKET_LOCKS_PER_CPU 128UL -/* Base bits plus 1 bit for nulls marker */ -#define HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) - -enum { - RHT_LOCK_NORMAL, - RHT_LOCK_NESTED, -}; - -/* The bucket lock is selected based on the hash and protects mutations - * on a group of hash buckets. - * - * A maximum of tbl->size/2 bucket locks is allocated. This ensures that - * a single lock always covers both buckets which may both contains - * entries which link to the same bucket of the old table during resizing. - * This allows to simplify the locking as locking the bucket in both - * tables during resize always guarantee protection. - * - * IMPORTANT: When holding the bucket lock of both the old and new table - * during expansions and shrinking, the old bucket lock must always be - * acquired first. - */ -static spinlock_t *bucket_lock(const struct bucket_table *tbl, u32 hash) -{ - return &tbl->locks[hash & tbl->locks_mask]; -} - -static void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) -{ - return (void *) he - ht->p.head_offset; -} - -static u32 rht_bucket_index(const struct bucket_table *tbl, u32 hash) -{ - return (hash >> HASH_RESERVED_SPACE) & (tbl->size - 1); -} - -static u32 key_hashfn(struct rhashtable *ht, const struct bucket_table *tbl, - const void *key) -{ - return rht_bucket_index(tbl, ht->p.hashfn(key, ht->p.key_len, - tbl->hash_rnd)); -} - static u32 head_hashfn(struct rhashtable *ht, const struct bucket_table *tbl, const struct rhash_head *he) { - const char *ptr = rht_obj(ht, he); - - return likely(ht->p.key_len) ? - key_hashfn(ht, tbl, ptr + ht->p.key_offset) : - rht_bucket_index(tbl, ht->p.obj_hashfn(ptr, tbl->hash_rnd)); + return rht_head_hashfn(ht, tbl, he, ht->p); } #ifdef CONFIG_PROVE_LOCKING @@ -95,7 +48,7 @@ EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) { - spinlock_t *lock = bucket_lock(tbl, hash); + spinlock_t *lock = rht_bucket_lock(tbl, hash); return (debug_locks) ? lockdep_is_held(lock) : 1; } @@ -105,7 +58,8 @@ EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held); #endif -static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl) +static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, + gfp_t gfp) { unsigned int i, size; #if defined(CONFIG_PROVE_LOCKING) @@ -122,12 +76,13 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl) if (sizeof(spinlock_t) != 0) { #ifdef CONFIG_NUMA - if (size * sizeof(spinlock_t) > PAGE_SIZE) + if (size * sizeof(spinlock_t) > PAGE_SIZE && + gfp == GFP_KERNEL) tbl->locks = vmalloc(size * sizeof(spinlock_t)); else #endif tbl->locks = kmalloc_array(size, sizeof(spinlock_t), - GFP_KERNEL); + gfp); if (!tbl->locks) return -ENOMEM; for (i = 0; i < size; i++) @@ -146,71 +101,68 @@ static void bucket_table_free(const struct bucket_table *tbl) kvfree(tbl); } +static void bucket_table_free_rcu(struct rcu_head *head) +{ + bucket_table_free(container_of(head, struct bucket_table, rcu)); +} + static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, - size_t nbuckets, u32 hash_rnd) + size_t nbuckets, + gfp_t gfp) { struct bucket_table *tbl = NULL; size_t size; int i; size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]); - if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) - tbl = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - if (tbl == NULL) + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER) || + gfp != GFP_KERNEL) + tbl = kzalloc(size, gfp | __GFP_NOWARN | __GFP_NORETRY); + if (tbl == NULL && gfp == GFP_KERNEL) tbl = vzalloc(size); if (tbl == NULL) return NULL; tbl->size = nbuckets; - tbl->shift = ilog2(nbuckets); - tbl->hash_rnd = hash_rnd; - if (alloc_bucket_locks(ht, tbl) < 0) { + if (alloc_bucket_locks(ht, tbl, gfp) < 0) { bucket_table_free(tbl); return NULL; } + INIT_LIST_HEAD(&tbl->walkers); + + get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); + for (i = 0; i < nbuckets; i++) INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i); return tbl; } -/** - * rht_grow_above_75 - returns true if nelems > 0.75 * table-size - * @ht: hash table - * @tbl: current table - */ -static bool rht_grow_above_75(const struct rhashtable *ht, - const struct bucket_table *tbl) +static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, + struct bucket_table *tbl) { - /* Expand table when exceeding 75% load */ - return atomic_read(&ht->nelems) > (tbl->size / 4 * 3) && - (!ht->p.max_shift || tbl->shift < ht->p.max_shift); -} + struct bucket_table *new_tbl; -/** - * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size - * @ht: hash table - * @tbl: current table - */ -static bool rht_shrink_below_30(const struct rhashtable *ht, - const struct bucket_table *tbl) -{ - /* Shrink table beneath 30% load */ - return atomic_read(&ht->nelems) < (tbl->size * 3 / 10) && - tbl->shift > ht->p.min_shift; + do { + new_tbl = tbl; + tbl = rht_dereference_rcu(tbl->future_tbl, ht); + } while (tbl); + + return new_tbl; } -static int rhashtable_rehash_one(struct rhashtable *ht, unsigned old_hash) +static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) { - struct bucket_table *new_tbl = rht_dereference(ht->future_tbl, ht); struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); + struct bucket_table *new_tbl = rhashtable_last_table(ht, + rht_dereference_rcu(old_tbl->future_tbl, ht)); struct rhash_head __rcu **pprev = &old_tbl->buckets[old_hash]; int err = -ENOENT; struct rhash_head *head, *next, *entry; spinlock_t *new_bucket_lock; - unsigned new_hash; + unsigned int new_hash; rht_for_each(entry, old_tbl, old_hash) { err = 0; @@ -227,9 +179,9 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned old_hash) new_hash = head_hashfn(ht, new_tbl, entry); - new_bucket_lock = bucket_lock(new_tbl, new_hash); + new_bucket_lock = rht_bucket_lock(new_tbl, new_hash); - spin_lock_nested(new_bucket_lock, RHT_LOCK_NESTED); + spin_lock_nested(new_bucket_lock, SINGLE_DEPTH_NESTING); head = rht_dereference_bucket(new_tbl->buckets[new_hash], new_tbl, new_hash); @@ -247,50 +199,76 @@ out: return err; } -static void rhashtable_rehash_chain(struct rhashtable *ht, unsigned old_hash) +static void rhashtable_rehash_chain(struct rhashtable *ht, + unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); spinlock_t *old_bucket_lock; - old_bucket_lock = bucket_lock(old_tbl, old_hash); + old_bucket_lock = rht_bucket_lock(old_tbl, old_hash); spin_lock_bh(old_bucket_lock); while (!rhashtable_rehash_one(ht, old_hash)) ; + old_tbl->rehash++; spin_unlock_bh(old_bucket_lock); } -static void rhashtable_rehash(struct rhashtable *ht, - struct bucket_table *new_tbl) +static int rhashtable_rehash_attach(struct rhashtable *ht, + struct bucket_table *old_tbl, + struct bucket_table *new_tbl) { - struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - unsigned old_hash; + /* Protect future_tbl using the first bucket lock. */ + spin_lock_bh(old_tbl->locks); - get_random_bytes(&new_tbl->hash_rnd, sizeof(new_tbl->hash_rnd)); + /* Did somebody beat us to it? */ + if (rcu_access_pointer(old_tbl->future_tbl)) { + spin_unlock_bh(old_tbl->locks); + return -EEXIST; + } /* Make insertions go into the new, empty table right away. Deletions * and lookups will be attempted in both tables until we synchronize. - * The synchronize_rcu() guarantees for the new table to be picked up - * so no new additions go into the old table while we relink. */ - rcu_assign_pointer(ht->future_tbl, new_tbl); + rcu_assign_pointer(old_tbl->future_tbl, new_tbl); /* Ensure the new table is visible to readers. */ smp_wmb(); + spin_unlock_bh(old_tbl->locks); + + return 0; +} + +static int rhashtable_rehash_table(struct rhashtable *ht) +{ + struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); + struct bucket_table *new_tbl; + struct rhashtable_walker *walker; + unsigned int old_hash; + + new_tbl = rht_dereference(old_tbl->future_tbl, ht); + if (!new_tbl) + return 0; + for (old_hash = 0; old_hash < old_tbl->size; old_hash++) rhashtable_rehash_chain(ht, old_hash); /* Publish the new table pointer. */ rcu_assign_pointer(ht->tbl, new_tbl); + spin_lock(&ht->lock); + list_for_each_entry(walker, &old_tbl->walkers, list) + walker->tbl = NULL; + spin_unlock(&ht->lock); + /* Wait for readers. All new readers will see the new * table, and thus no references to the old table will * remain. */ - synchronize_rcu(); + call_rcu(&old_tbl->rcu, bucket_table_free_rcu); - bucket_table_free(old_tbl); + return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0; } /** @@ -308,27 +286,32 @@ static void rhashtable_rehash(struct rhashtable *ht, * It is valid to have concurrent insertions and deletions protected by per * bucket locks or concurrent RCU protected lookups and traversals. */ -int rhashtable_expand(struct rhashtable *ht) +static int rhashtable_expand(struct rhashtable *ht) { struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht); + int err; ASSERT_RHT_MUTEX(ht); - new_tbl = bucket_table_alloc(ht, old_tbl->size * 2, old_tbl->hash_rnd); + old_tbl = rhashtable_last_table(ht, old_tbl); + + new_tbl = bucket_table_alloc(ht, old_tbl->size * 2, GFP_KERNEL); if (new_tbl == NULL) return -ENOMEM; - rhashtable_rehash(ht, new_tbl); - return 0; + err = rhashtable_rehash_attach(ht, old_tbl, new_tbl); + if (err) + bucket_table_free(new_tbl); + + return err; } -EXPORT_SYMBOL_GPL(rhashtable_expand); /** * rhashtable_shrink - Shrink hash table while allowing concurrent lookups * @ht: the hash table to shrink * - * This function may only be called in a context where it is safe to call - * synchronize_rcu(), e.g. not within a rcu_read_lock() section. + * This function shrinks the hash table to fit, i.e., the smallest + * size would not cause it to expand right away automatically. * * The caller must ensure that no concurrent resizing occurs by holding * ht->mutex. @@ -339,359 +322,146 @@ EXPORT_SYMBOL_GPL(rhashtable_expand); * It is valid to have concurrent insertions and deletions protected by per * bucket locks or concurrent RCU protected lookups and traversals. */ -int rhashtable_shrink(struct rhashtable *ht) +static int rhashtable_shrink(struct rhashtable *ht) { struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht); + unsigned int size; + int err; ASSERT_RHT_MUTEX(ht); - new_tbl = bucket_table_alloc(ht, old_tbl->size / 2, old_tbl->hash_rnd); + size = roundup_pow_of_two(atomic_read(&ht->nelems) * 3 / 2); + if (size < ht->p.min_size) + size = ht->p.min_size; + + if (old_tbl->size <= size) + return 0; + + if (rht_dereference(old_tbl->future_tbl, ht)) + return -EEXIST; + + new_tbl = bucket_table_alloc(ht, size, GFP_KERNEL); if (new_tbl == NULL) return -ENOMEM; - rhashtable_rehash(ht, new_tbl); - return 0; + err = rhashtable_rehash_attach(ht, old_tbl, new_tbl); + if (err) + bucket_table_free(new_tbl); + + return err; } -EXPORT_SYMBOL_GPL(rhashtable_shrink); static void rht_deferred_worker(struct work_struct *work) { struct rhashtable *ht; struct bucket_table *tbl; - struct rhashtable_walker *walker; + int err = 0; ht = container_of(work, struct rhashtable, run_work); mutex_lock(&ht->mutex); - if (ht->being_destroyed) - goto unlock; tbl = rht_dereference(ht->tbl, ht); - - list_for_each_entry(walker, &ht->walkers, list) - walker->resize = true; + tbl = rhashtable_last_table(ht, tbl); if (rht_grow_above_75(ht, tbl)) rhashtable_expand(ht); - else if (rht_shrink_below_30(ht, tbl)) + else if (ht->p.automatic_shrinking && rht_shrink_below_30(ht, tbl)) rhashtable_shrink(ht); -unlock: - mutex_unlock(&ht->mutex); -} - -static bool __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj, - bool (*compare)(void *, void *), void *arg) -{ - struct bucket_table *tbl, *old_tbl; - struct rhash_head *head; - bool no_resize_running; - unsigned hash; - bool success = true; - - rcu_read_lock(); - - old_tbl = rht_dereference_rcu(ht->tbl, ht); - hash = head_hashfn(ht, old_tbl, obj); - - spin_lock_bh(bucket_lock(old_tbl, hash)); - /* Because we have already taken the bucket lock in old_tbl, - * if we find that future_tbl is not yet visible then that - * guarantees all other insertions of the same entry will - * also grab the bucket lock in old_tbl because until the - * rehash completes ht->tbl won't be changed. - */ - tbl = rht_dereference_rcu(ht->future_tbl, ht); - if (tbl != old_tbl) { - hash = head_hashfn(ht, tbl, obj); - spin_lock_nested(bucket_lock(tbl, hash), RHT_LOCK_NESTED); - } - - if (compare && - rhashtable_lookup_compare(ht, rht_obj(ht, obj) + ht->p.key_offset, - compare, arg)) { - success = false; - goto exit; - } - - no_resize_running = tbl == old_tbl; - - head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); - - if (rht_is_a_nulls(head)) - INIT_RHT_NULLS_HEAD(obj->next, ht, hash); - else - RCU_INIT_POINTER(obj->next, head); + err = rhashtable_rehash_table(ht); - rcu_assign_pointer(tbl->buckets[hash], obj); + mutex_unlock(&ht->mutex); - atomic_inc(&ht->nelems); - if (no_resize_running && rht_grow_above_75(ht, tbl)) + if (err) schedule_work(&ht->run_work); - -exit: - if (tbl != old_tbl) { - hash = head_hashfn(ht, tbl, obj); - spin_unlock(bucket_lock(tbl, hash)); - } - - hash = head_hashfn(ht, old_tbl, obj); - spin_unlock_bh(bucket_lock(old_tbl, hash)); - - rcu_read_unlock(); - - return success; } -/** - * rhashtable_insert - insert object into hash table - * @ht: hash table - * @obj: pointer to hash head inside object - * - * Will take a per bucket spinlock to protect against mutual mutations - * on the same bucket. Multiple insertions may occur in parallel unless - * they map to the same bucket lock. - * - * It is safe to call this function from atomic context. - * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). - */ -void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj) +static bool rhashtable_check_elasticity(struct rhashtable *ht, + struct bucket_table *tbl, + unsigned int hash) { - __rhashtable_insert(ht, obj, NULL, NULL); -} -EXPORT_SYMBOL_GPL(rhashtable_insert); - -static bool __rhashtable_remove(struct rhashtable *ht, - struct bucket_table *tbl, - struct rhash_head *obj) -{ - struct rhash_head __rcu **pprev; - struct rhash_head *he; - spinlock_t * lock; - unsigned hash; - bool ret = false; - - hash = head_hashfn(ht, tbl, obj); - lock = bucket_lock(tbl, hash); - - spin_lock_bh(lock); - - pprev = &tbl->buckets[hash]; - rht_for_each(he, tbl, hash) { - if (he != obj) { - pprev = &he->next; - continue; - } - - rcu_assign_pointer(*pprev, obj->next); - ret = true; - break; - } + unsigned int elasticity = ht->elasticity; + struct rhash_head *head; - spin_unlock_bh(lock); + rht_for_each(head, tbl, hash) + if (!--elasticity) + return true; - return ret; + return false; } -/** - * rhashtable_remove - remove object from hash table - * @ht: hash table - * @obj: pointer to hash head inside object - * - * Since the hash chain is single linked, the removal operation needs to - * walk the bucket chain upon removal. The removal operation is thus - * considerable slow if the hash table is not correctly sized. - * - * Will automatically shrink the table via rhashtable_expand() if the - * shrink_decision function specified at rhashtable_init() returns true. - * - * The caller must ensure that no concurrent table mutations occur. It is - * however valid to have concurrent lookups if they are RCU protected. - */ -bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj) +int rhashtable_insert_rehash(struct rhashtable *ht) { - struct bucket_table *tbl, *old_tbl; - bool ret; - - rcu_read_lock(); + struct bucket_table *old_tbl; + struct bucket_table *new_tbl; + struct bucket_table *tbl; + unsigned int size; + int err; old_tbl = rht_dereference_rcu(ht->tbl, ht); - ret = __rhashtable_remove(ht, old_tbl, obj); - - /* Because we have already taken (and released) the bucket - * lock in old_tbl, if we find that future_tbl is not yet - * visible then that guarantees the entry to still be in - * old_tbl if it exists. - */ - tbl = rht_dereference_rcu(ht->future_tbl, ht); - if (!ret && old_tbl != tbl) - ret = __rhashtable_remove(ht, tbl, obj); - - if (ret) { - bool no_resize_running = tbl == old_tbl; - - atomic_dec(&ht->nelems); - if (no_resize_running && rht_shrink_below_30(ht, tbl)) - schedule_work(&ht->run_work); - } - - rcu_read_unlock(); - - return ret; -} -EXPORT_SYMBOL_GPL(rhashtable_remove); + tbl = rhashtable_last_table(ht, old_tbl); -struct rhashtable_compare_arg { - struct rhashtable *ht; - const void *key; -}; - -static bool rhashtable_compare(void *ptr, void *arg) -{ - struct rhashtable_compare_arg *x = arg; - struct rhashtable *ht = x->ht; + size = tbl->size; - return !memcmp(ptr + ht->p.key_offset, x->key, ht->p.key_len); -} + if (rht_grow_above_75(ht, tbl)) + size *= 2; + /* More than two rehashes (not resizes) detected. */ + else if (WARN_ON(old_tbl != tbl && old_tbl->size == size)) + return -EBUSY; -/** - * rhashtable_lookup - lookup key in hash table - * @ht: hash table - * @key: pointer to key - * - * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. - * - * This lookup function may only be used for fixed key hash table (key_len - * parameter set). It will BUG() if used inappropriately. - * - * Lookups may occur in parallel with hashtable mutations and resizing. - */ -void *rhashtable_lookup(struct rhashtable *ht, const void *key) -{ - struct rhashtable_compare_arg arg = { - .ht = ht, - .key = key, - }; + new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC); + if (new_tbl == NULL) + return -ENOMEM; - BUG_ON(!ht->p.key_len); + err = rhashtable_rehash_attach(ht, tbl, new_tbl); + if (err) { + bucket_table_free(new_tbl); + if (err == -EEXIST) + err = 0; + } else + schedule_work(&ht->run_work); - return rhashtable_lookup_compare(ht, key, &rhashtable_compare, &arg); + return err; } -EXPORT_SYMBOL_GPL(rhashtable_lookup); +EXPORT_SYMBOL_GPL(rhashtable_insert_rehash); -/** - * rhashtable_lookup_compare - search hash table with compare function - * @ht: hash table - * @key: the pointer to the key - * @compare: compare function, must return true on match - * @arg: argument passed on to compare function - * - * Traverses the bucket chain behind the provided hash value and calls the - * specified compare function for each entry. - * - * Lookups may occur in parallel with hashtable mutations and resizing. - * - * Returns the first entry on which the compare function returned true. - */ -void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key, - bool (*compare)(void *, void *), void *arg) +int rhashtable_insert_slow(struct rhashtable *ht, const void *key, + struct rhash_head *obj, + struct bucket_table *tbl) { - const struct bucket_table *tbl, *old_tbl; - struct rhash_head *he; - u32 hash; + struct rhash_head *head; + unsigned int hash; + int err; - rcu_read_lock(); + tbl = rhashtable_last_table(ht, tbl); + hash = head_hashfn(ht, tbl, obj); + spin_lock_nested(rht_bucket_lock(tbl, hash), SINGLE_DEPTH_NESTING); - tbl = rht_dereference_rcu(ht->tbl, ht); -restart: - hash = key_hashfn(ht, tbl, key); - rht_for_each_rcu(he, tbl, hash) { - if (!compare(rht_obj(ht, he), arg)) - continue; - rcu_read_unlock(); - return rht_obj(ht, he); - } + err = -EEXIST; + if (key && rhashtable_lookup_fast(ht, key, ht->p)) + goto exit; - /* Ensure we see any new tables. */ - smp_rmb(); + err = -EAGAIN; + if (rhashtable_check_elasticity(ht, tbl, hash) || + rht_grow_above_100(ht, tbl)) + goto exit; - old_tbl = tbl; - tbl = rht_dereference_rcu(ht->future_tbl, ht); - if (unlikely(tbl != old_tbl)) - goto restart; - rcu_read_unlock(); + err = 0; - return NULL; -} -EXPORT_SYMBOL_GPL(rhashtable_lookup_compare); + head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); -/** - * rhashtable_lookup_insert - lookup and insert object into hash table - * @ht: hash table - * @obj: pointer to hash head inside object - * - * Locks down the bucket chain in both the old and new table if a resize - * is in progress to ensure that writers can't remove from the old table - * and can't insert to the new table during the atomic operation of search - * and insertion. Searches for duplicates in both the old and new table if - * a resize is in progress. - * - * This lookup function may only be used for fixed key hash table (key_len - * parameter set). It will BUG() if used inappropriately. - * - * It is safe to call this function from atomic context. - * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). - */ -bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj) -{ - struct rhashtable_compare_arg arg = { - .ht = ht, - .key = rht_obj(ht, obj) + ht->p.key_offset, - }; + RCU_INIT_POINTER(obj->next, head); - BUG_ON(!ht->p.key_len); + rcu_assign_pointer(tbl->buckets[hash], obj); - return rhashtable_lookup_compare_insert(ht, obj, &rhashtable_compare, - &arg); -} -EXPORT_SYMBOL_GPL(rhashtable_lookup_insert); + atomic_inc(&ht->nelems); -/** - * rhashtable_lookup_compare_insert - search and insert object to hash table - * with compare function - * @ht: hash table - * @obj: pointer to hash head inside object - * @compare: compare function, must return true on match - * @arg: argument passed on to compare function - * - * Locks down the bucket chain in both the old and new table if a resize - * is in progress to ensure that writers can't remove from the old table - * and can't insert to the new table during the atomic operation of search - * and insertion. Searches for duplicates in both the old and new table if - * a resize is in progress. - * - * Lookups may occur in parallel with hashtable mutations and resizing. - * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). - */ -bool rhashtable_lookup_compare_insert(struct rhashtable *ht, - struct rhash_head *obj, - bool (*compare)(void *, void *), - void *arg) -{ - BUG_ON(!ht->p.key_len); +exit: + spin_unlock(rht_bucket_lock(tbl, hash)); - return __rhashtable_insert(ht, obj, compare, arg); + return err; } -EXPORT_SYMBOL_GPL(rhashtable_lookup_compare_insert); +EXPORT_SYMBOL_GPL(rhashtable_insert_slow); /** * rhashtable_walk_init - Initialise an iterator @@ -725,11 +495,9 @@ int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter) if (!iter->walker) return -ENOMEM; - INIT_LIST_HEAD(&iter->walker->list); - iter->walker->resize = false; - mutex_lock(&ht->mutex); - list_add(&iter->walker->list, &ht->walkers); + iter->walker->tbl = rht_dereference(ht->tbl, ht); + list_add(&iter->walker->list, &iter->walker->tbl->walkers); mutex_unlock(&ht->mutex); return 0; @@ -745,7 +513,8 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_init); void rhashtable_walk_exit(struct rhashtable_iter *iter) { mutex_lock(&iter->ht->mutex); - list_del(&iter->walker->list); + if (iter->walker->tbl) + list_del(&iter->walker->list); mutex_unlock(&iter->ht->mutex); kfree(iter->walker); } @@ -766,13 +535,21 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_exit); * by calling rhashtable_walk_next. */ int rhashtable_walk_start(struct rhashtable_iter *iter) + __acquires(RCU) { + struct rhashtable *ht = iter->ht; + + mutex_lock(&ht->mutex); + + if (iter->walker->tbl) + list_del(&iter->walker->list); + rcu_read_lock(); - if (iter->walker->resize) { - iter->slot = 0; - iter->skip = 0; - iter->walker->resize = false; + mutex_unlock(&ht->mutex); + + if (!iter->walker->tbl) { + iter->walker->tbl = rht_dereference_rcu(ht->tbl, ht); return -EAGAIN; } @@ -794,13 +571,11 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_start); */ void *rhashtable_walk_next(struct rhashtable_iter *iter) { - const struct bucket_table *tbl; + struct bucket_table *tbl = iter->walker->tbl; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; void *obj = NULL; - tbl = rht_dereference_rcu(ht->tbl, ht); - if (p) { p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot); goto next; @@ -826,17 +601,20 @@ next: iter->skip = 0; } - iter->p = NULL; + /* Ensure we see any new tables. */ + smp_rmb(); -out: - if (iter->walker->resize) { - iter->p = NULL; + iter->walker->tbl = rht_dereference_rcu(tbl->future_tbl, ht); + if (iter->walker->tbl) { iter->slot = 0; iter->skip = 0; - iter->walker->resize = false; return ERR_PTR(-EAGAIN); } + iter->p = NULL; + +out: + return obj; } EXPORT_SYMBOL_GPL(rhashtable_walk_next); @@ -848,16 +626,39 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_next); * Finish a hash table walk. */ void rhashtable_walk_stop(struct rhashtable_iter *iter) + __releases(RCU) { - rcu_read_unlock(); + struct rhashtable *ht; + struct bucket_table *tbl = iter->walker->tbl; + + if (!tbl) + goto out; + + ht = iter->ht; + + spin_lock(&ht->lock); + if (tbl->rehash < tbl->size) + list_add(&iter->walker->list, &tbl->walkers); + else + iter->walker->tbl = NULL; + spin_unlock(&ht->lock); + iter->p = NULL; + +out: + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rhashtable_walk_stop); -static size_t rounded_hashtable_size(struct rhashtable_params *params) +static size_t rounded_hashtable_size(const struct rhashtable_params *params) { return max(roundup_pow_of_two(params->nelem_hint * 4 / 3), - 1UL << params->min_shift); + (unsigned long)params->min_size); +} + +static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) +{ + return jhash2(key, length, seed); } /** @@ -890,7 +691,7 @@ static size_t rounded_hashtable_size(struct rhashtable_params *params) * struct rhash_head node; * }; * - * u32 my_hash_fn(const void *data, u32 seed) + * u32 my_hash_fn(const void *data, u32 len, u32 seed) * { * struct test_obj *obj = data; * @@ -903,47 +704,74 @@ static size_t rounded_hashtable_size(struct rhashtable_params *params) * .obj_hashfn = my_hash_fn, * }; */ -int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params) +int rhashtable_init(struct rhashtable *ht, + const struct rhashtable_params *params) { struct bucket_table *tbl; size_t size; - u32 hash_rnd; size = HASH_DEFAULT_SIZE; - if ((params->key_len && !params->hashfn) || - (!params->key_len && !params->obj_hashfn)) + if ((!params->key_len && !params->obj_hashfn) || + (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT)) return -EINVAL; - params->min_shift = max_t(size_t, params->min_shift, - ilog2(HASH_MIN_SIZE)); - if (params->nelem_hint) size = rounded_hashtable_size(params); memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); + spin_lock_init(&ht->lock); memcpy(&ht->p, params, sizeof(*params)); - INIT_LIST_HEAD(&ht->walkers); + + if (params->min_size) + ht->p.min_size = roundup_pow_of_two(params->min_size); + + if (params->max_size) + ht->p.max_size = rounddown_pow_of_two(params->max_size); + + ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE); + + /* The maximum (not average) chain length grows with the + * size of the hash table, at a rate of (log N)/(log log N). + * The value of 16 is selected so that even if the hash + * table grew to 2^32 you would not expect the maximum + * chain length to exceed it unless we are under attack + * (or extremely unlucky). + * + * As this limit is only to detect attacks, we don't need + * to set it to a lower value as you'd need the chain + * length to vastly exceed 16 to have any real effect + * on the system. + */ + if (!params->insecure_elasticity) + ht->elasticity = 16; if (params->locks_mul) ht->p.locks_mul = roundup_pow_of_two(params->locks_mul); else ht->p.locks_mul = BUCKET_LOCKS_PER_CPU; - get_random_bytes(&hash_rnd, sizeof(hash_rnd)); + ht->key_len = ht->p.key_len; + if (!params->hashfn) { + ht->p.hashfn = jhash; - tbl = bucket_table_alloc(ht, size, hash_rnd); + if (!(ht->key_len & (sizeof(u32) - 1))) { + ht->key_len /= sizeof(u32); + ht->p.hashfn = rhashtable_jhash2; + } + } + + tbl = bucket_table_alloc(ht, size, GFP_KERNEL); if (tbl == NULL) return -ENOMEM; atomic_set(&ht->nelems, 0); RCU_INIT_POINTER(ht->tbl, tbl); - RCU_INIT_POINTER(ht->future_tbl, tbl); INIT_WORK(&ht->run_work, rht_deferred_worker); @@ -952,21 +780,53 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params) EXPORT_SYMBOL_GPL(rhashtable_init); /** - * rhashtable_destroy - destroy hash table + * rhashtable_free_and_destroy - free elements and destroy hash table * @ht: the hash table to destroy + * @free_fn: callback to release resources of element + * @arg: pointer passed to free_fn * - * Frees the bucket array. This function is not rcu safe, therefore the caller - * has to make sure that no resizing may happen by unpublishing the hashtable - * and waiting for the quiescent cycle before releasing the bucket array. + * Stops an eventual async resize. If defined, invokes free_fn for each + * element to releasal resources. Please note that RCU protected + * readers may still be accessing the elements. Releasing of resources + * must occur in a compatible manner. Then frees the bucket array. + * + * This function will eventually sleep to wait for an async resize + * to complete. The caller is responsible that no further write operations + * occurs in parallel. */ -void rhashtable_destroy(struct rhashtable *ht) +void rhashtable_free_and_destroy(struct rhashtable *ht, + void (*free_fn)(void *ptr, void *arg), + void *arg) { - ht->being_destroyed = true; + const struct bucket_table *tbl; + unsigned int i; cancel_work_sync(&ht->run_work); mutex_lock(&ht->mutex); - bucket_table_free(rht_dereference(ht->tbl, ht)); + tbl = rht_dereference(ht->tbl, ht); + if (free_fn) { + for (i = 0; i < tbl->size; i++) { + struct rhash_head *pos, *next; + + for (pos = rht_dereference(tbl->buckets[i], ht), + next = !rht_is_a_nulls(pos) ? + rht_dereference(pos->next, ht) : NULL; + !rht_is_a_nulls(pos); + pos = next, + next = !rht_is_a_nulls(pos) ? + rht_dereference(pos->next, ht) : NULL) + free_fn(rht_obj(ht, pos), arg); + } + } + + bucket_table_free(tbl); mutex_unlock(&ht->mutex); } +EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy); + +void rhashtable_destroy(struct rhashtable *ht) +{ + return rhashtable_free_and_destroy(ht, NULL, NULL); +} EXPORT_SYMBOL_GPL(rhashtable_destroy); diff --git a/lib/sha1.c b/lib/sha1.c index 1df191e04a24..5a56dfd7b99d 100644 --- a/lib/sha1.c +++ b/lib/sha1.c @@ -198,3 +198,4 @@ void sha_init(__u32 *buf) buf[3] = 0x10325476; buf[4] = 0xc3d2e1f0; } +EXPORT_SYMBOL(sha_init); diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 67c7593d1dd6..a42a0d44e818 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -38,6 +38,16 @@ struct test_obj { struct rhash_head node; }; +static const struct rhashtable_params test_rht_params = { + .nelem_hint = TEST_HT_SIZE, + .head_offset = offsetof(struct test_obj, node), + .key_offset = offsetof(struct test_obj, value), + .key_len = sizeof(int), + .hashfn = jhash, + .max_size = 2, /* we expand/shrink manually here */ + .nulls_base = (3U << RHT_BASE_SHIFT), +}; + static int __init test_rht_lookup(struct rhashtable *ht) { unsigned int i; @@ -47,7 +57,7 @@ static int __init test_rht_lookup(struct rhashtable *ht) bool expected = !(i % 2); u32 key = i; - obj = rhashtable_lookup(ht, &key); + obj = rhashtable_lookup_fast(ht, &key, test_rht_params); if (expected && !obj) { pr_warn("Test failed: Could not find key %u\n", key); @@ -80,7 +90,7 @@ static void test_bucket_stats(struct rhashtable *ht, bool quiet) rcu_cnt = cnt = 0; if (!quiet) - pr_info(" [%#4x/%zu]", i, tbl->size); + pr_info(" [%#4x/%u]", i, tbl->size); rht_for_each_entry_rcu(obj, pos, tbl, i, node) { cnt++; @@ -133,7 +143,11 @@ static int __init test_rhashtable(struct rhashtable *ht) obj->ptr = TEST_PTR; obj->value = i * 2; - rhashtable_insert(ht, &obj->node); + err = rhashtable_insert_fast(ht, &obj->node, test_rht_params); + if (err) { + kfree(obj); + goto error; + } } rcu_read_lock(); @@ -141,30 +155,6 @@ static int __init test_rhashtable(struct rhashtable *ht) test_rht_lookup(ht); rcu_read_unlock(); - for (i = 0; i < TEST_NEXPANDS; i++) { - pr_info(" Table expansion iteration %u...\n", i); - mutex_lock(&ht->mutex); - rhashtable_expand(ht); - mutex_unlock(&ht->mutex); - - rcu_read_lock(); - pr_info(" Verifying lookups...\n"); - test_rht_lookup(ht); - rcu_read_unlock(); - } - - for (i = 0; i < TEST_NEXPANDS; i++) { - pr_info(" Table shrinkage iteration %u...\n", i); - mutex_lock(&ht->mutex); - rhashtable_shrink(ht); - mutex_unlock(&ht->mutex); - - rcu_read_lock(); - pr_info(" Verifying lookups...\n"); - test_rht_lookup(ht); - rcu_read_unlock(); - } - rcu_read_lock(); test_bucket_stats(ht, true); rcu_read_unlock(); @@ -173,10 +163,10 @@ static int __init test_rhashtable(struct rhashtable *ht) for (i = 0; i < TEST_ENTRIES; i++) { u32 key = i * 2; - obj = rhashtable_lookup(ht, &key); + obj = rhashtable_lookup_fast(ht, &key, test_rht_params); BUG_ON(!obj); - rhashtable_remove(ht, &obj->node); + rhashtable_remove_fast(ht, &obj->node, test_rht_params); kfree(obj); } @@ -195,20 +185,11 @@ static struct rhashtable ht; static int __init test_rht_init(void) { - struct rhashtable_params params = { - .nelem_hint = TEST_HT_SIZE, - .head_offset = offsetof(struct test_obj, node), - .key_offset = offsetof(struct test_obj, value), - .key_len = sizeof(int), - .hashfn = jhash, - .max_shift = 1, /* we expand/shrink manually here */ - .nulls_base = (3U << RHT_BASE_SHIFT), - }; int err; pr_info("Running resizable hashtable tests...\n"); - err = rhashtable_init(&ht, ¶ms); + err = rhashtable_init(&ht, &test_rht_params); if (err < 0) { pr_warn("Test failed: Unable to initialize hashtable: %d\n", err); diff --git a/mm/Makefile b/mm/Makefile index 3c1caa2693bd..15dbe9903c27 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -21,7 +21,7 @@ obj-y := filemap.o mempool.o oom_kill.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o \ - iov_iter.o debug.o $(mmu-y) + debug.o $(mmu-y) obj-y += init-mm.o @@ -64,15 +64,17 @@ static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order) return (1UL << (align_order - cma->order_per_bit)) - 1; } +/* + * Find a PFN aligned to the specified order and return an offset represented in + * order_per_bits. + */ static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order) { - unsigned int alignment; - if (align_order <= cma->order_per_bit) return 0; - alignment = 1UL << (align_order - cma->order_per_bit); - return ALIGN(cma->base_pfn, alignment) - - (cma->base_pfn >> cma->order_per_bit); + + return (ALIGN(cma->base_pfn, (1UL << align_order)) + - cma->base_pfn) >> cma->order_per_bit; } static unsigned long cma_bitmap_maxno(struct cma *cma) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fc00c8cb5a82..626e93db28ba 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1295,8 +1295,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * Avoid grouping on DSO/COW pages in specific and RO pages * in general, RO pages shouldn't hurt as much anyway since * they can be in shared cache state. + * + * FIXME! This checks "pmd_dirty()" as an approximation of + * "is this a read-only page", since checking "pmd_write()" + * is even more broken. We haven't actually turned this into + * a writable page, so pmd_write() will always be false. */ - if (!pmd_write(pmd)) + if (!pmd_dirty(pmd)) flags |= TNF_NO_GROUP; /* @@ -1482,6 +1487,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; + ret = 1; /* * Avoid trapping faults against the zero page. The read-only @@ -1490,11 +1496,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (prot_numa && is_huge_zero_pmd(*pmd)) { spin_unlock(ptl); - return 0; + return ret; } if (!prot_numa || !pmd_protnone(*pmd)) { - ret = 1; entry = pmdp_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0a9ac6c26832..c41b2a0ee273 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -917,7 +917,6 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) __SetPageHead(page); __ClearPageReserved(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { - __SetPageTail(p); /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic @@ -933,6 +932,9 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) __ClearPageReserved(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 78fee632a7ee..936d81661c47 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -29,6 +29,7 @@ #include <linux/stacktrace.h> #include <linux/string.h> #include <linux/types.h> +#include <linux/vmalloc.h> #include <linux/kasan.h> #include "kasan.h" @@ -414,12 +415,19 @@ int kasan_module_alloc(void *addr, size_t size) GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, __builtin_return_address(0)); - return ret ? 0 : -ENOMEM; + + if (ret) { + find_vm_area(addr)->flags |= VM_KASAN; + return 0; + } + + return -ENOMEM; } -void kasan_module_free(void *addr) +void kasan_free_shadow(const struct vm_struct *vm) { - vfree(kasan_mem_to_shadow(addr)); + if (vm->flags & VM_KASAN) + vfree(kasan_mem_to_shadow(vm->addr)); } static void register_global(struct kasan_global *global) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9fe07692eaad..b34ef4a32a3b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5232,7 +5232,9 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) * on for the root memcg is enough. */ if (cgroup_on_dfl(root_css->cgroup)) - mem_cgroup_from_css(root_css)->use_hierarchy = true; + root_mem_cgroup->use_hierarchy = true; + else + root_mem_cgroup->use_hierarchy = false; } static u64 memory_current_read(struct cgroup_subsys_state *css, diff --git a/mm/memory.c b/mm/memory.c index 8068893697bb..411144f977b1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3072,8 +3072,13 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * Avoid grouping on DSO/COW pages in specific and RO pages * in general, RO pages shouldn't hurt as much anyway since * they can be in shared cache state. + * + * FIXME! This checks "pmd_dirty()" as an approximation of + * "is this a read-only page", since checking "pmd_write()" + * is even more broken. We haven't actually turned this into + * a writable page, so pmd_write() will always be false. */ - if (!pte_write(pte)) + if (!pte_dirty(pte)) flags |= TNF_NO_GROUP; /* diff --git a/mm/mlock.c b/mm/mlock.c index 73cf0987088c..8a54cd214925 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -26,10 +26,10 @@ int can_do_mlock(void) { - if (capable(CAP_IPC_LOCK)) - return 1; if (rlimit(RLIMIT_MEMLOCK) != 0) return 1; + if (capable(CAP_IPC_LOCK)) + return 1; return 0; } EXPORT_SYMBOL(can_do_mlock); diff --git a/mm/nommu.c b/mm/nommu.c index 3e67e7538ecf..3fba2dc97c44 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -62,6 +62,7 @@ void *high_memory; EXPORT_SYMBOL(high_memory); struct page *mem_map; unsigned long max_mapnr; +EXPORT_SYMBOL(max_mapnr); unsigned long highest_memmap_pfn; struct percpu_counter vm_committed_as; int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7abfa70cdc1a..40e29429e7b0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2373,7 +2373,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; } /* Exhausted what can be done so it's blamo time */ - if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)) + if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false) + || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) *did_some_progress = 1; out: oom_zonelist_unlock(ac->zonelist, gfp_mask); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 35b25e1340ca..49abccf29a29 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1418,6 +1418,7 @@ struct vm_struct *remove_vm_area(const void *addr) spin_unlock(&vmap_area_lock); vmap_debug_free_range(va->va_start, va->va_end); + kasan_free_shadow(vm); free_unmap_vmap_area(va); vm->size -= PAGE_SIZE; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 64c6bed4a3d3..98a30a5b8664 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -413,7 +413,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, vlan_transfer_features(dev, vlandev); break; - case NETDEV_DOWN: + case NETDEV_DOWN: { + struct net_device *tmp; + LIST_HEAD(close_list); + if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); @@ -425,11 +428,18 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) - dev_change_flags(vlandev, flgs & ~IFF_UP); + list_add(&vlandev->close_list, &close_list); + } + + dev_close_many(&close_list, false); + + list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { netif_stacked_transfer_operstate(dev, vlandev); + list_del_init(&vlandev->close_list); } + list_del(&close_list); break; - + } case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index f196552ec3c4..8b5ab9033b41 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -554,6 +554,7 @@ static int vlan_dev_init(struct net_device *dev) if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); + dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE; /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index d8e376a5f0f1..36a1a739ad68 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -658,14 +658,30 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) static void p9_virtio_remove(struct virtio_device *vdev) { struct virtio_chan *chan = vdev->priv; - - if (chan->inuse) - p9_virtio_close(chan->client); - vdev->config->del_vqs(vdev); + unsigned long warning_time; mutex_lock(&virtio_9p_lock); + + /* Remove self from list so we don't get new users. */ list_del(&chan->chan_list); + warning_time = jiffies; + + /* Wait for existing users to close. */ + while (chan->inuse) { + mutex_unlock(&virtio_9p_lock); + msleep(250); + if (time_after(jiffies, warning_time + 10 * HZ)) { + dev_emerg(&vdev->dev, + "p9_virtio_remove: waiting for device in use.\n"); + warning_time = jiffies; + } + mutex_lock(&virtio_9p_lock); + } + mutex_unlock(&virtio_9p_lock); + + vdev->config->del_vqs(vdev); + sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); kfree(chan->tag); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index b087d278c679..1849d96b3c91 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -563,6 +563,8 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) */ del_nbp(p); + dev_set_mtu(br->dev, br_min_mtu(br)); + spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index b260a97275db..f3884a1b942f 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,17 +37,16 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + #include <asm/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif -#define skb_origaddr(skb) (((struct bridge_skb_cb *) \ - (skb->nf_bridge->data))->daddr.ipv4) -#define store_orig_dstaddr(skb) (skb_origaddr(skb) = ip_hdr(skb)->daddr) -#define dnat_took_place(skb) (skb_origaddr(skb) != ip_hdr(skb)->daddr) - #ifdef CONFIG_SYSCTL static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables __read_mostly = 1; @@ -154,6 +153,18 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) return nf_bridge; } +static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) +{ + switch (skb->protocol) { + case __cpu_to_be16(ETH_P_8021Q): + return VLAN_HLEN; + case __cpu_to_be16(ETH_P_PPP_SES): + return PPPOE_SES_HLEN; + default: + return 0; + } +} + static inline void nf_bridge_push_encap_header(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); @@ -322,6 +333,22 @@ free_skb: return 0; } +static bool dnat_took_place(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || nf_ct_is_untracked(ct)) + return false; + + return test_bit(IPS_DST_NAT_BIT, &ct->status); +#else + return false; +#endif +} + /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * @@ -625,7 +652,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_DROP; if (!setup_pre_routing(skb)) return NF_DROP; - store_orig_dstaddr(skb); + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, @@ -721,8 +748,6 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb)) return NF_DROP; - /* The physdev module checks on this */ - nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; if (pf == NFPROTO_IPV4) skb->protocol = htons(ETH_P_IP); @@ -842,7 +867,12 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, struct net_device *realoutdev = bridge_parent(skb->dev); u_int8_t pf; - if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED)) + /* if nf_bridge is set, but ->physoutdev is NULL, this packet came in + * on a bridge, but was delivered locally and is now being routed: + * + * POST_ROUTING was already invoked from the ip stack. + */ + if (!nf_bridge || !nf_bridge->physoutdev) return NF_ACCEPT; if (!realoutdev) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 8bc6b67457dc..e1115a224a95 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -733,6 +733,9 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, + [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, + [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, + [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -762,6 +765,24 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return err; } + if (data[IFLA_BR_AGEING_TIME]) { + u32 ageing_time = nla_get_u32(data[IFLA_BR_AGEING_TIME]); + + br->ageing_time = clock_t_to_jiffies(ageing_time); + } + + if (data[IFLA_BR_STP_STATE]) { + u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); + + br_stp_set_enabled(br, stp_enabled); + } + + if (data[IFLA_BR_PRIORITY]) { + u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); + + br_stp_set_bridge_priority(br, priority); + } + return 0; } @@ -770,6 +791,9 @@ static size_t br_get_size(const struct net_device *brdev) return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ + nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ 0; } @@ -779,10 +803,16 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); + u32 ageing_time = jiffies_to_clock_t(br->ageing_time); + u32 stp_enabled = br->stp_enabled; + u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || - nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time)) + nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || + nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || + nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || + nla_put_u16(skb, IFLA_BR_PRIORITY, priority)) return -EMSGSIZE; return 0; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index b6bf51bb187d..4ec0c803aef1 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -281,7 +281,7 @@ static int caif_seqpkt_recvmsg(struct socket *sock, struct msghdr *m, int copylen; ret = -EOPNOTSUPP; - if (m->msg_flags&MSG_OOB) + if (flags & MSG_OOB) goto read_error; skb = skb_recv_datagram(sk, flags, 0 , &ret); diff --git a/net/compat.c b/net/compat.c index 478443182bbe..c4b6b0f43d5d 100644 --- a/net/compat.c +++ b/net/compat.c @@ -49,6 +49,13 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg, __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + + if (!uaddr) + kmsg->msg_namelen = 0; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_control = compat_ptr(tmp3); @@ -72,6 +79,8 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg, if (nr_segs > UIO_MAXIOV) return -EMSGSIZE; + kmsg->msg_iocb = NULL; + err = compat_rw_copy_check_uvector(save_addr ? READ : WRITE, compat_ptr(uiov), nr_segs, UIO_FASTIOV, *iov, iov); diff --git a/net/core/dev.c b/net/core/dev.c index 39fe369b46ad..3a06003ecafd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1385,7 +1385,7 @@ static int __dev_close(struct net_device *dev) return retval; } -static int dev_close_many(struct list_head *head) +int dev_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; @@ -1399,11 +1399,13 @@ static int dev_close_many(struct list_head *head) list_for_each_entry_safe(dev, tmp, head, close_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); call_netdevice_notifiers(NETDEV_DOWN, dev); - list_del_init(&dev->close_list); + if (unlink) + list_del_init(&dev->close_list); } return 0; } +EXPORT_SYMBOL(dev_close_many); /** * dev_close - shutdown an interface. @@ -1420,7 +1422,7 @@ int dev_close(struct net_device *dev) LIST_HEAD(single); list_add(&dev->close_list, &single); - dev_close_many(&single); + dev_close_many(&single, true); list_del(&single); } return 0; @@ -1694,6 +1696,7 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) } skb_scrub_packet(skb, true); + skb->priority = 0; skb->protocol = eth_type_trans(skb, dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -2559,12 +2562,26 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, return features; } +netdev_features_t passthru_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + return features; +} +EXPORT_SYMBOL(passthru_features_check); + +static netdev_features_t dflt_features_check(const struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + return vlan_features_check(skb, features); +} + netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; u16 gso_segs = skb_shinfo(skb)->gso_segs; - __be16 protocol = skb->protocol; if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs) features &= ~NETIF_F_GSO_MASK; @@ -2576,34 +2593,17 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) if (skb->encapsulation) features &= dev->hw_enc_features; - if (!skb_vlan_tag_present(skb)) { - if (unlikely(protocol == htons(ETH_P_8021Q) || - protocol == htons(ETH_P_8021AD))) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - } else { - goto finalize; - } - } - - features = netdev_intersect_features(features, - dev->vlan_features | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX); - - if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) + if (skb_vlan_tagged(skb)) features = netdev_intersect_features(features, - NETIF_F_SG | - NETIF_F_HIGHDMA | - NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | + dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); -finalize: if (dev->netdev_ops->ndo_features_check) features &= dev->netdev_ops->ndo_features_check(skb, dev, features); + else + features &= dflt_features_check(skb, dev, features); return harmonize_features(skb, features); } @@ -5912,6 +5912,24 @@ int dev_get_phys_port_id(struct net_device *dev, EXPORT_SYMBOL(dev_get_phys_port_id); /** + * dev_get_phys_port_name - Get device physical port name + * @dev: device + * @name: port name + * + * Get device physical port name + */ +int dev_get_phys_port_name(struct net_device *dev, + char *name, size_t len) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_get_phys_port_name) + return -EOPNOTSUPP; + return ops->ndo_get_phys_port_name(dev, name, len); +} +EXPORT_SYMBOL(dev_get_phys_port_name); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * @@ -5968,7 +5986,7 @@ static void rollback_registered_many(struct list_head *head) /* If device is running, close it first. */ list_for_each_entry(dev, head, unreg_list) list_add_tail(&dev->close_list, &close_head); - dev_close_many(&close_head); + dev_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ diff --git a/net/core/filter.c b/net/core/filter.c index 7a4eb7030dba..444a07e4f68d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -150,10 +150,62 @@ static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return prandom_u32(); } +static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + + switch (skb_field) { + case SKF_AD_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, mark)); + break; + + case SKF_AD_PKTTYPE: + *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); +#ifdef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); +#endif + break; + + case SKF_AD_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, queue_mapping)); + break; + + case SKF_AD_VLAN_TAG: + case SKF_AD_VLAN_TAG_PRESENT: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + + /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, vlan_tci)); + if (skb_field == SKF_AD_VLAN_TAG) { + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, + ~VLAN_TAG_PRESENT); + } else { + /* dst_reg >>= 12 */ + *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12); + /* dst_reg &= 1 */ + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1); + } + break; + } + + return insn - insn_buf; +} + static bool convert_bpf_extensions(struct sock_filter *fp, struct bpf_insn **insnp) { struct bpf_insn *insn = *insnp; + u32 cnt; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: @@ -167,13 +219,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_PKTTYPE: - *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX, - PKT_TYPE_OFFSET()); - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX); -#ifdef __BIG_ENDIAN_BITFIELD - insn++; - *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 5); -#endif + cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_IFINDEX: @@ -197,10 +244,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - - *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, mark)); + cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_RXHASH: @@ -211,29 +256,30 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); - - *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, queue_mapping)); + cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: + cnt = convert_skb_access(SKF_AD_VLAN_TAG, + BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; + break; + case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, + BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; + break; + + case SKF_AD_OFF + SKF_AD_VLAN_TPID: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); - /* A = *(u16 *) (CTX + offsetof(vlan_tci)) */ + /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, vlan_tci)); - if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, - ~VLAN_TAG_PRESENT); - } else { - /* A >>= 12 */ - *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); - /* A &= 1 */ - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1); - } + offsetof(struct sk_buff, vlan_proto)); + /* A = ntohs(A) [emitting a nop or swap16] */ + *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PAY_OFFSET: @@ -1129,6 +1175,56 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return 0; } +static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + unsigned int offset = (unsigned int) r2; + void *from = (void *) (long) r3; + unsigned int len = (unsigned int) r4; + char buf[16]; + void *ptr; + + /* bpf verifier guarantees that: + * 'from' pointer points to bpf program stack + * 'len' bytes of it were initialized + * 'len' > 0 + * 'skb' is a valid pointer to 'struct sk_buff' + * + * so check for invalid 'offset' and too large 'len' + */ + if (offset > 0xffff || len > sizeof(buf)) + return -EFAULT; + + if (skb_cloned(skb) && !skb_clone_writable(skb, offset + len)) + return -EFAULT; + + ptr = skb_header_pointer(skb, offset, len, buf); + if (unlikely(!ptr)) + return -EFAULT; + + skb_postpull_rcsum(skb, ptr, len); + + memcpy(ptr, from, len); + + if (ptr == buf) + /* skb_store_bits cannot return -EFAULT here */ + skb_store_bits(skb, offset, ptr, len); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(skb->csum, csum_partial(ptr, len, 0)); + return 0; +} + +const struct bpf_func_proto bpf_skb_store_bytes_proto = { + .func = bpf_skb_store_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_STACK, + .arg4_type = ARG_CONST_STACK_SIZE, +}; + static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) { @@ -1139,21 +1235,106 @@ sk_filter_func_proto(enum bpf_func_id func_id) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_get_prandom_u32: + return &bpf_get_prandom_u32_proto; + case BPF_FUNC_get_smp_processor_id: + return &bpf_get_smp_processor_id_proto; default: return NULL; } } +static const struct bpf_func_proto * +tc_cls_act_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_skb_store_bytes: + return &bpf_skb_store_bytes_proto; + default: + return sk_filter_func_proto(func_id); + } +} + static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type) { - /* skb fields cannot be accessed yet */ - return false; + /* only read is allowed */ + if (type != BPF_READ) + return false; + + /* check bounds */ + if (off < 0 || off >= sizeof(struct __sk_buff)) + return false; + + /* disallow misaligned access */ + if (off % size != 0) + return false; + + /* all __sk_buff fields are __u32 */ + if (size != 4) + return false; + + return true; +} + +static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + + switch (ctx_off) { + case offsetof(struct __sk_buff, len): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, len)); + break; + + case offsetof(struct __sk_buff, protocol): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, protocol)); + break; + + case offsetof(struct __sk_buff, vlan_proto): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, vlan_proto)); + break; + + case offsetof(struct __sk_buff, mark): + return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, pkt_type): + return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, queue_mapping): + return convert_skb_access(SKF_AD_QUEUE, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, vlan_present): + return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, + dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, vlan_tci): + return convert_skb_access(SKF_AD_VLAN_TAG, + dst_reg, src_reg, insn); + } + + return insn - insn_buf; } static const struct bpf_verifier_ops sk_filter_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, + .convert_ctx_access = sk_filter_convert_ctx_access, +}; + +static const struct bpf_verifier_ops tc_cls_act_ops = { + .get_func_proto = tc_cls_act_func_proto, + .is_valid_access = sk_filter_is_valid_access, + .convert_ctx_access = sk_filter_convert_ctx_access, }; static struct bpf_prog_type_list sk_filter_type __read_mostly = { @@ -1162,14 +1343,20 @@ static struct bpf_prog_type_list sk_filter_type __read_mostly = { }; static struct bpf_prog_type_list sched_cls_type __read_mostly = { - .ops = &sk_filter_ops, + .ops = &tc_cls_act_ops, .type = BPF_PROG_TYPE_SCHED_CLS, }; +static struct bpf_prog_type_list sched_act_type __read_mostly = { + .ops = &tc_cls_act_ops, + .type = BPF_PROG_TYPE_SCHED_ACT, +}; + static int __init register_sk_filter_ops(void) { bpf_register_prog_type(&sk_filter_type); bpf_register_prog_type(&sched_cls_type); + bpf_register_prog_type(&sched_act_type); return 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0e8b32efc031..3de654256028 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -817,10 +817,9 @@ out: static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES); - if (!(n->nud_state & NUD_PROBE)) - max_probes += NEIGH_VAR(p, MCAST_PROBES); - return max_probes; + return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + + (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) : + NEIGH_VAR(p, MCAST_PROBES)); } static void neigh_invalidate(struct neighbour *neigh) @@ -1742,6 +1741,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) NEIGH_VAR(parms, UCAST_PROBES)) || nla_put_u32(skb, NDTPA_MCAST_PROBES, NEIGH_VAR(parms, MCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_REPROBES, + NEIGH_VAR(parms, MCAST_REPROBES)) || nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, NEIGH_VAR(parms, BASE_REACHABLE_TIME)) || @@ -1901,6 +1902,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_APP_PROBES] = { .type = NLA_U32 }, [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_MCAST_REPROBES] = { .type = NLA_U32 }, [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, @@ -2001,6 +2003,10 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh) NEIGH_VAR_SET(p, MCAST_PROBES, nla_get_u32(tbp[i])); break; + case NDTPA_MCAST_REPROBES: + NEIGH_VAR_SET(p, MCAST_REPROBES, + nla_get_u32(tbp[i])); + break; case NDTPA_BASE_REACHABLE_TIME: NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, nla_get_msecs(tbp[i])); @@ -2987,6 +2993,7 @@ static struct neigh_sysctl_table { NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index cf30620a88e1..cc5cf689809c 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -418,6 +418,28 @@ static ssize_t phys_port_id_show(struct device *dev, } static DEVICE_ATTR_RO(phys_port_id); +static ssize_t phys_port_name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) { + char name[IFNAMSIZ]; + + ret = dev_get_phys_port_name(netdev, name, sizeof(name)); + if (!ret) + ret = sprintf(buf, "%s\n", name); + } + rtnl_unlock(); + + return ret; +} +static DEVICE_ATTR_RO(phys_port_name); + static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -465,6 +487,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_phys_port_id.attr, + &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, NULL, }; @@ -951,6 +974,60 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue, return sprintf(buf, "%lu", trans_timeout); } +#ifdef CONFIG_XPS +static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +{ + struct net_device *dev = queue->dev; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) + if (queue == &dev->_tx[i]) + break; + + BUG_ON(i >= dev->num_tx_queues); + + return i; +} + +static ssize_t show_tx_maxrate(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + char *buf) +{ + return sprintf(buf, "%lu\n", queue->tx_maxrate); +} + +static ssize_t set_tx_maxrate(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct net_device *dev = queue->dev; + int err, index = get_netdev_queue_index(queue); + u32 rate = 0; + + err = kstrtou32(buf, 10, &rate); + if (err < 0) + return err; + + if (!rtnl_trylock()) + return restart_syscall(); + + err = -EOPNOTSUPP; + if (dev->netdev_ops->ndo_set_tx_maxrate) + err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); + + rtnl_unlock(); + if (!err) { + queue->tx_maxrate = rate; + return len; + } + return err; +} + +static struct netdev_queue_attribute queue_tx_maxrate = + __ATTR(tx_maxrate, S_IRUGO | S_IWUSR, + show_tx_maxrate, set_tx_maxrate); +#endif + static struct netdev_queue_attribute queue_trans_timeout = __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL); @@ -1065,18 +1142,6 @@ static struct attribute_group dql_group = { #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS -static unsigned int get_netdev_queue_index(struct netdev_queue *queue) -{ - struct net_device *dev = queue->dev; - unsigned int i; - - i = queue - dev->_tx; - BUG_ON(i >= dev->num_tx_queues); - - return i; -} - - static ssize_t show_xps_map(struct netdev_queue *queue, struct netdev_queue_attribute *attribute, char *buf) { @@ -1153,6 +1218,7 @@ static struct attribute *netdev_queue_default_attrs[] = { &queue_trans_timeout.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, + &queue_tx_maxrate.attr, #endif NULL }; diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 04db318e6218..87b22c0bc08c 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -58,14 +58,14 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, return -ENOMEM; get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); - rwlock_init(&queue->syn_wait_lock); + spin_lock_init(&queue->syn_wait_lock); queue->rskq_accept_head = NULL; lopt->nr_table_entries = nr_table_entries; lopt->max_qlen_log = ilog2(nr_table_entries); - write_lock_bh(&queue->syn_wait_lock); + spin_lock_bh(&queue->syn_wait_lock); queue->listen_opt = lopt; - write_unlock_bh(&queue->syn_wait_lock); + spin_unlock_bh(&queue->syn_wait_lock); return 0; } @@ -81,10 +81,10 @@ static inline struct listen_sock *reqsk_queue_yank_listen_sk( { struct listen_sock *lopt; - write_lock_bh(&queue->syn_wait_lock); + spin_lock_bh(&queue->syn_wait_lock); lopt = queue->listen_opt; queue->listen_opt = NULL; - write_unlock_bh(&queue->syn_wait_lock); + spin_unlock_bh(&queue->syn_wait_lock); return lopt; } @@ -94,21 +94,26 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) /* make all the listen_opt local to us */ struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); - if (lopt->qlen != 0) { + if (listen_sock_qlen(lopt) != 0) { unsigned int i; for (i = 0; i < lopt->nr_table_entries; i++) { struct request_sock *req; + spin_lock_bh(&queue->syn_wait_lock); while ((req = lopt->syn_table[i]) != NULL) { lopt->syn_table[i] = req->dl_next; - lopt->qlen--; - reqsk_free(req); + atomic_inc(&lopt->qlen_dec); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); + reqsk_put(req); } + spin_unlock_bh(&queue->syn_wait_lock); } } - WARN_ON(lopt->qlen != 0); + if (WARN_ON(listen_sock_qlen(lopt) != 0)) + pr_err("qlen %u\n", listen_sock_qlen(lopt)); kvfree(lopt); } @@ -153,24 +158,22 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) * case might also exist in tcp_v4_hnd_req() that will trigger this locking * order. * - * When a TFO req is created, it needs to sock_hold its listener to prevent - * the latter data structure from going away. - * - * This function also sets "treq->listener" to NULL and unreference listener - * socket. treq->listener is used by the listener so it is protected by the + * This function also sets "treq->tfo_listener" to false. + * treq->tfo_listener is used by the listener so it is protected by the * fastopenq->lock in this function. */ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset) { - struct sock *lsk = tcp_rsk(req)->listener; - struct fastopen_queue *fastopenq = - inet_csk(lsk)->icsk_accept_queue.fastopenq; + struct sock *lsk = req->rsk_listener; + struct fastopen_queue *fastopenq; + + fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; - tcp_rsk(req)->listener = NULL; + tcp_rsk(req)->tfo_listener = false; if (req->sk) /* the child socket hasn't been accepted yet */ goto out; @@ -179,8 +182,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, * special RST handling below. */ spin_unlock_bh(&fastopenq->lock); - sock_put(lsk); - reqsk_free(req); + reqsk_put(req); return; } /* Wait for 60secs before removing a req that has triggered RST. @@ -190,7 +192,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, * * For more details see CoNext'11 "TCP Fast Open" paper. */ - req->expires = jiffies + 60*HZ; + req->rsk_timer.expires = jiffies + 60*HZ; if (fastopenq->rskq_rst_head == NULL) fastopenq->rskq_rst_head = req; else @@ -201,5 +203,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, fastopenq->qlen++; out: spin_unlock_bh(&fastopenq->lock); - sock_put(lsk); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 25b4b5d23485..b96ac2109c82 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -982,6 +982,24 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) +{ + char name[IFNAMSIZ]; + int err; + + err = dev_get_phys_port_name(dev, name, sizeof(name)); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name)) + return -EMSGSIZE; + + return 0; +} + static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; @@ -1072,6 +1090,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_phys_port_id_fill(skb, dev)) goto nla_put_failure; + if (rtnl_phys_port_name_fill(skb, dev)) + goto nla_put_failure; + if (rtnl_phys_switch_id_fill(skb, dev)) goto nla_put_failure; @@ -1815,6 +1836,42 @@ errout: return err; } +static int rtnl_group_dellink(const struct net *net, int group) +{ + struct net_device *dev, *aux; + LIST_HEAD(list_kill); + bool found = false; + + if (!group) + return -EPERM; + + for_each_netdev(net, dev) { + if (dev->group == group) { + const struct rtnl_link_ops *ops; + + found = true; + ops = dev->rtnl_link_ops; + if (!ops || !ops->dellink) + return -EOPNOTSUPP; + } + } + + if (!found) + return -ENODEV; + + for_each_netdev_safe(net, dev, aux) { + if (dev->group == group) { + const struct rtnl_link_ops *ops; + + ops = dev->rtnl_link_ops; + ops->dellink(dev, &list_kill); + } + } + unregister_netdevice_many(&list_kill); + + return 0; +} + static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); @@ -1838,6 +1895,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) dev = __dev_get_by_index(net, ifm->ifi_index); else if (tb[IFLA_IFNAME]) dev = __dev_get_by_name(net, ifname); + else if (tb[IFLA_GROUP]) + return rtnl_group_dellink(net, nla_get_u32(tb[IFLA_GROUP])); else return -EINVAL; @@ -2166,28 +2225,28 @@ replay: } } err = rtnl_configure_link(dev, ifm); - if (err < 0) { - if (ops->newlink) { - LIST_HEAD(list_kill); - - ops->dellink(dev, &list_kill); - unregister_netdevice_many(&list_kill); - } else { - unregister_netdevice(dev); - } - goto out; - } - + if (err < 0) + goto out_unregister; if (link_net) { err = dev_change_net_namespace(dev, dest_net, ifname); if (err < 0) - unregister_netdevice(dev); + goto out_unregister; } out: if (link_net) put_net(link_net); put_net(dest_net); return err; +out_unregister: + if (ops->newlink) { + LIST_HEAD(list_kill); + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + } else { + unregister_netdevice(dev); + } + goto out; } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 47c32413d5b9..cdb939b731aa 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3689,9 +3689,13 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, struct sock *sk, int tstype) { struct sk_buff *skb; - bool tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; + bool tsonly; - if (!sk || !skb_may_tx_timestamp(sk, tsonly)) + if (!sk) + return; + + tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; + if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) @@ -4129,7 +4133,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->ignore_df = 0; skb_dst_drop(skb); skb->mark = 0; - skb->sender_cpu = 0; + skb_sender_cpu_clear(skb); skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); diff --git a/net/core/sock.c b/net/core/sock.c index 4bc42efb3e40..119ae464b44a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -928,8 +928,6 @@ set_rcvbuf: sk->sk_mark = val; break; - /* We implement the SO_SNDLOWAT etc to - not be settable (1003.1g 5.3) */ case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; @@ -1234,6 +1232,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; default: + /* We implement the SO_SNDLOWAT etc to not be settable + * (1003.1g 7). + */ return -ENOPROTOOPT; } @@ -1454,8 +1455,8 @@ void sk_release_kernel(struct sock *sk) return; sock_hold(sk); - sock_release(sk->sk_socket); sock_net_set(sk, get_net(&init_net)); + sock_release(sk->sk_socket); sock_put(sk); } EXPORT_SYMBOL(sk_release_kernel); @@ -1655,27 +1656,16 @@ void sock_rfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_rfree); +/* + * Buffer destructor for skbs that are not used directly in read or write + * path, e.g. for error handler skbs. Automatically called from kfree_skb. + */ void sock_efree(struct sk_buff *skb) { sock_put(skb->sk); } EXPORT_SYMBOL(sock_efree); -#ifdef CONFIG_INET -void sock_edemux(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - if (sk->sk_state == TCP_TIME_WAIT) - inet_twsk_put(inet_twsk(sk)); - else if (sk->sk_state == TCP_NEW_SYN_RECV) - reqsk_put(inet_reqsk(sk)); - else - sock_put(sk); -} -EXPORT_SYMBOL(sock_edemux); -#endif - kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; @@ -2754,7 +2744,7 @@ static int req_prot_init(const struct proto *prot) rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, - SLAB_HWCACHE_ALIGN, NULL); + 0, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 433424804284..95b6139d710c 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -24,7 +24,8 @@ static int zero = 0; static int one = 1; -static int ushort_max = USHRT_MAX; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -237,7 +238,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_max", @@ -245,7 +246,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "wmem_default", @@ -253,7 +254,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_default", @@ -261,7 +262,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "dev_weight", @@ -401,7 +402,6 @@ static struct ctl_table netns_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .extra1 = &zero, - .extra2 = &ushort_max, .proc_handler = proc_dointvec_minmax }, { } diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 3b1d64d6e093..bebc735f5afc 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -280,8 +280,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev); + struct request_sock *req); int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); @@ -318,6 +317,7 @@ int inet_dccp_listen(struct socket *sock, int backlog); unsigned int dccp_poll(struct file *file, struct socket *sock, poll_table *wait); int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +void dccp_req_err(struct sock *sk, u64 seq); struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb); int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 7f6456afbaec..2b4f21d34df6 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -89,10 +89,9 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (inet->inet_saddr == 0) inet->inet_saddr = fl4->saddr; - inet->inet_rcv_saddr = inet->inet_saddr; - + sk_rcv_saddr_set(sk, inet->inet_saddr); inet->inet_dport = usin->sin_port; - inet->inet_daddr = daddr; + sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) @@ -196,6 +195,32 @@ static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk) dst->ops->redirect(dst, sk, skb); } +void dccp_req_err(struct sock *sk, u64 seq) + { + struct request_sock *req = inet_reqsk(sk); + struct net *net = sock_net(sk); + + /* + * ICMPs are not backlogged, hence we cannot get an established + * socket here. + */ + WARN_ON(req->sk); + + if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); + reqsk_put(req); + } else { + /* + * Still in RESPOND, just remove it silently. + * There is no good way to pass the error to the newly + * created socket, and POSIX does not want network + * errors returned from accept(). + */ + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + } +} +EXPORT_SYMBOL(dccp_req_err); + /* * This routine is called by the ICMP module when it gets some sort of error * condition. If err < 0 then the socket should be closed and the error @@ -228,10 +253,11 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) return; } - sk = inet_lookup(net, &dccp_hashinfo, - iph->daddr, dh->dccph_dport, - iph->saddr, dh->dccph_sport, inet_iif(skb)); - if (sk == NULL) { + sk = __inet_lookup_established(net, &dccp_hashinfo, + iph->daddr, dh->dccph_dport, + iph->saddr, ntohs(dh->dccph_sport), + inet_iif(skb)); + if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } @@ -240,6 +266,9 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) inet_twsk_put(inet_twsk(sk)); return; } + seq = dccp_hdr_seq(dh); + if (sk->sk_state == DCCP_NEW_SYN_RECV) + return dccp_req_err(sk, seq); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy @@ -252,7 +281,6 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) goto out; dp = dccp_sk(sk); - seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); @@ -289,35 +317,6 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) } switch (sk->sk_state) { - struct request_sock *req , **prev; - case DCCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - req = inet_csk_search_req(sk, &prev, dh->dccph_dport, - iph->daddr, iph->saddr); - if (!req) - goto out; - - /* - * ICMPs are not backlogged, hence we cannot get an established - * socket here. - */ - WARN_ON(req->sk); - - if (!between48(seq, dccp_rsk(req)->dreq_iss, - dccp_rsk(req)->dreq_gss)) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - /* - * Still in RESPOND, just remove it silently. - * There is no good way to pass the error to the newly - * created socket, and POSIX does not want network - * errors returned from accept(). - */ - inet_csk_reqsk_queue_drop(sk, req, prev); - goto out; - case DCCP_REQUESTING: case DCCP_RESPOND: if (!sock_owned_by_user(sk)) { @@ -408,8 +407,8 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->inet_daddr = ireq->ir_rmt_addr; - newinet->inet_rcv_saddr = ireq->ir_loc_addr; + sk_daddr_set(newsk, ireq->ir_rmt_addr); + sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newinet->inet_saddr = ireq->ir_loc_addr; newinet->inet_opt = ireq->opt; ireq->opt = NULL; @@ -449,14 +448,14 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) const struct dccp_hdr *dh = dccp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); struct sock *nsk; - struct request_sock **prev; /* Find possible connection requests. */ - struct request_sock *req = inet_csk_search_req(sk, &prev, - dh->dccph_sport, + struct request_sock *req = inet_csk_search_req(sk, dh->dccph_sport, iph->saddr, iph->daddr); - if (req != NULL) - return dccp_check_req(sk, skb, req, prev); - + if (req) { + nsk = dccp_check_req(sk, skb, req); + reqsk_put(req); + return nsk; + } nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo, iph->saddr, dh->dccph_sport, iph->daddr, dh->dccph_dport, @@ -575,7 +574,7 @@ static void dccp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } -void dccp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +void dccp_syn_ack_timeout(const struct request_sock *req) { } EXPORT_SYMBOL(dccp_syn_ack_timeout); @@ -624,7 +623,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = inet_reqsk_alloc(&dccp_request_sock_ops); + req = inet_reqsk_alloc(&dccp_request_sock_ops, sk); if (req == NULL) goto drop; @@ -639,9 +638,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; ireq = inet_rsk(req); - ireq->ir_loc_addr = ip_hdr(skb)->daddr; - ireq->ir_rmt_addr = ip_hdr(skb)->saddr; - write_pnet(&ireq->ireq_net, sock_net(sk)); + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); ireq->ireq_family = AF_INET; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5166b0043f95..9d0551092c6c 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -40,19 +40,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped; static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; -static void dccp_v6_hash(struct sock *sk) -{ - if (sk->sk_state != DCCP_CLOSED) { - if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) { - inet_hash(sk); - return; - } - local_bh_disable(); - __inet6_hash(sk, NULL); - local_bh_enable(); - } -} - /* add pseudo-header to DCCP checksum stored in skb->csum */ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, const struct in6_addr *saddr, @@ -98,11 +85,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; } - sk = inet6_lookup(net, &dccp_hashinfo, - &hdr->daddr, dh->dccph_dport, - &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); + sk = __inet6_lookup_established(net, &dccp_hashinfo, + &hdr->daddr, dh->dccph_dport, + &hdr->saddr, ntohs(dh->dccph_sport), + inet6_iif(skb)); - if (sk == NULL) { + if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; @@ -112,6 +100,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, inet_twsk_put(inet_twsk(sk)); return; } + seq = dccp_hdr_seq(dh); + if (sk->sk_state == DCCP_NEW_SYN_RECV) + return dccp_req_err(sk, seq); bh_lock_sock(sk); if (sock_owned_by_user(sk)) @@ -121,7 +112,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; dp = dccp_sk(sk); - seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); @@ -162,32 +152,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; - case DCCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, - &hdr->daddr, &hdr->saddr, - inet6_iif(skb)); - if (req == NULL) - goto out; - - /* - * ICMPs are not backlogged, hence we cannot get an established - * socket here. - */ - WARN_ON(req->sk != NULL); - - if (!between48(seq, dccp_rsk(req)->dreq_iss, - dccp_rsk(req)->dreq_gss)) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - - inet_csk_reqsk_queue_drop(sk, req, prev); - goto out; - case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ @@ -330,17 +294,16 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); const struct ipv6hdr *iph = ipv6_hdr(skb); + struct request_sock *req; struct sock *nsk; - struct request_sock **prev; - /* Find possible connection requests. */ - struct request_sock *req = inet6_csk_search_req(sk, &prev, - dh->dccph_sport, - &iph->saddr, - &iph->daddr, - inet6_iif(skb)); - if (req != NULL) - return dccp_check_req(sk, skb, req, prev); + req = inet6_csk_search_req(sk, dh->dccph_sport, &iph->saddr, + &iph->daddr, inet6_iif(skb)); + if (req) { + nsk = dccp_check_req(sk, skb, req); + reqsk_put(req); + return nsk; + } nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, &iph->saddr, dh->dccph_sport, &iph->daddr, ntohs(dh->dccph_dport), @@ -386,7 +349,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = inet_reqsk_alloc(&dccp6_request_sock_ops); + req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk); if (req == NULL) goto drop; @@ -403,7 +366,6 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - write_pnet(&ireq->ireq_net, sock_net(sk)); ireq->ireq_family = AF_INET6; if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || @@ -471,11 +433,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); - - ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - - newsk->sk_v6_rcv_saddr = newnp->saddr; + newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; newsk->sk_backlog_rcv = dccp_v4_do_rcv; @@ -593,7 +551,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, dccp_done(newsk); goto out; } - __inet6_hash(newsk, NULL); + __inet_hash(newsk, NULL); return newsk; @@ -918,9 +876,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_backlog_rcv = dccp_v6_do_rcv; goto failure; } - ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr); - + np->saddr = sk->sk_v6_rcv_saddr; return err; } @@ -1063,7 +1019,7 @@ static struct proto dccp_v6_prot = { .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v6_do_rcv, - .hash = dccp_v6_hash, + .hash = inet_hash, .unhash = inet_unhash, .accept = inet_csk_accept, .get_port = inet_csk_get_port, diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index b50dc436db1f..332f7d6d9942 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -152,8 +152,7 @@ EXPORT_SYMBOL_GPL(dccp_create_openreq_child); * as an request_sock. */ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { struct sock *child = NULL; struct dccp_request_sock *dreq = dccp_rsk(req); @@ -200,7 +199,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, if (child == NULL) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); inet_csk_reqsk_queue_add(sk, req, child); out: @@ -212,7 +211,7 @@ drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); goto out; } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 1cd46a345cb0..3ef7acef3ce8 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -161,33 +161,11 @@ out: sock_put(sk); } -/* - * Timer for listening sockets - */ -static void dccp_response_timer(struct sock *sk) -{ - inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, DCCP_TIMEOUT_INIT, - DCCP_RTO_MAX); -} - static void dccp_keepalive_timer(unsigned long data) { struct sock *sk = (struct sock *)data; - /* Only process if socket is not in use. */ - bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - /* Try again later. */ - inet_csk_reset_keepalive_timer(sk, HZ / 20); - goto out; - } - - if (sk->sk_state == DCCP_LISTEN) { - dccp_response_timer(sk); - goto out; - } -out: - bh_unlock_sock(sk); + pr_err("dccp should not use a keepalive timer !\n"); sock_put(sk); } diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index b45206e8dd3e..ff7736f7ff42 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -5,10 +5,12 @@ config HAVE_NET_DSA # Drivers must select NET_DSA and the appropriate tagging format config NET_DSA - tristate - depends on HAVE_NET_DSA + tristate "Distributed Switch Architecture" + depends on HAVE_NET_DSA && NET_SWITCHDEV select PHYLIB - select NET_SWITCHDEV + ---help--- + Say Y if you want to enable support for the hardware switches supported + by the Distributed Switch Architecture. if NET_DSA diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6511552039d6..3597724ec3d8 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -16,6 +16,7 @@ #include <linux/of_net.h> #include <linux/of_mdio.h> #include <net/rtnetlink.h> +#include <net/switchdev.h> #include <linux/if_bridge.h> #include "dsa_priv.h" @@ -200,6 +201,105 @@ out: return 0; } +static int dsa_slave_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, u16 nlm_flags) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + if (ds->drv->fdb_add) + ret = ds->drv->fdb_add(ds, p->port, addr, vid); + + return ret; +} + +static int dsa_slave_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + if (ds->drv->fdb_del) + ret = ds->drv->fdb_del(ds, p->port, addr, vid); + + return ret; +} + +static int dsa_slave_fill_info(struct net_device *dev, struct sk_buff *skb, + const unsigned char *addr, u16 vid, + bool is_static, + u32 portid, u32 seq, int type, + unsigned int flags) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = NTF_EXT_LEARNED; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dev->ifindex; + ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; + + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + goto nla_put_failure; + + if (vid && nla_put_u16(skb, NDA_VLAN, vid)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +/* Dump information about entries, in response to GETNEIGH */ +static int dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, + struct net_device *filter_dev, int idx) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + unsigned char addr[ETH_ALEN] = { 0 }; + int ret; + + if (!ds->drv->fdb_getnext) + return -EOPNOTSUPP; + + for (; ; idx++) { + bool is_static; + + ret = ds->drv->fdb_getnext(ds, p->port, addr, &is_static); + if (ret < 0) + break; + + if (idx < cb->args[0]) + continue; + + ret = dsa_slave_fill_info(dev, skb, addr, 0, + is_static, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, NLM_F_MULTI); + if (ret < 0) + break; + } + + return idx; +} + static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -571,9 +671,15 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, + .ndo_fdb_add = dsa_slave_fdb_add, + .ndo_fdb_del = dsa_slave_fdb_del, + .ndo_fdb_dump = dsa_slave_fdb_dump, .ndo_do_ioctl = dsa_slave_ioctl, - .ndo_switch_parent_id_get = dsa_slave_parent_id_get, - .ndo_switch_port_stp_update = dsa_slave_stp_update, +}; + +static const struct swdev_ops dsa_slave_swdev_ops = { + .swdev_parent_id_get = dsa_slave_parent_id_get, + .swdev_port_stp_update = dsa_slave_stp_update, }; static void dsa_slave_adjust_link(struct net_device *dev) @@ -755,6 +861,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, eth_hw_addr_inherit(slave_dev, master); slave_dev->tx_queue_len = 0; slave_dev->netdev_ops = &dsa_slave_netdev_ops; + slave_dev->swdev_ops = &dsa_slave_swdev_ops; SET_NETDEV_DEV(slave_dev, parent); slave_dev->dev.of_node = ds->pd->port_dn[port]; @@ -825,12 +932,13 @@ static bool dsa_slave_dev_check(struct net_device *dev) static int dsa_slave_master_changed(struct net_device *dev) { struct net_device *master = netdev_master_upper_dev_get(dev); + struct dsa_slave_priv *p = netdev_priv(dev); int err = 0; if (master && master->rtnl_link_ops && !strcmp(master->rtnl_link_ops->kind, "bridge")) err = dsa_slave_bridge_port_join(dev, master); - else + else if (dsa_port_is_bridged(p)) err = dsa_slave_bridge_port_leave(dev); return err; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5105759e4e00..975ee5e30c64 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -107,7 +107,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; -static u32 inet_addr_hash(struct net *net, __be32 addr) +static u32 inet_addr_hash(const struct net *net, __be32 addr) { u32 val = (__force u32) addr ^ net_hash_mix(net); @@ -560,9 +560,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) lock_sock(sk); if (join) - ret = __ip_mc_join_group(sk, &mreq); + ret = ip_mc_join_group(sk, &mreq); else - ret = __ip_mc_leave_group(sk, &mreq); + ret = ip_mc_leave_group(sk, &mreq); release_sock(sk); return ret; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e3b4aee4244e..2c7c299ee2b9 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -830,7 +830,7 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn) /* Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. */ - while (should_inflate(tp, tn) && max_work--) { + while (should_inflate(tp, tn) && max_work) { tp = inflate(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS @@ -839,17 +839,21 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn) break; } + max_work--; tn = get_child(tp, cindex); } + /* update parent in case inflate failed */ + tp = node_parent(tn); + /* Return if at least one inflate is run */ if (max_work != MAX_WORK) - return node_parent(tn); + return tp; /* Halve as long as the number of empty children in this * node is above threshold. */ - while (should_halve(tp, tn) && max_work--) { + while (should_halve(tp, tn) && max_work) { tp = halve(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS @@ -858,6 +862,7 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn) break; } + max_work--; tn = get_child(tp, cindex); } @@ -865,7 +870,7 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn) if (should_collapse(tn)) return collapse(t, tn); - /* update parent in case inflate or halve failed */ + /* update parent in case halve failed */ tp = node_parent(tn); /* Return if at least one deflate was run */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 5cb1ef4ce292..ad09213ac5b2 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -370,7 +370,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -1850,7 +1850,10 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) pmc->sfcount[MCAST_EXCLUDE] = 1; } -int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) +/* Join a multicast group + */ + +int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; @@ -1898,20 +1901,6 @@ int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) done: return err; } -EXPORT_SYMBOL(__ip_mc_join_group); - -/* Join a multicast group - */ -int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) -{ - int ret; - - rtnl_lock(); - ret = __ip_mc_join_group(sk, imr); - rtnl_unlock(); - - return ret; -} EXPORT_SYMBOL(ip_mc_join_group); static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, @@ -1934,7 +1923,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, return err; } -int __ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) +int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; @@ -1979,18 +1968,6 @@ int __ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) out: return ret; } -EXPORT_SYMBOL(__ip_mc_leave_group); - -int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) -{ - int ret; - - rtnl_lock(); - ret = __ip_mc_leave_group(sk, imr); - rtnl_unlock(); - - return ret; -} EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct @@ -2010,7 +1987,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (!ipv4_is_multicast(addr)) return -EINVAL; - rtnl_lock(); + ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; @@ -2124,9 +2101,8 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: - rtnl_unlock(); if (leavegroup) - return ip_mc_leave_group(sk, &imr); + err = ip_mc_leave_group(sk, &imr); return err; } @@ -2148,7 +2124,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; - rtnl_lock(); + ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; @@ -2210,7 +2186,6 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) pmc->sfmode = msf->imsf_fmode; err = 0; done: - rtnl_unlock(); if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 34581f928afa..79c0c9439fdc 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -23,6 +23,7 @@ #include <net/route.h> #include <net/tcp_states.h> #include <net/xfrm.h> +#include <net/tcp.h> #ifdef INET_CSK_DEBUG const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; @@ -268,6 +269,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) release_sock(sk); if (reqsk_queue_empty(&icsk->icsk_accept_queue)) timeo = schedule_timeout(timeo); + sched_annotate_sleep(); lock_sock(sk); err = 0; if (!reqsk_queue_empty(&icsk->icsk_accept_queue)) @@ -293,8 +295,8 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; - struct sock *newsk; struct request_sock *req; + struct sock *newsk; int error; lock_sock(sk); @@ -323,9 +325,11 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) newsk = req->sk; sk_acceptq_removed(sk); - if (sk->sk_protocol == IPPROTO_TCP && queue->fastopenq != NULL) { + if (sk->sk_protocol == IPPROTO_TCP && + tcp_rsk(req)->tfo_listener && + queue->fastopenq) { spin_lock_bh(&queue->fastopenq->lock); - if (tcp_rsk(req)->listener) { + if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to * NULL to signify that the child socket is taken @@ -340,7 +344,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) out: release_sock(sk); if (req) - __reqsk_free(req); + reqsk_put(req); return newsk; out_err: newsk = NULL; @@ -399,18 +403,17 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, const struct request_sock *req) { - struct rtable *rt; const struct inet_request_sock *ireq = inet_rsk(req); - struct ip_options_rcu *opt = inet_rsk(req)->opt; - struct net *net = sock_net(sk); - int flags = inet_sk_flowi_flags(sk); + struct net *net = read_pnet(&ireq->ireq_net); + struct ip_options_rcu *opt = ireq->opt; + struct rtable *rt; - flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark, + flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, - sk->sk_protocol, - flags, + sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, - ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport); + ireq->ir_loc_addr, ireq->ir_rmt_port, + htons(ireq->ir_num)); security_req_classify_flow(req, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) @@ -432,9 +435,9 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); + struct net *net = read_pnet(&ireq->ireq_net); struct inet_sock *newinet = inet_sk(newsk); struct ip_options_rcu *opt; - struct net *net = sock_net(sk); struct flowi4 *fl4; struct rtable *rt; @@ -442,11 +445,12 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, rcu_read_lock(); opt = rcu_dereference(newinet->inet_opt); - flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark, + flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, - ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport); + ireq->ir_loc_addr, ireq->ir_rmt_port, + htons(ireq->ir_num)); security_req_classify_flow(req, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) @@ -474,33 +478,37 @@ static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport, #if IS_ENABLED(CONFIG_IPV6) #define AF_INET_FAMILY(fam) ((fam) == AF_INET) #else -#define AF_INET_FAMILY(fam) 1 +#define AF_INET_FAMILY(fam) true #endif -struct request_sock *inet_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, - const __be16 rport, const __be32 raddr, +/* Note: this is temporary : + * req sock will no longer be in listener hash table +*/ +struct request_sock *inet_csk_search_req(struct sock *sk, + const __be16 rport, + const __be32 raddr, const __be32 laddr) { - const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; + struct request_sock *req; + u32 hash = inet_synq_hash(raddr, rport, lopt->hash_rnd, + lopt->nr_table_entries); - for (prev = &lopt->syn_table[inet_synq_hash(raddr, rport, lopt->hash_rnd, - lopt->nr_table_entries)]; - (req = *prev) != NULL; - prev = &req->dl_next) { + spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); + for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) { const struct inet_request_sock *ireq = inet_rsk(req); if (ireq->ir_rmt_port == rport && ireq->ir_rmt_addr == raddr && ireq->ir_loc_addr == laddr && AF_INET_FAMILY(req->rsk_ops->family)) { + atomic_inc(&req->rsk_refcnt); WARN_ON(req->sk); - *prevp = prev; break; } } + spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); return req; } @@ -556,23 +564,24 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); -void inet_csk_reqsk_queue_prune(struct sock *parent, - const unsigned long interval, - const unsigned long timeout, - const unsigned long max_rto) +static void reqsk_timer_handler(unsigned long data) { - struct inet_connection_sock *icsk = inet_csk(parent); + struct request_sock *req = (struct request_sock *)data; + struct sock *sk_listener = req->rsk_listener; + struct inet_connection_sock *icsk = inet_csk(sk_listener); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct listen_sock *lopt = queue->listen_opt; - int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; - int thresh = max_retries; - unsigned long now = jiffies; - struct request_sock **reqp, *req; - int i, budget; + int qlen, expire = 0, resend = 0; + int max_retries, thresh; + u8 defer_accept; - if (lopt == NULL || lopt->qlen == 0) + if (sk_listener->sk_state != TCP_LISTEN || !lopt) { + reqsk_put(req); return; + } + max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + thresh = max_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means @@ -590,67 +599,65 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ - if (lopt->qlen>>(lopt->max_qlen_log-1)) { - int young = (lopt->qlen_young<<1); + qlen = listen_sock_qlen(lopt); + if (qlen >> (lopt->max_qlen_log - 1)) { + int young = listen_sock_young(lopt) << 1; while (thresh > 2) { - if (lopt->qlen < young) + if (qlen < young) break; thresh--; young <<= 1; } } + defer_accept = READ_ONCE(queue->rskq_defer_accept); + if (defer_accept) + max_retries = defer_accept; + syn_ack_recalc(req, thresh, max_retries, defer_accept, + &expire, &resend); + req->rsk_ops->syn_ack_timeout(req); + if (!expire && + (!resend || + !inet_rtx_syn_ack(sk_listener, req) || + inet_rsk(req)->acked)) { + unsigned long timeo; + + if (req->num_timeout++ == 0) + atomic_inc(&lopt->young_dec); + timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); + mod_timer_pinned(&req->rsk_timer, jiffies + timeo); + return; + } + inet_csk_reqsk_queue_drop(sk_listener, req); + reqsk_put(req); +} - if (queue->rskq_defer_accept) - max_retries = queue->rskq_defer_accept; - - budget = 2 * (lopt->nr_table_entries / (timeout / interval)); - i = lopt->clock_hand; - - do { - reqp=&lopt->syn_table[i]; - while ((req = *reqp) != NULL) { - if (time_after_eq(now, req->expires)) { - int expire = 0, resend = 0; - - syn_ack_recalc(req, thresh, max_retries, - queue->rskq_defer_accept, - &expire, &resend); - req->rsk_ops->syn_ack_timeout(parent, req); - if (!expire && - (!resend || - !inet_rtx_syn_ack(parent, req) || - inet_rsk(req)->acked)) { - unsigned long timeo; - - if (req->num_timeout++ == 0) - lopt->qlen_young--; - timeo = min(timeout << req->num_timeout, - max_rto); - req->expires = now + timeo; - reqp = &req->dl_next; - continue; - } - - /* Drop this request */ - inet_csk_reqsk_queue_unlink(parent, req, reqp); - reqsk_queue_removed(queue, req); - reqsk_free(req); - continue; - } - reqp = &req->dl_next; - } +void reqsk_queue_hash_req(struct request_sock_queue *queue, + u32 hash, struct request_sock *req, + unsigned long timeout) +{ + struct listen_sock *lopt = queue->listen_opt; - i = (i + 1) & (lopt->nr_table_entries - 1); + req->num_retrans = 0; + req->num_timeout = 0; + req->sk = NULL; - } while (--budget > 0); + /* before letting lookups find us, make sure all req fields + * are committed to memory and refcnt initialized. + */ + smp_wmb(); + atomic_set(&req->rsk_refcnt, 2); + setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req); + req->rsk_hash = hash; - lopt->clock_hand = i; + spin_lock(&queue->syn_wait_lock); + req->dl_next = lopt->syn_table[hash]; + lopt->syn_table[hash] = req; + spin_unlock(&queue->syn_wait_lock); - if (lopt->qlen) - inet_csk_reset_keepalive_timer(parent, interval); + mod_timer_pinned(&req->rsk_timer, jiffies + timeout); } -EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune); +EXPORT_SYMBOL(reqsk_queue_hash_req); /** * inet_csk_clone_lock - clone an inet socket, and lock its clone @@ -786,8 +793,6 @@ void inet_csk_listen_stop(struct sock *sk) struct request_sock *acc_req; struct request_sock *req; - inet_csk_delete_keepalive_timer(sk); - /* make all the listen_opt local to us */ acc_req = reqsk_queue_yank_acceptq(queue); @@ -817,9 +822,9 @@ void inet_csk_listen_stop(struct sock *sk) percpu_counter_inc(sk->sk_prot->orphan_count); - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->listener) { + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(tcp_sk(child)->fastopen_rsk != req); - BUG_ON(sk != tcp_rsk(req)->listener); + BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if * an inbound pkt destined for child is @@ -828,7 +833,6 @@ void inet_csk_listen_stop(struct sock *sk) * tcp_v4_destroy_sock(). */ tcp_sk(child)->fastopen_rsk = NULL; - sock_put(sk); } inet_csk_destroy_sock(child); @@ -837,7 +841,7 @@ void inet_csk_listen_stop(struct sock *sk) sock_put(child); sk_acceptq_removed(sk); - __reqsk_free(req); + reqsk_put(req); } if (queue->fastopenq != NULL) { /* Free all the reqs queued in rskq_rst_head. */ @@ -847,7 +851,7 @@ void inet_csk_listen_stop(struct sock *sk) spin_unlock_bh(&queue->fastopenq->lock); while ((req = acc_req) != NULL) { acc_req = req->dl_next; - __reqsk_free(req); + reqsk_put(req); } } WARN_ON(sk->sk_ack_backlog); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index ac7b5c909fe7..76322c9867d5 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -90,6 +90,20 @@ static void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk) } } +static size_t inet_sk_attr_size(void) +{ + return nla_total_size(sizeof(struct tcp_info)) + + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(sizeof(struct inet_diag_meminfo)) + + nla_total_size(sizeof(struct inet_diag_msg)) + + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + + nla_total_size(TCP_CA_NAME_MAX) + + nla_total_size(sizeof(struct tcpvegas_info)) + + 64; +} + int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, @@ -113,14 +127,13 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, return -EMSGSIZE; r = nlmsg_data(nlh); - BUG_ON((1 << sk->sk_state) & (TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV)); + BUG_ON(!sk_fullsock(sk)); inet_diag_msg_common_fill(r, sk); r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; - if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) goto errout; @@ -229,7 +242,6 @@ static int inet_csk_diag_fill(struct sock *sk, static int inet_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, - const struct inet_diag_req_v2 *req, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { @@ -265,6 +277,39 @@ static int inet_twsk_diag_fill(struct sock *sk, return 0; } +static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, + u32 portid, u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh) +{ + struct inet_diag_msg *r; + struct nlmsghdr *nlh; + long tmo; + + nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), + nlmsg_flags); + if (!nlh) + return -EMSGSIZE; + + r = nlmsg_data(nlh); + inet_diag_msg_common_fill(r, sk); + r->idiag_state = TCP_SYN_RECV; + r->idiag_timer = 1; + r->idiag_retrans = inet_reqsk(sk)->num_retrans; + + BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != + offsetof(struct sock, sk_cookie)); + + tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies; + r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0; + r->idiag_rqueue = 0; + r->idiag_wqueue = 0; + r->idiag_uid = 0; + r->idiag_inode = 0; + + nlmsg_end(skb, nlh); + return 0; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, @@ -272,9 +317,13 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) - return inet_twsk_diag_fill(sk, skb, r, portid, seq, + return inet_twsk_diag_fill(sk, skb, portid, seq, nlmsg_flags, unlh); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return inet_req_diag_fill(sk, skb, portid, seq, + nlmsg_flags, unlh); + return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh); } @@ -314,9 +363,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, if (err) goto out; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + - sizeof(struct tcp_info) + 64, GFP_KERNEL); + rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; @@ -502,7 +549,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry_fill_addrs(&entry, sk); entry.sport = inet->inet_num; entry.dport = ntohs(inet->inet_dport); - entry.userlocks = (sk->sk_state != TCP_TIME_WAIT) ? sk->sk_userlocks : 0; + entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; return inet_diag_bc_run(bc, &entry); } @@ -661,61 +708,6 @@ static void twsk_build_assert(void) #endif } -static int inet_twsk_diag_dump(struct sock *sk, - struct sk_buff *skb, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - const struct nlattr *bc) -{ - twsk_build_assert(); - - if (!inet_diag_bc_sk(bc, sk)) - return 0; - - return inet_twsk_diag_fill(sk, skb, r, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); -} - -static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, - struct request_sock *req, - struct user_namespace *user_ns, - u32 portid, u32 seq, - const struct nlmsghdr *unlh) -{ - const struct inet_request_sock *ireq = inet_rsk(req); - struct inet_diag_msg *r; - struct nlmsghdr *nlh; - long tmo; - - nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), - NLM_F_MULTI); - if (!nlh) - return -EMSGSIZE; - - r = nlmsg_data(nlh); - inet_diag_msg_common_fill(r, (struct sock *)ireq); - r->idiag_state = TCP_SYN_RECV; - r->idiag_timer = 1; - r->idiag_retrans = req->num_retrans; - - BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != - offsetof(struct sock, sk_cookie)); - - tmo = req->expires - jiffies; - if (tmo < 0) - tmo = 0; - - r->idiag_expires = jiffies_to_msecs(tmo); - r->idiag_rqueue = 0; - r->idiag_wqueue = 0; - r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); - r->idiag_inode = 0; - - nlmsg_end(skb, nlh); - return 0; -} - static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, @@ -736,10 +728,10 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, entry.family = sk->sk_family; - read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); lopt = icsk->icsk_accept_queue.listen_opt; - if (!lopt || !lopt->qlen) + if (!lopt || !listen_sock_qlen(lopt)) goto out; if (bc) { @@ -762,17 +754,17 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, if (bc) { /* Note: entry.sport and entry.userlocks are already set */ - entry_fill_addrs(&entry, (struct sock *)req); + entry_fill_addrs(&entry, req_to_sk(req)); entry.dport = ntohs(ireq->ir_rmt_port); if (!inet_diag_bc_run(bc, &entry)) continue; } - err = inet_diag_fill_req(skb, sk, req, - sk_user_ns(NETLINK_CB(cb->skb).sk), + err = inet_req_diag_fill(req_to_sk(req), skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, cb->nlh); + cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb->nlh); if (err < 0) { cb->args[3] = j + 1; cb->args[4] = reqnum; @@ -784,7 +776,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, } out: - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); return err; } @@ -903,10 +895,16 @@ skip_listen_ht: if (r->id.idiag_dport != sk->sk_dport && r->id.idiag_dport) goto next_normal; - if (sk->sk_state == TCP_TIME_WAIT) - res = inet_twsk_diag_dump(sk, skb, cb, r, bc); - else - res = inet_csk_diag_dump(sk, skb, cb, r, bc); + twsk_build_assert(); + + if (!inet_diag_bc_sk(bc, sk)) + goto next_normal; + + res = sk_diag_fill(sk, skb, r, + sk_user_ns(NETLINK_CB(cb->skb).sk), + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->nlh); if (res < 0) { spin_unlock_bh(lock); goto done; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 64401a2fdd33..0fb841b9d834 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -24,9 +24,9 @@ #include <net/secure_seq.h> #include <net/ip.h> -static unsigned int inet_ehashfn(struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +static u32 inet_ehashfn(const struct net *net, const __be32 laddr, + const __u16 lport, const __be32 faddr, + const __be16 fport) { static u32 inet_ehash_secret __read_mostly; @@ -36,17 +36,21 @@ static unsigned int inet_ehashfn(struct net *net, const __be32 laddr, inet_ehash_secret + net_hash_mix(net)); } - -static unsigned int inet_sk_ehashfn(const struct sock *sk) +/* This function handles inet_sock, but also timewait and request sockets + * for IPv4/IPv6. + */ +u32 sk_ehashfn(const struct sock *sk) { - const struct inet_sock *inet = inet_sk(sk); - const __be32 laddr = inet->inet_rcv_saddr; - const __u16 lport = inet->inet_num; - const __be32 faddr = inet->inet_daddr; - const __be16 fport = inet->inet_dport; - struct net *net = sock_net(sk); - - return inet_ehashfn(net, laddr, lport, faddr, fport); +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) + return inet6_ehashfn(sock_net(sk), + &sk->sk_v6_rcv_saddr, sk->sk_num, + &sk->sk_v6_daddr, sk->sk_dport); +#endif + return inet_ehashfn(sock_net(sk), + sk->sk_rcv_saddr, sk->sk_num, + sk->sk_daddr, sk->sk_dport); } /* @@ -269,6 +273,12 @@ void sock_gen_put(struct sock *sk) } EXPORT_SYMBOL_GPL(sock_gen_put); +void sock_edemux(struct sk_buff *skb) +{ + sock_gen_put(skb->sk); +} +EXPORT_SYMBOL(sock_edemux); + struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, @@ -401,13 +411,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; - spinlock_t *lock; struct inet_ehash_bucket *head; + spinlock_t *lock; int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); - sk->sk_hash = inet_sk_ehashfn(sk); + sk->sk_hash = sk_ehashfn(sk); head = inet_ehash_bucket(hashinfo, sk->sk_hash); list = &head->chain; lock = inet_ehash_lockp(hashinfo, sk->sk_hash); @@ -424,15 +434,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); -static void __inet_hash(struct sock *sk) +int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb; - if (sk->sk_state != TCP_LISTEN) { - __inet_hash_nolisten(sk, NULL); - return; - } + if (sk->sk_state != TCP_LISTEN) + return __inet_hash_nolisten(sk, tw); WARN_ON(!sk_unhashed(sk)); ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; @@ -441,13 +449,15 @@ static void __inet_hash(struct sock *sk) __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); spin_unlock(&ilb->lock); + return 0; } +EXPORT_SYMBOL(__inet_hash); void inet_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { local_bh_disable(); - __inet_hash(sk); + __inet_hash(sk, NULL); local_bh_enable(); } } @@ -478,8 +488,7 @@ EXPORT_SYMBOL_GPL(inet_unhash); int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, - struct sock *, __u16, struct inet_timewait_sock **), - int (*hash)(struct sock *sk, struct inet_timewait_sock *twp)) + struct sock *, __u16, struct inet_timewait_sock **)) { struct inet_hashinfo *hinfo = death_row->hashinfo; const unsigned short snum = inet_sk(sk)->inet_num; @@ -549,7 +558,7 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - twrefcnt += hash(sk, tw); + twrefcnt += __inet_hash_nolisten(sk, tw); } if (tw) twrefcnt += inet_twsk_bind_unhash(tw, hinfo); @@ -571,7 +580,7 @@ ok: tb = inet_csk(sk)->icsk_bind_hash; spin_lock_bh(&head->lock); if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - hash(sk, NULL); + __inet_hash_nolisten(sk, NULL); spin_unlock_bh(&head->lock); return 0; } else { @@ -591,7 +600,7 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk), - __inet_check_established, __inet_hash_nolisten); + __inet_check_established); } EXPORT_SYMBOL_GPL(inet_hash_connect); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 86ebf020925b..f38e387448fb 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -487,6 +487,7 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; restart_rcu: + cond_resched(); rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 787b3c294ce6..d9bc28ac5d1b 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -67,6 +67,7 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + skb_sender_cpu_clear(skb); return dst_output(skb); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a7aea2048a0d..8259e777b249 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(skb, sk); + ip_select_ident(sock_net(sk), skb, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -430,7 +430,8 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); + ip_select_ident_segs(sock_net(sk), skb, sk, + skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; @@ -636,10 +637,7 @@ slow_path: left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ - /* for bridged IP traffic encapsulated inside f.e. a vlan header, - * we need to make room for the encapsulating header - */ - ll_rs = LL_RESERVED_SPACE_EXTRA(rt->dst.dev, nf_bridge_pad(skb)); + ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* * Fragment the datagram. @@ -1382,7 +1380,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(skb, sk); + ip_select_ident(net, skb, sk); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5cd99271d3a6..f6a0d54b308a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -536,12 +536,34 @@ out: * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. */ +static bool setsockopt_needs_rtnl(int optname) +{ + switch (optname) { + case IP_ADD_MEMBERSHIP: + case IP_ADD_SOURCE_MEMBERSHIP: + case IP_BLOCK_SOURCE: + case IP_DROP_MEMBERSHIP: + case IP_DROP_SOURCE_MEMBERSHIP: + case IP_MSFILTER: + case IP_UNBLOCK_SOURCE: + case MCAST_BLOCK_SOURCE: + case MCAST_MSFILTER: + case MCAST_JOIN_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_UNBLOCK_SOURCE: + return true; + } + return false; +} static int do_ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); int val = 0, err; + bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { case IP_PKTINFO: @@ -584,6 +606,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, return ip_mroute_setsockopt(sk, optname, optval, optlen); err = 0; + if (needs_rtnl) + rtnl_lock(); lock_sock(sk); switch (optname) { @@ -1118,10 +1142,14 @@ mc_msf_out: break; } release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return err; e_inval: release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return -EINVAL; } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 88c386cf7d85..8c4dcc46acd2 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -74,7 +74,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1); + __ip_select_ident(sock_net(sk), iph, skb_shinfo(skb)->gso_segs ?: 1); err = ip_local_out_sk(sk, skb); if (unlikely(net_xmit_eval(err))) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 5b188832800f..c688cd1b2110 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1642,7 +1642,8 @@ static struct notifier_block ip_mr_notifier = { * important for multicast video. */ -static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) +static void ip_encap(struct net *net, struct sk_buff *skb, + __be32 saddr, __be32 daddr) { struct iphdr *iph; const struct iphdr *old_iph = ip_hdr(skb); @@ -1661,7 +1662,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1758,7 +1759,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * What do we do with netfilter? -- RR */ if (vif->flags & VIFF_TUNNEL) { - ip_encap(skb, vif->local, vif->remote); + ip_encap(net, skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ vif->dev->stats.tx_packets++; vif->dev->stats.tx_bytes += skb->len; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 99e810f84671..cf5e82f39d3b 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -272,9 +272,9 @@ static void trace_packet(const struct sk_buff *skb, &chainname, &comment, &rulenum) != 0) break; - nf_log_packet(net, AF_INET, hook, skb, in, out, &trace_loginfo, - "TRACE: %s:%s:%s:%u ", - tablename, chainname, comment, rulenum); + nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo, + "TRACE: %s:%s:%s:%u ", + tablename, chainname, comment, rulenum); } #endif diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index a460a87e14f8..f0dfe92a00d6 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -300,7 +300,9 @@ static int exp_seq_show(struct seq_file *s, void *v) __nf_ct_l3proto_find(exp->tuple.src.l3num), __nf_ct_l4proto_find(exp->tuple.src.l3num, exp->tuple.dst.protonum)); - return seq_putc(s, '\n'); + seq_putc(s, '\n'); + + return 0; } static const struct seq_operations exp_seq_ops = { diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index d059182c1466..e7ad950cf9ef 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -10,8 +10,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -27,7 +29,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 5, + .level = LOGLEVEL_NOTICE, .logflags = NF_LOG_MASK, }, }, diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 75101980eeee..076aadda0473 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -5,8 +5,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -26,7 +28,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 5, + .level = LOGLEVEL_NOTICE, .logflags = NF_LOG_MASK, }, }, diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index fd88f868776f..344e7cdfb8d4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -64,11 +64,11 @@ EXPORT_SYMBOL_GPL(pingv6_ops); static u16 ping_port_rover; -static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int mask) +static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask) { - int res = (num + net_hash_mix(net)) & mask; + u32 res = (num + net_hash_mix(net)) & mask; - pr_debug("hash(%d) = %d\n", num, res); + pr_debug("hash(%u) = %u\n", num, res); return res; } EXPORT_SYMBOL_GPL(ping_hash); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 923cf538fce1..56946f47d446 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -404,7 +404,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 649c8a3f0189..be8703d02ef0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -482,7 +482,7 @@ u32 ip_idents_reserve(u32 hash, int segs) } EXPORT_SYMBOL(ip_idents_reserve); -void __ip_select_ident(struct iphdr *iph, int segs) +void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { static u32 ip_idents_hashrnd __read_mostly; u32 hash, id; @@ -491,7 +491,7 @@ void __ip_select_ident(struct iphdr *iph, int segs) hash = jhash_3words((__force u32)iph->daddr, (__force u32)iph->saddr, - iph->protocol, + iph->protocol ^ net_hash_mix(net), ip_idents_hashrnd); id = ip_idents_reserve(hash, segs); iph->id = htons(id); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f17db898ed26..df849e5a10f1 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -219,19 +219,20 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, } EXPORT_SYMBOL_GPL(__cookie_v4_check); -static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) +static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); struct sock *child; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + if (child) { + atomic_set(&req->rsk_refcnt, 1); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } @@ -325,7 +326,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops, sk); /* for safety */ if (!req) goto out; @@ -336,8 +337,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) req->mss = mss; ireq->ir_num = ntohs(th->dest); ireq->ir_rmt_port = th->source; - ireq->ir_loc_addr = ip_hdr(skb)->daddr; - ireq->ir_rmt_addr = ip_hdr(skb)->saddr; + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); ireq->ir_mark = inet_request_mark(sk, skb); ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; @@ -345,9 +346,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; - treq->listener = NULL; - write_pnet(&ireq->ireq_net, sock_net(sk)); - ireq->ireq_family = AF_INET; + treq->tfo_listener = false; ireq->ir_iif = sk->sk_bound_dev_if; @@ -361,7 +360,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; } - req->expires = 0UL; req->num_retrans = 0; /* diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 62f38428279a..dbd51cefaf02 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1913,18 +1913,19 @@ EXPORT_SYMBOL_GPL(tcp_set_state); static const unsigned char new_state[16] = { /* current state: new state: action: */ - /* (Invalid) */ TCP_CLOSE, - /* TCP_ESTABLISHED */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, - /* TCP_SYN_SENT */ TCP_CLOSE, - /* TCP_SYN_RECV */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, - /* TCP_FIN_WAIT1 */ TCP_FIN_WAIT1, - /* TCP_FIN_WAIT2 */ TCP_FIN_WAIT2, - /* TCP_TIME_WAIT */ TCP_CLOSE, - /* TCP_CLOSE */ TCP_CLOSE, - /* TCP_CLOSE_WAIT */ TCP_LAST_ACK | TCP_ACTION_FIN, - /* TCP_LAST_ACK */ TCP_LAST_ACK, - /* TCP_LISTEN */ TCP_CLOSE, - /* TCP_CLOSING */ TCP_CLOSING, + [0 /* (Invalid) */] = TCP_CLOSE, + [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_SYN_SENT] = TCP_CLOSE, + [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, + [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, + [TCP_TIME_WAIT] = TCP_CLOSE, + [TCP_CLOSE] = TCP_CLOSE, + [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, + [TCP_LAST_ACK] = TCP_LAST_ACK, + [TCP_LISTEN] = TCP_CLOSE, + [TCP_CLOSING] = TCP_CLOSING, + [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int tcp_close_state(struct sock *sk) diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index d4c3a5e66380..7a5ae50c80c8 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -378,6 +378,12 @@ EXPORT_SYMBOL_GPL(tcp_slow_start); */ void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { + /* If credits accumulated at a higher w, apply them gently now. */ + if (tp->snd_cwnd_cnt >= w) { + tp->snd_cwnd_cnt = 0; + tp->snd_cwnd++; + } + tp->snd_cwnd_cnt += acked; if (tp->snd_cwnd_cnt >= w) { u32 delta = tp->snd_cwnd_cnt / w; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 4b276d1ed980..06d3d665a9fd 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -306,8 +306,10 @@ tcp_friendliness: } } - if (ca->cnt == 0) /* cannot be zero */ - ca->cnt = 1; + /* The maximum rate of cwnd increase CUBIC allows is 1 packet per + * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. + */ + ca->cnt = max(ca->cnt, 2U); } static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index fe77417fc137..2eb887ec0ce3 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -155,12 +155,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, tp = tcp_sk(child); tp->fastopen_rsk = req; - /* Do a hold on the listner sk so that if the listener is being - * closed, the child that has been accepted can live on and still - * access listen_lock. - */ - sock_hold(sk); - tcp_rsk(req)->listener = sk; + tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never * scaled. So correct it appropriately. @@ -174,6 +169,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); + atomic_set(&req->rsk_refcnt, 1); /* Add the child socket directly into the accept queue */ inet_csk_reqsk_queue_add(sk, req, child); @@ -244,7 +240,7 @@ static bool tcp_fastopen_queue_check(struct sock *sk) struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; - if ((req1 == NULL) || time_after(req1->expires, jiffies)) { + if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) { spin_unlock(&fastopenq->lock); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); @@ -253,7 +249,7 @@ static bool tcp_fastopen_queue_check(struct sock *sk) fastopenq->rskq_rst_head = req1->dl_next; fastopenq->qlen--; spin_unlock(&fastopenq->lock); - reqsk_free(req1); + reqsk_put(req1); } return true; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 717d437b6ce1..18b80e8bc533 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3321,6 +3321,36 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +/* Return true if we're currently rate-limiting out-of-window ACKs and + * thus shouldn't send a dupack right now. We rate-limit dupacks in + * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS + * attacks that send repeated SYNs or ACKs for the same connection. To + * do this, we do not send a duplicate SYNACK or ACK if the remote + * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. + */ +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time) +{ + /* Data packets without SYNs are not likely part of an ACK loop. */ + if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && + !tcp_hdr(skb)->syn) + goto not_rate_limited; + + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS_BH(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + +not_rate_limited: + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* RFC 5961 7 [ACK Throttling] */ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) { @@ -5664,7 +5694,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (tcp_check_req(sk, skb, req, NULL, true) == NULL) + if (tcp_check_req(sk, skb, req, true) == NULL) goto discard; } @@ -5912,6 +5942,80 @@ static void tcp_ecn_create_request(struct request_sock *req, inet_rsk(req)->ecn_ok = 1; } +static void tcp_openreq_init(struct request_sock *req, + const struct tcp_options_received *rx_opt, + struct sk_buff *skb, const struct sock *sk) +{ + struct inet_request_sock *ireq = inet_rsk(req); + + req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ + req->cookie_ts = 0; + tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_rsk(req)->last_oow_ack_time = 0; + req->mss = rx_opt->mss_clamp; + req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; + ireq->tstamp_ok = rx_opt->tstamp_ok; + ireq->sack_ok = rx_opt->sack_ok; + ireq->snd_wscale = rx_opt->snd_wscale; + ireq->wscale_ok = rx_opt->wscale_ok; + ireq->acked = 0; + ireq->ecn_ok = 0; + ireq->ir_rmt_port = tcp_hdr(skb)->source; + ireq->ir_num = ntohs(tcp_hdr(skb)->dest); + ireq->ir_mark = inet_request_mark(sk, skb); +} + +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener) +{ + struct request_sock *req = reqsk_alloc(ops, sk_listener); + + if (req) { + struct inet_request_sock *ireq = inet_rsk(req); + + kmemcheck_annotate_bitfield(ireq, flags); + ireq->opt = NULL; + atomic64_set(&ireq->ir_cookie, 0); + ireq->ireq_state = TCP_NEW_SYN_RECV; + write_pnet(&ireq->ireq_net, sock_net(sk_listener)); + ireq->ireq_family = sk_listener->sk_family; + } + + return req; +} +EXPORT_SYMBOL(inet_reqsk_alloc); + +/* + * Return true if a syncookie should be sent + */ +static bool tcp_syn_flood_action(struct sock *sk, + const struct sk_buff *skb, + const char *proto) +{ + const char *msg = "Dropping request"; + bool want_cookie = false; + struct listen_sock *lopt; + +#ifdef CONFIG_SYN_COOKIES + if (sysctl_tcp_syncookies) { + msg = "Sending cookies"; + want_cookie = true; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); + } else +#endif + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); + + lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; + if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { + lopt->synflood_warned = 1; + pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); + } + return want_cookie; +} + int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) @@ -5949,7 +6053,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop; } - req = inet_reqsk_alloc(rsk_ops); + req = inet_reqsk_alloc(rsk_ops, sk); if (!req) goto drop; @@ -5965,7 +6069,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); - write_pnet(&inet_rsk(req)->ireq_net, sock_net(sk)); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; @@ -6042,7 +6145,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (err || want_cookie) goto drop_and_free; - tcp_rsk(req)->listener = NULL; + tcp_rsk(req)->tfo_listener = false; af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1f514a0c5e60..5aababa20a21 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -189,7 +189,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (!inet->inet_saddr) inet->inet_saddr = fl4->saddr; - inet->inet_rcv_saddr = inet->inet_saddr; + sk_rcv_saddr_set(sk, inet->inet_saddr); if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ @@ -204,7 +204,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_fetch_timewait_stamp(sk, &rt->dst); inet->inet_dport = usin->sin_port; - inet->inet_daddr = daddr; + sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) @@ -310,6 +310,34 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) dst->ops->redirect(dst, sk, skb); } + +/* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ +void tcp_req_err(struct sock *sk, u32 seq) +{ + struct request_sock *req = inet_reqsk(sk); + struct net *net = sock_net(sk); + + /* ICMPs are not backlogged, hence we cannot get + * an established socket here. + */ + WARN_ON(req->sk); + + if (seq != tcp_rsk(req)->snt_isn) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); + reqsk_put(req); + } else { + /* + * Still in SYN_RECV, just remove it silently. + * There is no good way to pass the error to the newly + * created socket, and POSIX does not want network + * errors returned from accept(). + */ + NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS); + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + } +} +EXPORT_SYMBOL(tcp_req_err); + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -343,8 +371,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) int err; struct net *net = dev_net(icmp_skb->dev); - sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest, - iph->saddr, th->source, inet_iif(icmp_skb)); + sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, + th->dest, iph->saddr, ntohs(th->source), + inet_iif(icmp_skb)); if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; @@ -353,6 +382,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) inet_twsk_put(inet_twsk(sk)); return; } + seq = ntohl(th->seq); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return tcp_req_err(sk, seq); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy @@ -374,7 +406,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); - seq = ntohl(th->seq); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = tp->fastopen_rsk; snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; @@ -458,36 +489,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } switch (sk->sk_state) { - struct request_sock *req, **prev; - case TCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - req = inet_csk_search_req(sk, &prev, th->dest, - iph->daddr, iph->saddr); - if (!req) - goto out; - - /* ICMPs are not backlogged, hence we cannot get - an established socket here. - */ - WARN_ON(req->sk); - - if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - - /* - * Still in SYN_RECV, just remove it silently. - * There is no good way to pass the error to the newly - * created socket, and POSIX does not want network - * errors returned from accept(). - */ - inet_csk_reqsk_queue_drop(sk, req, prev); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - goto out; - case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is @@ -647,7 +648,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) if (!key) goto release_sk1; - genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb); + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; } else { @@ -855,35 +856,6 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } -/* - * Return true if a syncookie should be sent - */ -bool tcp_syn_flood_action(struct sock *sk, - const struct sk_buff *skb, - const char *proto) -{ - const char *msg = "Dropping request"; - bool want_cookie = false; - struct listen_sock *lopt; - -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) { - msg = "Sending cookies"; - want_cookie = true; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); - } else -#endif - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - - lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { - lopt->synflood_warned = 1; - pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); - } - return want_cookie; -} -EXPORT_SYMBOL(tcp_syn_flood_action); #ifdef CONFIG_TCP_MD5SIG /* @@ -897,10 +869,10 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, const union tcp_md5_addr *addr, int family) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); - struct tcp_md5sig_info *md5sig; + const struct tcp_md5sig_info *md5sig; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, @@ -923,24 +895,15 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, - struct sock *addr_sk) + const struct sock *addr_sk) { union tcp_md5_addr *addr; - addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr; + addr = (union tcp_md5_addr *)&sk->sk_daddr; return tcp_md5_do_lookup(sk, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); -static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk, - struct request_sock *req) -{ - union tcp_md5_addr *addr; - - addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr; - return tcp_md5_do_lookup(sk, addr, AF_INET); -} - /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) @@ -1101,8 +1064,8 @@ clear_hash_noput: return 1; } -int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - const struct sock *sk, const struct request_sock *req, +int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb) { struct tcp_md5sig_pool *hp; @@ -1110,12 +1073,9 @@ int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, const struct tcphdr *th = tcp_hdr(skb); __be32 saddr, daddr; - if (sk) { - saddr = inet_sk(sk)->inet_saddr; - daddr = inet_sk(sk)->inet_daddr; - } else if (req) { - saddr = inet_rsk(req)->ir_loc_addr; - daddr = inet_rsk(req)->ir_rmt_addr; + if (sk) { /* valid for establish/request sockets */ + saddr = sk->sk_rcv_saddr; + daddr = sk->sk_daddr; } else { const struct iphdr *iph = ip_hdr(skb); saddr = iph->saddr; @@ -1152,8 +1112,9 @@ clear_hash_noput: } EXPORT_SYMBOL(tcp_v4_md5_hash_skb); -static bool __tcp_v4_inbound_md5_hash(struct sock *sk, - const struct sk_buff *skb) +/* Called with rcu_read_lock() */ +static bool tcp_v4_inbound_md5_hash(struct sock *sk, + const struct sk_buff *skb) { /* * This gets called for each TCP segment that arrives @@ -1193,7 +1154,7 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk, */ genhash = tcp_v4_md5_hash_skb(newhash, hash_expected, - NULL, NULL, skb); + NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", @@ -1205,30 +1166,17 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk, } return false; } - -static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) -{ - bool ret; - - rcu_read_lock(); - ret = __tcp_v4_inbound_md5_hash(sk, skb); - rcu_read_unlock(); - - return ret; -} - #endif -static void tcp_v4_init_req(struct request_sock *req, struct sock *sk, +static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); - ireq->ir_loc_addr = ip_hdr(skb)->daddr; - ireq->ir_rmt_addr = ip_hdr(skb)->saddr; - ireq->no_srccheck = inet_sk(sk)->transparent; + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); + ireq->no_srccheck = inet_sk(sk_listener)->transparent; ireq->opt = tcp_v4_save_options(skb); - ireq->ireq_family = AF_INET; } static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl, @@ -1260,7 +1208,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG - .md5_lookup = tcp_v4_reqsk_md5_lookup, + .req_md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, #endif .init_req = tcp_v4_init_req, @@ -1319,8 +1267,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->inet_daddr = ireq->ir_rmt_addr; - newinet->inet_rcv_saddr = ireq->ir_loc_addr; + sk_daddr_set(newsk, ireq->ir_rmt_addr); + sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = ireq->opt; rcu_assign_pointer(newinet->inet_opt, inet_opt); @@ -1392,15 +1340,17 @@ EXPORT_SYMBOL(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); + struct request_sock *req; struct sock *nsk; - struct request_sock **prev; - /* Find possible connection requests. */ - struct request_sock *req = inet_csk_search_req(sk, &prev, th->source, - iph->saddr, iph->daddr); - if (req) - return tcp_check_req(sk, skb, req, prev, false); + + req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); + if (req) { + nsk = tcp_check_req(sk, skb, req, false); + reqsk_put(req); + return nsk; + } nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); @@ -1518,7 +1468,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) if (sk) { skb->sk = sk; skb->destructor = sock_edemux; - if (sk->sk_state != TCP_TIME_WAIT) { + if (sk_fullsock(sk)) { struct dst_entry *dst = sk->sk_rx_dst; if (dst) @@ -1905,13 +1855,13 @@ get_req: } sk = sk_nulls_next(st->syn_wait_sk); st->state = TCP_SEQ_STATE_LISTENING; - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } else { icsk = inet_csk(sk); - read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); if (reqsk_queue_len(&icsk->icsk_accept_queue)) goto start_req; - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); sk = sk_nulls_next(sk); } get_sk: @@ -1923,7 +1873,7 @@ get_sk: goto out; } icsk = inet_csk(sk); - read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); if (reqsk_queue_len(&icsk->icsk_accept_queue)) { start_req: st->uid = sock_i_uid(sk); @@ -1932,7 +1882,7 @@ start_req: st->sbucket = 0; goto get_req; } - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } spin_unlock_bh(&ilb->lock); st->offset = 0; @@ -2151,7 +2101,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) case TCP_SEQ_STATE_OPENREQ: if (v) { struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk); - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) @@ -2209,7 +2159,7 @@ static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i, kuid_t uid) { const struct inet_request_sock *ireq = inet_rsk(req); - long delta = req->expires - jiffies; + long delta = req->rsk_timer.expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 366728cbee4a..5bef3513af77 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -152,6 +152,9 @@ static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst #define TCP_METRICS_RECLAIM_DEPTH 5 #define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL +#define deref_locked(p) \ + rcu_dereference_protected(p, lockdep_is_held(&tcp_metrics_lock)) + static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, struct inetpeer_addr *saddr, struct inetpeer_addr *daddr, @@ -180,9 +183,9 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, if (unlikely(reclaim)) { struct tcp_metrics_block *oldest; - oldest = rcu_dereference(tcp_metrics_hash[hash].chain); - for (tm = rcu_dereference(oldest->tcpm_next); tm; - tm = rcu_dereference(tm->tcpm_next)) { + oldest = deref_locked(tcp_metrics_hash[hash].chain); + for (tm = deref_locked(oldest->tcpm_next); tm; + tm = deref_locked(tm->tcpm_next)) { if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) oldest = tm; } @@ -1040,12 +1043,6 @@ out_free: return ret; } -#define deref_locked_genl(p) \ - rcu_dereference_protected(p, lockdep_genl_is_held() && \ - lockdep_is_held(&tcp_metrics_lock)) - -#define deref_genl(p) rcu_dereference_protected(p, lockdep_genl_is_held()) - static void tcp_metrics_flush_all(struct net *net) { unsigned int max_rows = 1U << tcp_metrics_hash_log; @@ -1057,8 +1054,7 @@ static void tcp_metrics_flush_all(struct net *net) struct tcp_metrics_block __rcu **pp; spin_lock_bh(&tcp_metrics_lock); pp = &hb->chain; - for (tm = deref_locked_genl(*pp); tm; - tm = deref_locked_genl(*pp)) { + for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { if (net_eq(tm_net(tm), net)) { *pp = tm->tcpm_next; kfree_rcu(tm, rcu_head); @@ -1097,7 +1093,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) hb = tcp_metrics_hash + hash; pp = &hb->chain; spin_lock_bh(&tcp_metrics_lock); - for (tm = deref_locked_genl(*pp); tm; tm = deref_locked_genl(*pp)) { + for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { if (addr_same(&tm->tcpm_daddr, &daddr) && (!src || addr_same(&tm->tcpm_saddr, &saddr)) && net_eq(tm_net(tm), net)) { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index dd11ac7798c6..274e96fb369b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -572,7 +572,6 @@ EXPORT_SYMBOL(tcp_create_openreq_child); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct request_sock **prev, bool fastopen) { struct tcp_options_received tmp_opt; @@ -630,8 +629,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, &tcp_rsk(req)->last_oow_ack_time) && !inet_rtx_syn_ack(sk, req)) - req->expires = min(TCP_TIMEOUT_INIT << req->num_timeout, - TCP_RTO_MAX) + jiffies; + mod_timer_pending(&req->rsk_timer, jiffies + + min(TCP_TIMEOUT_INIT << req->num_timeout, + TCP_RTO_MAX)); return NULL; } @@ -766,7 +766,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (child == NULL) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); inet_csk_reqsk_queue_add(sk, req, child); @@ -791,7 +791,7 @@ embryonic_reset: tcp_reset(sk); } if (!fastopen) { - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); } return NULL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5a73ad5afaf7..2e69b8d16e68 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -601,15 +601,14 @@ static unsigned int tcp_synack_options(struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5, + const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; #ifdef CONFIG_TCP_MD5SIG - *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); - if (*md5) { + if (md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; @@ -620,8 +619,6 @@ static unsigned int tcp_synack_options(struct sock *sk, */ ireq->tstamp_ok &= !ireq->sack_ok; } -#else - *md5 = NULL; #endif /* We always send an MSS option. */ @@ -989,7 +986,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (md5) { sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, - md5, sk, NULL, skb); + md5, sk, skb); } #endif @@ -2820,15 +2817,11 @@ void tcp_send_fin(struct sock *sk) } else { /* Socket is locked, keep trying until memory is available. */ for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, - sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); if (skb) break; yield(); } - - /* Reserve space for headers and prepare control bits. */ - skb_reserve(skb, MAX_TCP_HEADER); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); @@ -2917,7 +2910,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; struct sk_buff *skb; - struct tcp_md5sig_key *md5; + struct tcp_md5sig_key *md5 = NULL; int tcp_header_size; int mss; @@ -2930,7 +2923,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_reserve(skb, MAX_TCP_HEADER); skb_dst_set(skb, dst); - security_skb_owned_by(skb, sk); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) @@ -2943,7 +2935,12 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, else #endif skb_mstamp_get(&skb->skb_mstamp); - tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5, + +#ifdef CONFIG_TCP_MD5SIG + rcu_read_lock(); + md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); +#endif + tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, foc) + sizeof(*th); skb_push(skb, tcp_header_size); @@ -2974,10 +2971,10 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ - if (md5) { + if (md5) tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, - md5, NULL, req, skb); - } + md5, req_to_sk(req), skb); + rcu_read_unlock(); #endif return skb; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 15505936511d..2568fd282873 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -327,7 +327,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) struct request_sock *req; req = tcp_sk(sk)->fastopen_rsk; - req->rsk_ops->syn_ack_timeout(sk, req); + req->rsk_ops->syn_ack_timeout(req); if (req->num_timeout >= max_retries) { tcp_write_err(sk); @@ -539,19 +539,11 @@ static void tcp_write_timer(unsigned long data) sock_put(sk); } -/* - * Timer for listening sockets - */ - -static void tcp_synack_timer(struct sock *sk) +void tcp_syn_ack_timeout(const struct request_sock *req) { - inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, - TCP_TIMEOUT_INIT, TCP_RTO_MAX); -} + struct net *net = read_pnet(&inet_rsk(req)->ireq_net); -void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req) -{ - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); + NET_INC_STATS_BH(net, LINUX_MIB_TCPTIMEOUTS); } EXPORT_SYMBOL(tcp_syn_ack_timeout); @@ -583,7 +575,7 @@ static void tcp_keepalive_timer (unsigned long data) } if (sk->sk_state == TCP_LISTEN) { - tcp_synack_timer(sk); + pr_err("Hmm... keepalive on a LISTEN ???\n"); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f27556e2158b..294af16633af 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -318,8 +318,8 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)); } -static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr, - unsigned int port) +static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr, + unsigned int port) { return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; } @@ -421,9 +421,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, return score; } -static unsigned int udp_ehashfn(struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +static u32 udp_ehashfn(const struct net *net, const __be32 laddr, + const __u16 lport, const __be32 faddr, + const __be16 fport) { static u32 udp_ehash_secret __read_mostly; diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 91771a7c802f..35feda676464 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -63,7 +63,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; - ip_select_ident(skb, NULL); + ip_select_ident(dev_net(dst->dev), skb, NULL); return 0; } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d5f6bd9a210a..dab73813cb92 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -63,6 +63,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) return err; IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; + skb->protocol = htons(ETH_P_IP); return x->outer_mode->output2(x, skb); } @@ -71,7 +72,6 @@ EXPORT_SYMBOL(xfrm4_prepare_output); int xfrm4_output_finish(struct sk_buff *skb) { memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - skb->protocol = htons(ETH_P_IP); #ifdef CONFIG_NETFILTER IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 88d2cf0cae52..2660263e1131 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -46,6 +46,7 @@ #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> +#include <linux/inet.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_addr.h> @@ -102,6 +103,9 @@ #define INFINITY_LIFE_TIME 0xFFFFFFFF +#define IPV6_MAX_STRLEN \ + sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") + static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; @@ -127,6 +131,9 @@ static void ipv6_regen_rndid(unsigned long data); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(struct inet6_dev *idev); +static int ipv6_generate_stable_address(struct in6_addr *addr, + u8 dad_count, + const struct inet6_dev *idev); /* * Configured unicast address hash table @@ -202,6 +209,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, + .stable_secret = { + .initialized = false, + } }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -240,6 +250,9 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, + .stable_secret = { + .initialized = false, + }, }; /* Check if a valid qdisc is available */ @@ -860,7 +873,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->peer_addr = *peer_addr; spin_lock_init(&ifa->lock); - spin_lock_init(&ifa->state_lock); INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; @@ -1003,10 +1015,10 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ASSERT_RTNL(); - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (state == INET6_IFADDR_STATE_DEAD) goto out; @@ -1686,19 +1698,21 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) { int err = -ENOENT; - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DAD) { ifp->state = INET6_IFADDR_STATE_POSTDAD; err = 0; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); return err; } void addrconf_dad_failure(struct inet6_ifaddr *ifp) { + struct in6_addr addr; struct inet6_dev *idev = ifp->idev; + struct net *net = dev_net(ifp->idev->dev); if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); @@ -1708,9 +1722,57 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n", ifp->idev->dev->name, &ifp->addr); - if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { - struct in6_addr addr; + spin_lock_bh(&ifp->lock); + + if (ifp->flags & IFA_F_STABLE_PRIVACY) { + int scope = ifp->scope; + u32 flags = ifp->flags; + struct in6_addr new_addr; + struct inet6_ifaddr *ifp2; + u32 valid_lft, preferred_lft; + int pfxlen = ifp->prefix_len; + int retries = ifp->stable_privacy_retry + 1; + + if (retries > net->ipv6.sysctl.idgen_retries) { + net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n", + ifp->idev->dev->name); + goto errdad; + } + + new_addr = ifp->addr; + if (ipv6_generate_stable_address(&new_addr, retries, + idev)) + goto errdad; + valid_lft = ifp->valid_lft; + preferred_lft = ifp->prefered_lft; + + spin_unlock_bh(&ifp->lock); + + if (idev->cnf.max_addresses && + ipv6_count_addresses(idev) >= + idev->cnf.max_addresses) + goto lock_errdad; + + net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", + ifp->idev->dev->name); + + ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen, + scope, flags, valid_lft, + preferred_lft); + if (IS_ERR(ifp2)) + goto lock_errdad; + + spin_lock_bh(&ifp2->lock); + ifp2->stable_privacy_retry = retries; + ifp2->state = INET6_IFADDR_STATE_PREDAD; + spin_unlock_bh(&ifp2->lock); + + addrconf_mod_dad_work(ifp2, net->ipv6.sysctl.idgen_delay); + in6_ifa_put(ifp2); +lock_errdad: + spin_lock_bh(&ifp->lock); + } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { addr.s6_addr32[0] = htonl(0xfe800000); addr.s6_addr32[1] = 0; @@ -1724,10 +1786,10 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) } } - spin_lock_bh(&ifp->state_lock); +errdad: /* transition from _POSTDAD to _ERRDAD */ ifp->state = INET6_IFADDR_STATE_ERRDAD; - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); addrconf_mod_dad_work(ifp, 0); } @@ -2186,6 +2248,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) __u32 valid_lft; __u32 prefered_lft; int addr_type; + u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); @@ -2292,6 +2355,12 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) in6_dev->token.s6_addr + 8, 8); read_unlock_bh(&in6_dev->lock); tokenized = true; + } else if (in6_dev->addr_gen_mode == + IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + !ipv6_generate_stable_address(&addr, 0, + in6_dev)) { + addr_flags |= IFA_F_STABLE_PRIVACY; + goto ok; } else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { in6_dev_put(in6_dev); @@ -2310,7 +2379,6 @@ ok: if (ifp == NULL && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; - u32 addr_flags = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (in6_dev->cnf.optimistic_dad && @@ -2350,7 +2418,7 @@ ok: u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ - spin_lock(&ifp->lock); + spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; @@ -2380,12 +2448,12 @@ ok: ifp->tstamp = now; flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; - spin_unlock(&ifp->lock); + spin_unlock_bh(&ifp->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); } else - spin_unlock(&ifp->lock); + spin_unlock_bh(&ifp->lock); manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft, create, now); @@ -2473,9 +2541,9 @@ static int ipv6_mc_config(struct sock *sk, bool join, lock_sock(sk); if (join) - ret = __ipv6_sock_mc_join(sk, ifindex, addr); + ret = ipv6_sock_mc_join(sk, ifindex, addr); else - ret = __ipv6_sock_mc_drop(sk, ifindex, addr); + ret = ipv6_sock_mc_drop(sk, ifindex, addr); release_sock(sk); return ret; @@ -2789,10 +2857,11 @@ static void init_loopback(struct net_device *dev) } } -static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) +static void addrconf_add_linklocal(struct inet6_dev *idev, + const struct in6_addr *addr, u32 flags) { struct inet6_ifaddr *ifp; - u32 addr_flags = IFA_F_PERMANENT; + u32 addr_flags = flags | IFA_F_PERMANENT; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (idev->cnf.optimistic_dad && @@ -2800,7 +2869,6 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr addr_flags |= IFA_F_OPTIMISTIC; #endif - ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); if (!IS_ERR(ifp)) { @@ -2810,18 +2878,103 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr } } +static bool ipv6_reserved_interfaceid(struct in6_addr address) +{ + if ((address.s6_addr32[2] | address.s6_addr32[3]) == 0) + return true; + + if (address.s6_addr32[2] == htonl(0x02005eff) && + ((address.s6_addr32[3] & htonl(0xfe000000)) == htonl(0xfe000000))) + return true; + + if (address.s6_addr32[2] == htonl(0xfdffffff) && + ((address.s6_addr32[3] & htonl(0xffffff80)) == htonl(0xffffff80))) + return true; + + return false; +} + +static int ipv6_generate_stable_address(struct in6_addr *address, + u8 dad_count, + const struct inet6_dev *idev) +{ + static DEFINE_SPINLOCK(lock); + static __u32 digest[SHA_DIGEST_WORDS]; + static __u32 workspace[SHA_WORKSPACE_WORDS]; + + static union { + char __data[SHA_MESSAGE_BYTES]; + struct { + struct in6_addr secret; + __be32 prefix[2]; + unsigned char hwaddr[MAX_ADDR_LEN]; + u8 dad_count; + } __packed; + } data; + + struct in6_addr secret; + struct in6_addr temp; + struct net *net = dev_net(idev->dev); + + BUILD_BUG_ON(sizeof(data.__data) != sizeof(data)); + + if (idev->cnf.stable_secret.initialized) + secret = idev->cnf.stable_secret.secret; + else if (net->ipv6.devconf_dflt->stable_secret.initialized) + secret = net->ipv6.devconf_dflt->stable_secret.secret; + else + return -1; + +retry: + spin_lock_bh(&lock); + + sha_init(digest); + memset(&data, 0, sizeof(data)); + memset(workspace, 0, sizeof(workspace)); + memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len); + data.prefix[0] = address->s6_addr32[0]; + data.prefix[1] = address->s6_addr32[1]; + data.secret = secret; + data.dad_count = dad_count; + + sha_transform(digest, data.__data, workspace); + + temp = *address; + temp.s6_addr32[2] = (__force __be32)digest[0]; + temp.s6_addr32[3] = (__force __be32)digest[1]; + + spin_unlock_bh(&lock); + + if (ipv6_reserved_interfaceid(temp)) { + dad_count++; + if (dad_count > dev_net(idev->dev)->ipv6.sysctl.idgen_retries) + return -1; + goto retry; + } + + *address = temp; + return 0; +} + static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { - if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { - struct in6_addr addr; + struct in6_addr addr; - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + + if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) { + if (!ipv6_generate_stable_address(&addr, 0, idev)) + addrconf_add_linklocal(idev, &addr, + IFA_F_STABLE_PRIVACY); + else if (prefix_route) + addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + } else if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { /* addrconf_add_linklocal also adds a prefix_route and we * only need to care about prefix routes if ipv6_generate_eui64 * couldn't generate one. */ if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) - addrconf_add_linklocal(idev, &addr); + addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); } @@ -3159,10 +3312,10 @@ restart: write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->state_lock); + spin_lock_bh(&ifa->lock); state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifa->state_lock); + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); @@ -3320,12 +3473,12 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp) { bool begin_dad = false; - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state != INET6_IFADDR_STATE_DEAD) { ifp->state = INET6_IFADDR_STATE_PREDAD; begin_dad = true; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (begin_dad) addrconf_mod_dad_work(ifp, 0); @@ -3347,7 +3500,7 @@ static void addrconf_dad_work(struct work_struct *w) rtnl_lock(); - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_PREDAD) { action = DAD_BEGIN; ifp->state = INET6_IFADDR_STATE_DAD; @@ -3355,7 +3508,7 @@ static void addrconf_dad_work(struct work_struct *w) action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (action == DAD_BEGIN) { addrconf_dad_begin(ifp); @@ -4430,6 +4583,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; + /* we omit DEVCONF_STABLE_SECRET for now */ } static inline size_t inet6_ifla6_size(void) @@ -4664,8 +4818,15 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); if (mode != IN6_ADDR_GEN_MODE_EUI64 && - mode != IN6_ADDR_GEN_MODE_NONE) + mode != IN6_ADDR_GEN_MODE_NONE && + mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY) return -EINVAL; + + if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + !idev->cnf.stable_secret.initialized && + !dev_net(dev)->ipv6.devconf_dflt->stable_secret.initialized) + return -EINVAL; + idev->addr_gen_mode = mode; err = 0; } @@ -5074,6 +5235,74 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, return ret; } +static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int err; + struct in6_addr addr; + char str[IPV6_MAX_STRLEN]; + struct ctl_table lctl = *ctl; + struct net *net = ctl->extra2; + struct ipv6_stable_secret *secret = ctl->data; + + if (&net->ipv6.devconf_all->stable_secret == ctl->data) + return -EIO; + + lctl.maxlen = IPV6_MAX_STRLEN; + lctl.data = str; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (!write && !secret->initialized) { + err = -EIO; + goto out; + } + + if (!write) { + err = snprintf(str, sizeof(str), "%pI6", + &secret->secret); + if (err >= sizeof(str)) { + err = -EIO; + goto out; + } + } + + err = proc_dostring(&lctl, write, buffer, lenp, ppos); + if (err || !write) + goto out; + + if (in6_pton(str, -1, addr.in6_u.u6_addr8, -1, NULL) != 1) { + err = -EIO; + goto out; + } + + secret->initialized = true; + secret->secret = addr; + + if (&net->ipv6.devconf_dflt->stable_secret == ctl->data) { + struct net_device *dev; + + for_each_netdev(net, dev) { + struct inet6_dev *idev = __in6_dev_get(dev); + + if (idev) { + idev->addr_gen_mode = + IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + } + } + } else { + struct inet6_dev *idev = ctl->extra1; + + idev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + } + +out: + rtnl_unlock(); + + return err; +} static struct addrconf_sysctl_table { @@ -5347,6 +5576,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "stable_secret", + .data = &ipv6_devconf.stable_secret, + .maxlen = IPV6_MAX_STRLEN, + .mode = 0600, + .proc_handler = addrconf_sysctl_stable_secret, + }, + { /* sentinel */ } }, @@ -5442,6 +5678,9 @@ static int __net_init addrconf_init_net(struct net *net) dflt->autoconf = ipv6_defaults.autoconf; dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; + dflt->stable_secret.initialized = false; + all->stable_secret.initialized = false; + net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 6bafcc2c79e3..d8dcc526339e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -766,6 +766,8 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.flowlabel_consistency = 1; net->ipv6.sysctl.auto_flowlabels = 0; + net->ipv6.sysctl.idgen_retries = 3; + net->ipv6.sysctl.idgen_delay = 1 * HZ; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index baf2742d1ec4..9e6b0ee563f0 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -60,6 +60,8 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; + ASSERT_RTNL(); + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) @@ -73,7 +75,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; - rtnl_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -130,7 +131,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } error: - rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -146,7 +146,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_ac_socklist *pac, *prev_pac; struct net *net = sock_net(sk); - rtnl_lock(); + ASSERT_RTNL(); + prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && @@ -154,10 +155,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) break; prev_pac = pac; } - if (!pac) { - rtnl_unlock(); + if (!pac) return -ENOENT; - } if (prev_pac) prev_pac->acl_next = pac->acl_next; else @@ -166,7 +165,6 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) dev = __dev_get_by_index(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); - rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b4d5e1d97c1b..273eb26cd6d4 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto again; flp6->saddr = saddr; } + err = rt->dst.error; goto out; } again: @@ -298,19 +299,16 @@ static int __net_init fib6_rules_net_init(struct net *net) ops = fib_rules_register(&fib6_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); - net->ipv6.fib6_rules_ops = ops; - - err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0, - RT6_TABLE_LOCAL, 0); + err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0); if (err) goto out_fib6_rules_ops; - err = fib_default_rule_add(net->ipv6.fib6_rules_ops, - 0x7FFE, RT6_TABLE_MAIN, 0); + err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0); if (err) goto out_fib6_rules_ops; + net->ipv6.fib6_rules_ops = ops; out: return err; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 29b32206e494..6927f3fb5597 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -112,22 +112,20 @@ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, return c & (synq_hsize - 1); } -struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, +struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, const int iif) { - const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; + struct request_sock *req; + u32 hash = inet6_synq_hash(raddr, rport, lopt->hash_rnd, + lopt->nr_table_entries); - for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport, - lopt->hash_rnd, - lopt->nr_table_entries)]; - (req = *prev) != NULL; - prev = &req->dl_next) { + spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); + for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) { const struct inet_request_sock *ireq = inet_rsk(req); if (ireq->ir_rmt_port == rport && @@ -135,13 +133,14 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk, ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) && ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) && (!ireq->ir_iif || ireq->ir_iif == iif)) { + atomic_inc(&req->rsk_refcnt); WARN_ON(req->sk != NULL); - *prevp = prev; - return req; + break; } } + spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); - return NULL; + return req; } EXPORT_SYMBOL_GPL(inet6_csk_search_req); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 051dffb49c90..033f17816ef4 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -23,11 +23,9 @@ #include <net/secure_seq.h> #include <net/ip.h> -static unsigned int inet6_ehashfn(struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +u32 inet6_ehashfn(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport) { static u32 inet6_ehash_secret __read_mostly; static u32 ipv6_hash_secret __read_mostly; @@ -44,54 +42,6 @@ static unsigned int inet6_ehashfn(struct net *net, inet6_ehash_secret + net_hash_mix(net)); } -static int inet6_sk_ehashfn(const struct sock *sk) -{ - const struct inet_sock *inet = inet_sk(sk); - const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr; - const struct in6_addr *faddr = &sk->sk_v6_daddr; - const __u16 lport = inet->inet_num; - const __be16 fport = inet->inet_dport; - struct net *net = sock_net(sk); - - return inet6_ehashfn(net, laddr, lport, faddr, fport); -} - -int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) -{ - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - int twrefcnt = 0; - - WARN_ON(!sk_unhashed(sk)); - - if (sk->sk_state == TCP_LISTEN) { - struct inet_listen_hashbucket *ilb; - - ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - spin_lock(&ilb->lock); - __sk_nulls_add_node_rcu(sk, &ilb->head); - spin_unlock(&ilb->lock); - } else { - unsigned int hash; - struct hlist_nulls_head *list; - spinlock_t *lock; - - sk->sk_hash = hash = inet6_sk_ehashfn(sk); - list = &inet_ehash_bucket(hashinfo, hash)->chain; - lock = inet_ehash_lockp(hashinfo, hash); - spin_lock(lock); - __sk_nulls_add_node_rcu(sk, list); - if (tw) { - WARN_ON(sk->sk_hash != tw->tw_hash); - twrefcnt = inet_twsk_unhash(tw); - } - spin_unlock(lock); - } - - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - return twrefcnt; -} -EXPORT_SYMBOL(__inet6_hash); - /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM @@ -320,6 +270,6 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk), - __inet6_check_established, __inet6_hash); + __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 0a04a37305d5..b06ad00048d5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -318,6 +318,7 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) static inline int ip6_forward_finish(struct sk_buff *skb) { + skb_sender_cpu_clear(skb); return dst_output(skb); } @@ -627,7 +628,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(fh, rt); + ipv6_select_ident(net, fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); @@ -774,7 +775,7 @@ slow_path: fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { - ipv6_select_ident(fh, rt); + ipv6_select_ident(net, fh, rt); frag_id = fh->identification; } else fh->identification = frag_id; @@ -1078,7 +1079,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - sizeof(struct frag_hdr)) & ~7; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr, rt); + ipv6_select_ident(sock_net(sk), &fhdr, rt); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; append: diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 88300d42fc95..41f84f76ad9d 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -308,7 +308,7 @@ out: * Create tunnel matching given parameters. * * Return: - * created tunnel or NULL + * created tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) @@ -316,7 +316,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; - int err; + int err = -ENOMEM; if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); @@ -342,7 +342,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) failed_free: ip6_dev_free(dev); failed: - return NULL; + return ERR_PTR(err); } /** @@ -356,7 +356,7 @@ failed: * tunnel device is created and registered for use. * * Return: - * matching tunnel or NULL + * matching tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_locate(struct net *net, @@ -374,13 +374,13 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net, if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) { if (create) - return NULL; + return ERR_PTR(-EEXIST); return t; } } if (!create) - return NULL; + return ERR_PTR(-ENODEV); return ip6_tnl_create(net, p); } @@ -1414,7 +1414,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); - if (t == NULL) + if (IS_ERR(t)) t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); @@ -1439,7 +1439,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); if (cmd == SIOCCHGTUNNEL) { - if (t != NULL) { + if (!IS_ERR(t)) { if (t->dev != dev) { err = -EEXIST; break; @@ -1451,14 +1451,15 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) else err = ip6_tnl_update(t, &p1); } - if (t) { + if (!IS_ERR(t)) { err = 0; ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; - } else - err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + } else { + err = PTR_ERR(t); + } break; case SIOCDELTUNNEL: err = -EPERM; @@ -1472,7 +1473,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) err = -ENOENT; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); - if (t == NULL) + if (IS_ERR(t)) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) @@ -1666,12 +1667,13 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net *net = dev_net(dev); - struct ip6_tnl *nt; + struct ip6_tnl *nt, *t; nt = netdev_priv(dev); ip6_tnl_netlink_parms(data, &nt->parms); - if (ip6_tnl_locate(net, &nt->parms, 0)) + t = ip6_tnl_locate(net, &nt->parms, 0); + if (!IS_ERR(t)) return -EEXIST; return ip6_tnl_create2(dev); @@ -1691,8 +1693,7 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], ip6_tnl_netlink_parms(data, &p); t = ip6_tnl_locate(net, &p, 0); - - if (t) { + if (!IS_ERR(t)) { if (t->dev != dev) return -EEXIST; } else diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 8d766d9100cb..9b2cb1444230 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -117,6 +117,25 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, return opt; } +static bool setsockopt_needs_rtnl(int optname) +{ + switch (optname) { + case IPV6_ADD_MEMBERSHIP: + case IPV6_DROP_MEMBERSHIP: + case IPV6_JOIN_ANYCAST: + case IPV6_LEAVE_ANYCAST: + case MCAST_JOIN_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_BLOCK_SOURCE: + case MCAST_UNBLOCK_SOURCE: + case MCAST_MSFILTER: + return true; + } + return false; +} + static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { @@ -124,6 +143,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, struct net *net = sock_net(sk); int val, valbool; int retv = -ENOPROTOOPT; + bool needs_rtnl = setsockopt_needs_rtnl(optname); if (optval == NULL) val = 0; @@ -140,6 +160,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (ip6_mroute_opt(optname)) return ip6_mroute_setsockopt(sk, optname, optval, optlen); + if (needs_rtnl) + rtnl_lock(); lock_sock(sk); switch (optname) { @@ -624,10 +646,10 @@ done: psin6 = (struct sockaddr_in6 *)&greq.gr_group; if (optname == MCAST_JOIN_GROUP) retv = ipv6_sock_mc_join(sk, greq.gr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); else retv = ipv6_sock_mc_drop(sk, greq.gr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); break; } case MCAST_JOIN_SOURCE_GROUP: @@ -660,7 +682,7 @@ done: psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; retv = ipv6_sock_mc_join(sk, greqs.gsr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); /* prior join w/ different source is ok */ if (retv && retv != -EADDRINUSE) break; @@ -837,11 +859,15 @@ pref_skip_coa: } release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return retv; e_inval: release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return -EINVAL; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 1dd1fedff9f4..cbb66fd3da6d 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -132,7 +132,7 @@ static int unsolicited_report_interval(struct inet6_dev *idev) return iv > 0 ? iv : 1; } -int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) +int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; @@ -199,24 +199,12 @@ int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *add return 0; } -EXPORT_SYMBOL(__ipv6_sock_mc_join); - -int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) -{ - int ret; - - rtnl_lock(); - ret = __ipv6_sock_mc_join(sk, ifindex, addr); - rtnl_unlock(); - - return ret; -} EXPORT_SYMBOL(ipv6_sock_mc_join); /* * socket leave on multicast group */ -int __ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) +int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; @@ -255,18 +243,6 @@ int __ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *add return -EADDRNOTAVAIL; } -EXPORT_SYMBOL(__ipv6_sock_mc_drop); - -int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) -{ - int ret; - - rtnl_lock(); - ret = __ipv6_sock_mc_drop(sk, ifindex, addr); - rtnl_unlock(); - - return ret; -} EXPORT_SYMBOL(ipv6_sock_mc_drop); /* called with rcu_read_lock() */ @@ -460,7 +436,7 @@ done: read_unlock_bh(&idev->lock); rcu_read_unlock(); if (leavegroup) - return ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); + err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e080fbbbc0e5..83f59dc3cccc 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -9,7 +9,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> @@ -234,7 +237,7 @@ static struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 4, + .level = LOGLEVEL_WARNING, .logflags = NF_LOG_MASK, }, }, @@ -298,9 +301,9 @@ static void trace_packet(const struct sk_buff *skb, &chainname, &comment, &rulenum) != 0) break; - nf_log_packet(net, AF_INET6, hook, skb, in, out, &trace_loginfo, - "TRACE: %s:%s:%s:%u ", - tablename, chainname, comment, rulenum); + nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, + "TRACE: %s:%s:%s:%u ", + tablename, chainname, comment, rulenum); } #endif diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 544b0a9da1b5..12331efd49cf 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -83,7 +83,8 @@ static int reject_tg6_check(const struct xt_tgchk_param *par) return -EINVAL; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ipv6.proto != IPPROTO_TCP || + if (!(e->ipv6.flags & IP6T_F_PROTO) || + e->ipv6.proto != IPPROTO_TCP || (e->ipv6.invflags & XT_INV_PROTO)) { pr_info("TCP_RESET illegal for non-tcp\n"); return -EINVAL; diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index ddf07e6f59d7..8dd869642f45 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -5,8 +5,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -27,7 +29,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 5, + .level = LOGLEVEL_NOTICE, .logflags = NF_LOG_MASK, }, }, diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 74581f706c4d..4016a6ef9d61 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -9,13 +9,14 @@ #include <net/addrconf.h> #include <net/secure_seq.h> -static u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, - struct in6_addr *src) +static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, + struct in6_addr *dst, struct in6_addr *src) { u32 hash, id; hash = __ipv6_addr_jhash(dst, hashrnd); hash = __ipv6_addr_jhash(src, hash); + hash ^= net_hash_mix(net); /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, * set the hight order instead thus minimizing possible future @@ -36,7 +37,7 @@ static u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, * * The network header must be set before calling this. */ -void ipv6_proxy_select_ident(struct sk_buff *skb) +void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { static u32 ip6_proxy_idents_hashrnd __read_mostly; struct in6_addr buf[2]; @@ -53,20 +54,21 @@ void ipv6_proxy_select_ident(struct sk_buff *skb) net_get_random_once(&ip6_proxy_idents_hashrnd, sizeof(ip6_proxy_idents_hashrnd)); - id = __ipv6_select_ident(ip6_proxy_idents_hashrnd, + id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd, &addrs[1], &addrs[0]); skb_shinfo(skb)->ip6_frag_id = htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, + struct rt6_info *rt) { static u32 ip6_idents_hashrnd __read_mostly; u32 id; net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); - id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr, + id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr, &rt->rt6i_src.addr); fhdr->identification = htonl(id); } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 58875ce8e178..21bc2eb53c57 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -49,11 +49,12 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct sock *child; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + if (child) { + atomic_set(&req->rsk_refcnt, 1); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } @@ -189,15 +190,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops); + req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk); if (!req) goto out; ireq = inet_rsk(req); treq = tcp_rsk(req); - treq->listener = NULL; - write_pnet(&ireq->ireq_net, sock_net(sk)); - ireq->ireq_family = AF_INET6; + treq->tfo_listener = false; if (security_inet_conn_request(sk, skb, req)) goto out_free; @@ -222,7 +221,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->ir_mark = inet_request_mark(sk, skb); - req->expires = 0UL; req->num_retrans = 0; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index c5c10fafcfe2..30f5a4ad04eb 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -54,6 +54,20 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "idgen_retries", + .data = &init_net.ipv6.sysctl.idgen_retries, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "idgen_delay", + .data = &init_net.ipv6.sysctl.idgen_delay, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; @@ -93,6 +107,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels; ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect; + ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; + ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d89f028dc8c4..cbdf6912d2c6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -104,19 +104,6 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static void tcp_v6_hash(struct sock *sk) -{ - if (sk->sk_state != TCP_CLOSE) { - if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) { - tcp_prot.hash(sk); - return; - } - local_bh_disable(); - __inet6_hash(sk, NULL); - local_bh_enable(); - } -} - static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, @@ -233,11 +220,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; - } else { - ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &sk->sk_v6_rcv_saddr); } + np->saddr = sk->sk_v6_rcv_saddr; return err; } @@ -340,18 +324,20 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); + struct net *net = dev_net(skb->dev); + struct request_sock *fastopen; struct ipv6_pinfo *np; - struct sock *sk; - int err; struct tcp_sock *tp; - struct request_sock *fastopen; __u32 seq, snd_una; - struct net *net = dev_net(skb->dev); + struct sock *sk; + int err; - sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr, - th->dest, &hdr->saddr, th->source, skb->dev->ifindex); + sk = __inet6_lookup_established(net, &tcp_hashinfo, + &hdr->daddr, th->dest, + &hdr->saddr, ntohs(th->source), + skb->dev->ifindex); - if (sk == NULL) { + if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; @@ -361,6 +347,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, inet_twsk_put(inet_twsk(sk)); return; } + seq = ntohl(th->seq); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return tcp_req_err(sk, seq); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -375,7 +364,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } tp = tcp_sk(sk); - seq = ntohl(th->seq); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = tp->fastopen_rsk; snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; @@ -419,31 +407,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; - case TCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - /* Note : We use inet6_iif() here, not tcp_v6_iif() */ - req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, - &hdr->saddr, inet6_iif(skb)); - if (!req) - goto out; - - /* ICMPs are not backlogged, hence we cannot get - * an established socket here. - */ - WARN_ON(req->sk != NULL); - - if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - - inet_csk_reqsk_queue_drop(sk, req, prev); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - goto out; - case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is @@ -523,17 +486,11 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, } static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, - struct sock *addr_sk) + const struct sock *addr_sk) { return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } -static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, - struct request_sock *req) -{ - return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr); -} - static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, int optlen) { @@ -619,9 +576,9 @@ clear_hash_noput: return 1; } -static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, +static int tcp_v6_md5_hash_skb(char *md5_hash, + const struct tcp_md5sig_key *key, const struct sock *sk, - const struct request_sock *req, const struct sk_buff *skb) { const struct in6_addr *saddr, *daddr; @@ -629,12 +586,9 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, struct hash_desc *desc; const struct tcphdr *th = tcp_hdr(skb); - if (sk) { - saddr = &inet6_sk(sk)->saddr; + if (sk) { /* valid for establish/request sockets */ + saddr = &sk->sk_v6_rcv_saddr; daddr = &sk->sk_v6_daddr; - } else if (req) { - saddr = &inet_rsk(req)->ir_v6_loc_addr; - daddr = &inet_rsk(req)->ir_v6_rmt_addr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; @@ -670,8 +624,7 @@ clear_hash_noput: return 1; } -static int __tcp_v6_inbound_md5_hash(struct sock *sk, - const struct sk_buff *skb) +static bool tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; @@ -685,44 +638,32 @@ static int __tcp_v6_inbound_md5_hash(struct sock *sk, /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) - return 0; + return false; if (hash_expected && !hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - return 1; + return true; } if (!hash_expected && hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); - return 1; + return true; } /* check the signature */ genhash = tcp_v6_md5_hash_skb(newhash, hash_expected, - NULL, NULL, skb); + NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), &ip6h->daddr, ntohs(th->dest)); - return 1; + return true; } - return 0; + return false; } - -static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) -{ - int ret; - - rcu_read_lock(); - ret = __tcp_v6_inbound_md5_hash(sk, skb); - rcu_read_unlock(); - - return ret; -} - #endif static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, @@ -747,7 +688,6 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, atomic_inc(&skb->users); ireq->pktopts = skb; } - ireq->ireq_family = AF_INET6; } static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, @@ -773,7 +713,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG - .md5_lookup = tcp_v6_reqsk_md5_lookup, + .req_md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, #endif .init_req = tcp_v6_init_req, @@ -930,7 +870,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) if (!key) goto release_sk1; - genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb); + genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; } else { @@ -996,17 +936,19 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) { - struct request_sock *req, **prev; const struct tcphdr *th = tcp_hdr(skb); + struct request_sock *req; struct sock *nsk; /* Find possible connection requests. */ - req = inet6_csk_search_req(sk, &prev, th->source, + req = inet6_csk_search_req(sk, th->source, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); - if (req) - return tcp_check_req(sk, skb, req, prev, false); - + if (req) { + nsk = tcp_check_req(sk, skb, req, false); + reqsk_put(req); + return nsk; + } nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), @@ -1078,11 +1020,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); - - ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - - newsk->sk_v6_rcv_saddr = newnp->saddr; + newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1231,7 +1169,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_done(newsk); goto out; } - __inet6_hash(newsk, NULL); + __inet_hash(newsk, NULL); return newsk; @@ -1583,7 +1521,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) if (sk) { skb->sk = sk; skb->destructor = sock_edemux; - if (sk->sk_state != TCP_TIME_WAIT) { + if (sk_fullsock(sk)) { struct dst_entry *dst = sk->sk_rx_dst; if (dst) @@ -1690,7 +1628,7 @@ static void tcp_v6_destroy_sock(struct sock *sk) static void get_openreq6(struct seq_file *seq, struct request_sock *req, int i, kuid_t uid) { - int ttd = req->expires - jiffies; + long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; @@ -1890,7 +1828,7 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .hash = tcp_v6_hash, + .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 70568a4548e4..7fe0329c0d37 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -53,11 +53,11 @@ #include <trace/events/skb.h> #include "udp_impl.h" -static unsigned int udp6_ehashfn(struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +static u32 udp6_ehashfn(const struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) { static u32 udp6_ehash_secret __read_mostly; static u32 udp_ipv6_hash_secret __read_mostly; @@ -104,9 +104,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 0; } -static unsigned int udp6_portaddr_hash(struct net *net, - const struct in6_addr *addr6, - unsigned int port) +static u32 udp6_portaddr_hash(const struct net *net, + const struct in6_addr *addr6, + unsigned int port) { unsigned int hash, mix = net_hash_mix(net); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ab889bb16b3c..7441e1e63893 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -54,7 +54,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Set the IPv6 fragment id if not set yet */ if (!skb_shinfo(skb)->ip6_frag_id) - ipv6_proxy_select_ident(skb); + ipv6_proxy_select_ident(dev_net(skb->dev), skb); segs = NULL; goto out; @@ -112,11 +112,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - if (skb_shinfo(skb)->ip6_frag_id) - fptr->identification = skb_shinfo(skb)->ip6_frag_id; - else - ipv6_select_ident(fptr, - (struct rt6_info *)skb_dst(skb)); + if (!skb_shinfo(skb)->ip6_frag_id) + ipv6_proxy_select_ident(dev_net(skb->dev), skb); + fptr->identification = skb_shinfo(skb)->ip6_frag_id; /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index ca3f29b98ae5..010f8bd2d577 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -114,6 +114,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) return err; skb->ignore_df = 1; + skb->protocol = htons(ETH_P_IPV6); return x->outer_mode->output2(x, skb); } @@ -122,7 +123,6 @@ EXPORT_SYMBOL(xfrm6_prepare_output); int xfrm6_output_finish(struct sk_buff *skb) { memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); - skb->protocol = htons(ETH_P_IPV6); #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8ddf2b545151..11dbcc1790d2 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -200,6 +200,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: + offset += ipv6_optlen(exthdr); if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { struct ip6_mh *mh; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3afe36824703..8d53d65bd2ab 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -58,13 +58,24 @@ struct ieee80211_local; #define IEEE80211_UNSET_POWER_LEVEL INT_MIN /* - * Some APs experience problems when working with U-APSD. Decrease the - * probability of that happening by using legacy mode for all ACs but VO. - * The AP that caused us trouble was a Cisco 4410N. It ignores our - * setting, and always treats non-VO ACs as legacy. + * Some APs experience problems when working with U-APSD. Decreasing the + * probability of that happening by using legacy mode for all ACs but VO isn't + * enough. + * + * Cisco 4410N originally forced us to enable VO by default only because it + * treated non-VO ACs as legacy. + * + * However some APs (notably Netgear R7000) silently reclassify packets to + * different ACs. Since u-APSD ACs require trigger frames for frame retrieval + * clients would never see some frames (e.g. ARP responses) or would fetch them + * accidentally after a long time. + * + * It makes little sense to enable u-APSD queues by default because it needs + * userspace applications to be aware of it to actually take advantage of the + * possible additional powersavings. Implicitly depending on driver autotrigger + * frame support doesn't make much sense. */ -#define IEEE80211_DEFAULT_UAPSD_QUEUES \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_VO +#define IEEE80211_DEFAULT_UAPSD_QUEUES 0 #define IEEE80211_DEFAULT_MAX_SP_LEN \ IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL @@ -453,6 +464,7 @@ struct ieee80211_if_managed { unsigned int flags; bool csa_waiting_bcn; + bool csa_ignored_same_chan; bool beacon_crc_valid; u32 beacon_crc; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9f6f3562396a..a4b1dd332e0f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1150,6 +1150,17 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; } + if (cfg80211_chandef_identical(&csa_ie.chandef, + &sdata->vif.bss_conf.chandef)) { + if (ifmgd->csa_ignored_same_chan) + return; + sdata_info(sdata, + "AP %pM tries to chanswitch to same channel, ignore\n", + ifmgd->associated->bssid); + ifmgd->csa_ignored_same_chan = true; + return; + } + mutex_lock(&local->mtx); mutex_lock(&local->chanctx_mtx); conf = rcu_dereference_protected(sdata->vif.chanctx_conf, @@ -1210,6 +1221,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, sdata->vif.csa_active = true; sdata->csa_chandef = csa_ie.chandef; sdata->csa_block_tx = csa_ie.mode; + ifmgd->csa_ignored_same_chan = false; if (sdata->csa_block_tx) ieee80211_stop_vif_queues(local, sdata, @@ -2090,6 +2102,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.csa_active = false; ifmgd->csa_waiting_bcn = false; + ifmgd->csa_ignored_same_chan = false; if (sdata->csa_block_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); @@ -3204,7 +3217,8 @@ static const u64 care_about_ies = (1ULL << WLAN_EID_CHANNEL_SWITCH) | (1ULL << WLAN_EID_PWR_CONSTRAINT) | (1ULL << WLAN_EID_HT_CAPABILITY) | - (1ULL << WLAN_EID_HT_OPERATION); + (1ULL << WLAN_EID_HT_OPERATION) | + (1ULL << WLAN_EID_EXT_CHANSWITCH_ANN); static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1101563357ea..944bdc04e913 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2214,6 +2214,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *) skb->data; mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + if (ieee80211_drop_unencrypted(rx, hdr->frame_control)) + return RX_DROP_MONITOR; + /* frame is in RMC, don't forward */ if (ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 8428f4a95479..747bdcf72e92 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3178,7 +3178,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, wdev_iter = &sdata_iter->wdev; if (sdata_iter == sdata || - rcu_access_pointer(sdata_iter->vif.chanctx_conf) == NULL || + !ieee80211_sdata_running(sdata_iter) || local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype)) continue; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 971cd7526f4b..f70e34a68f70 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -522,7 +522,6 @@ config NFT_NAT typical Network Address Translation (NAT) packet transformations. config NFT_QUEUE - depends on NETFILTER_XTABLES depends on NETFILTER_NETLINK_QUEUE tristate "Netfilter nf_tables queue module" help diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 08d95559b6f7..19b9cce6c210 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1405,9 +1405,11 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) mreq.imr_ifindex = dev->ifindex; + rtnl_lock(); lock_sock(sk); ret = ip_mc_join_group(sk, &mreq); release_sock(sk); + rtnl_unlock(); return ret; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3aedbda7658a..bf02932b7188 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -209,7 +209,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) struct sock *sk = skb->sk; struct rtable *ort = skb_rtable(skb); - if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT) + if (!skb->dev && sk && sk_fullsock(sk)) ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); } @@ -924,7 +924,8 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + struct net *net = skb_net(skb); + struct netns_ipvs *ipvs = net_ipvs(net); struct rtable *rt; /* Route to the other host */ __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ @@ -991,7 +992,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = ttl; - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index a4b5e2a435ac..45da11afa785 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -47,9 +47,11 @@ seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir) return 0; counter = acct->counter; - return seq_printf(s, "packets=%llu bytes=%llu ", - (unsigned long long)atomic64_read(&counter[dir].packets), - (unsigned long long)atomic64_read(&counter[dir].bytes)); + seq_printf(s, "packets=%llu bytes=%llu ", + (unsigned long long)atomic64_read(&counter[dir].packets), + (unsigned long long)atomic64_read(&counter[dir].bytes)); + + return 0; }; EXPORT_SYMBOL_GPL(seq_print_acct); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 91a1837acd0e..7a17070c5dab 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -561,7 +561,9 @@ static int exp_seq_show(struct seq_file *s, void *v) helper->expect_policy[expect->class].name); } - return seq_putc(s, '\n'); + seq_putc(s, '\n'); + + return 0; } static const struct seq_operations exp_seq_ops = { diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 0d8448f19dfe..675d12c69e32 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -212,6 +212,30 @@ void nf_log_packet(struct net *net, } EXPORT_SYMBOL(nf_log_packet); +void nf_log_trace(struct net *net, + u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, const char *fmt, ...) +{ + va_list args; + char prefix[NF_LOG_PREFIXLEN]; + const struct nf_logger *logger; + + rcu_read_lock(); + logger = rcu_dereference(net->nf.nf_loggers[pf]); + if (logger) { + va_start(args, fmt); + vsnprintf(prefix, sizeof(prefix), fmt, args); + va_end(args); + logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(nf_log_trace); + #define S_SIZE (1024 - (sizeof(unsigned int) + 1)) struct nf_log_buf { diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index a2233e77cf39..2631876ac55b 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -133,7 +133,7 @@ EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header); void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk) { - if (!sk || sk->sk_state == TCP_TIME_WAIT) + if (!sk || !sk_fullsock(sk)) return; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ea51833c8f5a..5604c2df05d1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -198,36 +198,31 @@ static int nft_delchain(struct nft_ctx *ctx) static inline bool nft_rule_is_active(struct net *net, const struct nft_rule *rule) { - return (rule->genmask & (1 << net->nft.gencursor)) == 0; -} - -static inline int gencursor_next(struct net *net) -{ - return net->nft.gencursor+1 == 1 ? 1 : 0; + return (rule->genmask & nft_genmask_cur(net)) == 0; } static inline int nft_rule_is_active_next(struct net *net, const struct nft_rule *rule) { - return (rule->genmask & (1 << gencursor_next(net))) == 0; + return (rule->genmask & nft_genmask_next(net)) == 0; } static inline void nft_rule_activate_next(struct net *net, struct nft_rule *rule) { /* Now inactive, will be active in the future */ - rule->genmask = (1 << net->nft.gencursor); + rule->genmask = nft_genmask_cur(net); } static inline void nft_rule_deactivate_next(struct net *net, struct nft_rule *rule) { - rule->genmask = (1 << gencursor_next(net)); + rule->genmask = nft_genmask_next(net); } static inline void nft_rule_clear(struct net *net, struct nft_rule *rule) { - rule->genmask &= ~(1 << gencursor_next(net)); + rule->genmask &= ~nft_genmask_next(net); } static int @@ -687,11 +682,10 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, if (!try_module_get(afi->owner)) return -EAFNOSUPPORT; + err = -ENOMEM; table = kzalloc(sizeof(*table), GFP_KERNEL); - if (table == NULL) { - module_put(afi->owner); - return -ENOMEM; - } + if (table == NULL) + goto err1; nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN); INIT_LIST_HEAD(&table->chains); @@ -700,13 +694,16 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); - if (err < 0) { - kfree(table); - module_put(afi->owner); - return err; - } + if (err < 0) + goto err2; + list_add_tail_rcu(&table->list, &afi->tables); return 0; +err2: + kfree(table); +err1: + module_put(afi->owner); + return err; } static int nft_flush_table(struct nft_ctx *ctx) @@ -1226,7 +1223,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_CHAIN_POLICY]) { if ((chain != NULL && - !(chain->flags & NFT_BASE_CHAIN)) || + !(chain->flags & NFT_BASE_CHAIN))) + return -EOPNOTSUPP; + + if (chain == NULL && nla[NFTA_CHAIN_HOOK] == NULL) return -EOPNOTSUPP; @@ -1349,6 +1349,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, rcu_assign_pointer(basechain->stats, stats); } + write_pnet(&basechain->pnet, net); basechain->type = type; chain = &basechain->chain; @@ -1376,7 +1377,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); - chain->net = net; chain->table = table; nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN); @@ -2690,6 +2690,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, goto err2; INIT_LIST_HEAD(&set->bindings); + write_pnet(&set->pnet, net); set->ops = ops; set->ktype = ktype; set->klen = desc.klen; @@ -2766,10 +2767,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, const struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); enum nft_registers dreg; dreg = nft_type_to_reg(set->dtype); - return nft_validate_data_load(ctx, dreg, &elem->data, + return nft_validate_data_load(ctx, dreg, nft_set_ext_data(ext), set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE); } @@ -2822,6 +2824,22 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, nf_tables_set_destroy(ctx, set); } +const struct nft_set_ext_type nft_set_ext_types[] = { + [NFT_SET_EXT_KEY] = { + .len = sizeof(struct nft_data), + .align = __alignof__(struct nft_data), + }, + [NFT_SET_EXT_DATA] = { + .len = sizeof(struct nft_data), + .align = __alignof__(struct nft_data), + }, + [NFT_SET_EXT_FLAGS] = { + .len = sizeof(u8), + .align = __alignof__(u8), + }, +}; +EXPORT_SYMBOL_GPL(nft_set_ext_types); + /* * Set elements */ @@ -2868,6 +2886,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -2875,20 +2894,20 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nest == NULL) goto nla_put_failure; - if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, &elem->key, NFT_DATA_VALUE, - set->klen) < 0) + if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), + NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; - if (set->flags & NFT_SET_MAP && - !(elem->flags & NFT_SET_ELEM_INTERVAL_END) && - nft_data_dump(skb, NFTA_SET_ELEM_DATA, &elem->data, + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && + nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, set->dlen) < 0) goto nla_put_failure; - if (elem->flags != 0) - if (nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(elem->flags))) - goto nla_put_failure; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, + htonl(*nft_set_ext_flags(ext)))) + goto nla_put_failure; nla_nest_end(skb, nest); return 0; @@ -3109,15 +3128,54 @@ static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx, return trans; } +static void *nft_set_elem_init(const struct nft_set *set, + const struct nft_set_ext_tmpl *tmpl, + const struct nft_data *key, + const struct nft_data *data, + gfp_t gfp) +{ + struct nft_set_ext *ext; + void *elem; + + elem = kzalloc(set->ops->elemsize + tmpl->len, gfp); + if (elem == NULL) + return NULL; + + ext = nft_set_elem_ext(set, elem); + nft_set_ext_init(ext, tmpl); + + memcpy(nft_set_ext_key(ext), key, set->klen); + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) + memcpy(nft_set_ext_data(ext), data, set->dlen); + + return elem; +} + +void nft_set_elem_destroy(const struct nft_set *set, void *elem) +{ + struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + + nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE); + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) + nft_data_uninit(nft_set_ext_data(ext), set->dtype); + + kfree(elem); +} +EXPORT_SYMBOL_GPL(nft_set_elem_destroy); + static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_data_desc d1, d2; + struct nft_set_ext_tmpl tmpl; + struct nft_set_ext *ext; struct nft_set_elem elem; struct nft_set_binding *binding; + struct nft_data data; enum nft_registers dreg; struct nft_trans *trans; + u32 flags; int err; if (set->size && set->nelems == set->size) @@ -3131,19 +3189,26 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_KEY] == NULL) return -EINVAL; - elem.flags = 0; + nft_set_ext_prepare(&tmpl); + + flags = 0; if (nla[NFTA_SET_ELEM_FLAGS] != NULL) { - elem.flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS])); - if (elem.flags & ~NFT_SET_ELEM_INTERVAL_END) + flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS])); + if (flags & ~NFT_SET_ELEM_INTERVAL_END) + return -EINVAL; + if (!(set->flags & NFT_SET_INTERVAL) && + flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; + if (flags != 0) + nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && - !(elem.flags & NFT_SET_ELEM_INTERVAL_END)) + !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; if (nla[NFTA_SET_ELEM_DATA] != NULL && - elem.flags & NFT_SET_ELEM_INTERVAL_END) + flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) @@ -3157,12 +3222,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (d1.type != NFT_DATA_VALUE || d1.len != set->klen) goto err2; - err = -EEXIST; - if (set->ops->get(set, &elem) == 0) - goto err2; + nft_set_ext_add(&tmpl, NFT_SET_EXT_KEY); if (nla[NFTA_SET_ELEM_DATA] != NULL) { - err = nft_data_init(ctx, &elem.data, &d2, nla[NFTA_SET_ELEM_DATA]); + err = nft_data_init(ctx, &data, &d2, nla[NFTA_SET_ELEM_DATA]); if (err < 0) goto err2; @@ -3179,29 +3242,43 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, }; err = nft_validate_data_load(&bind_ctx, dreg, - &elem.data, d2.type); + &data, d2.type); if (err < 0) goto err3; } + + nft_set_ext_add(&tmpl, NFT_SET_EXT_DATA); } + err = -ENOMEM; + elem.priv = nft_set_elem_init(set, &tmpl, &elem.key, &data, GFP_KERNEL); + if (elem.priv == NULL) + goto err3; + + ext = nft_set_elem_ext(set, elem.priv); + if (flags) + *nft_set_ext_flags(ext) = flags; + trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) - goto err3; + goto err4; + ext->genmask = nft_genmask_cur(ctx->net); err = set->ops->insert(set, &elem); if (err < 0) - goto err4; + goto err5; nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; -err4: +err5: kfree(trans); +err4: + kfree(elem.priv); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) - nft_data_uninit(&elem.data, d2.type); + nft_data_uninit(&data, d2.type); err2: nft_data_uninit(&elem.key, d1.type); err1: @@ -3274,19 +3351,24 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) goto err2; - err = set->ops->get(set, &elem); - if (err < 0) - goto err2; - trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); if (trans == NULL) { err = -ENOMEM; goto err2; } + elem.priv = set->ops->deactivate(set, &elem); + if (elem.priv == NULL) { + err = -ENOENT; + goto err3; + } + nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; + +err3: + kfree(trans); err2: nft_data_uninit(&elem.key, desc.type); err1: @@ -3524,6 +3606,10 @@ static void nf_tables_commit_release(struct nft_trans *trans) case NFT_MSG_DELSET: nft_set_destroy(nft_trans_set(trans)); break; + case NFT_MSG_DELSETELEM: + nft_set_elem_destroy(nft_trans_elem_set(trans), + nft_trans_elem(trans).priv); + break; } kfree(trans); } @@ -3538,7 +3624,7 @@ static int nf_tables_commit(struct sk_buff *skb) while (++net->nft.base_seq == 0); /* A new generation has just started */ - net->nft.gencursor = gencursor_next(net); + net->nft.gencursor = nft_gencursor_next(net); /* Make sure all packets have left the previous generation before * purging old rules. @@ -3609,24 +3695,21 @@ static int nf_tables_commit(struct sk_buff *skb) NFT_MSG_DELSET, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: - nf_tables_setelem_notify(&trans->ctx, - nft_trans_elem_set(trans), - &nft_trans_elem(trans), + te = (struct nft_trans_elem *)trans->data; + + te->set->ops->activate(te->set, &te->elem); + nf_tables_setelem_notify(&trans->ctx, te->set, + &te->elem, NFT_MSG_NEWSETELEM, 0); nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; + nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_DELSETELEM, 0); - te->set->ops->get(te->set, &te->elem); - nft_data_uninit(&te->elem.key, NFT_DATA_VALUE); - if (te->set->flags & NFT_SET_MAP && - !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_uninit(&te->elem.data, te->set->dtype); te->set->ops->remove(te->set, &te->elem); - nft_trans_destroy(trans); break; } } @@ -3658,6 +3741,10 @@ static void nf_tables_abort_release(struct nft_trans *trans) case NFT_MSG_NEWSET: nft_set_destroy(nft_trans_set(trans)); break; + case NFT_MSG_NEWSETELEM: + nft_set_elem_destroy(nft_trans_elem_set(trans), + nft_trans_elem(trans).priv); + break; } kfree(trans); } @@ -3728,16 +3815,15 @@ static int nf_tables_abort(struct sk_buff *skb) case NFT_MSG_NEWSETELEM: nft_trans_elem_set(trans)->nelems--; te = (struct nft_trans_elem *)trans->data; - te->set->ops->get(te->set, &te->elem); - nft_data_uninit(&te->elem.key, NFT_DATA_VALUE); - if (te->set->flags & NFT_SET_MAP && - !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_uninit(&te->elem.data, te->set->dtype); + te->set->ops->remove(te->set, &te->elem); - nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: + te = (struct nft_trans_elem *)trans->data; + nft_trans_elem_set(trans)->nelems++; + te->set->ops->activate(te->set, &te->elem); + nft_trans_destroy(trans); break; } @@ -3812,13 +3898,18 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, const struct nft_set_elem *elem) { - if (elem->flags & NFT_SET_ELEM_INTERVAL_END) + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_data *data; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; - switch (elem->data.verdict) { + data = nft_set_ext_data(ext); + switch (data->verdict) { case NFT_JUMP: case NFT_GOTO: - return nf_tables_check_loops(ctx, elem->data.chain); + return nf_tables_check_loops(ctx, data->chain); default: return 0; } diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 77165bf023f3..ef4dfcbaf149 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -8,6 +8,7 @@ * Development of this code funded by Astaro AG (http://www.astaro.com/) */ +#include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/list.h> @@ -37,7 +38,7 @@ static struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 4, + .level = LOGLEVEL_WARNING, .logflags = NF_LOG_MASK, }, }, @@ -49,10 +50,10 @@ static void __nft_trace_packet(const struct nft_pktinfo *pkt, { struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_packet(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, - pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", - chain->table->name, chain->name, comments[type], - rulenum); + nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, + pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", + chain->table->name, chain->name, comments[type], + rulenum); } static inline void nft_trace_packet(const struct nft_pktinfo *pkt, @@ -112,6 +113,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) { const struct nft_chain *chain = ops->priv, *basechain = chain; + const struct net *net = read_pnet(&nft_base_chain(basechain)->pnet); const struct nft_rule *rule; const struct nft_expr *expr, *last; struct nft_data data[NFT_REG_MAX + 1]; @@ -119,11 +121,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; struct nft_stats *stats; int rulenum; - /* - * Cache cursor to avoid problems in case that the cursor is updated - * while traversing the ruleset. - */ - unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor); + unsigned int gencursor = nft_genmask_cur(net); do_chain: rulenum = 0; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index a5599fc51a6f..54330fb5efaf 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) return -EINVAL; + /* Not all fields are initialized so first zero the tuple */ + memset(tuple, 0, sizeof(struct nf_conntrack_tuple)); + tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM])); tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 11d85b3813f2..957b83a0223b 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -539,7 +539,7 @@ __build_packet_message(struct nfnl_log_net *log, /* UID */ sk = skb->sk; - if (sk && sk->sk_state != TCP_TIME_WAIT) { + if (sk && sk_fullsock(sk)) { read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { struct file *file = sk->sk_socket->file; @@ -998,11 +998,13 @@ static int seq_show(struct seq_file *s, void *v) { const struct nfulnl_instance *inst = v; - return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n", - inst->group_num, - inst->peer_portid, inst->qlen, - inst->copy_mode, inst->copy_range, - inst->flushtimeout, atomic_read(&inst->use)); + seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n", + inst->group_num, + inst->peer_portid, inst->qlen, + inst->copy_mode, inst->copy_range, + inst->flushtimeout, atomic_read(&inst->use)); + + return 0; } static const struct seq_operations nful_seq_ops = { diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 0db8515e76da..86ee8b05adae 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -257,7 +257,7 @@ static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk) { const struct cred *cred; - if (sk->sk_state == TCP_TIME_WAIT) + if (!sk_fullsock(sk)) return 0; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 0b0fd4e36294..589b8487cd08 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -135,6 +135,9 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; @@ -348,6 +351,9 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: + if (proto) + entry->e6.ipv6.flags |= IP6T_F_PROTO; + entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index c82df0a48fcd..c7e1a9d7d46f 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -23,119 +23,130 @@ /* We target a hash table size of 4, element hint is 75% of final size */ #define NFT_HASH_ELEMENT_HINT 3 +struct nft_hash { + struct rhashtable ht; +}; + struct nft_hash_elem { struct rhash_head node; - struct nft_data key; - struct nft_data data[]; + struct nft_set_ext ext; }; -static bool nft_hash_lookup(const struct nft_set *set, - const struct nft_data *key, - struct nft_data *data) -{ - struct rhashtable *priv = nft_set_priv(set); - const struct nft_hash_elem *he; +struct nft_hash_cmp_arg { + const struct nft_set *set; + const struct nft_data *key; + u8 genmask; +}; - he = rhashtable_lookup(priv, key); - if (he && set->flags & NFT_SET_MAP) - nft_data_copy(data, he->data); +static const struct rhashtable_params nft_hash_params; - return !!he; +static inline u32 nft_hash_key(const void *data, u32 len, u32 seed) +{ + const struct nft_hash_cmp_arg *arg = data; + + return jhash(arg->key, len, seed); } -static int nft_hash_insert(const struct nft_set *set, - const struct nft_set_elem *elem) +static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) { - struct rhashtable *priv = nft_set_priv(set); - struct nft_hash_elem *he; - unsigned int size; + const struct nft_hash_elem *he = data; - if (elem->flags != 0) - return -EINVAL; + return jhash(nft_set_ext_key(&he->ext), len, seed); +} - size = sizeof(*he); - if (set->flags & NFT_SET_MAP) - size += sizeof(he->data[0]); +static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct nft_hash_cmp_arg *x = arg->key; + const struct nft_hash_elem *he = ptr; - he = kzalloc(size, GFP_KERNEL); - if (he == NULL) - return -ENOMEM; + if (nft_data_cmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) + return 1; + if (!nft_set_elem_active(&he->ext, x->genmask)) + return 1; + return 0; +} - nft_data_copy(&he->key, &elem->key); - if (set->flags & NFT_SET_MAP) - nft_data_copy(he->data, &elem->data); +static bool nft_hash_lookup(const struct nft_set *set, + const struct nft_data *key, + const struct nft_set_ext **ext) +{ + struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_elem *he; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_cur(read_pnet(&set->pnet)), + .set = set, + .key = key, + }; - rhashtable_insert(priv, &he->node); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) + *ext = &he->ext; - return 0; + return !!he; } -static void nft_hash_elem_destroy(const struct nft_set *set, - struct nft_hash_elem *he) +static int nft_hash_insert(const struct nft_set *set, + const struct nft_set_elem *elem) { - nft_data_uninit(&he->key, NFT_DATA_VALUE); - if (set->flags & NFT_SET_MAP) - nft_data_uninit(he->data, set->dtype); - kfree(he); + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_next(read_pnet(&set->pnet)), + .set = set, + .key = &elem->key, + }; + + return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params); } -static void nft_hash_remove(const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_hash_activate(const struct nft_set *set, + const struct nft_set_elem *elem) { - struct rhashtable *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; - rhashtable_remove(priv, elem->cookie); - synchronize_rcu(); - kfree(elem->cookie); + nft_set_elem_change_active(set, &he->ext); } -struct nft_compare_arg { - const struct nft_set *set; - struct nft_set_elem *elem; -}; - -static bool nft_hash_compare(void *ptr, void *arg) +static void *nft_hash_deactivate(const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash_elem *he = ptr; - struct nft_compare_arg *x = arg; - - if (!nft_data_cmp(&he->key, &x->elem->key, x->set->klen)) { - x->elem->cookie = he; - x->elem->flags = 0; - if (x->set->flags & NFT_SET_MAP) - nft_data_copy(&x->elem->data, he->data); + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_next(read_pnet(&set->pnet)), + .set = set, + .key = &elem->key, + }; - return true; - } + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) + nft_set_elem_change_active(set, &he->ext); - return false; + return he; } -static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem) +static void nft_hash_remove(const struct nft_set *set, + const struct nft_set_elem *elem) { - struct rhashtable *priv = nft_set_priv(set); - struct nft_compare_arg arg = { - .set = set, - .elem = elem, - }; + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; - if (rhashtable_lookup_compare(priv, &elem->key, - &nft_hash_compare, &arg)) - return 0; - - return -ENOENT; + rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); } static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_iter *iter) { - struct rhashtable *priv = nft_set_priv(set); - const struct nft_hash_elem *he; + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; struct rhashtable_iter hti; struct nft_set_elem elem; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int err; - err = rhashtable_walk_init(priv, &hti); + err = rhashtable_walk_init(&priv->ht, &hti); iter->err = err; if (err) return; @@ -153,15 +164,16 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, iter->err = err; goto out; } + + continue; } if (iter->count < iter->skip) goto cont; + if (!nft_set_elem_active(&he->ext, genmask)) + goto cont; - memcpy(&elem.key, &he->key, sizeof(elem.key)); - if (set->flags & NFT_SET_MAP) - memcpy(&elem.data, he->data, sizeof(elem.data)); - elem.flags = 0; + elem.priv = he; iter->err = iter->fn(ctx, set, iter, &elem); if (iter->err < 0) @@ -178,45 +190,41 @@ out: static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) { - return sizeof(struct rhashtable); + return sizeof(struct nft_hash); } +static const struct rhashtable_params nft_hash_params = { + .head_offset = offsetof(struct nft_hash_elem, node), + .hashfn = nft_hash_key, + .obj_hashfn = nft_hash_obj, + .obj_cmpfn = nft_hash_cmp, + .automatic_shrinking = true, +}; + static int nft_hash_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const tb[]) { - struct rhashtable *priv = nft_set_priv(set); - struct rhashtable_params params = { - .nelem_hint = desc->size ? : NFT_HASH_ELEMENT_HINT, - .head_offset = offsetof(struct nft_hash_elem, node), - .key_offset = offsetof(struct nft_hash_elem, key), - .key_len = set->klen, - .hashfn = jhash, - }; + struct nft_hash *priv = nft_set_priv(set); + struct rhashtable_params params = nft_hash_params; + + params.nelem_hint = desc->size ?: NFT_HASH_ELEMENT_HINT; + params.key_len = set->klen; - return rhashtable_init(priv, ¶ms); + return rhashtable_init(&priv->ht, ¶ms); } -static void nft_hash_destroy(const struct nft_set *set) +static void nft_hash_elem_destroy(void *ptr, void *arg) { - struct rhashtable *priv = nft_set_priv(set); - const struct bucket_table *tbl; - struct nft_hash_elem *he; - struct rhash_head *pos, *next; - unsigned int i; - - /* Stop an eventual async resizing */ - priv->being_destroyed = true; - mutex_lock(&priv->mutex); + nft_set_elem_destroy((const struct nft_set *)arg, ptr); +} - tbl = rht_dereference(priv->tbl, priv); - for (i = 0; i < tbl->size; i++) { - rht_for_each_entry_safe(he, pos, next, tbl, i, node) - nft_hash_elem_destroy(set, he); - } - mutex_unlock(&priv->mutex); +static void nft_hash_destroy(const struct nft_set *set) +{ + struct nft_hash *priv = nft_set_priv(set); - rhashtable_destroy(priv); + rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, + (void *)set); } static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, @@ -225,11 +233,8 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, unsigned int esize; esize = sizeof(struct nft_hash_elem); - if (features & NFT_SET_MAP) - esize += FIELD_SIZEOF(struct nft_hash_elem, data[0]); - if (desc->size) { - est->size = sizeof(struct rhashtable) + + est->size = sizeof(struct nft_hash) + roundup_pow_of_two(desc->size * 4 / 3) * sizeof(struct nft_hash_elem *) + desc->size * esize; @@ -249,11 +254,13 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, static struct nft_set_ops nft_hash_ops __read_mostly = { .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), .estimate = nft_hash_estimate, .init = nft_hash_init, .destroy = nft_hash_destroy, - .get = nft_hash_get, .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, .remove = nft_hash_remove, .lookup = nft_hash_lookup, .walk = nft_hash_walk, diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index bde05f28cf14..e18af9db2f04 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -78,7 +78,7 @@ static int nft_log_init(const struct nft_ctx *ctx, li->u.log.level = ntohl(nla_get_be32(tb[NFTA_LOG_LEVEL])); } else { - li->u.log.level = 4; + li->u.log.level = LOGLEVEL_WARNING; } if (tb[NFTA_LOG_FLAGS] != NULL) { li->u.log.logflags = diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 9615b8b9fb37..a5f30b8760ea 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -31,9 +31,13 @@ static void nft_lookup_eval(const struct nft_expr *expr, { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; + const struct nft_set_ext *ext; - if (set->ops->lookup(set, &data[priv->sreg], &data[priv->dreg])) + if (set->ops->lookup(set, &data[priv->sreg], &ext)) { + if (set->flags & NFT_SET_MAP) + nft_data_copy(&data[priv->dreg], nft_set_ext_data(ext)); return; + } data[NFT_REG_VERDICT].verdict = NFT_BREAK; } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e99911eda915..5197874372ec 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -83,7 +83,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, *(u16 *)dest->data = out->type; break; case NFT_META_SKUID: - if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT) + if (skb->sk == NULL || !sk_fullsock(skb->sk)) goto err; read_lock_bh(&skb->sk->sk_callback_lock); @@ -99,7 +99,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, read_unlock_bh(&skb->sk->sk_callback_lock); break; case NFT_META_SKGID: - if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT) + if (skb->sk == NULL || !sk_fullsock(skb->sk)) goto err; read_lock_bh(&skb->sk->sk_callback_lock); @@ -153,7 +153,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, } break; case NFT_META_CPU: - dest->data[0] = smp_processor_id(); + dest->data[0] = raw_smp_processor_id(); break; case NFT_META_IIFGROUP: if (in == NULL) diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index 46214f245665..42d0ca45fb9e 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -26,25 +26,26 @@ struct nft_rbtree { struct nft_rbtree_elem { struct rb_node node; - u16 flags; - struct nft_data key; - struct nft_data data[]; + struct nft_set_ext ext; }; + static bool nft_rbtree_lookup(const struct nft_set *set, const struct nft_data *key, - struct nft_data *data) + const struct nft_set_ext **ext) { const struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; - const struct rb_node *parent = priv->root.rb_node; + const struct rb_node *parent; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int d; spin_lock_bh(&nft_rbtree_lock); + parent = priv->root.rb_node; while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = nft_data_cmp(&rbe->key, key, set->klen); + d = nft_data_cmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = parent->rb_left; interval = rbe; @@ -52,12 +53,17 @@ static bool nft_rbtree_lookup(const struct nft_set *set, parent = parent->rb_right; else { found: - if (rbe->flags & NFT_SET_ELEM_INTERVAL_END) + if (!nft_set_elem_active(&rbe->ext, genmask)) { + parent = parent->rb_left; + continue; + } + if (nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(&rbe->ext) & + NFT_SET_ELEM_INTERVAL_END) goto out; - if (set->flags & NFT_SET_MAP) - nft_data_copy(data, rbe->data); - spin_unlock_bh(&nft_rbtree_lock); + + *ext = &rbe->ext; return true; } } @@ -71,23 +77,13 @@ out: return false; } -static void nft_rbtree_elem_destroy(const struct nft_set *set, - struct nft_rbtree_elem *rbe) -{ - nft_data_uninit(&rbe->key, NFT_DATA_VALUE); - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_uninit(rbe->data, set->dtype); - - kfree(rbe); -} - static int __nft_rbtree_insert(const struct nft_set *set, struct nft_rbtree_elem *new) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; + u8 genmask = nft_genmask_next(read_pnet(&set->pnet)); int d; parent = NULL; @@ -95,13 +91,18 @@ static int __nft_rbtree_insert(const struct nft_set *set, while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = nft_data_cmp(&rbe->key, &new->key, set->klen); + d = nft_data_cmp(nft_set_ext_key(&rbe->ext), + nft_set_ext_key(&new->ext), + set->klen); if (d < 0) p = &parent->rb_left; else if (d > 0) p = &parent->rb_right; - else - return -EEXIST; + else { + if (nft_set_elem_active(&rbe->ext, genmask)) + return -EEXIST; + p = &parent->rb_left; + } } rb_link_node(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); @@ -111,31 +112,13 @@ static int __nft_rbtree_insert(const struct nft_set *set, static int nft_rbtree_insert(const struct nft_set *set, const struct nft_set_elem *elem) { - struct nft_rbtree_elem *rbe; - unsigned int size; + struct nft_rbtree_elem *rbe = elem->priv; int err; - size = sizeof(*rbe); - if (set->flags & NFT_SET_MAP && - !(elem->flags & NFT_SET_ELEM_INTERVAL_END)) - size += sizeof(rbe->data[0]); - - rbe = kzalloc(size, GFP_KERNEL); - if (rbe == NULL) - return -ENOMEM; - - rbe->flags = elem->flags; - nft_data_copy(&rbe->key, &elem->key); - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_copy(rbe->data, &elem->data); - spin_lock_bh(&nft_rbtree_lock); err = __nft_rbtree_insert(set, rbe); - if (err < 0) - kfree(rbe); - spin_unlock_bh(&nft_rbtree_lock); + return err; } @@ -143,42 +126,49 @@ static void nft_rbtree_remove(const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe = elem->cookie; + struct nft_rbtree_elem *rbe = elem->priv; spin_lock_bh(&nft_rbtree_lock); rb_erase(&rbe->node, &priv->root); spin_unlock_bh(&nft_rbtree_lock); - kfree(rbe); } -static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem) +static void nft_rbtree_activate(const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_rbtree_elem *rbe = elem->priv; + + nft_set_elem_change_active(set, &rbe->ext); +} + +static void *nft_rbtree_deactivate(const struct nft_set *set, + const struct nft_set_elem *elem) { const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int d; - spin_lock_bh(&nft_rbtree_lock); while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = nft_data_cmp(&rbe->key, &elem->key, set->klen); + d = nft_data_cmp(nft_set_ext_key(&rbe->ext), &elem->key, + set->klen); if (d < 0) parent = parent->rb_left; else if (d > 0) parent = parent->rb_right; else { - elem->cookie = rbe; - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_copy(&elem->data, rbe->data); - elem->flags = rbe->flags; - spin_unlock_bh(&nft_rbtree_lock); - return 0; + if (!nft_set_elem_active(&rbe->ext, genmask)) { + parent = parent->rb_left; + continue; + } + nft_set_elem_change_active(set, &rbe->ext); + return rbe; } } - spin_unlock_bh(&nft_rbtree_lock); - return -ENOENT; + return NULL; } static void nft_rbtree_walk(const struct nft_ctx *ctx, @@ -186,21 +176,21 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_set_iter *iter) { const struct nft_rbtree *priv = nft_set_priv(set); - const struct nft_rbtree_elem *rbe; + struct nft_rbtree_elem *rbe; struct nft_set_elem elem; struct rb_node *node; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); spin_lock_bh(&nft_rbtree_lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (iter->count < iter->skip) goto cont; + if (!nft_set_elem_active(&rbe->ext, genmask)) + goto cont; - rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_data_copy(&elem.key, &rbe->key); - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_copy(&elem.data, rbe->data); - elem.flags = rbe->flags; + elem.priv = rbe; iter->err = iter->fn(ctx, set, iter, &elem); if (iter->err < 0) { @@ -237,7 +227,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_rbtree_elem_destroy(set, rbe); + nft_set_elem_destroy(set, rbe); } } @@ -247,9 +237,6 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, unsigned int nsize; nsize = sizeof(struct nft_rbtree_elem); - if (features & NFT_SET_MAP) - nsize += FIELD_SIZEOF(struct nft_rbtree_elem, data[0]); - if (desc->size) est->size = sizeof(struct nft_rbtree) + desc->size * nsize; else @@ -262,12 +249,14 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, static struct nft_set_ops nft_rbtree_ops __read_mostly = { .privsize = nft_rbtree_privsize, + .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, .init = nft_rbtree_init, .destroy = nft_rbtree_destroy, .insert = nft_rbtree_insert, .remove = nft_rbtree_remove, - .get = nft_rbtree_get, + .deactivate = nft_rbtree_deactivate, + .activate = nft_rbtree_activate, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .features = NFT_SET_INTERVAL | NFT_SET_MAP, diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index ef8a926752a9..c205b26a2bee 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -42,15 +42,21 @@ enum nf_tproxy_lookup_t { static bool tproxy_sk_is_transparent(struct sock *sk) { - if (sk->sk_state != TCP_TIME_WAIT) { - if (inet_sk(sk)->transparent) - return true; - sock_put(sk); - } else { + switch (sk->sk_state) { + case TCP_TIME_WAIT: if (inet_twsk(sk)->tw_transparent) return true; - inet_twsk_put(inet_twsk(sk)); + break; + case TCP_NEW_SYN_RECV: + if (inet_rsk(inet_reqsk(sk))->no_srccheck) + return true; + break; + default: + if (inet_sk(sk)->transparent) + return true; } + + sock_gen_put(sk); return false; } @@ -513,8 +519,8 @@ static int tproxy_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_ip6 *i = par->entryinfo; - if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) - && !(i->flags & IP6T_INV_PROTO)) + if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) && + !(i->invflags & IP6T_INV_PROTO)) return 0; pr_info("Can be used only in combination with " diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index f440f57a452f..50a52043650f 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -56,8 +56,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) /* This only makes sense in the FORWARD and POSTROUTING chains */ if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) && - (!!(nf_bridge->mask & BRNF_BRIDGED) ^ - !(info->invert & XT_PHYSDEV_OP_BRIDGED))) + (!!nf_bridge->physoutdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return false; if ((info->bitmask & XT_PHYSDEV_OP_ISIN && diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 13332dbf291d..895534e87a47 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -129,6 +129,20 @@ xt_socket_get_sock_v4(struct net *net, const u8 protocol, return NULL; } +static bool xt_socket_sk_is_transparent(struct sock *sk) +{ + switch (sk->sk_state) { + case TCP_TIME_WAIT: + return inet_twsk(sk)->tw_transparent; + + case TCP_NEW_SYN_RECV: + return inet_rsk(inet_reqsk(sk))->no_srccheck; + + default: + return inet_sk(sk)->transparent; + } +} + static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) @@ -195,16 +209,14 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && - sk->sk_state != TCP_TIME_WAIT && + sk_fullsock(sk) && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, - if XT_SOCKET_TRANSPARENT is used */ + * if XT_SOCKET_TRANSPARENT is used + */ if (info->flags & XT_SOCKET_TRANSPARENT) - transparent = ((sk->sk_state != TCP_TIME_WAIT && - inet_sk(sk)->transparent) || - (sk->sk_state == TCP_TIME_WAIT && - inet_twsk(sk)->tw_transparent)); + transparent = xt_socket_sk_is_transparent(sk); if (sk != skb->sk) sock_gen_put(sk); @@ -363,16 +375,14 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && - sk->sk_state != TCP_TIME_WAIT && + sk_fullsock(sk) && ipv6_addr_any(&sk->sk_v6_rcv_saddr)); /* Ignore non-transparent sockets, - if XT_SOCKET_TRANSPARENT is used */ + * if XT_SOCKET_TRANSPARENT is used + */ if (info->flags & XT_SOCKET_TRANSPARENT) - transparent = ((sk->sk_state != TCP_TIME_WAIT && - inet_sk(sk)->transparent) || - (sk->sk_state == TCP_TIME_WAIT && - inet_twsk(sk)->tw_transparent)); + transparent = xt_socket_sk_is_transparent(sk); if (sk != skb->sk) sock_gen_put(sk); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6b0f21950e09..19909d0786a2 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -116,6 +116,8 @@ static ATOMIC_NOTIFIER_HEAD(netlink_chain); static DEFINE_SPINLOCK(netlink_tap_lock); static struct list_head netlink_tap_all __read_mostly; +static const struct rhashtable_params netlink_rhashtable_params; + static inline u32 netlink_group_mask(u32 group) { return group ? 1 << (group - 1) : 0; @@ -970,41 +972,50 @@ netlink_unlock_table(void) struct netlink_compare_arg { - struct net *net; + possible_net_t pnet; u32 portid; }; -static bool netlink_compare(void *ptr, void *arg) +/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ +#define netlink_compare_arg_len \ + (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) + +static inline int netlink_compare(struct rhashtable_compare_arg *arg, + const void *ptr) { - struct netlink_compare_arg *x = arg; - struct sock *sk = ptr; + const struct netlink_compare_arg *x = arg->key; + const struct netlink_sock *nlk = ptr; - return nlk_sk(sk)->portid == x->portid && - net_eq(sock_net(sk), x->net); + return nlk->portid != x->portid || + !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); +} + +static void netlink_compare_arg_init(struct netlink_compare_arg *arg, + struct net *net, u32 portid) +{ + memset(arg, 0, sizeof(*arg)); + write_pnet(&arg->pnet, net); + arg->portid = portid; } static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, struct net *net) { - struct netlink_compare_arg arg = { - .net = net, - .portid = portid, - }; + struct netlink_compare_arg arg; - return rhashtable_lookup_compare(&table->hash, &portid, - &netlink_compare, &arg); + netlink_compare_arg_init(&arg, net, portid); + return rhashtable_lookup_fast(&table->hash, &arg, + netlink_rhashtable_params); } -static bool __netlink_insert(struct netlink_table *table, struct sock *sk) +static int __netlink_insert(struct netlink_table *table, struct sock *sk) { - struct netlink_compare_arg arg = { - .net = sock_net(sk), - .portid = nlk_sk(sk)->portid, - }; + struct netlink_compare_arg arg; - return rhashtable_lookup_compare_insert(&table->hash, - &nlk_sk(sk)->node, - &netlink_compare, &arg); + netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); + return rhashtable_lookup_insert_key(&table->hash, &arg, + &nlk_sk(sk)->node, + netlink_rhashtable_params); } static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) @@ -1066,9 +1077,10 @@ static int netlink_insert(struct sock *sk, u32 portid) nlk_sk(sk)->portid = portid; sock_hold(sk); - err = 0; - if (!__netlink_insert(table, sk)) { - err = -EADDRINUSE; + err = __netlink_insert(table, sk); + if (err) { + if (err == -EEXIST) + err = -EADDRINUSE; sock_put(sk); } @@ -1082,7 +1094,8 @@ static void netlink_remove(struct sock *sk) struct netlink_table *table; table = &nl_table[sk->sk_protocol]; - if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node)) { + if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, + netlink_rhashtable_params)) { WARN_ON(atomic_read(&sk->sk_refcnt) == 1); __sock_put(sk); } @@ -3114,17 +3127,28 @@ static struct pernet_operations __net_initdata netlink_net_ops = { .exit = netlink_net_exit, }; +static inline u32 netlink_hash(const void *data, u32 len, u32 seed) +{ + const struct netlink_sock *nlk = data; + struct netlink_compare_arg arg; + + netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); + return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); +} + +static const struct rhashtable_params netlink_rhashtable_params = { + .head_offset = offsetof(struct netlink_sock, node), + .key_len = netlink_compare_arg_len, + .obj_hashfn = netlink_hash, + .obj_cmpfn = netlink_compare, + .max_size = 65536, + .automatic_shrinking = true, +}; + static int __init netlink_proto_init(void) { int i; int err = proto_register(&netlink_proto, 0); - struct rhashtable_params ht_params = { - .head_offset = offsetof(struct netlink_sock, node), - .key_offset = offsetof(struct netlink_sock, portid), - .key_len = sizeof(u32), /* portid */ - .hashfn = jhash, - .max_shift = 16, /* 64K */ - }; if (err != 0) goto out; @@ -3136,7 +3160,8 @@ static int __init netlink_proto_init(void) goto panic; for (i = 0; i < MAX_LINKS; i++) { - if (rhashtable_init(&nl_table[i].hash, &ht_params) < 0) { + if (rhashtable_init(&nl_table[i].hash, + &netlink_rhashtable_params) < 0) { while (--i > 0) rhashtable_destroy(&nl_table[i].hash); kfree(nl_table); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b91ac5946ad1..5102c3cc4eec 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1916,14 +1916,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } } - if (skb->ip_summed == CHECKSUM_PARTIAL) - status |= TP_STATUS_CSUMNOTREADY; - snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + status |= TP_STATUS_CSUMNOTREADY; + else if (skb->pkt_type != PACKET_OUTGOING && + (skb->ip_summed == CHECKSUM_COMPLETE || + skb_csum_unnecessary(skb))) + status |= TP_STATUS_CSUM_VALID; + if (snaplen > res) snaplen = res; @@ -3030,6 +3035,11 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; + else if (skb->pkt_type != PACKET_OUTGOING && + (skb->ip_summed == CHECKSUM_COMPLETE || + skb_csum_unnecessary(skb))) + aux.tp_status |= TP_STATUS_CSUM_VALID; + aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index a817705ce2d0..dba8d0864f18 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -88,7 +88,9 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, int *unpinned); static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr); -static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id) +static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst, + struct rds_iw_device **rds_iwdev, + struct rdma_cm_id **cm_id) { struct rds_iw_device *iwdev; struct rds_iw_cm_id *i_cm_id; @@ -112,15 +114,15 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd src_addr->sin_port, dst_addr->sin_addr.s_addr, dst_addr->sin_port, - rs->rs_bound_addr, - rs->rs_bound_port, - rs->rs_conn_addr, - rs->rs_conn_port); + src->sin_addr.s_addr, + src->sin_port, + dst->sin_addr.s_addr, + dst->sin_port); #ifdef WORKING_TUPLE_DETECTION - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr && - src_addr->sin_port == rs->rs_bound_port && - dst_addr->sin_addr.s_addr == rs->rs_conn_addr && - dst_addr->sin_port == rs->rs_conn_port) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr && + src_addr->sin_port == src->sin_port && + dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr && + dst_addr->sin_port == dst->sin_port) { #else /* FIXME - needs to compare the local and remote * ipaddr/port tuple, but the ipaddr is the only @@ -128,7 +130,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd * zero'ed. It doesn't appear to be properly populated * during connection setup... */ - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) { #endif spin_unlock_irq(&iwdev->spinlock); *rds_iwdev = iwdev; @@ -180,19 +182,13 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i { struct sockaddr_in *src_addr, *dst_addr; struct rds_iw_device *rds_iwdev_old; - struct rds_sock rs; struct rdma_cm_id *pcm_id; int rc; src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr; dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr; - rs.rs_bound_addr = src_addr->sin_addr.s_addr; - rs.rs_bound_port = src_addr->sin_port; - rs.rs_conn_addr = dst_addr->sin_addr.s_addr; - rs.rs_conn_port = dst_addr->sin_port; - - rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id); + rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id); if (rc) rds_iw_remove_cm_id(rds_iwdev, cm_id); @@ -598,9 +594,17 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_iw_device *rds_iwdev; struct rds_iw_mr *ibmr = NULL; struct rdma_cm_id *cm_id; + struct sockaddr_in src = { + .sin_addr.s_addr = rs->rs_bound_addr, + .sin_port = rs->rs_bound_port, + }; + struct sockaddr_in dst = { + .sin_addr.s_addr = rs->rs_conn_addr, + .sin_port = rs->rs_conn_port, + }; int ret; - ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id); + ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id); if (ret || !cm_id) { ret = -ENODEV; goto out; diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index a4f883e2d66f..b92beded7459 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -87,7 +87,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (!skb) { /* nothing remains on the queue */ if (copied && - (msg->msg_flags & MSG_PEEK || timeo == 0)) + (flags & MSG_PEEK || timeo == 0)) goto out; /* wait for a message to turn up */ diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 82c5d7fc1988..4d2cede17468 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -13,71 +13,140 @@ #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/filter.h> +#include <linux/bpf.h> + #include <net/netlink.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_bpf.h> #include <net/tc_act/tc_bpf.h> -#define BPF_TAB_MASK 15 +#define BPF_TAB_MASK 15 +#define ACT_BPF_NAME_LEN 256 + +struct tcf_bpf_cfg { + struct bpf_prog *filter; + struct sock_filter *bpf_ops; + char *bpf_name; + u32 bpf_fd; + u16 bpf_num_ops; +}; -static int tcf_bpf(struct sk_buff *skb, const struct tc_action *a, +static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { - struct tcf_bpf *b = a->priv; - int action; - int filter_res; - - spin_lock(&b->tcf_lock); - b->tcf_tm.lastuse = jiffies; - bstats_update(&b->tcf_bstats, skb); - action = b->tcf_action; - - filter_res = BPF_PROG_RUN(b->filter, skb); - if (filter_res == 0) { - /* Return code 0 from the BPF program - * is being interpreted as a drop here. - */ - action = TC_ACT_SHOT; - b->tcf_qstats.drops++; + struct tcf_bpf *prog = act->priv; + int action, filter_res; + + spin_lock(&prog->tcf_lock); + + prog->tcf_tm.lastuse = jiffies; + bstats_update(&prog->tcf_bstats, skb); + + /* Needed here for accessing maps. */ + rcu_read_lock(); + filter_res = BPF_PROG_RUN(prog->filter, skb); + rcu_read_unlock(); + + /* A BPF program may overwrite the default action opcode. + * Similarly as in cls_bpf, if filter_res == -1 we use the + * default action specified from tc. + * + * In case a different well-known TC_ACT opcode has been + * returned, it will overwrite the default one. + * + * For everything else that is unkown, TC_ACT_UNSPEC is + * returned. + */ + switch (filter_res) { + case TC_ACT_PIPE: + case TC_ACT_RECLASSIFY: + case TC_ACT_OK: + action = filter_res; + break; + case TC_ACT_SHOT: + action = filter_res; + prog->tcf_qstats.drops++; + break; + case TC_ACT_UNSPEC: + action = prog->tcf_action; + break; + default: + action = TC_ACT_UNSPEC; + break; } - spin_unlock(&b->tcf_lock); + spin_unlock(&prog->tcf_lock); return action; } -static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *a, +static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog) +{ + return !prog->bpf_ops; +} + +static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog, + struct sk_buff *skb) +{ + struct nlattr *nla; + + if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops)) + return -EMSGSIZE; + + nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops * + sizeof(struct sock_filter)); + if (nla == NULL) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); + + return 0; +} + +static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, + struct sk_buff *skb) +{ + if (nla_put_u32(skb, TCA_ACT_BPF_FD, prog->bpf_fd)) + return -EMSGSIZE; + + if (prog->bpf_name && + nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) + return -EMSGSIZE; + + return 0; +} + +static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref) { unsigned char *tp = skb_tail_pointer(skb); - struct tcf_bpf *b = a->priv; + struct tcf_bpf *prog = act->priv; struct tc_act_bpf opt = { - .index = b->tcf_index, - .refcnt = b->tcf_refcnt - ref, - .bindcnt = b->tcf_bindcnt - bind, - .action = b->tcf_action, + .index = prog->tcf_index, + .refcnt = prog->tcf_refcnt - ref, + .bindcnt = prog->tcf_bindcnt - bind, + .action = prog->tcf_action, }; - struct tcf_t t; - struct nlattr *nla; + struct tcf_t tm; + int ret; if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, b->bpf_num_ops)) - goto nla_put_failure; - - nla = nla_reserve(skb, TCA_ACT_BPF_OPS, b->bpf_num_ops * - sizeof(struct sock_filter)); - if (!nla) + if (tcf_bpf_is_ebpf(prog)) + ret = tcf_bpf_dump_ebpf_info(prog, skb); + else + ret = tcf_bpf_dump_bpf_info(prog, skb); + if (ret) goto nla_put_failure; - memcpy(nla_data(nla), b->bpf_ops, nla_len(nla)); + tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install); + tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse); + tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires); - t.install = jiffies_to_clock_t(jiffies - b->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - b->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(b->tcf_tm.expires); - if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(t), &t)) + if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm)) goto nla_put_failure; + return skb->len; nla_put_failure: @@ -87,36 +156,21 @@ nla_put_failure: static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, + [TCA_ACT_BPF_FD] = { .type = NLA_U32 }, + [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN }, [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; -static int tcf_bpf_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action *a, - int ovr, int bind) +static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { - struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; - struct tc_act_bpf *parm; - struct tcf_bpf *b; - u16 bpf_size, bpf_num_ops; struct sock_filter *bpf_ops; - struct sock_fprog_kern tmp; + struct sock_fprog_kern fprog_tmp; struct bpf_prog *fp; + u16 bpf_size, bpf_num_ops; int ret; - if (!nla) - return -EINVAL; - - ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy); - if (ret < 0) - return ret; - - if (!tb[TCA_ACT_BPF_PARMS] || - !tb[TCA_ACT_BPF_OPS_LEN] || !tb[TCA_ACT_BPF_OPS]) - return -EINVAL; - parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]); if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) return -EINVAL; @@ -126,68 +180,165 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return -EINVAL; bpf_ops = kzalloc(bpf_size, GFP_KERNEL); - if (!bpf_ops) + if (bpf_ops == NULL) return -ENOMEM; memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size); - tmp.len = bpf_num_ops; - tmp.filter = bpf_ops; + fprog_tmp.len = bpf_num_ops; + fprog_tmp.filter = bpf_ops; - ret = bpf_prog_create(&fp, &tmp); - if (ret) - goto free_bpf_ops; + ret = bpf_prog_create(&fp, &fprog_tmp); + if (ret < 0) { + kfree(bpf_ops); + return ret; + } - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*b), bind); - if (ret) + cfg->bpf_ops = bpf_ops; + cfg->bpf_num_ops = bpf_num_ops; + cfg->filter = fp; + + return 0; +} + +static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) +{ + struct bpf_prog *fp; + char *name = NULL; + u32 bpf_fd; + + bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]); + + fp = bpf_prog_get(bpf_fd); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + if (fp->type != BPF_PROG_TYPE_SCHED_ACT) { + bpf_prog_put(fp); + return -EINVAL; + } + + if (tb[TCA_ACT_BPF_NAME]) { + name = kmemdup(nla_data(tb[TCA_ACT_BPF_NAME]), + nla_len(tb[TCA_ACT_BPF_NAME]), + GFP_KERNEL); + if (!name) { + bpf_prog_put(fp); + return -ENOMEM; + } + } + + cfg->bpf_fd = bpf_fd; + cfg->bpf_name = name; + cfg->filter = fp; + + return 0; +} + +static int tcf_bpf_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *act, + int replace, int bind) +{ + struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tc_act_bpf *parm; + struct tcf_bpf *prog; + struct tcf_bpf_cfg cfg; + bool is_bpf, is_ebpf; + int ret; + + if (!nla) + return -EINVAL; + + ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy); + if (ret < 0) + return ret; + + is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; + is_ebpf = tb[TCA_ACT_BPF_FD]; + + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || + !tb[TCA_ACT_BPF_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_ACT_BPF_PARMS]); + + memset(&cfg, 0, sizeof(cfg)); + + ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : + tcf_bpf_init_from_efd(tb, &cfg); + if (ret < 0) + return ret; + + if (!tcf_hash_check(parm->index, act, bind)) { + ret = tcf_hash_create(parm->index, est, act, + sizeof(*prog), bind); + if (ret < 0) goto destroy_fp; ret = ACT_P_CREATED; } else { + /* Don't override defaults. */ if (bind) goto destroy_fp; - tcf_hash_release(a, bind); - if (!ovr) { + + tcf_hash_release(act, bind); + if (!replace) { ret = -EEXIST; goto destroy_fp; } } - b = to_bpf(a); - spin_lock_bh(&b->tcf_lock); - b->tcf_action = parm->action; - b->bpf_num_ops = bpf_num_ops; - b->bpf_ops = bpf_ops; - b->filter = fp; - spin_unlock_bh(&b->tcf_lock); + prog = to_bpf(act); + spin_lock_bh(&prog->tcf_lock); + + prog->bpf_ops = cfg.bpf_ops; + prog->bpf_name = cfg.bpf_name; + + if (cfg.bpf_num_ops) + prog->bpf_num_ops = cfg.bpf_num_ops; + if (cfg.bpf_fd) + prog->bpf_fd = cfg.bpf_fd; + + prog->tcf_action = parm->action; + prog->filter = cfg.filter; + + spin_unlock_bh(&prog->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(act); + return ret; destroy_fp: - bpf_prog_destroy(fp); -free_bpf_ops: - kfree(bpf_ops); + if (is_ebpf) + bpf_prog_put(cfg.filter); + else + bpf_prog_destroy(cfg.filter); + + kfree(cfg.bpf_ops); + kfree(cfg.bpf_name); + return ret; } -static void tcf_bpf_cleanup(struct tc_action *a, int bind) +static void tcf_bpf_cleanup(struct tc_action *act, int bind) { - struct tcf_bpf *b = a->priv; + const struct tcf_bpf *prog = act->priv; - bpf_prog_destroy(b->filter); + if (tcf_bpf_is_ebpf(prog)) + bpf_prog_put(prog->filter); + else + bpf_prog_destroy(prog->filter); } -static struct tc_action_ops act_bpf_ops = { - .kind = "bpf", - .type = TCA_ACT_BPF, - .owner = THIS_MODULE, - .act = tcf_bpf, - .dump = tcf_bpf_dump, - .cleanup = tcf_bpf_cleanup, - .init = tcf_bpf_init, +static struct tc_action_ops act_bpf_ops __read_mostly = { + .kind = "bpf", + .type = TCA_ACT_BPF, + .owner = THIS_MODULE, + .act = tcf_bpf, + .dump = tcf_bpf_dump, + .cleanup = tcf_bpf_cleanup, + .init = tcf_bpf_init, }; static int __init bpf_init_module(void) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 375e51b71c80..cab9e9b43967 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -78,8 +78,11 @@ struct tc_u_hnode { struct tc_u_common *tp_c; int refcnt; unsigned int divisor; - struct tc_u_knode __rcu *ht[1]; struct rcu_head rcu; + /* The 'ht' field MUST be the last field in structure to allow for + * more entries allocated at end of structure. + */ + struct tc_u_knode __rcu *ht[1]; }; struct tc_u_common { diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f1a65398f311..f09de7fac2e6 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -102,11 +102,6 @@ static int sctp_autobind(struct sock *sk); static void sctp_sock_migrate(struct sock *, struct sock *, struct sctp_association *, sctp_socket_type_t); -extern struct kmem_cache *sctp_bucket_cachep; -extern long sysctl_sctp_mem[3]; -extern int sysctl_sctp_rmem[3]; -extern int sysctl_sctp_wmem[3]; - static int sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; struct percpu_counter sctp_sockets_allocated; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 2e9ada10fd84..26d50c565f54 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -58,10 +58,6 @@ static unsigned long max_autoclose_max = (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; -extern long sysctl_sctp_mem[3]; -extern int sysctl_sctp_rmem[3]; -extern int sysctl_sctp_wmem[3]; - static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/net/socket.c b/net/socket.c index 95d3085cb477..073809f4125f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -798,7 +798,8 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; - struct msghdr msg = {.msg_iter = *to}; + struct msghdr msg = {.msg_iter = *to, + .msg_iocb = iocb}; ssize_t res; if (file->f_flags & O_NONBLOCK) @@ -819,7 +820,8 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; - struct msghdr msg = {.msg_iter = *from}; + struct msghdr msg = {.msg_iter = *from, + .msg_iocb = iocb}; ssize_t res; if (iocb->ki_pos != 0) @@ -1650,6 +1652,8 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, if (len > INT_MAX) len = INT_MAX; + if (unlikely(!access_ok(VERIFY_READ, buff, len))) + return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1708,6 +1712,8 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, if (size > INT_MAX) size = INT_MAX; + if (unlikely(!access_ok(VERIFY_WRITE, ubuf, size))) + return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1890,6 +1896,8 @@ static ssize_t copy_msghdr_from_user(struct msghdr *kmsg, if (nr_segs > UIO_MAXIOV) return -EMSGSIZE; + kmsg->msg_iocb = NULL; + err = rw_copy_check_uvector(save_addr ? READ : WRITE, uiov, nr_segs, UIO_FASTIOV, *iov, iov); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index b7a23132c610..46568b85c333 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -28,11 +28,11 @@ int netdev_switch_parent_id_get(struct net_device *dev, struct netdev_phys_item_id *psid) { - const struct net_device_ops *ops = dev->netdev_ops; + const struct swdev_ops *ops = dev->swdev_ops; - if (!ops->ndo_switch_parent_id_get) + if (!ops || !ops->swdev_parent_id_get) return -EOPNOTSUPP; - return ops->ndo_switch_parent_id_get(dev, psid); + return ops->swdev_parent_id_get(dev, psid); } EXPORT_SYMBOL_GPL(netdev_switch_parent_id_get); @@ -46,12 +46,21 @@ EXPORT_SYMBOL_GPL(netdev_switch_parent_id_get); */ int netdev_switch_port_stp_update(struct net_device *dev, u8 state) { - const struct net_device_ops *ops = dev->netdev_ops; + const struct swdev_ops *ops = dev->swdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; - if (!ops->ndo_switch_port_stp_update) - return -EOPNOTSUPP; - WARN_ON(!ops->ndo_switch_parent_id_get); - return ops->ndo_switch_port_stp_update(dev, state); + if (ops && ops->swdev_port_stp_update) + return ops->swdev_port_stp_update(dev, state); + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = netdev_switch_port_stp_update(lower_dev, state); + if (err && err != -EOPNOTSUPP) + return err; + } + + return err; } EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update); @@ -230,17 +239,17 @@ EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_dellink); static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) { - const struct net_device_ops *ops = dev->netdev_ops; + const struct swdev_ops *ops = dev->swdev_ops; struct net_device *lower_dev; struct net_device *port_dev; struct list_head *iter; /* Recusively search down until we find a sw port dev. - * (A sw port dev supports ndo_switch_parent_id_get). + * (A sw port dev supports swdev_parent_id_get). */ if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD && - ops->ndo_switch_parent_id_get) + ops && ops->swdev_parent_id_get) return dev; netdev_for_each_lower_dev(dev, lower_dev, iter) { @@ -304,7 +313,7 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id) { struct net_device *dev; - const struct net_device_ops *ops; + const struct swdev_ops *ops; int err = 0; /* Don't offload route if using custom ip rules or if @@ -322,12 +331,12 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, dev = netdev_switch_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->netdev_ops; + ops = dev->swdev_ops; - if (ops->ndo_switch_fib_ipv4_add) { - err = ops->ndo_switch_fib_ipv4_add(dev, htonl(dst), dst_len, - fi, tos, type, nlflags, - tb_id); + if (ops->swdev_fib_ipv4_add) { + err = ops->swdev_fib_ipv4_add(dev, htonl(dst), dst_len, + fi, tos, type, nlflags, + tb_id); if (!err) fi->fib_flags |= RTNH_F_EXTERNAL; } @@ -352,7 +361,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { struct net_device *dev; - const struct net_device_ops *ops; + const struct swdev_ops *ops; int err = 0; if (!(fi->fib_flags & RTNH_F_EXTERNAL)) @@ -361,11 +370,11 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, dev = netdev_switch_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->netdev_ops; + ops = dev->swdev_ops; - if (ops->ndo_switch_fib_ipv4_del) { - err = ops->ndo_switch_fib_ipv4_del(dev, htonl(dst), dst_len, - fi, tos, type, tb_id); + if (ops->swdev_fib_ipv4_del) { + err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len, + fi, tos, type, tb_id); if (!err) fi->fib_flags &= ~RTNH_F_EXTERNAL; } diff --git a/net/tipc/addr.c b/net/tipc/addr.c index 48fd3b5a73fb..ba7daa864d44 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -38,6 +38,13 @@ #include "addr.h" #include "core.h" +u32 tipc_own_addr(struct net *net) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + + return tn->own_addr; +} + /** * in_own_cluster - test for cluster inclusion; <0.0.0> always matches */ diff --git a/net/tipc/addr.h b/net/tipc/addr.h index c700c2d28e09..7ba6d5c8ae40 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -55,6 +55,7 @@ static inline u32 tipc_cluster_mask(u32 addr) return addr & TIPC_CLUSTER_MASK; } +u32 tipc_own_addr(struct net *net); int in_own_cluster(struct net *net, u32 addr); int in_own_cluster_exact(struct net *net, u32 addr); int in_own_node(struct net *net, u32 addr); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 5aff0844d4d3..ae558dd7f8ee 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -62,21 +62,8 @@ static void tipc_bclink_lock(struct net *net) static void tipc_bclink_unlock(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_node *node = NULL; - if (likely(!tn->bclink->flags)) { - spin_unlock_bh(&tn->bclink->lock); - return; - } - - if (tn->bclink->flags & TIPC_BCLINK_RESET) { - tn->bclink->flags &= ~TIPC_BCLINK_RESET; - node = tipc_bclink_retransmit_to(net); - } spin_unlock_bh(&tn->bclink->lock); - - if (node) - tipc_link_reset_all(node); } void tipc_bclink_input(struct net *net) @@ -91,13 +78,6 @@ uint tipc_bclink_get_mtu(void) return MAX_PKT_DEFAULT_MCAST; } -void tipc_bclink_set_flags(struct net *net, unsigned int flags) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - - tn->bclink->flags |= flags; -} - static u32 bcbuf_acks(struct sk_buff *buf) { return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle; @@ -156,7 +136,6 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) seqno : node->bclink.last_sent; } - /** * tipc_bclink_retransmit_to - get most recent node to request retransmission * @@ -350,13 +329,12 @@ static void bclink_peek_nack(struct net *net, struct tipc_msg *msg) return; tipc_node_lock(n_ptr); - if (n_ptr->bclink.recv_permitted && (n_ptr->bclink.last_in != n_ptr->bclink.last_sent) && (n_ptr->bclink.last_in == msg_bcgap_after(msg))) n_ptr->bclink.oos_state = 2; - tipc_node_unlock(n_ptr); + tipc_node_put(n_ptr); } /* tipc_bclink_xmit - deliver buffer chain to all nodes in cluster @@ -476,17 +454,18 @@ void tipc_bclink_rcv(struct net *net, struct sk_buff *buf) goto unlock; if (msg_destnode(msg) == tn->own_addr) { tipc_bclink_acknowledge(node, msg_bcast_ack(msg)); - tipc_node_unlock(node); tipc_bclink_lock(net); bcl->stats.recv_nacks++; tn->bclink->retransmit_to = node; bclink_retransmit_pkt(tn, msg_bcgap_after(msg), msg_bcgap_to(msg)); tipc_bclink_unlock(net); + tipc_node_unlock(node); } else { tipc_node_unlock(node); bclink_peek_nack(net, msg); } + tipc_node_put(node); goto exit; } @@ -523,11 +502,13 @@ receive: tipc_bclink_unlock(net); tipc_node_unlock(node); } else if (msg_user(msg) == MSG_FRAGMENTER) { - tipc_buf_append(&node->bclink.reasm_buf, &buf); - if (unlikely(!buf && !node->bclink.reasm_buf)) - goto unlock; tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); + tipc_buf_append(&node->bclink.reasm_buf, &buf); + if (unlikely(!buf && !node->bclink.reasm_buf)) { + tipc_bclink_unlock(net); + goto unlock; + } bcl->stats.recv_fragments++; if (buf) { bcl->stats.recv_fragmented++; @@ -589,6 +570,7 @@ receive: unlock: tipc_node_unlock(node); + tipc_node_put(node); exit: kfree_skb(buf); } @@ -829,7 +811,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->queue_limit[0])) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window)) goto prop_msg_full; nla_nest_end(msg->skb, prop); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 43f397fbac55..4bdc12277d33 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -55,7 +55,6 @@ struct tipc_bcbearer_pair { struct tipc_bearer *secondary; }; -#define TIPC_BCLINK_RESET 1 #define BCBEARER MAX_BEARERS /** @@ -86,7 +85,6 @@ struct tipc_bcbearer { * @lock: spinlock governing access to structure * @link: (non-standard) broadcast link structure * @node: (non-standard) node structure representing b'cast link's peer node - * @flags: represent bclink states * @bcast_nodes: map of broadcast-capable nodes * @retransmit_to: node that most recently requested a retransmit * @@ -96,7 +94,6 @@ struct tipc_bclink { spinlock_t lock; struct tipc_link link; struct tipc_node node; - unsigned int flags; struct sk_buff_head arrvq; struct sk_buff_head inputq; struct tipc_node_map bcast_nodes; @@ -117,7 +114,6 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, int tipc_bclink_init(struct net *net); void tipc_bclink_stop(struct net *net); -void tipc_bclink_set_flags(struct net *tn, unsigned int flags); void tipc_bclink_add_node(struct net *net, u32 addr); void tipc_bclink_remove_node(struct net *net, u32 addr); struct tipc_node *tipc_bclink_retransmit_to(struct net *tn); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 169f3dd038b9..967e292f53c8 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -260,6 +260,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, } } tipc_node_unlock(node); + tipc_node_put(node); } /** diff --git a/net/tipc/link.c b/net/tipc/link.c index bc49120bfb44..514466efc25c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -139,6 +139,13 @@ static void tipc_link_put(struct tipc_link *l_ptr) kref_put(&l_ptr->ref, tipc_link_release); } +static struct tipc_link *tipc_parallel_link(struct tipc_link *l) +{ + if (l->owner->active_links[0] != l) + return l->owner->active_links[0]; + return l->owner->active_links[1]; +} + static void link_init_max_pkt(struct tipc_link *l_ptr) { struct tipc_node *node = l_ptr->owner; @@ -310,7 +317,6 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, link_init_max_pkt(l_ptr); l_ptr->priority = b_ptr->priority; tipc_link_set_queue_limits(l_ptr, b_ptr->window); - l_ptr->next_out_no = 1; __skb_queue_head_init(&l_ptr->transmq); __skb_queue_head_init(&l_ptr->backlogq); @@ -368,28 +374,43 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id, } /** - * link_schedule_user - schedule user for wakeup after congestion + * link_schedule_user - schedule a message sender for wakeup after congestion * @link: congested link - * @oport: sending port - * @chain_sz: size of buffer chain that was attempted sent - * @imp: importance of message attempted sent + * @list: message that was attempted sent * Create pseudo msg to send back to user when congestion abates + * Only consumes message if there is an error */ -static bool link_schedule_user(struct tipc_link *link, u32 oport, - uint chain_sz, uint imp) +static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) { - struct sk_buff *buf; + 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); + struct sk_buff *skb; - buf = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, - link_own_addr(link), link_own_addr(link), - oport, 0, 0); - if (!buf) - return false; - TIPC_SKB_CB(buf)->chain_sz = chain_sz; - TIPC_SKB_CB(buf)->chain_imp = imp; - skb_queue_tail(&link->wakeupq, buf); + /* This really cannot happen... */ + if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) { + pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); + tipc_link_reset(link); + goto err; + } + /* Non-blocking sender: */ + if (TIPC_SKB_CB(skb_peek(list))->wakeup_pending) + return -ELINKCONG; + + /* Create and schedule wakeup pseudo message */ + skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, + addr, addr, oport, 0, 0); + if (!skb) + goto err; + TIPC_SKB_CB(skb)->chain_sz = skb_queue_len(list); + TIPC_SKB_CB(skb)->chain_imp = imp; + skb_queue_tail(&link->wakeupq, skb); link->stats.link_congs++; - return true; + return -ELINKCONG; +err: + __skb_queue_purge(list); + return -ENOBUFS; } /** @@ -398,19 +419,22 @@ static bool link_schedule_user(struct tipc_link *link, u32 oport, * Move a number of waiting users, as permitted by available space in * the send queue, from link wait queue to node wait queue for wakeup */ -void link_prepare_wakeup(struct tipc_link *link) +void link_prepare_wakeup(struct tipc_link *l) { - uint pend_qsz = skb_queue_len(&link->backlogq); + int pnd[TIPC_SYSTEM_IMPORTANCE + 1] = {0,}; + int imp, lim; struct sk_buff *skb, *tmp; - skb_queue_walk_safe(&link->wakeupq, skb, tmp) { - if (pend_qsz >= link->queue_limit[TIPC_SKB_CB(skb)->chain_imp]) + skb_queue_walk_safe(&l->wakeupq, skb, tmp) { + imp = TIPC_SKB_CB(skb)->chain_imp; + lim = l->window + l->backlog[imp].limit; + pnd[imp] += TIPC_SKB_CB(skb)->chain_sz; + if ((pnd[imp] + l->backlog[imp].len) >= lim) break; - pend_qsz += TIPC_SKB_CB(skb)->chain_sz; - skb_unlink(skb, &link->wakeupq); - skb_queue_tail(&link->inputq, skb); - link->owner->inputq = &link->inputq; - link->owner->action_flags |= TIPC_MSG_EVT; + skb_unlink(skb, &l->wakeupq); + skb_queue_tail(&l->inputq, skb); + l->owner->inputq = &l->inputq; + l->owner->action_flags |= TIPC_MSG_EVT; } } @@ -424,6 +448,16 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr) l_ptr->reasm_buf = NULL; } +static void tipc_link_purge_backlog(struct tipc_link *l) +{ + __skb_queue_purge(&l->backlogq); + l->backlog[TIPC_LOW_IMPORTANCE].len = 0; + l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; + l->backlog[TIPC_HIGH_IMPORTANCE].len = 0; + l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0; + l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0; +} + /** * tipc_link_purge_queues - purge all pkt queues associated with link * @l_ptr: pointer to link @@ -432,7 +466,7 @@ void tipc_link_purge_queues(struct tipc_link *l_ptr) { __skb_queue_purge(&l_ptr->deferdq); __skb_queue_purge(&l_ptr->transmq); - __skb_queue_purge(&l_ptr->backlogq); + tipc_link_purge_backlog(l_ptr); tipc_link_reset_fragments(l_ptr); } @@ -466,13 +500,13 @@ void tipc_link_reset(struct tipc_link *l_ptr) /* Clean up all queues, except inputq: */ __skb_queue_purge(&l_ptr->transmq); - __skb_queue_purge(&l_ptr->backlogq); __skb_queue_purge(&l_ptr->deferdq); if (!owner->inputq) owner->inputq = &l_ptr->inputq; skb_queue_splice_init(&l_ptr->wakeupq, owner->inputq); if (!skb_queue_empty(owner->inputq)) owner->action_flags |= TIPC_MSG_EVT; + tipc_link_purge_backlog(l_ptr); l_ptr->rcv_unacked = 0; l_ptr->checkpoint = 1; l_ptr->next_out_no = 1; @@ -696,48 +730,15 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) } } -/* tipc_link_cong: determine return value and how to treat the - * sent buffer during link congestion. - * - For plain, errorless user data messages we keep the buffer and - * return -ELINKONG. - * - For all other messages we discard the buffer and return -EHOSTUNREACH - * - For TIPC internal messages we also reset the link - */ -static int tipc_link_cong(struct tipc_link *link, struct sk_buff_head *list) -{ - struct sk_buff *skb = skb_peek(list); - struct tipc_msg *msg = buf_msg(skb); - int imp = msg_importance(msg); - u32 oport = msg_tot_origport(msg); - - if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) { - pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); - tipc_link_reset(link); - goto drop; - } - if (unlikely(msg_errcode(msg))) - goto drop; - if (unlikely(msg_reroute_cnt(msg))) - goto drop; - if (TIPC_SKB_CB(skb)->wakeup_pending) - return -ELINKCONG; - if (link_schedule_user(link, oport, skb_queue_len(list), imp)) - return -ELINKCONG; -drop: - __skb_queue_purge(list); - return -EHOSTUNREACH; -} - /** * __tipc_link_xmit(): same as tipc_link_xmit, but destlink is known & locked * @link: link to use * @list: chain of buffers containing message * - * Consumes the buffer chain, except when returning -ELINKCONG - * Returns 0 if success, otherwise errno: -ELINKCONG, -EMSGSIZE (plain socket - * user data messages) or -EHOSTUNREACH (all other messages/senders) - * Only the socket functions tipc_send_stream() and tipc_send_packet() need - * to act on the return value, since they may need to do more send attempts. + * Consumes the buffer chain, except when returning -ELINKCONG, + * since the caller then may want to make more send attempts. + * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS + * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *list) @@ -754,16 +755,14 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *backlogq = &link->backlogq; struct sk_buff *skb, *tmp; - /* Match queue limit against msg importance: */ - if (unlikely(skb_queue_len(backlogq) >= link->queue_limit[imp])) - return tipc_link_cong(link, list); + /* Match backlog limit against msg importance: */ + if (unlikely(link->backlog[imp].len >= link->backlog[imp].limit)) + return link_schedule_user(link, list); - /* Has valid packet limit been used ? */ if (unlikely(msg_size(msg) > mtu)) { __skb_queue_purge(list); return -EMSGSIZE; } - /* Prepare each packet for sending, and add to relevant queue: */ skb_queue_walk_safe(list, skb, tmp) { __skb_unlink(skb, list); @@ -786,8 +785,10 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, if (tipc_msg_make_bundle(&skb, mtu, link->addr)) { link->stats.sent_bundled++; link->stats.sent_bundles++; + imp = msg_importance(buf_msg(skb)); } __skb_queue_tail(backlogq, skb); + link->backlog[imp].len++; seqno++; } link->next_out_no = seqno; @@ -808,13 +809,25 @@ static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb) return __tipc_link_xmit(link->owner->net, link, &head); } +/* tipc_link_xmit_skb(): send single buffer to destination + * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE + * messages, which will not be rejected + * The only exception is datagram messages rerouted after secondary + * lookup, which are rare and safe to dispose of anyway. + * TODO: Return real return value, and let callers use + * tipc_wait_for_sendpkt() where applicable + */ int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, u32 selector) { struct sk_buff_head head; + int rc; skb2list(skb, &head); - return tipc_link_xmit(net, &head, dnode, selector); + rc = tipc_link_xmit(net, &head, dnode, selector); + if (rc == -ELINKCONG) + kfree_skb(skb); + return 0; } /** @@ -841,12 +854,15 @@ int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, if (link) rc = __tipc_link_xmit(net, link, list); tipc_node_unlock(node); + tipc_node_put(node); } if (link) return rc; - if (likely(in_own_node(net, dnode))) - return tipc_sk_rcv(net, list); + if (likely(in_own_node(net, dnode))) { + tipc_sk_rcv(net, list); + return 0; + } __skb_queue_purge(list); return rc; @@ -912,6 +928,7 @@ void tipc_link_push_packets(struct tipc_link *link) if (!skb) break; msg = buf_msg(skb); + link->backlog[msg_importance(msg)].len--; msg_set_ack(msg, ack); msg_set_bcast_ack(msg, link->owner->bclink.last_in); link->rcv_unacked = 0; @@ -964,7 +981,6 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, (unsigned long) TIPC_SKB_CB(buf)->handle); n_ptr = tipc_bclink_retransmit_to(net); - tipc_node_lock(n_ptr); tipc_addr_string_fill(addr_string, n_ptr->addr); pr_info("Broadcast link info for %s\n", addr_string); @@ -976,9 +992,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, n_ptr->bclink.oos_state, n_ptr->bclink.last_sent); - tipc_node_unlock(n_ptr); - - tipc_bclink_set_flags(net, TIPC_BCLINK_RESET); + n_ptr->action_flags |= TIPC_BCAST_RESET; l_ptr->stale_count = 0; } } @@ -1017,6 +1031,32 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, } } +/* link_synch(): check if all packets arrived before the synch + * point have been consumed + * Returns true if the parallel links are synched, otherwise false + */ +static bool link_synch(struct tipc_link *l) +{ + unsigned int post_synch; + struct tipc_link *pl; + + pl = tipc_parallel_link(l); + if (pl == l) + goto synched; + + /* Was last pre-synch packet added to input queue ? */ + if (less_eq(pl->next_in_no, l->synch_point)) + return false; + + /* Is it still in the input queue ? */ + post_synch = mod(pl->next_in_no - l->synch_point) - 1; + if (skb_queue_len(&pl->inputq) > post_synch) + return false; +synched: + l->flags &= ~LINK_SYNCHING; + return true; +} + static void link_retrieve_defq(struct tipc_link *link, struct sk_buff_head *list) { @@ -1077,8 +1117,8 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) n_ptr = tipc_node_find(net, msg_prevnode(msg)); if (unlikely(!n_ptr)) goto discard; - tipc_node_lock(n_ptr); + tipc_node_lock(n_ptr); /* Locate unicast link endpoint that should handle message */ l_ptr = n_ptr->links[b_ptr->identity]; if (unlikely(!l_ptr)) @@ -1147,6 +1187,14 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) skb = NULL; goto unlock; } + /* Synchronize with parallel link if applicable */ + if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) { + link_handle_out_of_seq_msg(l_ptr, skb); + if (link_synch(l_ptr)) + link_retrieve_defq(l_ptr, &head); + skb = NULL; + goto unlock; + } l_ptr->next_in_no++; if (unlikely(!skb_queue_empty(&l_ptr->deferdq))) link_retrieve_defq(l_ptr, &head); @@ -1158,6 +1206,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) skb = NULL; unlock: tipc_node_unlock(n_ptr); + tipc_node_put(n_ptr); discard: if (unlikely(skb)) kfree_skb(skb); @@ -1222,6 +1271,10 @@ static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) switch (msg_user(msg)) { case CHANGEOVER_PROTOCOL: + if (msg_dup(msg)) { + link->flags |= LINK_SYNCHING; + link->synch_point = msg_seqno(msg_get_wrapped(msg)); + } if (!tipc_link_tunnel_rcv(node, &skb)) break; if (msg_user(buf_msg(skb)) != MSG_BUNDLER) { @@ -1608,6 +1661,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, CHANGEOVER_PROTOCOL, ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr); skb_queue_splice_tail_init(&l_ptr->backlogq, &l_ptr->transmq); + tipc_link_purge_backlog(l_ptr); msgcount = skb_queue_len(&l_ptr->transmq); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); msg_set_msgcnt(&tunnel_hdr, msgcount); @@ -1815,11 +1869,11 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) int max_bulk = TIPC_MAX_PUBLICATIONS / (l->max_pkt / ITEM_SIZE); l->window = win; - l->queue_limit[TIPC_LOW_IMPORTANCE] = win / 2; - l->queue_limit[TIPC_MEDIUM_IMPORTANCE] = win; - l->queue_limit[TIPC_HIGH_IMPORTANCE] = win / 2 * 3; - l->queue_limit[TIPC_CRITICAL_IMPORTANCE] = win * 2; - l->queue_limit[TIPC_SYSTEM_IMPORTANCE] = max_bulk; + l->backlog[TIPC_LOW_IMPORTANCE].limit = win / 2; + l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = win; + l->backlog[TIPC_HIGH_IMPORTANCE].limit = win / 2 * 3; + l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = win * 2; + l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk; } /* tipc_link_find_owner - locate owner node of link by link's name @@ -2118,7 +2172,7 @@ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, link->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, - link->queue_limit[TIPC_LOW_IMPORTANCE])) + link->window)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) goto prop_msg_full; @@ -2184,7 +2238,6 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) msg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); - if (prev_node) { node = tipc_node_find(net, prev_node); if (!node) { @@ -2197,6 +2250,7 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->prev_seq = 1; goto out; } + tipc_node_put(node); list_for_each_entry_continue_rcu(node, &tn->node_list, list) { @@ -2204,6 +2258,7 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) err = __tipc_nl_add_node_links(net, &msg, node, &prev_link); tipc_node_unlock(node); + tipc_node_put(node); if (err) goto out; diff --git a/net/tipc/link.h b/net/tipc/link.h index eec3ecf2d450..d2b5663643da 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -60,6 +60,7 @@ */ #define LINK_STARTED 0x0001 #define LINK_STOPPED 0x0002 +#define LINK_SYNCHING 0x0004 /* Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) @@ -118,7 +119,7 @@ struct tipc_stats { * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') - * @queue_limit: outbound message queue congestion thresholds (indexed by user) + * @backlog_limit: backlog queue congestion thresholds (indexed by importance) * @exp_msg_count: # of tunnelled messages expected during link changeover * @reset_checkpoint: seq # of last acknowledged message at time of link reset * @max_pkt: current maximum packet size for this link @@ -166,11 +167,11 @@ struct tipc_link { struct tipc_msg *pmsg; u32 priority; char net_plane; - u32 queue_limit[15]; /* queue_limit[0]==window limit */ /* Changeover */ u32 exp_msg_count; u32 reset_checkpoint; + u32 synch_point; /* Max packet negotiation */ u32 max_pkt; @@ -180,6 +181,10 @@ struct tipc_link { /* Sending */ struct sk_buff_head transmq; struct sk_buff_head backlogq; + struct { + u16 len; + u16 limit; + } backlog[5]; u32 next_out_no; u32 window; u32 last_retransmitted; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 0c6dad8180a0..3bb499c61918 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -511,15 +511,18 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, { struct tipc_msg *msg = buf_msg(skb); u32 dport; + u32 own_addr = tipc_own_addr(net); if (!msg_isdata(msg)) return false; if (!msg_named(msg)) return false; + if (msg_errcode(msg)) + return false; *err = -TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; - if (msg_reroute_cnt(msg) > 0) + if (msg_reroute_cnt(msg)) return false; *dnode = addr_domain(net, msg_lookup_scope(msg)); dport = tipc_nametbl_translate(net, msg_nametype(msg), @@ -527,6 +530,8 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, if (!dport) return false; msg_incr_reroute_cnt(msg); + if (*dnode != own_addr) + msg_set_prevnode(msg, own_addr); msg_set_destnode(msg, *dnode); msg_set_destport(msg, dport); *err = TIPC_OK; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index bd3969a80dd4..d273207ede28 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -240,6 +240,15 @@ static inline void msg_set_size(struct tipc_msg *m, u32 sz) m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz); } +static inline unchar *msg_data(struct tipc_msg *m) +{ + return ((unchar *)m) + msg_hdr_sz(m); +} + +static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) +{ + return (struct tipc_msg *)msg_data(m); +} /* * Word 1 @@ -372,6 +381,8 @@ static inline void msg_set_prevnode(struct tipc_msg *m, u32 a) static inline u32 msg_origport(struct tipc_msg *m) { + if (msg_user(m) == MSG_FRAGMENTER) + m = msg_get_wrapped(m); return msg_word(m, 4); } @@ -467,16 +478,6 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) msg_set_word(m, 10, n); } -static inline unchar *msg_data(struct tipc_msg *m) -{ - return ((unchar *)m) + msg_hdr_sz(m); -} - -static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) -{ - return (struct tipc_msg *)msg_data(m); -} - /* * Constants and routines used to read and write TIPC internal message headers */ @@ -553,6 +554,14 @@ static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 15, 0x1fff, n); } +static inline bool msg_dup(struct tipc_msg *m) +{ + if (likely(msg_user(m) != CHANGEOVER_PROTOCOL)) + return false; + if (msg_type(m) != DUPLICATE_MSG) + return false; + return true; +} /* * Word 2 @@ -753,13 +762,6 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } -static inline u32 msg_tot_origport(struct tipc_msg *m) -{ - if ((msg_user(m) == MSG_FRAGMENTER) && (msg_type(m) == FIRST_FRAGMENT)) - return msg_origport(msg_get_wrapped(m)); - return msg_origport(m); -} - struct sk_buff *tipc_buf_acquire(u32 size); bool tipc_msg_validate(struct sk_buff *skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 506aaa565da7..41e7b7e4dda0 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -244,6 +244,7 @@ static void tipc_publ_subscribe(struct net *net, struct publication *publ, tipc_node_lock(node); list_add_tail(&publ->nodesub_list, &node->publ_list); tipc_node_unlock(node); + tipc_node_put(node); } static void tipc_publ_unsubscribe(struct net *net, struct publication *publ, @@ -258,6 +259,7 @@ static void tipc_publ_unsubscribe(struct net *net, struct publication *publ, tipc_node_lock(node); list_del_init(&publ->nodesub_list); tipc_node_unlock(node); + tipc_node_put(node); } /** diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 105ba7adf06f..ab0ac62a1287 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -811,8 +811,8 @@ static void tipc_purge_publications(struct net *net, struct name_seq *seq) sseq = seq->sseqs; info = sseq->info; list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) { - tipc_nametbl_remove_publ(net, publ->type, publ->lower, - publ->node, publ->ref, publ->key); + tipc_nameseq_remove_publ(net, seq, publ->lower, publ->node, + publ->ref, publ->key); kfree_rcu(publ, rcu); } hlist_del_init_rcu(&seq->ns_list); diff --git a/net/tipc/node.c b/net/tipc/node.c index 26d1de1bf34d..3e4f04897c03 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -42,6 +42,7 @@ static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); +static void tipc_node_delete(struct tipc_node *node); struct tipc_sock_conn { u32 port; @@ -67,6 +68,23 @@ static unsigned int tipc_hashfn(u32 addr) return addr & (NODE_HTABLE_SIZE - 1); } +static void tipc_node_kref_release(struct kref *kref) +{ + struct tipc_node *node = container_of(kref, struct tipc_node, kref); + + tipc_node_delete(node); +} + +void tipc_node_put(struct tipc_node *node) +{ + kref_put(&node->kref, tipc_node_kref_release); +} + +static void tipc_node_get(struct tipc_node *node) +{ + kref_get(&node->kref); +} + /* * tipc_node_find - locate specified node object, if it exists */ @@ -82,6 +100,7 @@ struct tipc_node *tipc_node_find(struct net *net, u32 addr) hlist_for_each_entry_rcu(node, &tn->node_htable[tipc_hashfn(addr)], hash) { if (node->addr == addr) { + tipc_node_get(node); rcu_read_unlock(); return node; } @@ -106,6 +125,7 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) } n_ptr->addr = addr; n_ptr->net = net; + kref_init(&n_ptr->kref); spin_lock_init(&n_ptr->lock); INIT_HLIST_NODE(&n_ptr->hash); INIT_LIST_HEAD(&n_ptr->list); @@ -120,16 +140,17 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) list_add_tail_rcu(&n_ptr->list, &temp_node->list); n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN; n_ptr->signature = INVALID_NODE_SIG; + tipc_node_get(n_ptr); exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; } -static void tipc_node_delete(struct tipc_net *tn, struct tipc_node *n_ptr) +static void tipc_node_delete(struct tipc_node *node) { - list_del_rcu(&n_ptr->list); - hlist_del_rcu(&n_ptr->hash); - kfree_rcu(n_ptr, rcu); + list_del_rcu(&node->list); + hlist_del_rcu(&node->hash); + kfree_rcu(node, rcu); } void tipc_node_stop(struct net *net) @@ -139,7 +160,7 @@ void tipc_node_stop(struct net *net) spin_lock_bh(&tn->node_list_lock); list_for_each_entry_safe(node, t_node, &tn->node_list, list) - tipc_node_delete(tn, node); + tipc_node_put(node); spin_unlock_bh(&tn->node_list_lock); } @@ -147,6 +168,7 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port) { struct tipc_node *node; struct tipc_sock_conn *conn; + int err = 0; if (in_own_node(net, dnode)) return 0; @@ -157,8 +179,10 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port) return -EHOSTUNREACH; } conn = kmalloc(sizeof(*conn), GFP_ATOMIC); - if (!conn) - return -EHOSTUNREACH; + if (!conn) { + err = -EHOSTUNREACH; + goto exit; + } conn->peer_node = dnode; conn->port = port; conn->peer_port = peer_port; @@ -166,7 +190,9 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port) tipc_node_lock(node); list_add_tail(&conn->list, &node->conn_sks); tipc_node_unlock(node); - return 0; +exit: + tipc_node_put(node); + return err; } void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) @@ -189,6 +215,7 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) kfree(conn); } tipc_node_unlock(node); + tipc_node_put(node); } /** @@ -417,19 +444,25 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, char *linkname, size_t len) { struct tipc_link *link; + int err = -EINVAL; struct tipc_node *node = tipc_node_find(net, addr); - if ((bearer_id >= MAX_BEARERS) || !node) - return -EINVAL; + if (!node) + return err; + + if (bearer_id >= MAX_BEARERS) + goto exit; + tipc_node_lock(node); link = node->links[bearer_id]; if (link) { strncpy(linkname, link->name, len); - tipc_node_unlock(node); - return 0; + err = 0; } +exit: tipc_node_unlock(node); - return -EINVAL; + tipc_node_put(node); + return err; } void tipc_node_unlock(struct tipc_node *node) @@ -459,7 +492,7 @@ void tipc_node_unlock(struct tipc_node *node) TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP | TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT | - TIPC_NAMED_MSG_EVT); + TIPC_NAMED_MSG_EVT | TIPC_BCAST_RESET); spin_unlock_bh(&node->lock); @@ -488,6 +521,9 @@ void tipc_node_unlock(struct tipc_node *node) if (flags & TIPC_BCAST_MSG_EVT) tipc_bclink_input(net); + + if (flags & TIPC_BCAST_RESET) + tipc_link_reset_all(node); } /* Caller should hold node lock for the passed node */ @@ -542,17 +578,21 @@ int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) msg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); - - if (last_addr && !tipc_node_find(net, last_addr)) { - rcu_read_unlock(); - /* We never set seq or call nl_dump_check_consistent() this - * means that setting prev_seq here will cause the consistence - * check to fail in the netlink callback handler. Resulting in - * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if - * the node state changed while we released the lock. - */ - cb->prev_seq = 1; - return -EPIPE; + if (last_addr) { + node = tipc_node_find(net, last_addr); + if (!node) { + rcu_read_unlock(); + /* We never set seq or call nl_dump_check_consistent() + * this means that setting prev_seq here will cause the + * consistence check to fail in the netlink callback + * handler. Resulting in the NLMSG_DONE message having + * the NLM_F_DUMP_INTR flag set if the node state + * changed while we released the lock. + */ + cb->prev_seq = 1; + return -EPIPE; + } + tipc_node_put(node); } list_for_each_entry_rcu(node, &tn->node_list, list) { diff --git a/net/tipc/node.h b/net/tipc/node.h index e89ac04ec2c3..02d5c20dc551 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -64,7 +64,8 @@ enum { TIPC_NOTIFY_LINK_UP = (1 << 6), TIPC_NOTIFY_LINK_DOWN = (1 << 7), TIPC_NAMED_MSG_EVT = (1 << 8), - TIPC_BCAST_MSG_EVT = (1 << 9) + TIPC_BCAST_MSG_EVT = (1 << 9), + TIPC_BCAST_RESET = (1 << 10) }; /** @@ -93,6 +94,7 @@ struct tipc_node_bclink { /** * struct tipc_node - TIPC node structure * @addr: network address of node + * @ref: reference counter to node object * @lock: spinlock governing access to structure * @net: the applicable net namespace * @hash: links to adjacent nodes in unsorted hash chain @@ -114,6 +116,7 @@ struct tipc_node_bclink { */ struct tipc_node { u32 addr; + struct kref kref; spinlock_t lock; struct net *net; struct hlist_node hash; @@ -136,6 +139,7 @@ struct tipc_node { }; struct tipc_node *tipc_node_find(struct net *net, u32 addr); +void tipc_node_put(struct tipc_node *node); struct tipc_node *tipc_node_create(struct net *net, u32 addr); void tipc_node_stop(struct net *net); void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); @@ -170,10 +174,12 @@ static inline uint tipc_node_get_mtu(struct net *net, u32 addr, u32 selector) node = tipc_node_find(net, addr); - if (likely(node)) + if (likely(node)) { mtu = node->act_mtus[selector & 1]; - else + tipc_node_put(node); + } else { mtu = MAX_MSG_SIZE; + } return mtu; } diff --git a/net/tipc/server.c b/net/tipc/server.c index eadd4ed45905..ab6183cdb121 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -37,11 +37,13 @@ #include "core.h" #include "socket.h" #include <net/sock.h> +#include <linux/module.h> /* Number of messages to send before rescheduling */ #define MAX_SEND_MSG_COUNT 25 #define MAX_RECV_MSG_COUNT 25 #define CF_CONNECTED 1 +#define CF_SERVER 2 #define sock2con(x) ((struct tipc_conn *)(x)->sk_user_data) @@ -88,9 +90,19 @@ static void tipc_clean_outqueues(struct tipc_conn *con); static void tipc_conn_kref_release(struct kref *kref) { struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); + struct sockaddr_tipc *saddr = con->server->saddr; + struct socket *sock = con->sock; + struct sock *sk; - if (con->sock) { - tipc_sock_release_local(con->sock); + if (sock) { + sk = sock->sk; + if (test_bit(CF_SERVER, &con->flags)) { + __module_get(sock->ops->owner); + __module_get(sk->sk_prot_creator->owner); + } + saddr->scope = -TIPC_NODE_SCOPE; + kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); + sk_release_kernel(sk); con->sock = NULL; } @@ -281,7 +293,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con) struct tipc_conn *newcon; int ret; - ret = tipc_sock_accept_local(sock, &newsock, O_NONBLOCK); + ret = kernel_accept(sock, &newsock, O_NONBLOCK); if (ret < 0) return ret; @@ -309,9 +321,12 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) struct socket *sock = NULL; int ret; - ret = tipc_sock_create_local(s->net, s->type, &sock); + ret = sock_create_kern(AF_TIPC, SOCK_SEQPACKET, 0, &sock); if (ret < 0) return NULL; + + sk_change_net(sock->sk, s->net); + ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, (char *)&s->imp, sizeof(s->imp)); if (ret < 0) @@ -337,11 +352,31 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) pr_err("Unknown socket type %d\n", s->type); goto create_err; } + + /* As server's listening socket owner and creator is the same module, + * we have to decrease TIPC module reference count to guarantee that + * it remains zero after the server socket is created, otherwise, + * executing "rmmod" command is unable to make TIPC module deleted + * after TIPC module is inserted successfully. + * + * However, the reference count is ever increased twice in + * sock_create_kern(): one is to increase the reference count of owner + * of TIPC socket's proto_ops struct; another is to increment the + * reference count of owner of TIPC proto struct. Therefore, we must + * decrement the module reference count twice to ensure that it keeps + * zero after server's listening socket is created. Of course, we + * must bump the module reference count twice as well before the socket + * is closed. + */ + module_put(sock->ops->owner); + module_put(sock->sk->sk_prot_creator->owner); + set_bit(CF_SERVER, &con->flags); + return sock; create_err: - sock_release(sock); - con->sock = NULL; + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sock->sk); return NULL; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 934947f038b6..ee90d74d7516 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -35,7 +35,6 @@ */ #include <linux/rhashtable.h> -#include <linux/jhash.h> #include "core.h" #include "name_table.h" #include "node.h" @@ -74,6 +73,7 @@ * @link_cong: non-zero if owner must sleep because of link congestion * @sent_unacked: # messages sent by socket, and not yet acked by peer * @rcv_unacked: # messages read by user, but not yet acked back to peer + * @remote: 'connected' peer for dgram/rdm * @node: hash table node * @rcu: rcu struct for tipc_sock */ @@ -96,6 +96,7 @@ struct tipc_sock { bool link_cong; uint sent_unacked; uint rcv_unacked; + struct sockaddr_tipc remote; struct rhash_head node; struct rcu_head rcu; }; @@ -121,9 +122,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; static const struct proto_ops msg_ops; - static struct proto tipc_proto; -static struct proto tipc_proto_kern; static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { [TIPC_NLA_SOCK_UNSPEC] = { .type = NLA_UNSPEC }, @@ -133,6 +132,8 @@ static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { [TIPC_NLA_SOCK_HAS_PUBL] = { .type = NLA_FLAG } }; +static const struct rhashtable_params tsk_rht_params; + /* * Revised TIPC socket locking policy: * @@ -341,11 +342,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, } /* Allocate socket's protocol area */ - if (!kern) - sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto); - else - sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto_kern); - + sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto); if (sk == NULL) return -ENOMEM; @@ -383,75 +380,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, return 0; } -/** - * tipc_sock_create_local - create TIPC socket from inside TIPC module - * @type: socket type - SOCK_RDM or SOCK_SEQPACKET - * - * We cannot use sock_creat_kern here because it bumps module user count. - * Since socket owner and creator is the same module we must make sure - * that module count remains zero for module local sockets, otherwise - * we cannot do rmmod. - * - * Returns 0 on success, errno otherwise - */ -int tipc_sock_create_local(struct net *net, int type, struct socket **res) -{ - int rc; - - rc = sock_create_lite(AF_TIPC, type, 0, res); - if (rc < 0) { - pr_err("Failed to create kernel socket\n"); - return rc; - } - tipc_sk_create(net, *res, 0, 1); - - return 0; -} - -/** - * tipc_sock_release_local - release socket created by tipc_sock_create_local - * @sock: the socket to be released. - * - * Module reference count is not incremented when such sockets are created, - * so we must keep it from being decremented when they are released. - */ -void tipc_sock_release_local(struct socket *sock) -{ - tipc_release(sock); - sock->ops = NULL; - sock_release(sock); -} - -/** - * tipc_sock_accept_local - accept a connection on a socket created - * with tipc_sock_create_local. Use this function to avoid that - * module reference count is inadvertently incremented. - * - * @sock: the accepting socket - * @newsock: reference to the new socket to be created - * @flags: socket flags - */ - -int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, - int flags) -{ - struct sock *sk = sock->sk; - int ret; - - ret = sock_create_lite(sk->sk_family, sk->sk_type, - sk->sk_protocol, newsock); - if (ret < 0) - return ret; - - ret = tipc_accept(sock, *newsock, flags); - if (ret < 0) { - sock_release(*newsock); - return ret; - } - (*newsock)->ops = sock->ops; - return ret; -} - static void tipc_sk_callback(struct rcu_head *head) { struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu); @@ -929,22 +857,23 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) u32 dnode, dport; struct sk_buff_head *pktchain = &sk->sk_write_queue; struct sk_buff *skb; - struct tipc_name_seq *seq = &dest->addr.nameseq; + struct tipc_name_seq *seq; struct iov_iter save; u32 mtu; long timeo; int rc; - if (unlikely(!dest)) - return -EDESTADDRREQ; - - if (unlikely((m->msg_namelen < sizeof(*dest)) || - (dest->family != AF_TIPC))) - return -EINVAL; - if (dsz > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; - + if (unlikely(!dest)) { + if (tsk->connected && sock->state == SS_READY) + dest = &tsk->remote; + else + return -EDESTADDRREQ; + } else if (unlikely(m->msg_namelen < sizeof(*dest)) || + dest->family != AF_TIPC) { + return -EINVAL; + } if (unlikely(sock->state != SS_READY)) { if (sock->state == SS_LISTENING) return -EPIPE; @@ -957,7 +886,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) tsk->conn_instance = dest->addr.name.name.instance; } } - + seq = &dest->addr.nameseq; timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); if (dest->addrtype == TIPC_ADDR_MCAST) { @@ -1908,17 +1837,26 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, int destlen, int flags) { struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; struct msghdr m = {NULL,}; - long timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout; + long timeout = (flags & O_NONBLOCK) ? 0 : tsk->conn_timeout; socket_state previous; - int res; + int res = 0; lock_sock(sk); - /* For now, TIPC does not allow use of connect() with DGRAM/RDM types */ + /* DGRAM/RDM connect(), just save the destaddr */ if (sock->state == SS_READY) { - res = -EOPNOTSUPP; + if (dst->family == AF_UNSPEC) { + memset(&tsk->remote, 0, sizeof(struct sockaddr_tipc)); + tsk->connected = 0; + } else if (destlen != sizeof(struct sockaddr_tipc)) { + res = -EINVAL; + } else { + memcpy(&tsk->remote, dest, destlen); + tsk->connected = 1; + } goto exit; } @@ -2153,7 +2091,6 @@ restart: TIPC_CONN_SHUTDOWN)) tipc_link_xmit_skb(net, skb, dnode, tsk->portid); - tipc_node_remove_conn(net, dnode, tsk->portid); } else { dnode = tsk_peer_node(tsk); @@ -2311,7 +2248,7 @@ static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) struct tipc_sock *tsk; rcu_read_lock(); - tsk = rhashtable_lookup(&tn->sk_rht, &portid); + tsk = rhashtable_lookup_fast(&tn->sk_rht, &portid, tsk_rht_params); if (tsk) sock_hold(&tsk->sk); rcu_read_unlock(); @@ -2333,7 +2270,8 @@ static int tipc_sk_insert(struct tipc_sock *tsk) portid = TIPC_MIN_PORT; tsk->portid = portid; sock_hold(&tsk->sk); - if (rhashtable_lookup_insert(&tn->sk_rht, &tsk->node)) + if (!rhashtable_lookup_insert_fast(&tn->sk_rht, &tsk->node, + tsk_rht_params)) return 0; sock_put(&tsk->sk); } @@ -2346,26 +2284,27 @@ static void tipc_sk_remove(struct tipc_sock *tsk) struct sock *sk = &tsk->sk; struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id); - if (rhashtable_remove(&tn->sk_rht, &tsk->node)) { + if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) { WARN_ON(atomic_read(&sk->sk_refcnt) == 1); __sock_put(sk); } } +static const struct rhashtable_params tsk_rht_params = { + .nelem_hint = 192, + .head_offset = offsetof(struct tipc_sock, node), + .key_offset = offsetof(struct tipc_sock, portid), + .key_len = sizeof(u32), /* portid */ + .max_size = 1048576, + .min_size = 256, + .automatic_shrinking = true, +}; + int tipc_sk_rht_init(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct rhashtable_params rht_params = { - .nelem_hint = 192, - .head_offset = offsetof(struct tipc_sock, node), - .key_offset = offsetof(struct tipc_sock, portid), - .key_len = sizeof(u32), /* portid */ - .hashfn = jhash, - .max_shift = 20, /* 1M */ - .min_shift = 8, /* 256 */ - }; - return rhashtable_init(&tn->sk_rht, &rht_params); + return rhashtable_init(&tn->sk_rht, &tsk_rht_params); } void tipc_sk_rht_destroy(struct net *net) @@ -2608,12 +2547,6 @@ static struct proto tipc_proto = { .sysctl_rmem = sysctl_tipc_rmem }; -static struct proto tipc_proto_kern = { - .name = "TIPC", - .obj_size = sizeof(struct tipc_sock), - .sysctl_rmem = sysctl_tipc_rmem -}; - /** * tipc_socket_init - initialize TIPC socket interface * diff --git a/net/tipc/socket.h b/net/tipc/socket.h index 238f1b7bd9bd..bf6551389522 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -44,10 +44,6 @@ SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) int tipc_socket_init(void); void tipc_socket_stop(void); -int tipc_sock_create_local(struct net *net, int type, struct socket **res); -void tipc_sock_release_local(struct socket *sock); -int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, - int flags); int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq); void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index fc2fb11a354d..ef3d7aa2854a 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -44,6 +44,7 @@ #include <net/sock.h> #include <net/ip.h> #include <net/udp_tunnel.h> +#include <net/addrconf.h> #include <linux/tipc_netlink.h> #include "core.h" #include "bearer.h" @@ -192,7 +193,7 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ip6_dst_lookup(ub->ubsock->sk, &ndst, &fl6); + err = ipv6_stub->ipv6_dst_lookup(ub->ubsock->sk, &ndst, &fl6); if (err) goto tx_error; ttl = ip6_dst_hoplimit(ndst); @@ -246,11 +247,14 @@ static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote) return 0; mreqn.imr_multiaddr = remote->ipv4; mreqn.imr_ifindex = ub->ifindex; - err = __ip_mc_join_group(sk, &mreqn); + err = ip_mc_join_group(sk, &mreqn); +#if IS_ENABLED(CONFIG_IPV6) } else { if (!ipv6_addr_is_multicast(&remote->ipv6)) return 0; - err = __ipv6_sock_mc_join(sk, ub->ifindex, &remote->ipv6); + err = ipv6_stub->ipv6_sock_mc_join(sk, ub->ifindex, + &remote->ipv6); +#endif } return err; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 864b782c0202..d6ba4a6bbff6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4400,6 +4400,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms)) return -EINVAL; + /* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT + * as userspace might just pass through the capabilities from the IEs + * directly, rather than enforcing this restriction and returning an + * error in this case. + */ + if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) { + params.ht_capa = NULL; + params.vht_capa = NULL; + } + /* When you run into this, adjust the code below for the new flag */ BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index cee479bc655c..638af0655aaf 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2269,11 +2269,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, * have the xfrm_state's. We need to wait for KM to * negotiate new SA's or bail out with error.*/ if (net->xfrm.sysctl_larval_drop) { - dst_release(dst); - xfrm_pols_put(pols, drop_pols); XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - - return ERR_PTR(-EREMOTE); + err = -EREMOTE; + goto error; } err = -EAGAIN; @@ -2324,7 +2322,8 @@ nopol: error: dst_release(dst); dropdst: - dst_release(dst_orig); + if (!(flags & XFRM_LOOKUP_KEEP_DST_REF)) + dst_release(dst_orig); xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } @@ -2338,7 +2337,8 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, - flags | XFRM_LOOKUP_QUEUE); + flags | XFRM_LOOKUP_QUEUE | + XFRM_LOOKUP_KEEP_DST_REF); if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c index 066892662915..ed18e9a4909c 100644 --- a/samples/bpf/sockex1_kern.c +++ b/samples/bpf/sockex1_kern.c @@ -1,5 +1,6 @@ #include <uapi/linux/bpf.h> #include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include "bpf_helpers.h" @@ -11,14 +12,17 @@ struct bpf_map_def SEC("maps") my_map = { }; SEC("socket1") -int bpf_prog1(struct sk_buff *skb) +int bpf_prog1(struct __sk_buff *skb) { int index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); long *value; + if (skb->pkt_type != PACKET_OUTGOING) + return 0; + value = bpf_map_lookup_elem(&my_map, &index); if (value) - __sync_fetch_and_add(value, 1); + __sync_fetch_and_add(value, skb->len); return 0; } diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c index 34a443ff3831..678ce4693551 100644 --- a/samples/bpf/sockex1_user.c +++ b/samples/bpf/sockex1_user.c @@ -40,7 +40,7 @@ int main(int ac, char **argv) key = IPPROTO_ICMP; assert(bpf_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0); - printf("TCP %lld UDP %lld ICMP %lld packets\n", + printf("TCP %lld UDP %lld ICMP %lld bytes\n", tcp_cnt, udp_cnt, icmp_cnt); sleep(1); } diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c index 6f0135f0f217..ba0e177ff561 100644 --- a/samples/bpf/sockex2_kern.c +++ b/samples/bpf/sockex2_kern.c @@ -42,13 +42,13 @@ static inline int proto_ports_offset(__u64 proto) } } -static inline int ip_is_fragment(struct sk_buff *ctx, __u64 nhoff) +static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff) { return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off)) & (IP_MF | IP_OFFSET); } -static inline __u32 ipv6_addr_hash(struct sk_buff *ctx, __u64 off) +static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off) { __u64 w0 = load_word(ctx, off); __u64 w1 = load_word(ctx, off + 4); @@ -58,7 +58,7 @@ static inline __u32 ipv6_addr_hash(struct sk_buff *ctx, __u64 off) return (__u32)(w0 ^ w1 ^ w2 ^ w3); } -static inline __u64 parse_ip(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto, +static inline __u64 parse_ip(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto, struct flow_keys *flow) { __u64 verlen; @@ -82,7 +82,7 @@ static inline __u64 parse_ip(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto, return nhoff; } -static inline __u64 parse_ipv6(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto, +static inline __u64 parse_ipv6(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto, struct flow_keys *flow) { *ip_proto = load_byte(skb, @@ -96,7 +96,7 @@ static inline __u64 parse_ipv6(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto return nhoff; } -static inline bool flow_dissector(struct sk_buff *skb, struct flow_keys *flow) +static inline bool flow_dissector(struct __sk_buff *skb, struct flow_keys *flow) { __u64 nhoff = ETH_HLEN; __u64 ip_proto; @@ -183,18 +183,23 @@ static inline bool flow_dissector(struct sk_buff *skb, struct flow_keys *flow) return true; } +struct pair { + long packets; + long bytes; +}; + struct bpf_map_def SEC("maps") hash_map = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__be32), - .value_size = sizeof(long), + .value_size = sizeof(struct pair), .max_entries = 1024, }; SEC("socket2") -int bpf_prog2(struct sk_buff *skb) +int bpf_prog2(struct __sk_buff *skb) { struct flow_keys flow; - long *value; + struct pair *value; u32 key; if (!flow_dissector(skb, &flow)) @@ -203,9 +208,10 @@ int bpf_prog2(struct sk_buff *skb) key = flow.dst; value = bpf_map_lookup_elem(&hash_map, &key); if (value) { - __sync_fetch_and_add(value, 1); + __sync_fetch_and_add(&value->packets, 1); + __sync_fetch_and_add(&value->bytes, skb->len); } else { - long val = 1; + struct pair val = {1, skb->len}; bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY); } diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c index d2d5f5a790d3..29a276d766fc 100644 --- a/samples/bpf/sockex2_user.c +++ b/samples/bpf/sockex2_user.c @@ -6,6 +6,11 @@ #include <unistd.h> #include <arpa/inet.h> +struct pair { + __u64 packets; + __u64 bytes; +}; + int main(int ac, char **argv) { char filename[256]; @@ -29,13 +34,13 @@ int main(int ac, char **argv) for (i = 0; i < 5; i++) { int key = 0, next_key; - long long value; + struct pair value; while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) { bpf_lookup_elem(map_fd[0], &next_key, &value); - printf("ip %s count %lld\n", + printf("ip %s bytes %lld packets %lld\n", inet_ntoa((struct in_addr){htonl(next_key)}), - value); + value.bytes, value.packets); key = next_key; } sleep(1); diff --git a/samples/bpf/test_verifier.c b/samples/bpf/test_verifier.c index 7b56b59fad8e..75d561f9fd6a 100644 --- a/samples/bpf/test_verifier.c +++ b/samples/bpf/test_verifier.c @@ -14,6 +14,7 @@ #include <linux/unistd.h> #include <string.h> #include <linux/filter.h> +#include <stddef.h> #include "libbpf.h" #define MAX_INSNS 512 @@ -642,6 +643,84 @@ static struct bpf_test tests[] = { }, .result = ACCEPT, }, + { + "access skb fields ok", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, pkt_type)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, queue_mapping)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, protocol)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, vlan_present)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, vlan_tci)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "access skb fields bad1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -4), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "access skb fields bad2", + .insns = { + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, pkt_type)), + BPF_EXIT_INSN(), + }, + .fixup = {4}, + .errstr = "different pointers", + .result = REJECT, + }, + { + "access skb fields bad3", + .insns = { + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, pkt_type)), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JA, 0, 0, -12), + }, + .fixup = {6}, + .errstr = "different pointers", + .result = REJECT, + }, }; static int probe_filter_length(struct bpf_insn *fp) diff --git a/security/capability.c b/security/capability.c index 070dd46f62f4..58a1600c149b 100644 --- a/security/capability.c +++ b/security/capability.c @@ -776,11 +776,6 @@ static int cap_tun_dev_open(void *security) { return 0; } - -static void cap_skb_owned_by(struct sk_buff *skb, struct sock *sk) -{ -} - #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -1134,7 +1129,6 @@ void __init security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, tun_dev_open); set_to_cap_if_null(ops, tun_dev_attach_queue); set_to_cap_if_null(ops, tun_dev_attach); - set_to_cap_if_null(ops, skb_owned_by); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM set_to_cap_if_null(ops, xfrm_policy_alloc_security); diff --git a/security/security.c b/security/security.c index e81d5bbe7363..1f475aa53288 100644 --- a/security/security.c +++ b/security/security.c @@ -1359,11 +1359,6 @@ int security_tun_dev_open(void *security) } EXPORT_SYMBOL(security_tun_dev_open); -void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) -{ - security_ops->skb_owned_by(skb, sk); -} - #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4d1a54190388..edc66de39f2e 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -51,7 +51,6 @@ #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ -#include <net/sock.h> #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/inet_connection_sock.h> #include <net/net_namespace.h> @@ -4652,11 +4651,6 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } -static void selinux_skb_owned_by(struct sk_buff *skb, struct sock *sk) -{ - skb_set_owner_w(skb, sk); -} - static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; @@ -6041,7 +6035,6 @@ static struct security_operations selinux_ops = { .tun_dev_attach_queue = selinux_tun_dev_attach_queue, .tun_dev_attach = selinux_tun_dev_attach, .tun_dev_open = selinux_tun_dev_open, - .skb_owned_by = selinux_skb_owned_by, #ifdef CONFIG_SECURITY_NETWORK_XFRM .xfrm_policy_alloc_security = selinux_xfrm_policy_alloc, diff --git a/sound/core/control.c b/sound/core/control.c index 35324a8e83c8..eeb691d1911f 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1170,6 +1170,10 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, if (info->count < 1) return -EINVAL; + if (!*info->id.name) + return -EINVAL; + if (strnlen(info->id.name, sizeof(info->id.name)) >= sizeof(info->id.name)) + return -EINVAL; access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE : (info->access & (SNDRV_CTL_ELEM_ACCESS_READWRITE| SNDRV_CTL_ELEM_ACCESS_INACTIVE| diff --git a/sound/firewire/dice/dice-interface.h b/sound/firewire/dice/dice-interface.h index de7602bd69b5..27b044f84c81 100644 --- a/sound/firewire/dice/dice-interface.h +++ b/sound/firewire/dice/dice-interface.h @@ -299,23 +299,23 @@ #define RX_ISOCHRONOUS 0x008 /* + * Index of first quadlet to be interpreted; read/write. If > 0, that many + * quadlets at the beginning of each data block will be ignored, and all the + * audio and MIDI quadlets will follow. + */ +#define RX_SEQ_START 0x00c + +/* * The number of audio channels; read-only. There will be one quadlet per * channel. */ -#define RX_NUMBER_AUDIO 0x00c +#define RX_NUMBER_AUDIO 0x010 /* * The number of MIDI ports, 0-8; read-only. If > 0, there will be one * additional quadlet in each data block, following the audio quadlets. */ -#define RX_NUMBER_MIDI 0x010 - -/* - * Index of first quadlet to be interpreted; read/write. If > 0, that many - * quadlets at the beginning of each data block will be ignored, and all the - * audio and MIDI quadlets will follow. - */ -#define RX_SEQ_START 0x014 +#define RX_NUMBER_MIDI 0x014 /* * Names of all audio channels; read-only. Quadlets are byte-swapped. Names diff --git a/sound/firewire/dice/dice-proc.c b/sound/firewire/dice/dice-proc.c index ecfe20fd4de5..f5c1d1bced59 100644 --- a/sound/firewire/dice/dice-proc.c +++ b/sound/firewire/dice/dice-proc.c @@ -99,9 +99,9 @@ static void dice_proc_read(struct snd_info_entry *entry, } tx; struct { u32 iso; + u32 seq_start; u32 number_audio; u32 number_midi; - u32 seq_start; char names[RX_NAMES_SIZE]; u32 ac3_caps; u32 ac3_enable; @@ -204,10 +204,10 @@ static void dice_proc_read(struct snd_info_entry *entry, break; snd_iprintf(buffer, "rx %u:\n", stream); snd_iprintf(buffer, " iso channel: %d\n", (int)buf.rx.iso); + snd_iprintf(buffer, " sequence start: %u\n", buf.rx.seq_start); snd_iprintf(buffer, " audio channels: %u\n", buf.rx.number_audio); snd_iprintf(buffer, " midi ports: %u\n", buf.rx.number_midi); - snd_iprintf(buffer, " sequence start: %u\n", buf.rx.seq_start); if (quadlets >= 68) { dice_proc_fixup_string(buf.rx.names, RX_NAMES_SIZE); snd_iprintf(buffer, " names: %s\n", buf.rx.names); diff --git a/sound/firewire/iso-resources.c b/sound/firewire/iso-resources.c index 5f17b77ee152..f0e4d502d604 100644 --- a/sound/firewire/iso-resources.c +++ b/sound/firewire/iso-resources.c @@ -26,7 +26,7 @@ int fw_iso_resources_init(struct fw_iso_resources *r, struct fw_unit *unit) { r->channels_mask = ~0uLL; - r->unit = fw_unit_get(unit); + r->unit = unit; mutex_init(&r->mutex); r->allocated = false; @@ -42,7 +42,6 @@ void fw_iso_resources_destroy(struct fw_iso_resources *r) { WARN_ON(r->allocated); mutex_destroy(&r->mutex); - fw_unit_put(r->unit); } EXPORT_SYMBOL(fw_iso_resources_destroy); diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index a2ce773bdc62..17c2637d842c 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1164,7 +1164,7 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus, } } - if (!bus->no_response_fallback) + if (bus->no_response_fallback) return -1; if (!chip->polling_mode && chip->poll_count < 2) { diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index b680b4ec6331..8ec5289f8e05 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -687,12 +687,45 @@ static int get_amp_val_to_activate(struct hda_codec *codec, hda_nid_t nid, return val; } +/* is this a stereo widget or a stereo-to-mono mix? */ +static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, int dir) +{ + unsigned int wcaps = get_wcaps(codec, nid); + hda_nid_t conn; + + if (wcaps & AC_WCAP_STEREO) + return true; + if (dir != HDA_INPUT || get_wcaps_type(wcaps) != AC_WID_AUD_MIX) + return false; + if (snd_hda_get_num_conns(codec, nid) != 1) + return false; + if (snd_hda_get_connections(codec, nid, &conn, 1) < 0) + return false; + return !!(get_wcaps(codec, conn) & AC_WCAP_STEREO); +} + /* initialize the amp value (only at the first time) */ static void init_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx) { unsigned int caps = query_amp_caps(codec, nid, dir); int val = get_amp_val_to_activate(codec, nid, dir, caps, false); - snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val); + + if (is_stereo_amps(codec, nid, dir)) + snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val); + else + snd_hda_codec_amp_init(codec, nid, 0, dir, idx, 0xff, val); +} + +/* update the amp, doing in stereo or mono depending on NID */ +static int update_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx, + unsigned int mask, unsigned int val) +{ + if (is_stereo_amps(codec, nid, dir)) + return snd_hda_codec_amp_stereo(codec, nid, dir, idx, + mask, val); + else + return snd_hda_codec_amp_update(codec, nid, 0, dir, idx, + mask, val); } /* calculate amp value mask we can modify; @@ -732,7 +765,7 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir, return; val &= mask; - snd_hda_codec_amp_stereo(codec, nid, dir, idx, mask, val); + update_amp(codec, nid, dir, idx, mask, val); } static void activate_amp_out(struct hda_codec *codec, struct nid_path *path, @@ -4424,13 +4457,11 @@ static void mute_all_mixer_nid(struct hda_codec *codec, hda_nid_t mix) has_amp = nid_has_mute(codec, mix, HDA_INPUT); for (i = 0; i < nums; i++) { if (has_amp) - snd_hda_codec_amp_stereo(codec, mix, - HDA_INPUT, i, - 0xff, HDA_AMP_MUTE); + update_amp(codec, mix, HDA_INPUT, i, + 0xff, HDA_AMP_MUTE); else if (nid_has_volume(codec, conn[i], HDA_OUTPUT)) - snd_hda_codec_amp_stereo(codec, conn[i], - HDA_OUTPUT, 0, - 0xff, HDA_AMP_MUTE); + update_amp(codec, conn[i], HDA_OUTPUT, 0, + 0xff, HDA_AMP_MUTE); } } diff --git a/sound/pci/hda/hda_proc.c b/sound/pci/hda/hda_proc.c index ce5a6da83419..05e19f78b4cb 100644 --- a/sound/pci/hda/hda_proc.c +++ b/sound/pci/hda/hda_proc.c @@ -134,13 +134,38 @@ static void print_amp_caps(struct snd_info_buffer *buffer, (caps & AC_AMPCAP_MUTE) >> AC_AMPCAP_MUTE_SHIFT); } +/* is this a stereo widget or a stereo-to-mono mix? */ +static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, + int dir, unsigned int wcaps, int indices) +{ + hda_nid_t conn; + + if (wcaps & AC_WCAP_STEREO) + return true; + /* check for a stereo-to-mono mix; it must be: + * only a single connection, only for input, and only a mixer widget + */ + if (indices != 1 || dir != HDA_INPUT || + get_wcaps_type(wcaps) != AC_WID_AUD_MIX) + return false; + + if (snd_hda_get_raw_connections(codec, nid, &conn, 1) < 0) + return false; + /* the connection source is a stereo? */ + wcaps = snd_hda_param_read(codec, conn, AC_PAR_AUDIO_WIDGET_CAP); + return !!(wcaps & AC_WCAP_STEREO); +} + static void print_amp_vals(struct snd_info_buffer *buffer, struct hda_codec *codec, hda_nid_t nid, - int dir, int stereo, int indices) + int dir, unsigned int wcaps, int indices) { unsigned int val; + bool stereo; int i; + stereo = is_stereo_amps(codec, nid, dir, wcaps, indices); + dir = dir == HDA_OUTPUT ? AC_AMP_GET_OUTPUT : AC_AMP_GET_INPUT; for (i = 0; i < indices; i++) { snd_iprintf(buffer, " ["); @@ -757,12 +782,10 @@ static void print_codec_info(struct snd_info_entry *entry, (codec->single_adc_amp && wid_type == AC_WID_AUD_IN)) print_amp_vals(buffer, codec, nid, HDA_INPUT, - wid_caps & AC_WCAP_STEREO, - 1); + wid_caps, 1); else print_amp_vals(buffer, codec, nid, HDA_INPUT, - wid_caps & AC_WCAP_STEREO, - conn_len); + wid_caps, conn_len); } if (wid_caps & AC_WCAP_OUT_AMP) { snd_iprintf(buffer, " Amp-Out caps: "); @@ -771,11 +794,10 @@ static void print_codec_info(struct snd_info_entry *entry, if (wid_type == AC_WID_PIN && codec->pin_amp_workaround) print_amp_vals(buffer, codec, nid, HDA_OUTPUT, - wid_caps & AC_WCAP_STEREO, - conn_len); + wid_caps, conn_len); else print_amp_vals(buffer, codec, nid, HDA_OUTPUT, - wid_caps & AC_WCAP_STEREO, 1); + wid_caps, 1); } switch (wid_type) { diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 1589c9bcce3e..dd2b3d92071f 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -393,6 +393,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101), + SND_PCI_QUIRK(0x106b, 0x5600, "MacBookAir 5,2", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x5b00, "MacBookAir 4,2", CS420X_MBA42), SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS420X_APPLE), {} /* terminator */ @@ -584,6 +585,7 @@ static int patch_cs420x(struct hda_codec *codec) return -ENOMEM; spec->gen.automute_hook = cs_automute; + codec->single_adc_amp = 1; snd_hda_pick_fixup(codec, cs420x_models, cs420x_fixup_tbl, cs420x_fixups); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index fd3ed18670e9..da67ea8645a6 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -223,6 +223,7 @@ enum { CXT_PINCFG_LENOVO_TP410, CXT_PINCFG_LEMOTE_A1004, CXT_PINCFG_LEMOTE_A1205, + CXT_PINCFG_COMPAQ_CQ60, CXT_FIXUP_STEREO_DMIC, CXT_FIXUP_INC_MIC_BOOST, CXT_FIXUP_HEADPHONE_MIC_PIN, @@ -660,6 +661,15 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_PINS, .v.pins = cxt_pincfg_lemote, }, + [CXT_PINCFG_COMPAQ_CQ60] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + /* 0x17 was falsely set up as a mic, it should 0x1d */ + { 0x17, 0x400001f0 }, + { 0x1d, 0x97a70120 }, + { } + } + }, [CXT_FIXUP_STEREO_DMIC] = { .type = HDA_FIXUP_FUNC, .v.func = cxt_fixup_stereo_dmic, @@ -769,6 +779,7 @@ static const struct hda_model_fixup cxt5047_fixup_models[] = { }; static const struct snd_pci_quirk cxt5051_fixups[] = { + SND_PCI_QUIRK(0x103c, 0x360b, "Compaq CQ60", CXT_PINCFG_COMPAQ_CQ60), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo X200", CXT_PINCFG_LENOVO_X200), {} }; diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c index b67480f1b1aa..4373ada95648 100644 --- a/sound/soc/codecs/adav80x.c +++ b/sound/soc/codecs/adav80x.c @@ -317,7 +317,7 @@ static int adav80x_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec); - unsigned int deemph = ucontrol->value.enumerated.item[0]; + unsigned int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -333,7 +333,7 @@ static int adav80x_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = adav80x->deemph; + ucontrol->value.integer.value[0] = adav80x->deemph; return 0; }; diff --git a/sound/soc/codecs/ak4641.c b/sound/soc/codecs/ak4641.c index 70861c7b1631..81b54a270bd8 100644 --- a/sound/soc/codecs/ak4641.c +++ b/sound/soc/codecs/ak4641.c @@ -76,7 +76,7 @@ static int ak4641_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; @@ -92,7 +92,7 @@ static int ak4641_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = ak4641->deemph; + ucontrol->value.integer.value[0] = ak4641->deemph; return 0; }; diff --git a/sound/soc/codecs/ak4671.c b/sound/soc/codecs/ak4671.c index 632e89f793a7..2a58b1dccd2f 100644 --- a/sound/soc/codecs/ak4671.c +++ b/sound/soc/codecs/ak4671.c @@ -343,25 +343,25 @@ static const struct snd_soc_dapm_widget ak4671_dapm_widgets[] = { }; static const struct snd_soc_dapm_route ak4671_intercon[] = { - {"DAC Left", "NULL", "PMPLL"}, - {"DAC Right", "NULL", "PMPLL"}, - {"ADC Left", "NULL", "PMPLL"}, - {"ADC Right", "NULL", "PMPLL"}, + {"DAC Left", NULL, "PMPLL"}, + {"DAC Right", NULL, "PMPLL"}, + {"ADC Left", NULL, "PMPLL"}, + {"ADC Right", NULL, "PMPLL"}, /* Outputs */ - {"LOUT1", "NULL", "LOUT1 Mixer"}, - {"ROUT1", "NULL", "ROUT1 Mixer"}, - {"LOUT2", "NULL", "LOUT2 Mix Amp"}, - {"ROUT2", "NULL", "ROUT2 Mix Amp"}, - {"LOUT3", "NULL", "LOUT3 Mixer"}, - {"ROUT3", "NULL", "ROUT3 Mixer"}, + {"LOUT1", NULL, "LOUT1 Mixer"}, + {"ROUT1", NULL, "ROUT1 Mixer"}, + {"LOUT2", NULL, "LOUT2 Mix Amp"}, + {"ROUT2", NULL, "ROUT2 Mix Amp"}, + {"LOUT3", NULL, "LOUT3 Mixer"}, + {"ROUT3", NULL, "ROUT3 Mixer"}, {"LOUT1 Mixer", "DACL", "DAC Left"}, {"ROUT1 Mixer", "DACR", "DAC Right"}, {"LOUT2 Mixer", "DACHL", "DAC Left"}, {"ROUT2 Mixer", "DACHR", "DAC Right"}, - {"LOUT2 Mix Amp", "NULL", "LOUT2 Mixer"}, - {"ROUT2 Mix Amp", "NULL", "ROUT2 Mixer"}, + {"LOUT2 Mix Amp", NULL, "LOUT2 Mixer"}, + {"ROUT2 Mix Amp", NULL, "ROUT2 Mixer"}, {"LOUT3 Mixer", "DACSL", "DAC Left"}, {"ROUT3 Mixer", "DACSR", "DAC Right"}, @@ -381,18 +381,18 @@ static const struct snd_soc_dapm_route ak4671_intercon[] = { {"LIN2", NULL, "Mic Bias"}, {"RIN2", NULL, "Mic Bias"}, - {"ADC Left", "NULL", "LIN MUX"}, - {"ADC Right", "NULL", "RIN MUX"}, + {"ADC Left", NULL, "LIN MUX"}, + {"ADC Right", NULL, "RIN MUX"}, /* Analog Loops */ - {"LIN1 Mixing Circuit", "NULL", "LIN1"}, - {"RIN1 Mixing Circuit", "NULL", "RIN1"}, - {"LIN2 Mixing Circuit", "NULL", "LIN2"}, - {"RIN2 Mixing Circuit", "NULL", "RIN2"}, - {"LIN3 Mixing Circuit", "NULL", "LIN3"}, - {"RIN3 Mixing Circuit", "NULL", "RIN3"}, - {"LIN4 Mixing Circuit", "NULL", "LIN4"}, - {"RIN4 Mixing Circuit", "NULL", "RIN4"}, + {"LIN1 Mixing Circuit", NULL, "LIN1"}, + {"RIN1 Mixing Circuit", NULL, "RIN1"}, + {"LIN2 Mixing Circuit", NULL, "LIN2"}, + {"RIN2 Mixing Circuit", NULL, "RIN2"}, + {"LIN3 Mixing Circuit", NULL, "LIN3"}, + {"RIN3 Mixing Circuit", NULL, "RIN3"}, + {"LIN4 Mixing Circuit", NULL, "LIN4"}, + {"RIN4 Mixing Circuit", NULL, "RIN4"}, {"LOUT1 Mixer", "LINL1", "LIN1 Mixing Circuit"}, {"ROUT1 Mixer", "RINR1", "RIN1 Mixing Circuit"}, diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c index 79a4efcb894c..7d3a6accaf9a 100644 --- a/sound/soc/codecs/cs4271.c +++ b/sound/soc/codecs/cs4271.c @@ -286,7 +286,7 @@ static int cs4271_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = cs4271->deemph; + ucontrol->value.integer.value[0] = cs4271->deemph; return 0; } @@ -296,7 +296,7 @@ static int cs4271_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec); - cs4271->deemph = ucontrol->value.enumerated.item[0]; + cs4271->deemph = ucontrol->value.integer.value[0]; return cs4271_set_deemph(codec); } diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c index ffe96175a8a5..911c26c705fc 100644 --- a/sound/soc/codecs/da732x.c +++ b/sound/soc/codecs/da732x.c @@ -876,11 +876,11 @@ static const struct snd_soc_dapm_widget da732x_dapm_widgets[] = { static const struct snd_soc_dapm_route da732x_dapm_routes[] = { /* Inputs */ - {"AUX1L PGA", "NULL", "AUX1L"}, - {"AUX1R PGA", "NULL", "AUX1R"}, + {"AUX1L PGA", NULL, "AUX1L"}, + {"AUX1R PGA", NULL, "AUX1R"}, {"MIC1 PGA", NULL, "MIC1"}, - {"MIC2 PGA", "NULL", "MIC2"}, - {"MIC3 PGA", "NULL", "MIC3"}, + {"MIC2 PGA", NULL, "MIC2"}, + {"MIC3 PGA", NULL, "MIC3"}, /* Capture Path */ {"ADC1 Left MUX", "MIC1", "MIC1 PGA"}, diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c index f27325155ace..c5f35a07e8e4 100644 --- a/sound/soc/codecs/es8328.c +++ b/sound/soc/codecs/es8328.c @@ -120,7 +120,7 @@ static int es8328_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = es8328->deemph; + ucontrol->value.integer.value[0] = es8328->deemph; return 0; } @@ -129,7 +129,7 @@ static int es8328_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; int ret; if (deemph > 1) diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c index a722a023c262..477e13d30971 100644 --- a/sound/soc/codecs/pcm1681.c +++ b/sound/soc/codecs/pcm1681.c @@ -118,7 +118,7 @@ static int pcm1681_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = priv->deemph; + ucontrol->value.integer.value[0] = priv->deemph; return 0; } @@ -129,7 +129,7 @@ static int pcm1681_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec); - priv->deemph = ucontrol->value.enumerated.item[0]; + priv->deemph = ucontrol->value.integer.value[0]; return pcm1681_set_deemph(codec); } diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c index f374840a5a7c..9b541e52da8c 100644 --- a/sound/soc/codecs/rt286.c +++ b/sound/soc/codecs/rt286.c @@ -1198,7 +1198,7 @@ static struct dmi_system_id dmi_dell_dino[] = { .ident = "Dell Dino", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_BOARD_NAME, "0144P8") + DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9343") } }, { } diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index e182e6569bbd..3593a1496056 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1151,13 +1151,7 @@ static int sgtl5000_set_power_regs(struct snd_soc_codec *codec) /* Enable VDDC charge pump */ ana_pwr |= SGTL5000_VDDC_CHRGPMP_POWERUP; } else if (vddio >= 3100 && vdda >= 3100) { - /* - * if vddio and vddd > 3.1v, - * charge pump should be clean before set ana_pwr - */ - snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER, - SGTL5000_VDDC_CHRGPMP_POWERUP, 0); - + ana_pwr &= ~SGTL5000_VDDC_CHRGPMP_POWERUP; /* VDDC use VDDIO rail */ lreg_ctrl |= SGTL5000_VDDC_ASSN_OVRD; lreg_ctrl |= SGTL5000_VDDC_MAN_ASSN_VDDIO << diff --git a/sound/soc/codecs/sn95031.c b/sound/soc/codecs/sn95031.c index 47b257e41809..82095d6cd070 100644 --- a/sound/soc/codecs/sn95031.c +++ b/sound/soc/codecs/sn95031.c @@ -538,8 +538,8 @@ static const struct snd_soc_dapm_route sn95031_audio_map[] = { /* speaker map */ { "IHFOUTL", NULL, "Speaker Rail"}, { "IHFOUTR", NULL, "Speaker Rail"}, - { "IHFOUTL", "NULL", "Speaker Left Playback"}, - { "IHFOUTR", "NULL", "Speaker Right Playback"}, + { "IHFOUTL", NULL, "Speaker Left Playback"}, + { "IHFOUTR", NULL, "Speaker Right Playback"}, { "Speaker Left Playback", NULL, "Speaker Left Filter"}, { "Speaker Right Playback", NULL, "Speaker Right Filter"}, { "Speaker Left Filter", NULL, "IHFDAC Left"}, diff --git a/sound/soc/codecs/tas5086.c b/sound/soc/codecs/tas5086.c index 249ef5c4c762..32942bed34b1 100644 --- a/sound/soc/codecs/tas5086.c +++ b/sound/soc/codecs/tas5086.c @@ -281,7 +281,7 @@ static int tas5086_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = priv->deemph; + ucontrol->value.integer.value[0] = priv->deemph; return 0; } @@ -292,7 +292,7 @@ static int tas5086_put_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec); - priv->deemph = ucontrol->value.enumerated.item[0]; + priv->deemph = ucontrol->value.integer.value[0]; return tas5086_set_deemph(codec); } diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index 8d9de49a5052..21d5402e343f 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -610,7 +610,7 @@ static int wm2000_anc_mode_get(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - ucontrol->value.enumerated.item[0] = wm2000->anc_active; + ucontrol->value.integer.value[0] = wm2000->anc_active; return 0; } @@ -620,7 +620,7 @@ static int wm2000_anc_mode_put(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - int anc_active = ucontrol->value.enumerated.item[0]; + int anc_active = ucontrol->value.integer.value[0]; int ret; if (anc_active > 1) @@ -643,7 +643,7 @@ static int wm2000_speaker_get(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - ucontrol->value.enumerated.item[0] = wm2000->spk_ena; + ucontrol->value.integer.value[0] = wm2000->spk_ena; return 0; } @@ -653,7 +653,7 @@ static int wm2000_speaker_put(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev); - int val = ucontrol->value.enumerated.item[0]; + int val = ucontrol->value.integer.value[0]; int ret; if (val > 1) diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index 098c143f44d6..c6d10533e2bd 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -125,7 +125,7 @@ static int wm8731_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8731->deemph; + ucontrol->value.integer.value[0] = wm8731->deemph; return 0; } @@ -135,7 +135,7 @@ static int wm8731_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; int ret = 0; if (deemph > 1) diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c index dde462c082be..04b04f8e147c 100644 --- a/sound/soc/codecs/wm8903.c +++ b/sound/soc/codecs/wm8903.c @@ -442,7 +442,7 @@ static int wm8903_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8903->deemph; + ucontrol->value.integer.value[0] = wm8903->deemph; return 0; } @@ -452,7 +452,7 @@ static int wm8903_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; int ret = 0; if (deemph > 1) diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index d3b3f57668cc..215e93c1ddf0 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -525,7 +525,7 @@ static int wm8904_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8904->deemph; + ucontrol->value.integer.value[0] = wm8904->deemph; return 0; } @@ -534,7 +534,7 @@ static int wm8904_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c index 1ab2d462afad..00bec915d652 100644 --- a/sound/soc/codecs/wm8955.c +++ b/sound/soc/codecs/wm8955.c @@ -393,7 +393,7 @@ static int wm8955_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8955->deemph; + ucontrol->value.integer.value[0] = wm8955->deemph; return 0; } @@ -402,7 +402,7 @@ static int wm8955_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index cf8fecf97f2c..3035d9856415 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -184,7 +184,7 @@ static int wm8960_get_deemph(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.enumerated.item[0] = wm8960->deemph; + ucontrol->value.integer.value[0] = wm8960->deemph; return 0; } @@ -193,7 +193,7 @@ static int wm8960_put_deemph(struct snd_kcontrol *kcontrol, { struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec); - int deemph = ucontrol->value.enumerated.item[0]; + int deemph = ucontrol->value.integer.value[0]; if (deemph > 1) return -EINVAL; diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c index 9517571e820d..98c9525bd751 100644 --- a/sound/soc/codecs/wm9712.c +++ b/sound/soc/codecs/wm9712.c @@ -180,7 +180,7 @@ static int wm9712_hp_mixer_put(struct snd_kcontrol *kcontrol, struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol); struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm); struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec); - unsigned int val = ucontrol->value.enumerated.item[0]; + unsigned int val = ucontrol->value.integer.value[0]; struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; unsigned int mixer, mask, shift, old; @@ -193,7 +193,7 @@ static int wm9712_hp_mixer_put(struct snd_kcontrol *kcontrol, mutex_lock(&wm9712->lock); old = wm9712->hp_mixer[mixer]; - if (ucontrol->value.enumerated.item[0]) + if (ucontrol->value.integer.value[0]) wm9712->hp_mixer[mixer] |= mask; else wm9712->hp_mixer[mixer] &= ~mask; @@ -231,7 +231,7 @@ static int wm9712_hp_mixer_get(struct snd_kcontrol *kcontrol, mixer = mc->shift >> 8; shift = mc->shift & 0xff; - ucontrol->value.enumerated.item[0] = + ucontrol->value.integer.value[0] = (wm9712->hp_mixer[mixer] >> shift) & 1; return 0; diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c index 68222917b396..79552953e1bd 100644 --- a/sound/soc/codecs/wm9713.c +++ b/sound/soc/codecs/wm9713.c @@ -255,7 +255,7 @@ static int wm9713_hp_mixer_put(struct snd_kcontrol *kcontrol, struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol); struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm); struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec); - unsigned int val = ucontrol->value.enumerated.item[0]; + unsigned int val = ucontrol->value.integer.value[0]; struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; unsigned int mixer, mask, shift, old; @@ -268,7 +268,7 @@ static int wm9713_hp_mixer_put(struct snd_kcontrol *kcontrol, mutex_lock(&wm9713->lock); old = wm9713->hp_mixer[mixer]; - if (ucontrol->value.enumerated.item[0]) + if (ucontrol->value.integer.value[0]) wm9713->hp_mixer[mixer] |= mask; else wm9713->hp_mixer[mixer] &= ~mask; @@ -306,7 +306,7 @@ static int wm9713_hp_mixer_get(struct snd_kcontrol *kcontrol, mixer = mc->shift >> 8; shift = mc->shift & 0xff; - ucontrol->value.enumerated.item[0] = + ucontrol->value.integer.value[0] = (wm9713->hp_mixer[mixer] >> shift) & 1; return 0; diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c index 75870c0ea2c9..91eb3aef7f02 100644 --- a/sound/soc/fsl/fsl_spdif.c +++ b/sound/soc/fsl/fsl_spdif.c @@ -1049,7 +1049,7 @@ static u32 fsl_spdif_txclk_caldiv(struct fsl_spdif_priv *spdif_priv, enum spdif_txrate index, bool round) { const u32 rate[] = { 32000, 44100, 48000, 96000, 192000 }; - bool is_sysclk = clk == spdif_priv->sysclk; + bool is_sysclk = clk_is_match(clk, spdif_priv->sysclk); u64 rate_ideal, rate_actual, sub; u32 sysclk_dfmin, sysclk_dfmax; u32 txclk_df, sysclk_df, arate; @@ -1143,7 +1143,7 @@ static int fsl_spdif_probe_txclk(struct fsl_spdif_priv *spdif_priv, spdif_priv->txclk_src[index], rate[index]); dev_dbg(&pdev->dev, "use txclk df %d for %dHz sample rate\n", spdif_priv->txclk_df[index], rate[index]); - if (spdif_priv->txclk[index] == spdif_priv->sysclk) + if (clk_is_match(spdif_priv->txclk[index], spdif_priv->sysclk)) dev_dbg(&pdev->dev, "use sysclk df %d for %dHz sample rate\n", spdif_priv->sysclk_df[index], rate[index]); dev_dbg(&pdev->dev, "the best rate for %dHz sample rate is %dHz\n", diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index b9fabbf69db6..6b0c8f717ec2 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -603,7 +603,7 @@ static int fsl_ssi_set_bclk(struct snd_pcm_substream *substream, factor = (div2 + 1) * (7 * psr + 1) * 2; for (i = 0; i < 255; i++) { - tmprate = freq * factor * (i + 2); + tmprate = freq * factor * (i + 1); if (baudclk_is_used) clkrate = clk_get_rate(ssi_private->baudclk); @@ -1227,7 +1227,7 @@ static int fsl_ssi_imx_probe(struct platform_device *pdev, ssi_private->dma_params_tx.addr = ssi_private->ssi_phys + CCSR_SSI_STX0; ssi_private->dma_params_rx.addr = ssi_private->ssi_phys + CCSR_SSI_SRX0; - ret = !of_property_read_u32_array(np, "dmas", dmas, 4); + ret = of_property_read_u32_array(np, "dmas", dmas, 4); if (ssi_private->use_dma && !ret && dmas[2] == IMX_DMATYPE_SSI_DUAL) { ssi_private->use_dual_fifo = true; /* When using dual fifo mode, we need to keep watermark diff --git a/sound/soc/intel/sst-haswell-dsp.c b/sound/soc/intel/sst-haswell-dsp.c index c42ffae5fe9f..402b728c0a06 100644 --- a/sound/soc/intel/sst-haswell-dsp.c +++ b/sound/soc/intel/sst-haswell-dsp.c @@ -207,9 +207,6 @@ static int hsw_parse_fw_image(struct sst_fw *sst_fw) module = (void *)module + sizeof(*module) + module->mod_size; } - /* allocate scratch mem regions */ - sst_block_alloc_scratch(dsp); - return 0; } diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c index 394af5684c05..863a9ca34b8e 100644 --- a/sound/soc/intel/sst-haswell-ipc.c +++ b/sound/soc/intel/sst-haswell-ipc.c @@ -1732,6 +1732,7 @@ static void sst_hsw_drop_all(struct sst_hsw *hsw) int sst_hsw_dsp_load(struct sst_hsw *hsw) { struct sst_dsp *dsp = hsw->dsp; + struct sst_fw *sst_fw, *t; int ret; dev_dbg(hsw->dev, "loading audio DSP...."); @@ -1748,12 +1749,17 @@ int sst_hsw_dsp_load(struct sst_hsw *hsw) return ret; } - ret = sst_fw_reload(hsw->sst_fw); - if (ret < 0) { - dev_err(hsw->dev, "error: SST FW reload failed\n"); - sst_dsp_dma_put_channel(dsp); - return -ENOMEM; + list_for_each_entry_safe_reverse(sst_fw, t, &dsp->fw_list, list) { + ret = sst_fw_reload(sst_fw); + if (ret < 0) { + dev_err(hsw->dev, "error: SST FW reload failed\n"); + sst_dsp_dma_put_channel(dsp); + return -ENOMEM; + } } + ret = sst_block_alloc_scratch(hsw->dsp); + if (ret < 0) + return -EINVAL; sst_dsp_dma_put_channel(dsp); return 0; @@ -1809,12 +1815,17 @@ int sst_hsw_dsp_runtime_suspend(struct sst_hsw *hsw) int sst_hsw_dsp_runtime_sleep(struct sst_hsw *hsw) { - sst_fw_unload(hsw->sst_fw); - sst_block_free_scratch(hsw->dsp); + struct sst_fw *sst_fw, *t; + struct sst_dsp *dsp = hsw->dsp; + + list_for_each_entry_safe(sst_fw, t, &dsp->fw_list, list) { + sst_fw_unload(sst_fw); + } + sst_block_free_scratch(dsp); hsw->boot_complete = false; - sst_dsp_sleep(hsw->dsp); + sst_dsp_sleep(dsp); return 0; } @@ -1943,6 +1954,11 @@ int sst_hsw_dsp_init(struct device *dev, struct sst_pdata *pdata) goto fw_err; } + /* allocate scratch mem regions */ + ret = sst_block_alloc_scratch(hsw->dsp); + if (ret < 0) + goto boot_err; + /* wait for DSP boot completion */ sst_dsp_boot(hsw->dsp); ret = wait_event_timeout(hsw->boot_wait, hsw->boot_complete, diff --git a/sound/soc/kirkwood/kirkwood-i2s.c b/sound/soc/kirkwood/kirkwood-i2s.c index def7d8260c4e..d19483081f9b 100644 --- a/sound/soc/kirkwood/kirkwood-i2s.c +++ b/sound/soc/kirkwood/kirkwood-i2s.c @@ -579,7 +579,7 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev) if (PTR_ERR(priv->extclk) == -EPROBE_DEFER) return -EPROBE_DEFER; } else { - if (priv->extclk == priv->clk) { + if (clk_is_match(priv->extclk, priv->clk)) { devm_clk_put(&pdev->dev, priv->extclk); priv->extclk = ERR_PTR(-EINVAL); } else { diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 30579ca5bacb..e5c990889dcc 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -347,6 +347,8 @@ static ssize_t codec_list_read_file(struct file *file, char __user *user_buf, if (!buf) return -ENOMEM; + mutex_lock(&client_mutex); + list_for_each_entry(codec, &codec_list, list) { len = snprintf(buf + ret, PAGE_SIZE - ret, "%s\n", codec->component.name); @@ -358,6 +360,8 @@ static ssize_t codec_list_read_file(struct file *file, char __user *user_buf, } } + mutex_unlock(&client_mutex); + if (ret >= 0) ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret); @@ -382,6 +386,8 @@ static ssize_t dai_list_read_file(struct file *file, char __user *user_buf, if (!buf) return -ENOMEM; + mutex_lock(&client_mutex); + list_for_each_entry(component, &component_list, list) { list_for_each_entry(dai, &component->dai_list, list) { len = snprintf(buf + ret, PAGE_SIZE - ret, "%s\n", @@ -395,6 +401,8 @@ static ssize_t dai_list_read_file(struct file *file, char __user *user_buf, } } + mutex_unlock(&client_mutex); + ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret); kfree(buf); @@ -418,6 +426,8 @@ static ssize_t platform_list_read_file(struct file *file, if (!buf) return -ENOMEM; + mutex_lock(&client_mutex); + list_for_each_entry(platform, &platform_list, list) { len = snprintf(buf + ret, PAGE_SIZE - ret, "%s\n", platform->component.name); @@ -429,6 +439,8 @@ static ssize_t platform_list_read_file(struct file *file, } } + mutex_unlock(&client_mutex); + ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret); kfree(buf); @@ -836,6 +848,8 @@ static struct snd_soc_component *soc_find_component( { struct snd_soc_component *component; + lockdep_assert_held(&client_mutex); + list_for_each_entry(component, &component_list, list) { if (of_node) { if (component->dev->of_node == of_node) @@ -854,6 +868,8 @@ static struct snd_soc_dai *snd_soc_find_dai( struct snd_soc_component *component; struct snd_soc_dai *dai; + lockdep_assert_held(&client_mutex); + /* Find CPU DAI from registered DAIs*/ list_for_each_entry(component, &component_list, list) { if (dlc->of_node && component->dev->of_node != dlc->of_node) @@ -1508,6 +1524,7 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card) struct snd_soc_codec *codec; int ret, i, order; + mutex_lock(&client_mutex); mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_INIT); /* bind DAIs */ @@ -1662,6 +1679,7 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card) card->instantiated = 1; snd_soc_dapm_sync(&card->dapm); mutex_unlock(&card->mutex); + mutex_unlock(&client_mutex); return 0; @@ -1680,6 +1698,7 @@ card_probe_error: base_error: mutex_unlock(&card->mutex); + mutex_unlock(&client_mutex); return ret; } @@ -2713,13 +2732,6 @@ static void snd_soc_component_del_unlocked(struct snd_soc_component *component) list_del(&component->list); } -static void snd_soc_component_del(struct snd_soc_component *component) -{ - mutex_lock(&client_mutex); - snd_soc_component_del_unlocked(component); - mutex_unlock(&client_mutex); -} - int snd_soc_register_component(struct device *dev, const struct snd_soc_component_driver *cmpnt_drv, struct snd_soc_dai_driver *dai_drv, @@ -2767,14 +2779,17 @@ void snd_soc_unregister_component(struct device *dev) { struct snd_soc_component *cmpnt; + mutex_lock(&client_mutex); list_for_each_entry(cmpnt, &component_list, list) { if (dev == cmpnt->dev && cmpnt->registered_as_component) goto found; } + mutex_unlock(&client_mutex); return; found: - snd_soc_component_del(cmpnt); + snd_soc_component_del_unlocked(cmpnt); + mutex_unlock(&client_mutex); snd_soc_component_cleanup(cmpnt); kfree(cmpnt); } @@ -2882,10 +2897,14 @@ struct snd_soc_platform *snd_soc_lookup_platform(struct device *dev) { struct snd_soc_platform *platform; + mutex_lock(&client_mutex); list_for_each_entry(platform, &platform_list, list) { - if (dev == platform->dev) + if (dev == platform->dev) { + mutex_unlock(&client_mutex); return platform; + } } + mutex_unlock(&client_mutex); return NULL; } @@ -3090,15 +3109,15 @@ void snd_soc_unregister_codec(struct device *dev) { struct snd_soc_codec *codec; + mutex_lock(&client_mutex); list_for_each_entry(codec, &codec_list, list) { if (dev == codec->dev) goto found; } + mutex_unlock(&client_mutex); return; found: - - mutex_lock(&client_mutex); list_del(&codec->list); snd_soc_component_del_unlocked(&codec->component); mutex_unlock(&client_mutex); diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 67d476548dcf..07f984d5f516 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -1773,6 +1773,36 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, +{ + USB_DEVICE(0x0582, 0x0159), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + /* .vendor_name = "Roland", */ + /* .product_name = "UA-22", */ + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = & (const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, /* this catches most recent vendor-specific Roland devices */ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | diff --git a/tools/net/bpf_exp.l b/tools/net/bpf_exp.l index 833a96611da6..7cc72a336645 100644 --- a/tools/net/bpf_exp.l +++ b/tools/net/bpf_exp.l @@ -90,8 +90,10 @@ extern void yyerror(const char *str); "#"?("hatype") { return K_HATYPE; } "#"?("rxhash") { return K_RXHASH; } "#"?("cpu") { return K_CPU; } -"#"?("vlan_tci") { return K_VLANT; } -"#"?("vlan_pr") { return K_VLANP; } +"#"?("vlan_tci") { return K_VLAN_TCI; } +"#"?("vlan_pr") { return K_VLAN_AVAIL; } +"#"?("vlan_avail") { return K_VLAN_AVAIL; } +"#"?("vlan_tpid") { return K_VLAN_TPID; } "#"?("rand") { return K_RAND; } ":" { return ':'; } diff --git a/tools/net/bpf_exp.y b/tools/net/bpf_exp.y index e6306c51c26f..e24eea1b0db5 100644 --- a/tools/net/bpf_exp.y +++ b/tools/net/bpf_exp.y @@ -56,7 +56,7 @@ static void bpf_set_jmp_label(char *label, enum jmp_type type); %token OP_LDXI %token K_PKT_LEN K_PROTO K_TYPE K_NLATTR K_NLATTR_NEST K_MARK K_QUEUE K_HATYPE -%token K_RXHASH K_CPU K_IFIDX K_VLANT K_VLANP K_POFF K_RAND +%token K_RXHASH K_CPU K_IFIDX K_VLAN_TCI K_VLAN_AVAIL K_VLAN_TPID K_POFF K_RAND %token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%' @@ -155,10 +155,10 @@ ldb | OP_LDB K_CPU { bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_CPU); } - | OP_LDB K_VLANT { + | OP_LDB K_VLAN_TCI { bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_VLAN_TAG); } - | OP_LDB K_VLANP { + | OP_LDB K_VLAN_AVAIL { bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); } | OP_LDB K_POFF { @@ -167,6 +167,9 @@ ldb | OP_LDB K_RAND { bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_RANDOM); } + | OP_LDB K_VLAN_TPID { + bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, + SKF_AD_OFF + SKF_AD_VLAN_TPID); } ; ldh @@ -206,10 +209,10 @@ ldh | OP_LDH K_CPU { bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_CPU); } - | OP_LDH K_VLANT { + | OP_LDH K_VLAN_TCI { bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_VLAN_TAG); } - | OP_LDH K_VLANP { + | OP_LDH K_VLAN_AVAIL { bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); } | OP_LDH K_POFF { @@ -218,6 +221,9 @@ ldh | OP_LDH K_RAND { bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_RANDOM); } + | OP_LDH K_VLAN_TPID { + bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, + SKF_AD_OFF + SKF_AD_VLAN_TPID); } ; ldi @@ -262,10 +268,10 @@ ld | OP_LD K_CPU { bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_CPU); } - | OP_LD K_VLANT { + | OP_LD K_VLAN_TCI { bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_VLAN_TAG); } - | OP_LD K_VLANP { + | OP_LD K_VLAN_AVAIL { bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); } | OP_LD K_POFF { @@ -274,6 +280,9 @@ ld | OP_LD K_RAND { bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_RANDOM); } + | OP_LD K_VLAN_TPID { + bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, + SKF_AD_OFF + SKF_AD_VLAN_TPID); } | OP_LD 'M' '[' number ']' { bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); } | OP_LD '[' 'x' '+' number ']' { diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 61bf9128e1f2..9d9db3b296dd 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -30,6 +30,8 @@ static int disasm_line__parse(char *line, char **namep, char **rawp); static void ins__delete(struct ins_operands *ops) { + if (ops == NULL) + return; zfree(&ops->source.raw); zfree(&ops->source.name); zfree(&ops->target.raw); diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 3ed7c0476d48..2e2ba2efa0d9 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -209,7 +209,7 @@ $(OUTPUT)%.o: %.c $(OUTPUT)cpupower: $(UTIL_OBJS) $(OUTPUT)libcpupower.so.$(LIB_MAJ) $(ECHO) " CC " $@ - $(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -Wl,-rpath=./ -lrt -lpci -L$(OUTPUT) -o $@ + $(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -lrt -lpci -L$(OUTPUT) -o $@ $(QUIET) $(STRIPCMD) $@ $(OUTPUT)po/$(PACKAGE).pot: $(UTIL_SRC) diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c index e238c9559caf..8d5d1d2ee7c1 100644 --- a/tools/testing/selftests/exec/execveat.c +++ b/tools/testing/selftests/exec/execveat.c @@ -30,7 +30,7 @@ static int execveat_(int fd, const char *path, char **argv, char **envp, #ifdef __NR_execveat return syscall(__NR_execveat, fd, path, argv, envp, flags); #else - errno = -ENOSYS; + errno = ENOSYS; return -1; #endif } @@ -234,6 +234,14 @@ static int run_tests(void) int fd_cloexec = open_or_die("execveat", O_RDONLY|O_CLOEXEC); int fd_script_cloexec = open_or_die("script", O_RDONLY|O_CLOEXEC); + /* Check if we have execveat at all, and bail early if not */ + errno = 0; + execveat_(-1, NULL, NULL, NULL, 0); + if (errno == ENOSYS) { + printf("[FAIL] ENOSYS calling execveat - no kernel support?\n"); + return 1; + } + /* Change file position to confirm it doesn't affect anything */ lseek(fd, 10, SEEK_SET); diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c index a0a7b5d1a070..f9b9c7c51372 100644 --- a/virt/kvm/arm/vgic-v2.c +++ b/virt/kvm/arm/vgic-v2.c @@ -72,6 +72,8 @@ static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, { if (!(lr_desc.state & LR_STATE_MASK)) vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr); + else + vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr &= ~(1ULL << lr); } static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu) @@ -84,6 +86,11 @@ static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu) return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr; } +static void vgic_v2_clear_eisr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr = 0; +} + static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu) { u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr; @@ -148,6 +155,7 @@ static const struct vgic_ops vgic_v2_ops = { .sync_lr_elrsr = vgic_v2_sync_lr_elrsr, .get_elrsr = vgic_v2_get_elrsr, .get_eisr = vgic_v2_get_eisr, + .clear_eisr = vgic_v2_clear_eisr, .get_interrupt_status = vgic_v2_get_interrupt_status, .enable_underflow = vgic_v2_enable_underflow, .disable_underflow = vgic_v2_disable_underflow, diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c index 3a62d8a9a2c6..dff06021e748 100644 --- a/virt/kvm/arm/vgic-v3.c +++ b/virt/kvm/arm/vgic-v3.c @@ -104,6 +104,8 @@ static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, { if (!(lr_desc.state & LR_STATE_MASK)) vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr); + else + vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr &= ~(1U << lr); } static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu) @@ -116,6 +118,11 @@ static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu) return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr; } +static void vgic_v3_clear_eisr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr = 0; +} + static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu) { u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr; @@ -192,6 +199,7 @@ static const struct vgic_ops vgic_v3_ops = { .sync_lr_elrsr = vgic_v3_sync_lr_elrsr, .get_elrsr = vgic_v3_get_elrsr, .get_eisr = vgic_v3_get_eisr, + .clear_eisr = vgic_v3_clear_eisr, .get_interrupt_status = vgic_v3_get_interrupt_status, .enable_underflow = vgic_v3_enable_underflow, .disable_underflow = vgic_v3_disable_underflow, diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 0cc6ab6005a0..c9f60f524588 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -883,6 +883,11 @@ static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu) return vgic_ops->get_eisr(vcpu); } +static inline void vgic_clear_eisr(struct kvm_vcpu *vcpu) +{ + vgic_ops->clear_eisr(vcpu); +} + static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu) { return vgic_ops->get_interrupt_status(vcpu); @@ -922,6 +927,7 @@ static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu) vgic_set_lr(vcpu, lr_nr, vlr); clear_bit(lr_nr, vgic_cpu->lr_used); vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; + vgic_sync_lr_elrsr(vcpu, lr_nr, vlr); } /* @@ -978,6 +984,7 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); vlr.state |= LR_STATE_PENDING; vgic_set_lr(vcpu, lr, vlr); + vgic_sync_lr_elrsr(vcpu, lr, vlr); return true; } } @@ -999,6 +1006,7 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) vlr.state |= LR_EOI_INT; vgic_set_lr(vcpu, lr, vlr); + vgic_sync_lr_elrsr(vcpu, lr, vlr); return true; } @@ -1136,6 +1144,14 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) if (status & INT_STATUS_UNDERFLOW) vgic_disable_underflow(vcpu); + /* + * In the next iterations of the vcpu loop, if we sync the vgic state + * after flushing it, but before entering the guest (this happens for + * pending signals and vmid rollovers), then make sure we don't pick + * up any old maintenance interrupts here. + */ + vgic_clear_eisr(vcpu); + return level_pending; } @@ -1583,8 +1599,10 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) * emulation. So check this here again. KVM_CREATE_DEVICE does * the proper checks already. */ - if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2) - return -ENODEV; + if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2) { + ret = -ENODEV; + goto out; + } /* * Any time a vcpu is run, vcpu_load is called which tries to grab the diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a1093700f3a4..a2214d9609bd 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2492,6 +2492,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_SIGNAL_MSI: #endif #ifdef CONFIG_HAVE_KVM_IRQFD + case KVM_CAP_IRQFD: case KVM_CAP_IRQFD_RESAMPLE: #endif case KVM_CAP_CHECK_EXTENSION_VM: |